{"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":"2026-10-20T12:36:59Z","heatmap_track_id":"full_freedom/intensive","models":[{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-astra:42003ea533b21c57","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":1.30343,"median":1.3074612499999998,"min":1.077205,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":10.42744},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.48718,"mean":0.4090425,"median":0.40659249999999997,"min":0.311405,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":3.2723400000000002},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.26443,"mean":0.23918625000000002,"median":0.241805,"min":0.2072175,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":1.91349}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.48718,"mean":0.4090425,"median":0.40659249999999997,"min":0.311405,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":3.27234},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.26443,"mean":0.23918625000000002,"median":0.241805,"min":0.2072175,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":1.91349},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":1.30343,"median":1.3074612499999998,"min":1.077205,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":10.42744}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":24},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":0.6505529166666667,"median":0.40659249999999997,"min":0.2072175,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":24},"run_count":24,"token_priced_attempt_count":24,"total":15.61327},"codegen_output_tokens":{"attempt_count":24,"output_max":27674,"output_mean":11074.333333333334,"output_min":2260,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":27674,"output_mean":24131.875,"output_min":19038,"run_count":8},"medium":{"attempt_count":8,"output_max":7733,"output_mean":6244.125,"output_min":3722,"run_count":8},"none":{"attempt_count":8,"output_max":3278,"output_mean":2847.0,"output_min":2260,"run_count":8}},"display_name":"GPT-6 Astra","economics":{"all":89.61782749824646,"highest":94.53988467265376,"medium":89.39517527602239,"none":84.91842254606327},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":24,"finish_reasons":["stop"],"indexed_attempts":24,"output_token_observations":24,"provider_post_attempt_observations":24,"provider_post_attempts":24,"reasoning_token_observations":24,"reconciliation_get_attempt_observations":24,"total_output_tokens":265784,"total_reasoning_output_tokens":150836,"total_visible_output_tokens":114948,"visible_token_observations":24},"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-6-astra","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":88.32553095422658,"score":88.32553095422658},"GB2-02":{"attempts":3,"playable":83.11448327490113,"score":83.11448327490113},"GB2-03":{"attempts":3,"playable":89.48905232541192,"score":89.48905232541192},"GB2-04":{"attempts":3,"playable":89.50085286411894,"score":89.50085286411894},"GB2-05":{"attempts":3,"playable":95.3824487818655,"score":95.3824487818655},"GB2-06":{"attempts":3,"playable":86.46788705711317,"score":86.46788705711317},"GB2-07":{"attempts":3,"playable":96.29210792864403,"score":96.29210792864403},"GB2-08":{"attempts":3,"playable":88.37025679969047,"score":88.37025679969047}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":96.76605994154798,"score":96.76605994154798},"GB2-02":{"attempts":1,"playable":96.25553540489828,"score":96.25553540489828},"GB2-03":{"attempts":1,"playable":97.80645035612199,"score":97.80645035612199},"GB2-04":{"attempts":1,"playable":92.83216380172516,"score":92.83216380172516},"GB2-05":{"attempts":1,"playable":98.82297049482304,"score":98.82297049482304},"GB2-06":{"attempts":1,"playable":88.44046079120618,"score":88.44046079120618},"GB2-07":{"attempts":1,"playable":97.67362231194657,"score":97.67362231194657},"GB2-08":{"attempts":1,"playable":87.72181427896075,"score":87.72181427896075}},"medium":{"GB2-01":{"attempts":1,"playable":75.35426545789929,"score":75.35426545789929},"GB2-02":{"attempts":1,"playable":81.1662140041307,"score":81.1662140041307},"GB2-03":{"attempts":1,"playable":94.75304189449174,"score":94.75304189449174},"GB2-04":{"attempts":1,"playable":91.89742445509904,"score":91.89742445509904},"GB2-05":{"attempts":1,"playable":92.88008983338887,"score":92.88008983338887},"GB2-06":{"attempts":1,"playable":88.12150153766366,"score":88.12150153766366},"GB2-07":{"attempts":1,"playable":96.83753523768007,"score":96.83753523768007},"GB2-08":{"attempts":1,"playable":94.15132978782572,"score":94.15132978782572}},"none":{"GB2-01":{"attempts":1,"playable":92.8562674632325,"score":92.8562674632325},"GB2-02":{"attempts":1,"playable":71.92170041567442,"score":71.92170041567442},"GB2-03":{"attempts":1,"playable":75.90766472562197,"score":75.90766472562197},"GB2-04":{"attempts":1,"playable":83.7729703355326,"score":83.7729703355326},"GB2-05":{"attempts":1,"playable":94.44428601738464,"score":94.44428601738464},"GB2-06":{"attempts":1,"playable":82.84169884246968,"score":82.84169884246968},"GB2-07":{"attempts":1,"playable":94.36516623630544,"score":94.36516623630544},"GB2-08":{"attempts":1,"playable":83.2376263322849,"score":83.2376263322849}}},"id":"gpt-6-astra","is_recent_addition":false,"last_measured_at":"2026-10-20T11:44:13Z","match_totals_all":{"draws":792,"losses":752,"wins":9538},"match_totals_tracks":{"highest":{"draws":86,"losses":151,"wins":3457},"medium":{"draws":241,"losses":269,"wins":3184},"none":{"draws":465,"losses":332,"wins":2897}},"model_slug":"gpt-6-astra","overall":{"max":98.82297049482304,"mean":89.61782749824647,"min":71.92170041567442},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":1,"overall_ranking_status":"ranked","per_game":{"GB2-01":96.76605994154798,"GB2-02":96.25553540489828,"GB2-03":97.80645035612199,"GB2-04":92.83216380172516,"GB2-05":98.82297049482304,"GB2-06":88.44046079120618,"GB2-07":97.67362231194657,"GB2-08":87.72181427896075},"per_game_all":{"GB2-01":88.32553095422658,"GB2-02":83.11448327490113,"GB2-03":89.48905232541192,"GB2-04":89.50085286411894,"GB2-05":95.3824487818655,"GB2-06":86.46788705711317,"GB2-07":96.29210792864403,"GB2-08":88.37025679969047},"per_game_match_totals_all":{"GB2-01":{"draws":55,"losses":138,"wins":1211},"GB2-02":{"draws":363,"losses":43,"wins":890},"GB2-03":{"draws":154,"losses":74,"wins":1110},"GB2-04":{"draws":145,"losses":74,"wins":1125},"GB2-05":{"draws":0,"losses":61,"wins":1391},"GB2-06":{"draws":75,"losses":145,"wins":1148},"GB2-07":{"draws":0,"losses":44,"wins":1378},"GB2-08":{"draws":0,"losses":173,"wins":1285}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":14,"wins":454},"GB2-02":{"draws":18,"losses":6,"wins":408},"GB2-03":{"draws":7,"losses":5,"wins":434},"GB2-04":{"draws":34,"losses":16,"wins":398},"GB2-05":{"draws":0,"losses":3,"wins":481},"GB2-06":{"draws":27,"losses":38,"wins":391},"GB2-07":{"draws":0,"losses":8,"wins":466},"GB2-08":{"draws":0,"losses":61,"wins":425}},"medium":{"GB2-01":{"draws":34,"losses":101,"wins":333},"GB2-02":{"draws":142,"losses":13,"wins":277},"GB2-03":{"draws":6,"losses":21,"wins":419},"GB2-04":{"draws":39,"losses":18,"wins":391},"GB2-05":{"draws":0,"losses":33,"wins":451},"GB2-06":{"draws":20,"losses":43,"wins":393},"GB2-07":{"draws":0,"losses":12,"wins":462},"GB2-08":{"draws":0,"losses":28,"wins":458}},"none":{"GB2-01":{"draws":21,"losses":23,"wins":424},"GB2-02":{"draws":203,"losses":24,"wins":205},"GB2-03":{"draws":141,"losses":48,"wins":257},"GB2-04":{"draws":72,"losses":40,"wins":336},"GB2-05":{"draws":0,"losses":25,"wins":459},"GB2-06":{"draws":28,"losses":64,"wins":364},"GB2-07":{"draws":0,"losses":24,"wins":450},"GB2-08":{"draws":0,"losses":84,"wins":402}}},"per_game_raw_elo_all":{"GB2-01":2028.1237079203365,"GB2-02":1864.667020573843,"GB2-03":2122.3029032084924,"GB2-04":1927.0040486138416,"GB2-05":2622.857186413279,"GB2-06":2111.2962856920517,"GB2-07":2539.2908190808625,"GB2-08":2109.1104403290296},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2255.4416928931123,"GB2-02":2156.99656625332,"GB2-03":2443.7367520634734,"GB2-04":1998.5706741243703,"GB2-05":2944.792054279404,"GB2-06":2156.280320202538,"GB2-07":2646.911377769551,"GB2-08":2072.130775619897},"medium":{"GB2-01":1749.7687194529703,"GB2-02":1773.2333070491288,"GB2-03":2213.4455809512,"GB2-04":1971.934842739421,"GB2-05":2416.90255028946,"GB2-06":2148.2706918613235,"GB2-07":2570.5481166080303,"GB2-08":2298.900366670386},"none":{"GB2-01":2079.1607114149274,"GB2-02":1663.7711884190805,"GB2-03":1709.726376610804,"GB2-04":1810.506628977734,"GB2-05":2506.8769546709736,"GB2-06":2029.3378450122948,"GB2-07":2400.4129628650066,"GB2-08":1956.3001786968055}},"per_game_tracks":{"highest":{"GB2-01":96.76605994154798,"GB2-02":96.25553540489828,"GB2-03":97.80645035612199,"GB2-04":92.83216380172516,"GB2-05":98.82297049482304,"GB2-06":88.44046079120618,"GB2-07":97.67362231194657,"GB2-08":87.72181427896075},"medium":{"GB2-01":75.35426545789929,"GB2-02":81.1662140041307,"GB2-03":94.75304189449174,"GB2-04":91.89742445509904,"GB2-05":92.88008983338887,"GB2-06":88.12150153766366,"GB2-07":96.83753523768007,"GB2-08":94.15132978782572},"none":{"GB2-01":92.8562674632325,"GB2-02":71.92170041567442,"GB2-03":75.90766472562197,"GB2-04":83.7729703355326,"GB2-05":94.44428601738464,"GB2-06":82.84169884246968,"GB2-07":94.36516623630544,"GB2-08":83.2376263322849}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-14T17:24:37Z","reasoning":{"highest":94.53988467265376,"medium":89.39517527602239,"none":84.91842254606327},"reasoning_agg":{"highest":{"max":98.82297049482304,"mean":94.53988467265376,"min":87.72181427896075},"medium":{"max":96.83753523768007,"mean":89.39517527602239,"min":75.35426545789929},"none":{"max":94.44428601738464,"mean":84.91842254606327,"min":71.92170041567442}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":9.621462126590487}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5-5:d42a4c4c0f7d3cdf","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":1.98688675,"median":1.871197,"min":1.357152,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":9,"token_priced_attempt_count":11,"total":17.677191999999998},"medium":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.728964,"mean":0.33381875,"median":0.267474,"min":0.167816,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"run_count":9,"token_priced_attempt_count":10,"total":3.006308},"none":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.124844,"mean":0.11677924999999999,"median":0.118817,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":9,"token_priced_attempt_count":9,"total":1.052792}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.728964,"mean":0.33381875,"median":0.267474,"min":0.167816,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"run_count":9,"token_priced_attempt_count":10,"total":3.0063079999999998},"historical-provider-setting-baseline":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.124844,"mean":0.11677924999999999,"median":0.118817,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":9,"token_priced_attempt_count":9,"total":1.0527920000000002},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":1.98688675,"median":1.871197,"min":1.357152,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":9,"token_priced_attempt_count":11,"total":17.677191999999998}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":30},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":0.8124949166666666,"median":0.267474,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":30},"run_count":27,"token_priced_attempt_count":30,"total":21.736292000000002},"codegen_output_tokens":{"attempt_count":30,"output_max":149830,"output_mean":37334.40740740741,"output_min":2400,"run_count":27},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":149830,"output_mean":94967.22222222222,"output_min":65515,"run_count":9},"medium":{"attempt_count":10,"output_max":31033,"output_mean":13777.666666666666,"output_min":6104,"run_count":9},"none":{"attempt_count":9,"output_max":3890,"output_mean":3258.3333333333335,"output_min":2400,"run_count":9}},"display_name":"Claude Opus 5.5","economics":{"all":88.62453546742353,"highest":95.1809377309599,"medium":92.78816186379063,"none":77.90450680752008},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":30,"effective_max_output_tokens":[65536,128000],"finish_reason_observations":30,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":30,"provider_post_attempts":30,"reasoning_token_observations":30,"reconciliation_get_attempt_observations":30,"requested_max_output_token_observations":30,"requested_max_output_tokens":[65536,128000],"total_output_tokens":1008029,"total_reasoning_output_tokens":820640,"total_visible_output_tokens":187389,"visible_token_observations":30},"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":"anthropic","provider_model":"claude-opus-5-5","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":9,"evaluated_cells":9,"first_pass_admitted":8,"first_pass_rate":0.8888888888888888,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.1111111111111111},"baseline":{"admitted_plugins":9,"evaluated_cells":9,"first_pass_admitted":9,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-08"],"infra_failures_excluded":1,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":89.64285978529199,"score":89.64285978529199},"GB2-02":{"attempts":3,"playable":90.679034540698,"score":90.679034540698},"GB2-03":{"attempts":3,"playable":80.77989765512189,"score":80.77989765512189},"GB2-04":{"attempts":3,"playable":84.24007516231059,"score":84.24007516231059},"GB2-05":{"attempts":3,"playable":93.4452755026178,"score":93.4452755026178},"GB2-06":{"attempts":3,"playable":89.20188178929315,"score":89.20188178929315},"GB2-07":{"attempts":3,"playable":94.32603914594188,"score":94.32603914594188},"GB2-08":{"attempts":5,"playable":86.68122015811302,"score":86.68122015811302}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":84.74464275017975,"score":84.74464275017975},"GB2-02":{"attempts":1,"playable":96.14707622818015,"score":96.14707622818015},"GB2-03":{"attempts":1,"playable":97.21854984166579,"score":97.21854984166579},"GB2-04":{"attempts":1,"playable":94.17544696952449,"score":94.17544696952449},"GB2-05":{"attempts":1,"playable":98.04291572699371,"score":98.04291572699371},"GB2-06":{"attempts":1,"playable":99.27889371384272,"score":99.27889371384272},"GB2-07":{"attempts":1,"playable":97.88308116049026,"score":97.88308116049026},"GB2-08":{"attempts":1,"playable":93.95689545680231,"score":93.95689545680231}},"medium":{"GB2-01":{"attempts":1,"playable":93.36219094514912,"score":93.36219094514912},"GB2-02":{"attempts":1,"playable":95.38708251509495,"score":95.38708251509495},"GB2-03":{"attempts":1,"playable":92.28842791070826,"score":92.28842791070826},"GB2-04":{"attempts":1,"playable":89.07260526207534,"score":89.07260526207534},"GB2-05":{"attempts":1,"playable":90.18639676234893,"score":90.18639676234893},"GB2-06":{"attempts":1,"playable":91.2138701486663,"score":91.2138701486663},"GB2-07":{"attempts":1,"playable":93.7557699048833,"score":93.7557699048833},"GB2-08":{"attempts":2,"playable":97.03895146139887,"score":97.03895146139887}},"none":{"GB2-01":{"attempts":1,"playable":90.82174566054711,"score":90.82174566054711},"GB2-02":{"attempts":1,"playable":80.50294487881887,"score":80.50294487881887},"GB2-03":{"attempts":1,"playable":52.8327152129916,"score":52.8327152129916},"GB2-04":{"attempts":1,"playable":69.47217325533192,"score":69.47217325533192},"GB2-05":{"attempts":1,"playable":92.10651401851081,"score":92.10651401851081},"GB2-06":{"attempts":1,"playable":77.11288150537041,"score":77.11288150537041},"GB2-07":{"attempts":1,"playable":91.33926637245206,"score":91.33926637245206},"GB2-08":{"attempts":2,"playable":69.0478135561379,"score":69.0478135561379}}},"id":"claude-opus-5-5","is_recent_addition":false,"last_measured_at":"2026-10-20T11:37:56Z","match_totals_all":{"draws":877,"losses":1000,"wins":10177},"match_totals_tracks":{"highest":{"draws":74,"losses":133,"wins":3487},"medium":{"draws":116,"losses":218,"wins":3846},"none":{"draws":687,"losses":649,"wins":2844}},"model_slug":"claude-opus-5-5","overall":{"max":99.27889371384272,"mean":88.62453546742354,"min":52.8327152129916},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":2,"overall_ranking_status":"ranked","per_game":{"GB2-01":84.74464275017975,"GB2-02":96.14707622818015,"GB2-03":97.21854984166579,"GB2-04":94.17544696952449,"GB2-05":98.04291572699371,"GB2-06":99.27889371384272,"GB2-07":97.88308116049026,"GB2-08":93.95689545680231},"per_game_all":{"GB2-01":89.64285978529199,"GB2-02":90.679034540698,"GB2-03":80.77989765512189,"GB2-04":84.24007516231059,"GB2-05":93.4452755026178,"GB2-06":89.20188178929315,"GB2-07":94.32603914594188,"GB2-08":86.68122015811302},"per_game_match_totals_all":{"GB2-01":{"draws":59,"losses":118,"wins":1227},"GB2-02":{"draws":129,"losses":57,"wins":1110},"GB2-03":{"draws":326,"losses":111,"wins":901},"GB2-04":{"draws":281,"losses":79,"wins":984},"GB2-05":{"draws":0,"losses":91,"wins":1361},"GB2-06":{"draws":57,"losses":116,"wins":1195},"GB2-07":{"draws":0,"losses":73,"wins":1349},"GB2-08":{"draws":25,"losses":355,"wins":2050}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":69,"wins":391},"GB2-02":{"draws":23,"losses":4,"wins":405},"GB2-03":{"draws":3,"losses":10,"wins":433},"GB2-04":{"draws":39,"losses":7,"wins":402},"GB2-05":{"draws":0,"losses":7,"wins":477},"GB2-06":{"draws":1,"losses":0,"wins":455},"GB2-07":{"draws":0,"losses":7,"wins":467},"GB2-08":{"draws":0,"losses":29,"wins":457}},"medium":{"GB2-01":{"draws":30,"losses":16,"wins":422},"GB2-02":{"draws":10,"losses":14,"wins":408},"GB2-03":{"draws":21,"losses":26,"wins":399},"GB2-04":{"draws":34,"losses":34,"wins":380},"GB2-05":{"draws":0,"losses":47,"wins":437},"GB2-06":{"draws":21,"losses":28,"wins":407},"GB2-07":{"draws":0,"losses":27,"wins":447},"GB2-08":{"draws":0,"losses":26,"wins":946}},"none":{"GB2-01":{"draws":21,"losses":33,"wins":414},"GB2-02":{"draws":96,"losses":39,"wins":297},"GB2-03":{"draws":302,"losses":75,"wins":69},"GB2-04":{"draws":208,"losses":38,"wins":202},"GB2-05":{"draws":0,"losses":37,"wins":447},"GB2-06":{"draws":35,"losses":88,"wins":333},"GB2-07":{"draws":0,"losses":39,"wins":435},"GB2-08":{"draws":25,"losses":300,"wins":647}}},"per_game_raw_elo_all":{"GB2-01":2001.4427648601431,"GB2-02":2008.8843659851893,"GB2-03":1979.451427007386,"GB2-04":1862.968985458223,"GB2-05":2493.270136112422,"GB2-06":2319.074029340095,"GB2-07":2425.489111186793,"GB2-08":2153.516441300137},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1888.8486517040856,"GB2-02":2150.8673515923247,"GB2-03":2386.002648312433,"GB2-04":2042.6204249962825,"GB2-05":2818.3803654699163,"GB2-06":2808.389225932371,"GB2-07":2669.0204607289807,"GB2-08":2289.925581328413},"medium":{"GB2-01":2096.3072012663065,"GB2-02":2111.6910839647435,"GB2-03":2094.599134550566,"GB2-04":1904.7834317387174,"GB2-05":2284.8431577913407,"GB2-06":2232.7087374086846,"GB2-07":2365.249745907633,"GB2-08":2495.1335338973972},"none":{"GB2-01":2019.172441610037,"GB2-02":1764.0946623985005,"GB2-03":1457.752498159159,"GB2-04":1641.5030996396695,"GB2-05":2376.5868850760085,"GB2-06":1916.1241246792295,"GB2-07":2242.197126923765,"GB2-08":1675.4902086746006}},"per_game_tracks":{"highest":{"GB2-01":84.74464275017975,"GB2-02":96.14707622818015,"GB2-03":97.21854984166579,"GB2-04":94.17544696952449,"GB2-05":98.04291572699371,"GB2-06":99.27889371384272,"GB2-07":97.88308116049026,"GB2-08":93.95689545680231},"medium":{"GB2-01":93.36219094514912,"GB2-02":95.38708251509495,"GB2-03":92.28842791070826,"GB2-04":89.07260526207534,"GB2-05":90.18639676234893,"GB2-06":91.2138701486663,"GB2-07":93.7557699048833,"GB2-08":97.03895146139887},"none":{"GB2-01":90.82174566054711,"GB2-02":80.50294487881887,"GB2-03":52.8327152129916,"GB2-04":69.47217325533192,"GB2-05":92.10651401851081,"GB2-06":77.11288150537041,"GB2-07":91.33926637245206,"GB2-08":69.0478135561379}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T23:00:37Z","reasoning":{"highest":95.1809377309599,"medium":92.78816186379063,"none":77.90450680752008},"reasoning_agg":{"highest":{"max":99.27889371384272,"mean":95.1809377309599,"min":84.74464275017975},"medium":{"max":97.03895146139887,"mean":92.78816186379063,"min":89.07260526207534},"none":{"max":92.10651401851081,"mean":77.90450680752008,"min":52.8327152129916}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":17.27643092343982}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5-1:bbc1e2b29dda8249","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":5.021086745700856,"median":3.933625,"min":2.3764558334148846,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":3,"boardgame-list-prices-2026-09-08":10},"run_count":11,"token_priced_attempt_count":13,"total":48.73911793121369},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.511677676840267,"mean":1.1541937045345083,"median":1.126127596791556,"min":0.7961115304367101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":9.233549636276067},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.8940315948861309,"mean":0.7923815012907612,"median":0.7948316688813246,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":6.339052010326091}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.511677676840267,"mean":1.1541937045345083,"median":1.126127596791556,"min":0.7961115304367101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":9.233549636276065},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.8940315948861309,"mean":0.7923815012907612,"median":0.7948316688813246,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":6.339052010326091},"historical-provider-setting-intensive":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":5.021086745700856,"median":3.933625,"min":2.3764558334148846,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":3,"boardgame-list-prices-2026-09-08":10},"run_count":11,"token_priced_attempt_count":13,"total":48.7391179312137}},"codegen_cost_usd":{"admitted_cell_count":27,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":30},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":2.3225539838420417,"median":1.126127596791556,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":20,"boardgame-list-prices-2026-09-08":10},"run_count":27,"token_priced_attempt_count":30,"total":64.31171957781585},"codegen_output_tokens":{"attempt_count":35,"output_max":231035,"output_mean":46647.59375,"output_min":5610,"run_count":32},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":231035,"output_mean":80471.125,"output_min":38285,"run_count":16},"medium":{"attempt_count":9,"output_max":25949,"output_mean":17238.625,"output_min":9715,"run_count":8},"none":{"attempt_count":8,"output_max":10198,"output_mean":8409.5,"output_min":5610,"run_count":8}},"display_name":"Claude Fable 5.1","economics":{"all":88.49598123542427,"highest":94.08438594681675,"medium":84.94781483967367,"none":86.4557429197824},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[128000],"finish_reason_observations":30,"finish_reasons":["end_turn","stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":35,"provider_post_attempts":35,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":35,"requested_max_output_token_observations":10,"requested_max_output_tokens":[128000],"total_output_tokens":1492723,"total_reasoning_output_tokens":1266567,"total_visible_output_tokens":226156,"visible_token_observations":35},"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-5-1","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":11,"evaluated_cells":11,"first_pass_admitted":9,"first_pass_rate":0.8181818181818182,"game_attempts":{"GB2-01":{"admitted":1,"infra_failures_excluded":1},"GB2-02":{"admitted":1,"infra_failures_excluded":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":1,"infra_failures_excluded":1},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":2},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-05","GB2-06","GB2-08"],"infra_failures_excluded":5,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.18181818181818182}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":85.23622705573749,"score":85.23622705573749},"GB2-02":{"attempts":3,"playable":89.63769036297457,"score":89.63769036297457},"GB2-03":{"attempts":4,"playable":93.73475656514086,"score":93.73475656514086},"GB2-04":{"attempts":4,"playable":74.39145633644772,"score":74.39145633644772},"GB2-05":{"attempts":3,"playable":91.34267417839169,"score":91.34267417839169},"GB2-06":{"attempts":3,"playable":89.28093652063451,"score":89.28093652063451},"GB2-07":{"attempts":4,"playable":92.18295329468407,"score":92.18295329468407},"GB2-08":{"attempts":3,"playable":92.16115556938327,"score":92.16115556938327}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":92.95754560732603,"score":92.95754560732603},"GB2-02":{"attempts":1,"playable":94.40864574428699,"score":94.40864574428699},"GB2-03":{"attempts":2,"playable":95.6418542562993,"score":95.6418542562993},"GB2-04":{"attempts":2,"playable":87.05794039185358,"score":87.05794039185358},"GB2-05":{"attempts":1,"playable":93.26878280048379,"score":93.26878280048379},"GB2-06":{"attempts":1,"playable":98.05010854366924,"score":98.05010854366924},"GB2-07":{"attempts":2,"playable":93.85717514387697,"score":93.85717514387697},"GB2-08":{"attempts":1,"playable":97.43303508673816,"score":97.43303508673816}},"medium":{"GB2-01":{"attempts":1,"playable":73.57191245848367,"score":73.57191245848367},"GB2-02":{"attempts":1,"playable":92.01397374364979,"score":92.01397374364979},"GB2-03":{"attempts":1,"playable":91.89503153590766,"score":91.89503153590766},"GB2-04":{"attempts":1,"playable":63.580444158179986,"score":63.580444158179986},"GB2-05":{"attempts":1,"playable":88.65272571618048,"score":88.65272571618048},"GB2-06":{"attempts":1,"playable":86.63618254942314,"score":86.63618254942314},"GB2-07":{"attempts":1,"playable":93.7557699048833,"score":93.7557699048833},"GB2-08":{"attempts":1,"playable":89.47647865068137,"score":89.47647865068137}},"none":{"GB2-01":{"attempts":1,"playable":89.17922310140275,"score":89.17922310140275},"GB2-02":{"attempts":1,"playable":82.49045160098693,"score":82.49045160098693},"GB2-03":{"attempts":1,"playable":93.66738390321558,"score":93.66738390321558},"GB2-04":{"attempts":1,"playable":72.53598445930957,"score":72.53598445930957},"GB2-05":{"attempts":1,"playable":92.10651401851081,"score":92.10651401851081},"GB2-06":{"attempts":1,"playable":83.15651846881117,"score":83.15651846881117},"GB2-07":{"attempts":1,"playable":88.93591483529197,"score":88.93591483529197},"GB2-08":{"attempts":1,"playable":89.57395297073029,"score":89.57395297073029}}},"id":"claude-fable-5-1","is_recent_addition":false,"last_measured_at":"2026-10-20T11:49:26Z","match_totals_all":{"draws":706,"losses":1030,"wins":10712},"match_totals_tracks":{"highest":{"draws":116,"losses":260,"wins":4686},"medium":{"draws":276,"losses":424,"wins":2993},"none":{"draws":314,"losses":346,"wins":3033}},"model_slug":"claude-fable-5-1","overall":{"max":98.05010854366924,"mean":88.49598123542427,"min":63.580444158179986},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":3,"overall_ranking_status":"ranked","per_game":{"GB2-01":92.95754560732603,"GB2-02":94.40864574428699,"GB2-03":95.6418542562993,"GB2-04":87.05794039185358,"GB2-05":93.26878280048379,"GB2-06":98.05010854366924,"GB2-07":93.85717514387697,"GB2-08":97.43303508673816},"per_game_all":{"GB2-01":85.23622705573749,"GB2-02":89.63769036297457,"GB2-03":93.73475656514086,"GB2-04":74.39145633644772,"GB2-05":91.34267417839169,"GB2-06":89.28093652063451,"GB2-07":92.18295329468407,"GB2-08":92.16115556938327},"per_game_match_totals_all":{"GB2-01":{"draws":2,"losses":32,"wins":434},"GB2-02":{"draws":23,"losses":12,"wins":397},"GB2-03":{"draws":2,"losses":20,"wins":424},"GB2-04":{"draws":44,"losses":26,"wins":378},"GB2-05":{"draws":0,"losses":31,"wins":453},"GB2-06":{"draws":3,"losses":5,"wins":448},"GB2-07":{"draws":0,"losses":27,"wins":447},"GB2-08":{"draws":0,"losses":11,"wins":475}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":32,"wins":434},"GB2-02":{"draws":23,"losses":12,"wins":397},"GB2-03":{"draws":2,"losses":20,"wins":424},"GB2-04":{"draws":44,"losses":26,"wins":378},"GB2-05":{"draws":0,"losses":31,"wins":453},"GB2-06":{"draws":3,"losses":5,"wins":448},"GB2-07":{"draws":0,"losses":27,"wins":447},"GB2-08":{"draws":0,"losses":11,"wins":475}}},"per_game_raw_elo_all":{"GB2-01":1929.4850643624507,"GB2-02":1949.202414221927,"GB2-03":2167.540083495488,"GB2-04":1709.748243737243,"GB2-05":2344.3562357048413,"GB2-06":2246.081951494603,"GB2-07":2292.7303641675485,"GB2-08":2252.4601193071144},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2082.508506833723,"GB2-02":2068.799051317495,"GB2-03":2267.3975682263836,"GB2-04":1869.405066355737,"GB2-05":2438.078171427197,"GB2-06":2589.8377283076875,"GB2-07":2370.9955880028356,"GB2-08":2506.1269558532263},"medium":{"GB2-01":1727.5815138643352,"GB2-02":1986.4949878559146,"GB2-03":2078.5608536274385,"GB2-04":1587.9127544051235,"GB2-05":2218.403650611318,"GB2-06":2112.5021775116547,"GB2-07":2365.249745907633,"GB2-08":2124.107192408347},"none":{"GB2-01":1978.365172389294,"GB2-02":1792.3132034923715,"GB2-03":2156.661828632642,"GB2-04":1671.9269104508687,"GB2-05":2376.586885076009,"GB2-06":2035.9059486644665,"GB2-07":2141.9457585921764,"GB2-08":2127.1462096597697}},"per_game_tracks":{"highest":{"GB2-01":92.95754560732603,"GB2-02":94.40864574428699,"GB2-03":95.6418542562993,"GB2-04":87.05794039185358,"GB2-05":93.26878280048379,"GB2-06":98.05010854366924,"GB2-07":93.85717514387697,"GB2-08":97.43303508673816},"medium":{"GB2-01":73.57191245848367,"GB2-02":92.01397374364979,"GB2-03":91.89503153590766,"GB2-04":63.580444158179986,"GB2-05":88.65272571618048,"GB2-06":86.63618254942314,"GB2-07":93.7557699048833,"GB2-08":89.47647865068137},"none":{"GB2-01":89.17922310140275,"GB2-02":82.49045160098693,"GB2-03":93.66738390321558,"GB2-04":72.53598445930957,"GB2-05":92.10651401851081,"GB2-06":83.15651846881117,"GB2-07":88.93591483529197,"GB2-08":89.57395297073029}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:45:21Z","reasoning":{"highest":94.08438594681675,"medium":84.94781483967367,"none":86.4557429197824},"reasoning_agg":{"highest":{"max":98.05010854366924,"mean":94.08438594681675,"min":87.05794039185358},"medium":{"max":93.7557699048833,"mean":84.94781483967367,"min":63.580444158179986},"none":{"max":93.66738390321558,"mean":86.4557429197824,"min":72.53598445930957}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":9.136571107143084}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-1-sol:4769998e8ac60f55","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.355686,"mean":0.2665285,"median":0.263151,"min":0.174431,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.132228},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.134667,"mean":0.084337375,"median":0.0768835,"min":0.057491,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6746989999999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.057226,"mean":0.0485635,"median":0.049051,"min":0.0400035,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.38850799999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.134667,"mean":0.084337375,"median":0.0768835,"min":0.057491,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6746989999999999},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.057226,"mean":0.0485635,"median":0.049051,"min":0.0400035,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.38850799999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.355686,"mean":0.2665285,"median":0.263151,"min":0.174431,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.132228}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.355686,"mean":0.133143125,"median":0.0768835,"min":0.0400035,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":24,"token_priced_attempt_count":25,"total":3.195435},"codegen_latency_ms":{"attempt_count":25,"max_ms":926657,"mean_ms":272565.25,"min_ms":42196,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":926657,"mean_ms":625149.0,"min_ms":331732,"run_count":8},"medium":{"attempt_count":9,"max_ms":198934,"mean_ms":135760.75,"min_ms":63072,"run_count":8},"none":{"attempt_count":8,"max_ms":73464,"mean_ms":56786.0,"min_ms":42196,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":33557,"output_mean":11287.458333333334,"output_min":2159,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":33557,"output_mean":24715.125,"output_min":14936,"run_count":8},"medium":{"attempt_count":9,"output_max":9484,"output_mean":6228.625,"output_min":3242,"run_count":8},"none":{"attempt_count":8,"output_max":3711,"output_mean":2918.625,"output_min":2159,"run_count":8}},"display_name":"GPT-6.1 Sol","economics":{"all":85.77429191725858,"highest":92.67803660965436,"medium":87.23259621694265,"none":77.41224292517872},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[128000],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[128000],"total_output_tokens":270899,"total_reasoning_output_tokens":149779,"total_visible_output_tokens":121120,"visible_token_observations":25},"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":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6.1-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":67.80409429128532,"score":67.80409429128532},"GB2-02":{"attempts":3,"playable":79.20086636979178,"score":79.20086636979178},"GB2-03":{"attempts":3,"playable":93.60418502314724,"score":93.60418502314724},"GB2-04":{"attempts":3,"playable":85.12294771680116,"score":85.12294771680116},"GB2-05":{"attempts":3,"playable":95.00031341951963,"score":95.00031341951963},"GB2-06":{"attempts":3,"playable":86.3833369680642,"score":86.3833369680642},"GB2-07":{"attempts":3,"playable":95.38974746393666,"score":95.38974746393666},"GB2-08":{"attempts":3,"playable":83.68884408552262,"score":83.68884408552262}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":76.82057227740718,"score":76.82057227740718},"GB2-02":{"attempts":1,"playable":94.51740947746974,"score":94.51740947746974},"GB2-03":{"attempts":1,"playable":98.29369563948246,"score":98.29369563948246},"GB2-04":{"attempts":1,"playable":94.89503044441004,"score":94.89503044441004},"GB2-05":{"attempts":1,"playable":98.04291572699371,"score":98.04291572699371},"GB2-06":{"attempts":1,"playable":89.29213686001277,"score":89.29213686001277},"GB2-07":{"attempts":1,"playable":95.80013112143844,"score":95.80013112143844},"GB2-08":{"attempts":1,"playable":93.7624013300205,"score":93.7624013300205}},"medium":{"GB2-01":{"attempts":1,"playable":75.6685971297808,"score":75.6685971297808},"GB2-02":{"attempts":1,"playable":78.73041784525215,"score":78.73041784525215},"GB2-03":{"attempts":1,"playable":96.92368416712306,"score":96.92368416712306},"GB2-04":{"attempts":1,"playable":87.17413117171134,"score":87.17413117171134},"GB2-05":{"attempts":1,"playable":95.23674478941798,"score":95.23674478941798},"GB2-06":{"attempts":1,"playable":90.35889575470995,"score":90.35889575470995},"GB2-07":{"attempts":1,"playable":95.80013112143844,"score":95.80013112143844},"GB2-08":{"attempts":1,"playable":77.96816775610748,"score":77.96816775610748}},"none":{"GB2-01":{"attempts":1,"playable":50.92311346666798,"score":50.92311346666798},"GB2-02":{"attempts":1,"playable":64.35477178665346,"score":64.35477178665346},"GB2-03":{"attempts":1,"playable":85.59517526283616,"score":85.59517526283616},"GB2-04":{"attempts":1,"playable":73.29968153428212,"score":73.29968153428212},"GB2-05":{"attempts":1,"playable":91.72127974214719,"score":91.72127974214719},"GB2-06":{"attempts":1,"playable":79.49897828946986,"score":79.49897828946986},"GB2-07":{"attempts":1,"playable":94.5689801489331,"score":94.5689801489331},"GB2-08":{"attempts":1,"playable":79.3359631704399,"score":79.3359631704399}}},"id":"gpt-6.1-sol","is_recent_addition":false,"last_measured_at":"2026-10-20T11:37:59Z","match_totals_all":{"draws":835,"losses":1171,"wins":9076},"match_totals_tracks":{"highest":{"draws":103,"losses":213,"wins":3378},"medium":{"draws":206,"losses":373,"wins":3115},"none":{"draws":526,"losses":585,"wins":2583}},"model_slug":"gpt-6-1-sol","overall":{"max":98.29369563948246,"mean":85.77429191725857,"min":50.92311346666798},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":4,"overall_ranking_status":"ranked","per_game":{"GB2-01":76.82057227740718,"GB2-02":94.51740947746974,"GB2-03":98.29369563948246,"GB2-04":94.89503044441004,"GB2-05":98.04291572699371,"GB2-06":89.29213686001277,"GB2-07":95.80013112143844,"GB2-08":93.7624013300205},"per_game_all":{"GB2-01":67.80409429128532,"GB2-02":79.20086636979178,"GB2-03":93.60418502314724,"GB2-04":85.12294771680116,"GB2-05":95.00031341951963,"GB2-06":86.3833369680642,"GB2-07":95.38974746393666,"GB2-08":83.68884408552262},"per_game_match_totals_all":{"GB2-01":{"draws":67,"losses":428,"wins":909},"GB2-02":{"draws":410,"losses":72,"wins":814},"GB2-03":{"draws":33,"losses":73,"wins":1232},"GB2-04":{"draws":217,"losses":99,"wins":1028},"GB2-05":{"draws":0,"losses":67,"wins":1385},"GB2-06":{"draws":106,"losses":131,"wins":1131},"GB2-07":{"draws":0,"losses":57,"wins":1365},"GB2-08":{"draws":2,"losses":244,"wins":1212}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":111,"wins":357},"GB2-02":{"draws":28,"losses":9,"wins":395},"GB2-03":{"draws":2,"losses":5,"wins":439},"GB2-04":{"draws":32,"losses":7,"wins":409},"GB2-05":{"draws":0,"losses":7,"wins":477},"GB2-06":{"draws":41,"losses":27,"wins":388},"GB2-07":{"draws":0,"losses":17,"wins":457},"GB2-08":{"draws":0,"losses":30,"wins":456}},"medium":{"GB2-01":{"draws":11,"losses":111,"wins":346},"GB2-02":{"draws":126,"losses":32,"wins":274},"GB2-03":{"draws":4,"losses":11,"wins":431},"GB2-04":{"draws":34,"losses":43,"wins":371},"GB2-05":{"draws":0,"losses":21,"wins":463},"GB2-06":{"draws":31,"losses":27,"wins":398},"GB2-07":{"draws":0,"losses":17,"wins":457},"GB2-08":{"draws":0,"losses":111,"wins":375}},"none":{"GB2-01":{"draws":56,"losses":206,"wins":206},"GB2-02":{"draws":256,"losses":31,"wins":145},"GB2-03":{"draws":27,"losses":57,"wins":362},"GB2-04":{"draws":151,"losses":49,"wins":248},"GB2-05":{"draws":0,"losses":39,"wins":445},"GB2-06":{"draws":34,"losses":77,"wins":345},"GB2-07":{"draws":0,"losses":23,"wins":451},"GB2-08":{"draws":2,"losses":103,"wins":381}}},"per_game_raw_elo_all":{"GB2-01":1671.3193266968062,"GB2-02":1802.14219264257,"GB2-03":2249.5266954291637,"GB2-04":1872.4204457960666,"GB2-05":2578.101814831139,"GB2-06":2116.0174618458373,"GB2-07":2465.6937141091207,"GB2-08":1996.5149980759797},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1768.7752464907687,"GB2-02":2073.228362143411,"GB2-03":2501.5487985376462,"GB2-04":2069.987028356503,"GB2-05":2818.3803654699163,"GB2-06":2178.3466501799026,"GB2-07":2492.231169752288,"GB2-08":2281.1616948043757},"medium":{"GB2-01":1753.7821649688212,"GB2-02":1740.868630762489,"GB2-03":2360.476667490304,"GB2-04":1867.4139940809605,"GB2-05":2558.6209917434344,"GB2-06":2207.623690443258,"GB2-07":2492.231169752288,"GB2-08":1839.868225791851},"none":{"GB2-01":1491.4005686308283,"GB2-02":1592.3295850218108,"GB2-03":1886.5546202595415,"GB2-04":1679.8603149507362,"GB2-05":2357.3040872800675,"GB2-06":1962.0820449143523,"GB2-07":2412.6188028227853,"GB2-08":1868.5150736317123}},"per_game_tracks":{"highest":{"GB2-01":76.82057227740718,"GB2-02":94.51740947746974,"GB2-03":98.29369563948246,"GB2-04":94.89503044441004,"GB2-05":98.04291572699371,"GB2-06":89.29213686001277,"GB2-07":95.80013112143844,"GB2-08":93.7624013300205},"medium":{"GB2-01":75.6685971297808,"GB2-02":78.73041784525215,"GB2-03":96.92368416712306,"GB2-04":87.17413117171134,"GB2-05":95.23674478941798,"GB2-06":90.35889575470995,"GB2-07":95.80013112143844,"GB2-08":77.96816775610748},"none":{"GB2-01":50.92311346666798,"GB2-02":64.35477178665346,"GB2-03":85.59517526283616,"GB2-04":73.29968153428212,"GB2-05":91.72127974214719,"GB2-06":79.49897828946986,"GB2-07":94.5689801489331,"GB2-08":79.3359631704399}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T22:14:54Z","reasoning":{"highest":92.67803660965436,"medium":87.23259621694265,"none":77.41224292517872},"reasoning_agg":{"highest":{"max":98.29369563948246,"mean":92.67803660965436,"min":76.82057227740718},"medium":{"max":96.92368416712306,"mean":87.23259621694265,"min":75.6685971297808},"none":{"max":94.5689801489331,"mean":77.41224292517872,"min":50.92311346666798}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":15.26579368447564}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5:092cc29c5fe928e5","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"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":7.138875},"historical-provider-setting-baseline":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"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},"historical-provider-setting-intensive":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"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}},"codegen_cost_usd":{"admitted_cell_count":41,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":48},"cost_is_complete":false,"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":77.32188209503799,"highest":85.9313398599251,"medium":76.58124096663174,"none":71.90631583454406},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"first_pass_admitted":14,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"performance_rejections":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":2},"baseline":{"admitted_plugins":14,"evaluated_cells":16,"first_pass_admitted":14,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"performance_rejections":1},"GB2-07":{"admitted":1,"performance_rejections":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06","GB2-07"],"performance_rejections":2},"intensive":{"admitted_plugins":13,"evaluated_cells":16,"first_pass_admitted":13,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"performance_rejections":2},"GB2-07":{"admitted":1,"performance_rejections":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06","GB2-07"],"performance_rejections":3}},"headline_games_all":{"GB2-01":{"attempts":6,"playable":72.07113246704125,"score":72.07113246704125},"GB2-02":{"attempts":6,"playable":75.07003903313762,"score":75.07003903313762},"GB2-03":{"attempts":6,"playable":77.88227111900203,"score":77.88227111900203},"GB2-04":{"attempts":6,"playable":58.096720127220514,"score":58.096720127220514},"GB2-05":{"attempts":6,"playable":90.53501433552343,"score":90.53501433552343},"GB2-06":{"attempts":1,"playable":89.07906846645271,"score":89.07906846645271},"GB2-07":{"attempts":4,"playable":85.40419743620377,"score":85.40419743620377},"GB2-08":{"attempts":6,"playable":82.19380014713728,"score":82.19380014713728}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":69.12208880556864,"score":69.12208880556864},"GB2-02":{"attempts":2,"playable":82.69969729396965,"score":82.69969729396965},"GB2-03":{"attempts":2,"playable":95.14809608917705,"score":95.14809608917705},"GB2-04":{"attempts":2,"playable":80.99767141749209,"score":80.99767141749209},"GB2-05":{"attempts":2,"playable":93.54391847088934,"score":93.54391847088934},"GB2-07":{"attempts":1,"playable":95.80013112143844,"score":95.80013112143844},"GB2-08":{"attempts":2,"playable":84.20777582094058,"score":84.20777582094058}},"medium":{"GB2-01":{"attempts":2,"playable":71.288810831736,"score":71.288810831736},"GB2-02":{"attempts":2,"playable":70.77413122446953,"score":70.77413122446953},"GB2-03":{"attempts":2,"playable":86.73224083970302,"score":86.73224083970302},"GB2-04":{"attempts":2,"playable":44.3282080832518,"score":44.3282080832518},"GB2-05":{"attempts":2,"playable":89.12046756742103,"score":89.12046756742103},"GB2-07":{"attempts":2,"playable":84.44771289978769,"score":84.44771289978769},"GB2-08":{"attempts":2,"playable":89.37711532005304,"score":89.37711532005304}},"none":{"GB2-01":{"attempts":2,"playable":75.80249776381912,"score":75.80249776381912},"GB2-02":{"attempts":2,"playable":71.73628858097368,"score":71.73628858097368},"GB2-03":{"attempts":2,"playable":51.76647642812598,"score":51.76647642812598},"GB2-04":{"attempts":2,"playable":48.96428088091764,"score":48.96428088091764},"GB2-05":{"attempts":2,"playable":88.94065696825992,"score":88.94065696825992},"GB2-06":{"attempts":1,"playable":89.07906846645271,"score":89.07906846645271},"GB2-07":{"attempts":1,"playable":75.96474828738522,"score":75.96474828738522},"GB2-08":{"attempts":2,"playable":72.99650930041824,"score":72.99650930041824}}},"id":"claude-opus-5","is_recent_addition":false,"last_measured_at":"2026-10-20T11:39:05Z","match_totals_all":{"draws":2457,"losses":3165,"wins":13313},"match_totals_tracks":{"highest":{"draws":341,"losses":734,"wins":4927},"medium":{"draws":875,"losses":1094,"wins":4506},"none":{"draws":1241,"losses":1337,"wins":3880}},"model_slug":"claude-opus-5","overall":{"max":95.80013112143844,"mean":78.13963222036698,"min":44.3282080832518},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":5,"overall_ranking_status":"ranked","per_game":{"GB2-01":69.12208880556864,"GB2-02":82.69969729396965,"GB2-03":95.14809608917705,"GB2-04":80.99767141749209,"GB2-05":93.54391847088934,"GB2-07":95.80013112143844,"GB2-08":84.20777582094058},"per_game_all":{"GB2-01":72.07113246704125,"GB2-02":75.07003903313762,"GB2-03":77.88227111900203,"GB2-04":58.096720127220514,"GB2-05":90.53501433552343,"GB2-07":85.40419743620377,"GB2-08":82.19380014713728},"per_game_match_totals_all":{"GB2-01":{"draws":441,"losses":579,"wins":1788},"GB2-02":{"draws":886,"losses":224,"wins":1481},"GB2-03":{"draws":148,"losses":561,"wins":1967},"GB2-04":{"draws":910,"losses":701,"wins":1077},"GB2-05":{"draws":0,"losses":272,"wins":2632},"GB2-06":{"draws":25,"losses":36,"wins":395},"GB2-07":{"draws":0,"losses":280,"wins":1616},"GB2-08":{"draws":47,"losses":512,"wins":2357}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":16,"losses":286,"wins":634},"GB2-02":{"draws":178,"losses":65,"wins":621},"GB2-03":{"draws":8,"losses":40,"wins":844},"GB2-04":{"draws":139,"losses":108,"wins":649},"GB2-05":{"draws":0,"losses":60,"wins":908},"GB2-07":{"draws":0,"losses":17,"wins":457},"GB2-08":{"draws":0,"losses":158,"wins":814}},"medium":{"GB2-01":{"draws":91,"losses":229,"wins":616},"GB2-02":{"draws":359,"losses":81,"wins":423},"GB2-03":{"draws":15,"losses":122,"wins":755},"GB2-04":{"draws":408,"losses":306,"wins":182},"GB2-05":{"draws":0,"losses":105,"wins":863},"GB2-07":{"draws":0,"losses":147,"wins":801},"GB2-08":{"draws":2,"losses":104,"wins":866}},"none":{"GB2-01":{"draws":334,"losses":64,"wins":538},"GB2-02":{"draws":349,"losses":78,"wins":437},"GB2-03":{"draws":125,"losses":399,"wins":368},"GB2-04":{"draws":363,"losses":287,"wins":246},"GB2-05":{"draws":0,"losses":107,"wins":861},"GB2-06":{"draws":25,"losses":36,"wins":395},"GB2-07":{"draws":0,"losses":116,"wins":358},"GB2-08":{"draws":45,"losses":250,"wins":677}}},"per_game_raw_elo_all":{"GB2-01":1748.7837022757965,"GB2-02":1705.7292338308227,"GB2-03":1866.7405253042468,"GB2-04":1562.2595275260592,"GB2-05":2357.934142533552,"GB2-07":2119.416627575123,"GB2-08":1964.4565000495913},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1740.3662742465547,"GB2-02":1800.4066494113183,"GB2-03":2237.426627515669,"GB2-04":1782.1824338675733,"GB2-05":2590.0359321667574,"GB2-07":2492.231169752288,"GB2-08":2004.3581301173786},"medium":{"GB2-01":1713.2820341348086,"GB2-02":1652.239823376121,"GB2-03":1914.502001190549,"GB2-04":1434.1090343176993,"GB2-05":2253.295346586859,"GB2-07":2047.6409830273892,"GB2-08":2142.161910279629},"none":{"GB2-01":1792.702798446026,"GB2-02":1664.5412287050299,"GB2-03":1448.2929472065218,"GB2-04":1470.4871143929045,"GB2-05":2230.4711488470402,"GB2-06":2172.727181039574,"GB2-07":1818.3777299456929,"GB2-08":1746.849459751766}},"per_game_tracks":{"highest":{"GB2-01":69.12208880556864,"GB2-02":82.69969729396965,"GB2-03":95.14809608917705,"GB2-04":80.99767141749209,"GB2-05":93.54391847088934,"GB2-07":95.80013112143844,"GB2-08":84.20777582094058},"medium":{"GB2-01":71.288810831736,"GB2-02":70.77413122446953,"GB2-03":86.73224083970302,"GB2-04":44.3282080832518,"GB2-05":89.12046756742103,"GB2-07":84.44771289978769,"GB2-08":89.37711532005304},"none":{"GB2-01":75.80249776381912,"GB2-02":71.73628858097368,"GB2-03":51.76647642812598,"GB2-04":48.96428088091764,"GB2-05":88.94065696825992,"GB2-06":89.07906846645271,"GB2-07":75.96474828738522,"GB2-08":72.99650930041824}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-14T17:54:41Z","reasoning":{"highest":85.9313398599251,"medium":76.58124096663174,"none":71.90631583454406},"reasoning_agg":{"highest":{"max":95.80013112143844,"mean":85.9313398599251,"min":69.12208880556864},"medium":{"max":89.37711532005304,"mean":76.58124096663174,"min":44.3282080832518},"none":{"max":89.07906846645271,"mean":71.90631583454406,"min":48.96428088091764}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":14.025024025381043}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-sol:bcc368392551468c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.20679475000000003,"median":0.2051385,"min":0.185721,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.6543580000000002},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.1118895,"mean":0.07831456249999999,"median":0.0772785,"min":0.0550535,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6265165},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.052136,"mean":0.043196000000000005,"median":0.04354475,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.345568}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.1118895,"mean":0.07831456249999999,"median":0.0772785,"min":0.0550535,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6265164999999999},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.052136,"mean":0.043196000000000005,"median":0.04354475,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.34556800000000004},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.20679475000000003,"median":0.2051385,"min":0.185721,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.6543580000000002}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.10943510416666667,"median":0.0772785,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":24,"token_priced_attempt_count":25,"total":2.6264425000000005},"codegen_output_tokens":{"attempt_count":25,"output_max":20604,"output_mean":8932.083333333334,"output_min":1527,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":20604,"output_mean":18742.75,"output_min":16066,"run_count":8},"medium":{"attempt_count":9,"output_max":7600,"output_mean":5670.625,"output_min":3698,"run_count":8},"none":{"attempt_count":8,"output_max":3203,"output_mean":2382.875,"output_min":1527,"run_count":8}},"display_name":"GPT-6 Sol","economics":{"all":74.47669080172597,"highest":80.56746997009382,"medium":76.18165706876842,"none":66.68094536631567},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[65536],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[65536],"total_output_tokens":214370,"total_reasoning_output_tokens":129853,"total_visible_output_tokens":84517,"visible_token_observations":25},"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":65536,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":37.27245332374723,"score":37.27245332374723},"GB2-02":{"attempts":3,"playable":68.34499279010767,"score":68.34499279010767},"GB2-03":{"attempts":3,"playable":83.74996664093835,"score":83.74996664093835},"GB2-04":{"attempts":3,"playable":68.50822520047028,"score":68.50822520047028},"GB2-05":{"attempts":3,"playable":88.04150216684144,"score":88.04150216684144},"GB2-06":{"attempts":3,"playable":81.77812290934605,"score":81.77812290934605},"GB2-07":{"attempts":3,"playable":82.1511422576511,"score":82.1511422576511},"GB2-08":{"attempts":3,"playable":85.96712112470563,"score":85.96712112470563}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":10.026476022142008,"score":10.026476022142008},"GB2-02":{"attempts":1,"playable":83.48165813925743,"score":83.48165813925743},"GB2-03":{"attempts":1,"playable":94.16067114624566,"score":94.16067114624566},"GB2-04":{"attempts":1,"playable":88.23024296173259,"score":88.23024296173259},"GB2-05":{"attempts":1,"playable":94.05075853545293,"score":94.05075853545293},"GB2-06":{"attempts":1,"playable":90.14536171343663,"score":90.14536171343663},"GB2-07":{"attempts":1,"playable":94.77316514386038,"score":94.77316514386038},"GB2-08":{"attempts":1,"playable":89.67142609862297,"score":89.67142609862297}},"medium":{"GB2-01":{"attempts":1,"playable":39.57452256372167,"score":39.57452256372167},"GB2-02":{"attempts":1,"playable":69.33409189343118,"score":69.33409189343118},"GB2-03":{"attempts":1,"playable":75.08281874712162,"score":75.08281874712162},"GB2-04":{"attempts":1,"playable":73.29968153428212,"score":73.29968153428212},"GB2-05":{"attempts":1,"playable":91.72127974214719,"score":91.72127974214719},"GB2-06":{"attempts":1,"playable":81.37584046337942,"score":81.37584046337942},"GB2-07":{"attempts":1,"playable":94.36516623630544,"score":94.36516623630544},"GB2-08":{"attempts":1,"playable":84.69985536975864,"score":84.69985536975864}},"none":{"GB2-01":{"attempts":1,"playable":62.21636138537801,"score":62.21636138537801},"GB2-02":{"attempts":1,"playable":52.219228337634405,"score":52.219228337634405},"GB2-03":{"attempts":1,"playable":82.00641002944779,"score":82.00641002944779},"GB2-04":{"attempts":1,"playable":43.99475110539615,"score":43.99475110539615},"GB2-05":{"attempts":1,"playable":78.35246822292417,"score":78.35246822292417},"GB2-06":{"attempts":1,"playable":73.8131665512221,"score":73.8131665512221},"GB2-07":{"attempts":1,"playable":57.31509539278746,"score":57.31509539278746},"GB2-08":{"attempts":1,"playable":83.5300819057353,"score":83.5300819057353}}},"id":"gpt-6-sol","is_recent_addition":false,"last_measured_at":"2026-10-20T11:13:33Z","match_totals_all":{"draws":1470,"losses":2143,"wins":7469},"match_totals_tracks":{"highest":{"draws":225,"losses":611,"wins":2858},"medium":{"draws":596,"losses":598,"wins":2500},"none":{"draws":649,"losses":934,"wins":2111}},"model_slug":"gpt-6-sol","overall":{"max":94.77316514386038,"mean":74.47669080172597,"min":10.026476022142008},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":6,"overall_ranking_status":"ranked","per_game":{"GB2-01":10.026476022142008,"GB2-02":83.48165813925743,"GB2-03":94.16067114624566,"GB2-04":88.23024296173259,"GB2-05":94.05075853545293,"GB2-06":90.14536171343663,"GB2-07":94.77316514386038,"GB2-08":89.67142609862297},"per_game_all":{"GB2-01":37.27245332374723,"GB2-02":68.34499279010767,"GB2-03":83.74996664093835,"GB2-04":68.50822520047028,"GB2-05":88.04150216684144,"GB2-06":81.77812290934605,"GB2-07":82.1511422576511,"GB2-08":85.96712112470563},"per_game_match_totals_all":{"GB2-01":{"draws":197,"losses":794,"wins":413},"GB2-02":{"draws":583,"losses":131,"wins":582},"GB2-03":{"draws":72,"losses":202,"wins":1064},"GB2-04":{"draws":476,"losses":198,"wins":670},"GB2-05":{"draws":0,"losses":173,"wins":1279},"GB2-06":{"draws":120,"losses":190,"wins":1058},"GB2-07":{"draws":0,"losses":256,"wins":1166},"GB2-08":{"draws":22,"losses":199,"wins":1237}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":29,"losses":410,"wins":29},"GB2-02":{"draws":115,"losses":16,"wins":301},"GB2-03":{"draws":4,"losses":25,"wins":417},"GB2-04":{"draws":50,"losses":30,"wins":368},"GB2-05":{"draws":0,"losses":27,"wins":457},"GB2-06":{"draws":27,"losses":30,"wins":399},"GB2-07":{"draws":0,"losses":22,"wins":452},"GB2-08":{"draws":0,"losses":51,"wins":435}},"medium":{"GB2-01":{"draws":155,"losses":210,"wins":103},"GB2-02":{"draws":200,"losses":37,"wins":195},"GB2-03":{"draws":37,"losses":104,"wins":305},"GB2-04":{"draws":145,"losses":52,"wins":251},"GB2-05":{"draws":0,"losses":39,"wins":445},"GB2-06":{"draws":48,"losses":61,"wins":347},"GB2-07":{"draws":0,"losses":24,"wins":450},"GB2-08":{"draws":11,"losses":71,"wins":404}},"none":{"GB2-01":{"draws":13,"losses":174,"wins":281},"GB2-02":{"draws":268,"losses":78,"wins":86},"GB2-03":{"draws":31,"losses":73,"wins":342},"GB2-04":{"draws":281,"losses":116,"wins":51},"GB2-05":{"draws":0,"losses":107,"wins":377},"GB2-06":{"draws":45,"losses":99,"wins":312},"GB2-07":{"draws":0,"losses":210,"wins":264},"GB2-08":{"draws":11,"losses":77,"wins":398}}},"per_game_raw_elo_all":{"GB2-01":1326.8860112483417,"GB2-02":1646.144144691778,"GB2-03":1896.6655817286435,"GB2-04":1666.3576331247198,"GB2-05":2244.400361016734,"GB2-06":2018.4618182226484,"GB2-07":2122.961907426509,"GB2-08":2028.4851915222855},"per_game_raw_elo_tracks":{"highest":{"GB2-01":995.9661064404579,"GB2-02":1807.409263578661,"GB2-03":2181.4611724676583,"GB2-04":1887.590484404198,"GB2-05":2482.939211534385,"GB2-06":2201.5983612838895,"GB2-07":2425.0920736882163,"GB2-08":2130.203141737538},"medium":{"GB2-01":1382.5593291074117,"GB2-02":1638.0742609730753,"GB2-03":1697.9529957441537,"GB2-04":1679.8603149507362,"GB2-05":2357.3040872800675,"GB2-06":1999.3379916783801,"GB2-07":2400.4129628650066,"GB2-08":1991.9573605339147},"none":{"GB2-01":1602.1325981971552,"GB2-02":1492.9489095235974,"GB2-03":1810.5825769741177,"GB2-04":1431.6221000192252,"GB2-05":1892.95778423575,"GB2-06":1854.4491017056753,"GB2-07":1543.3806857263032,"GB2-08":1963.2950722954051}},"per_game_tracks":{"highest":{"GB2-01":10.026476022142008,"GB2-02":83.48165813925743,"GB2-03":94.16067114624566,"GB2-04":88.23024296173259,"GB2-05":94.05075853545293,"GB2-06":90.14536171343663,"GB2-07":94.77316514386038,"GB2-08":89.67142609862297},"medium":{"GB2-01":39.57452256372167,"GB2-02":69.33409189343118,"GB2-03":75.08281874712162,"GB2-04":73.29968153428212,"GB2-05":91.72127974214719,"GB2-06":81.37584046337942,"GB2-07":94.36516623630544,"GB2-08":84.69985536975864},"none":{"GB2-01":62.21636138537801,"GB2-02":52.219228337634405,"GB2-03":82.00641002944779,"GB2-04":43.99475110539615,"GB2-05":78.35246822292417,"GB2-06":73.8131665512221,"GB2-07":57.31509539278746,"GB2-08":83.5300819057353}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T22:40:34Z","reasoning":{"highest":80.56746997009382,"medium":76.18165706876842,"none":66.68094536631567},"reasoning_agg":{"highest":{"max":94.77316514386038,"mean":80.56746997009382,"min":10.026476022142008},"medium":{"max":94.36516623630544,"mean":76.18165706876842,"min":39.57452256372167},"none":{"max":83.5300819057353,"mean":66.68094536631567,"min":43.99475110539615}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":13.886524603778156}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-sol:21b3ef9c75b3fd07","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.7965692187500001,"median":0.7419175,"min":0.6308437499999999,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":6.37255375},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.24740375,"mean":0.229063125,"median":0.23243875,"min":0.20046375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.832505},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.15394249999999998,"mean":0.12786562499999998,"median":0.13029000000000002,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.022925}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.24740375,"mean":0.229063125,"median":0.23243875,"min":0.20046375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.832505},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.15394249999999998,"mean":0.12786562499999998,"median":0.13029000000000002,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.022925},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.7965692187500001,"median":0.7419175,"min":0.6308437499999999,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":6.37255375}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.3844993229166666,"median":0.23243875,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":9.227983749999998},"codegen_output_tokens":{"attempt_count":25,"output_max":35149,"output_mean":11102.833333333334,"output_min":1851,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":35149,"output_mean":24638.75,"output_min":19522,"run_count":8},"medium":{"attempt_count":8,"output_max":6769,"output_mean":6021.5,"output_min":5176,"run_count":8},"none":{"attempt_count":8,"output_max":3391,"output_mean":2648.25,"output_min":1851,"run_count":8}},"display_name":"GPT-5.6 Sol","economics":{"all":68.34187181109105,"highest":81.08768126915385,"medium":66.82022742998268,"none":57.11770673413663},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"total_output_tokens":266468,"total_reasoning_output_tokens":151113,"total_visible_output_tokens":115355,"visible_token_observations":25},"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-5.6-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":75.10324864458863,"score":75.10324864458863},"GB2-02":{"attempts":3,"playable":62.47730603415467,"score":62.47730603415467},"GB2-03":{"attempts":3,"playable":65.9799409279745,"score":65.9799409279745},"GB2-04":{"attempts":3,"playable":68.03066948259465,"score":68.03066948259465},"GB2-05":{"attempts":3,"playable":68.88646974577567,"score":68.88646974577567},"GB2-06":{"attempts":3,"playable":62.423785401028915,"score":62.423785401028915},"GB2-07":{"attempts":3,"playable":69.32461981587764,"score":69.32461981587764},"GB2-08":{"attempts":3,"playable":74.50893443673378,"score":74.50893443673378}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":76.29706265938827,"score":76.29706265938827},"GB2-02":{"attempts":1,"playable":74.72183691156071,"score":74.72183691156071},"GB2-03":{"attempts":1,"playable":81.6045655916751,"score":81.6045655916751},"GB2-04":{"attempts":1,"playable":84.73269236807019,"score":84.73269236807019},"GB2-05":{"attempts":1,"playable":75.48597795585601,"score":75.48597795585601},"GB2-06":{"attempts":1,"playable":85.0507349862858,"score":85.0507349862858},"GB2-07":{"attempts":1,"playable":88.93591483529197,"score":88.93591483529197},"GB2-08":{"attempts":1,"playable":81.87266484510275,"score":81.87266484510275}},"medium":{"GB2-01":{"attempts":1,"playable":68.95136568627734,"score":68.95136568627734},"GB2-02":{"attempts":1,"playable":66.62270071458425,"score":66.62270071458425},"GB2-03":{"attempts":1,"playable":62.38963723226465,"score":62.38963723226465},"GB2-04":{"attempts":1,"playable":78.29357217645955,"score":78.29357217645955},"GB2-05":{"attempts":1,"playable":76.92238753405299,"score":76.92238753405299},"GB2-06":{"attempts":1,"playable":41.086154769249546,"score":41.086154769249546},"GB2-07":{"attempts":1,"playable":72.19597206212278,"score":72.19597206212278},"GB2-08":{"attempts":1,"playable":68.10002926485032,"score":68.10002926485032}},"none":{"GB2-01":{"attempts":1,"playable":80.06131758810027,"score":80.06131758810027},"GB2-02":{"attempts":1,"playable":46.087380476319034,"score":46.087380476319034},"GB2-03":{"attempts":1,"playable":53.945619959983745,"score":53.945619959983745},"GB2-04":{"attempts":1,"playable":41.06574390325419,"score":41.06574390325419},"GB2-05":{"attempts":1,"playable":54.251043747418,"score":54.251043747418},"GB2-06":{"attempts":1,"playable":61.134466447551404,"score":61.134466447551404},"GB2-07":{"attempts":1,"playable":46.841972550218166,"score":46.841972550218166},"GB2-08":{"attempts":1,"playable":73.55410920024829,"score":73.55410920024829}}},"id":"gpt-5.6-sol","is_recent_addition":false,"last_measured_at":"2026-10-20T07:18:35Z","match_totals_all":{"draws":1593,"losses":2820,"wins":6669},"match_totals_tracks":{"highest":{"draws":274,"losses":582,"wins":2838},"medium":{"draws":526,"losses":1008,"wins":2160},"none":{"draws":793,"losses":1230,"wins":1671}},"model_slug":"gpt-5-6-sol","overall":{"max":88.93591483529197,"mean":68.34187181109105,"min":41.06574390325419},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":7,"overall_ranking_status":"ranked","per_game":{"GB2-01":76.29706265938827,"GB2-02":74.72183691156071,"GB2-03":81.6045655916751,"GB2-04":84.73269236807019,"GB2-05":75.48597795585601,"GB2-06":85.0507349862858,"GB2-07":88.93591483529197,"GB2-08":81.87266484510275},"per_game_all":{"GB2-01":75.10324864458863,"GB2-02":62.47730603415467,"GB2-03":65.9799409279745,"GB2-04":68.03066948259465,"GB2-05":68.88646974577567,"GB2-06":62.423785401028915,"GB2-07":69.32461981587764,"GB2-08":74.50893443673378},"per_game_match_totals_all":{"GB2-01":{"draws":113,"losses":301,"wins":990},"GB2-02":{"draws":687,"losses":157,"wins":452},"GB2-03":{"draws":180,"losses":404,"wins":754},"GB2-04":{"draws":479,"losses":203,"wins":662},"GB2-05":{"draws":0,"losses":458,"wins":994},"GB2-06":{"draws":27,"losses":517,"wins":824},"GB2-07":{"draws":0,"losses":448,"wins":974},"GB2-08":{"draws":107,"losses":332,"wins":1019}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":107,"wins":348},"GB2-02":{"draws":164,"losses":31,"wins":237},"GB2-03":{"draws":5,"losses":88,"wins":353},"GB2-04":{"draws":75,"losses":34,"wins":339},"GB2-05":{"draws":0,"losses":121,"wins":363},"GB2-06":{"draws":17,"losses":59,"wins":380},"GB2-07":{"draws":0,"losses":51,"wins":423},"GB2-08":{"draws":0,"losses":91,"wins":395}},"medium":{"GB2-01":{"draws":99,"losses":99,"wins":270},"GB2-02":{"draws":196,"losses":51,"wins":185},"GB2-03":{"draws":47,"losses":159,"wins":240},"GB2-04":{"draws":115,"losses":44,"wins":289},"GB2-05":{"draws":0,"losses":114,"wins":370},"GB2-06":{"draws":7,"losses":276,"wins":173},"GB2-07":{"draws":0,"losses":135,"wins":339},"GB2-08":{"draws":62,"losses":130,"wins":294}},"none":{"GB2-01":{"draws":1,"losses":95,"wins":372},"GB2-02":{"draws":327,"losses":75,"wins":30},"GB2-03":{"draws":128,"losses":157,"wins":161},"GB2-04":{"draws":289,"losses":125,"wins":34},"GB2-05":{"draws":0,"losses":223,"wins":261},"GB2-06":{"draws":3,"losses":182,"wins":271},"GB2-07":{"draws":0,"losses":262,"wins":212},"GB2-08":{"draws":45,"losses":111,"wins":330}}},"per_game_raw_elo_all":{"GB2-01":1749.8162686892476,"GB2-02":1583.9242227803254,"GB2-03":1606.4691650397028,"GB2-04":1656.8293996745715,"GB2-05":1731.976833627912,"GB2-06":1676.0347863201987,"GB2-07":1769.2516085030682,"GB2-08":1779.496566992024},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1761.9046747078073,"GB2-02":1693.5463691299715,"GB2-03":1803.0058670594406,"GB2-04":1825.5064604040435,"GB2-05":1829.9625604261719,"GB2-06":2076.572636675549,"GB2-07":2141.9457585921764,"GB2-08":1924.473724341564},"medium":{"GB2-01":1673.7940876945804,"GB2-02":1612.6442731265402,"GB2-03":1548.5666900398428,"GB2-04":1736.1530314533827,"GB2-05":1860.478461798299,"GB2-06":1319.1174094143282,"GB2-07":1754.7189461160124,"GB2-08":1660.1202004647935},"none":{"GB2-01":1813.750043665355,"GB2-02":1445.582026084465,"GB2-03":1467.8349380198251,"GB2-04":1408.828707166288,"GB2-05":1505.489478659265,"GB2-06":1632.414312870719,"GB2-07":1411.090120801016,"GB2-08":1753.8957761697145}},"per_game_tracks":{"highest":{"GB2-01":76.29706265938827,"GB2-02":74.72183691156071,"GB2-03":81.6045655916751,"GB2-04":84.73269236807019,"GB2-05":75.48597795585601,"GB2-06":85.0507349862858,"GB2-07":88.93591483529197,"GB2-08":81.87266484510275},"medium":{"GB2-01":68.95136568627734,"GB2-02":66.62270071458425,"GB2-03":62.38963723226465,"GB2-04":78.29357217645955,"GB2-05":76.92238753405299,"GB2-06":41.086154769249546,"GB2-07":72.19597206212278,"GB2-08":68.10002926485032},"none":{"GB2-01":80.06131758810027,"GB2-02":46.087380476319034,"GB2-03":53.945619959983745,"GB2-04":41.06574390325419,"GB2-05":54.251043747418,"GB2-06":61.134466447551404,"GB2-07":46.841972550218166,"GB2-08":73.55410920024829}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T22:45:33Z","reasoning":{"highest":81.08768126915385,"medium":66.82022742998268,"none":57.11770673413663},"reasoning_agg":{"highest":{"max":88.93591483529197,"mean":81.08768126915385,"min":74.72183691156071},"medium":{"max":78.29357217645955,"mean":66.82022742998268,"min":41.086154769249546},"none":{"max":80.06131758810027,"mean":57.11770673413663,"min":41.06574390325419}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":23.969974535017215}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5:cd329d16ad5e23ab","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":1.47056875,"median":1.411685,"min":0.98262,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":11.76455},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.73774,"mean":0.5233875,"median":0.47084000000000004,"min":0.34112,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":4.1871},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.35085,"mean":0.28860625,"median":0.282885,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.30885}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.73774,"mean":0.5233875,"median":0.47084000000000004,"min":0.34112,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":4.1871},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.35085,"mean":0.28860625,"median":0.282885,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.3088499999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":1.47056875,"median":1.411685,"min":0.98262,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":11.76455}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":0.7608541666666667,"median":0.47084000000000004,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":18.260499999999997},"codegen_output_tokens":{"attempt_count":24,"output_max":40578,"output_mean":12704.708333333334,"output_min":2179,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":40578,"output_mean":26899.0,"output_min":17366,"run_count":8},"medium":{"attempt_count":8,"output_max":12403,"output_mean":7955.375,"output_min":4188,"run_count":8},"none":{"attempt_count":8,"output_max":4224,"output_mean":3259.75,"output_min":2179,"run_count":8}},"display_name":"Claude Fable 5","economics":{"all":67.15170299197061,"highest":75.13488860632076,"medium":65.96233926799736,"none":60.357881101593705},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":24,"effective_max_output_tokens":[128000],"finish_reason_observations":24,"finish_reasons":["end_turn"],"indexed_attempts":24,"output_token_observations":24,"provider_post_attempt_observations":24,"provider_post_attempts":24,"reasoning_token_observations":24,"reconciliation_get_attempt_observations":24,"requested_max_output_token_observations":24,"requested_max_output_tokens":[128000],"total_output_tokens":304913,"total_reasoning_output_tokens":206534,"total_visible_output_tokens":98379,"visible_token_observations":24},"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-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":77.88335222846315,"score":77.88335222846315},"GB2-02":{"attempts":3,"playable":60.52801745237881,"score":60.52801745237881},"GB2-03":{"attempts":3,"playable":47.819450280134504,"score":47.819450280134504},"GB2-04":{"attempts":3,"playable":60.13932933101379,"score":60.13932933101379},"GB2-05":{"attempts":3,"playable":64.69141223888018,"score":64.69141223888018},"GB2-06":{"attempts":3,"playable":81.81009018020585,"score":81.81009018020585},"GB2-07":{"attempts":3,"playable":67.04521739583215,"score":67.04521739583215},"GB2-08":{"attempts":3,"playable":77.29675482885644,"score":77.29675482885644}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":86.19461557245239,"score":86.19461557245239},"GB2-02":{"attempts":1,"playable":79.3957679483841,"score":79.3957679483841},"GB2-03":{"attempts":1,"playable":86.88031498424452,"score":86.88031498424452},"GB2-04":{"attempts":1,"playable":86.96250289564354,"score":86.96250289564354},"GB2-05":{"attempts":1,"playable":56.34348939412628,"score":56.34348939412628},"GB2-06":{"attempts":1,"playable":86.21278500782272,"score":86.21278500782272},"GB2-07":{"attempts":1,"playable":65.85823561152807,"score":65.85823561152807},"GB2-08":{"attempts":1,"playable":53.23139743636441,"score":53.23139743636441}},"medium":{"GB2-01":{"attempts":1,"playable":76.08760417835484,"score":76.08760417835484},"GB2-02":{"attempts":1,"playable":58.424534918777724,"score":58.424534918777724},"GB2-03":{"attempts":1,"playable":21.33566415205083,"score":21.33566415205083},"GB2-04":{"attempts":1,"playable":54.19508553681366,"score":54.19508553681366},"GB2-05":{"attempts":1,"playable":69.48892452812613,"score":69.48892452812613},"GB2-06":{"attempts":1,"playable":81.79410613667615,"score":81.79410613667615},"GB2-07":{"attempts":1,"playable":73.58354922037506,"score":73.58354922037506},"GB2-08":{"attempts":1,"playable":92.78924547280458,"score":92.78924547280458}},"none":{"GB2-01":{"attempts":1,"playable":71.36783693458224,"score":71.36783693458224},"GB2-02":{"attempts":1,"playable":43.763749489974614,"score":43.763749489974614},"GB2-03":{"attempts":1,"playable":35.24237170410818,"score":35.24237170410818},"GB2-04":{"attempts":1,"playable":39.26039956058416,"score":39.26039956058416},"GB2-05":{"attempts":1,"playable":68.24182279438811,"score":68.24182279438811},"GB2-06":{"attempts":1,"playable":77.42337939611865,"score":77.42337939611865},"GB2-07":{"attempts":1,"playable":61.69386735559333,"score":61.69386735559333},"GB2-08":{"attempts":1,"playable":85.86962157740032,"score":85.86962157740032}}},"id":"claude-fable-5","is_recent_addition":false,"last_measured_at":"2026-10-20T11:22:52Z","match_totals_all":{"draws":1991,"losses":2716,"wins":6375},"match_totals_tracks":{"highest":{"draws":480,"losses":719,"wins":2495},"medium":{"draws":674,"losses":931,"wins":2089},"none":{"draws":837,"losses":1066,"wins":1791}},"model_slug":"claude-fable-5","overall":{"max":92.78924547280458,"mean":67.15170299197061,"min":21.33566415205083},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":8,"overall_ranking_status":"ranked","per_game":{"GB2-01":86.19461557245239,"GB2-02":79.3957679483841,"GB2-03":86.88031498424452,"GB2-04":86.96250289564354,"GB2-05":56.34348939412628,"GB2-06":86.21278500782272,"GB2-07":65.85823561152807,"GB2-08":53.23139743636441},"per_game_all":{"GB2-01":77.88335222846315,"GB2-02":60.52801745237881,"GB2-03":47.819450280134504,"GB2-04":60.13932933101379,"GB2-05":64.69141223888018,"GB2-06":81.81009018020585,"GB2-07":67.04521739583215,"GB2-08":77.29675482885644},"per_game_match_totals_all":{"GB2-01":{"draws":93,"losses":271,"wins":1040},"GB2-02":{"draws":701,"losses":175,"wins":420},"GB2-03":{"draws":307,"losses":575,"wins":456},"GB2-04":{"draws":603,"losses":248,"wins":493},"GB2-05":{"draws":0,"losses":519,"wins":933},"GB2-06":{"draws":58,"losses":220,"wins":1090},"GB2-07":{"draws":0,"losses":483,"wins":939},"GB2-08":{"draws":229,"losses":225,"wins":1004}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":66,"wins":402},"GB2-02":{"draws":122,"losses":31,"wins":279},"GB2-03":{"draws":46,"losses":41,"wins":359},"GB2-04":{"draws":66,"losses":28,"wins":354},"GB2-05":{"draws":0,"losses":213,"wins":271},"GB2-06":{"draws":18,"losses":53,"wins":385},"GB2-07":{"draws":0,"losses":167,"wins":307},"GB2-08":{"draws":228,"losses":120,"wins":138}},"medium":{"GB2-01":{"draws":35,"losses":97,"wins":336},"GB2-02":{"draws":260,"losses":55,"wins":117},"GB2-03":{"draws":93,"losses":315,"wins":38},"GB2-04":{"draws":260,"losses":81,"wins":107},"GB2-05":{"draws":0,"losses":150,"wins":334},"GB2-06":{"draws":26,"losses":70,"wins":360},"GB2-07":{"draws":0,"losses":128,"wins":346},"GB2-08":{"draws":0,"losses":35,"wins":451}},"none":{"GB2-01":{"draws":58,"losses":108,"wins":302},"GB2-02":{"draws":319,"losses":89,"wins":24},"GB2-03":{"draws":168,"losses":219,"wins":59},"GB2-04":{"draws":277,"losses":139,"wins":32},"GB2-05":{"draws":0,"losses":156,"wins":328},"GB2-06":{"draws":14,"losses":97,"wins":345},"GB2-07":{"draws":0,"losses":188,"wins":286},"GB2-08":{"draws":1,"losses":70,"wins":415}}},"per_game_raw_elo_all":{"GB2-01":1792.026209998523,"GB2-02":1573.11145558795,"GB2-03":1461.5862614817559,"GB2-04":1589.6497335538634,"GB2-05":1650.5851626675687,"GB2-06":2010.8481027533915,"GB2-07":1679.3108458876277,"GB2-08":1907.1336201776483},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1915.568767872646,"GB2-02":1749.3951922881538,"GB2-03":1918.2861815054152,"GB2-04":1863.5359255368576,"GB2-05":1532.1726757898205,"GB2-06":2102.7060978492545,"GB2-07":1659.1583519010167,"GB2-08":1459.4685866217492},"medium":{"GB2-01":1759.1826907703526,"GB2-02":1542.2678531886436,"GB2-03":1163.7650979315567,"GB2-04":1510.7889612948888,"GB2-05":1719.9035564744804,"GB2-06":2007.8073890314695,"GB2-07":1777.3997080260224,"GB2-08":2240.0989964042383},"none":{"GB2-01":1701.32717135257,"GB2-02":1427.6713212870527,"GB2-03":1302.7075050082954,"GB2-04":1394.6243138298435,"GB2-05":1699.6792557384056,"GB2-06":1922.0308213794503,"GB2-07":1601.374477735844,"GB2-08":2021.8332775069573}},"per_game_tracks":{"highest":{"GB2-01":86.19461557245239,"GB2-02":79.3957679483841,"GB2-03":86.88031498424452,"GB2-04":86.96250289564354,"GB2-05":56.34348939412628,"GB2-06":86.21278500782272,"GB2-07":65.85823561152807,"GB2-08":53.23139743636441},"medium":{"GB2-01":76.08760417835484,"GB2-02":58.424534918777724,"GB2-03":21.33566415205083,"GB2-04":54.19508553681366,"GB2-05":69.48892452812613,"GB2-06":81.79410613667615,"GB2-07":73.58354922037506,"GB2-08":92.78924547280458},"none":{"GB2-01":71.36783693458224,"GB2-02":43.763749489974614,"GB2-03":35.24237170410818,"GB2-04":39.26039956058416,"GB2-05":68.24182279438811,"GB2-06":77.42337939611865,"GB2-07":61.69386735559333,"GB2-08":85.86962157740032}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T22:00:28Z","reasoning":{"highest":75.13488860632076,"medium":65.96233926799736,"none":60.357881101593705},"reasoning_agg":{"highest":{"max":86.96250289564354,"mean":75.13488860632076,"min":53.23139743636441},"medium":{"max":92.78924547280458,"mean":65.96233926799736,"min":21.33566415205083},"none":{"max":85.86962157740032,"mean":60.357881101593705,"min":35.24237170410818}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":14.777007504727052}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-wonder:15240191bfce2009","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.680268,"mean":0.4875944,"median":0.46494,"min":0.362124,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":3.9007551999999994},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.4270272,"mean":0.2502732,"median":0.206604,"min":0.16216,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":2.0021856},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.187324,"mean":0.12070595,"median":0.10780200000000001,"min":0.09556,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.9656475999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.4270272,"mean":0.2502732,"median":0.206604,"min":0.16216,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":2.0021856},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.187324,"mean":0.12070595,"median":0.10780200000000001,"min":0.09556,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.9656475999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.680268,"mean":0.4875944,"median":0.46494,"min":0.362124,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":3.9007552}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.680268,"mean":0.2861911833333333,"median":0.206604,"min":0.09556,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":30},"recorded_attempt_count":30,"run_count":24,"total":6.868588399999999},"codegen_latency_ms":{"attempt_count":30,"max_ms":235793,"mean_ms":83718.41666666667,"min_ms":17910,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":235793,"mean_ms":170391.375,"min_ms":123596,"run_count":8},"medium":{"attempt_count":11,"max_ms":84789,"mean_ms":58477.125,"min_ms":40383,"run_count":8},"none":{"attempt_count":10,"max_ms":29743,"mean_ms":22286.75,"min_ms":17910,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":29674,"output_mean":12261.208333333334,"output_min":3304,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":29674,"output_mean":22547.25,"output_min":16651,"run_count":8},"medium":{"attempt_count":11,"output_max":17493,"output_mean":10166.125,"output_min":6634,"run_count":8},"none":{"attempt_count":10,"output_max":5361,"output_mean":4070.25,"output_min":3304,"run_count":8}},"display_name":"Muse Wonder","economics":{"all":66.26325892808232,"highest":78.52911170489202,"medium":63.561311445045824,"none":56.699353634309105},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":30,"effective_max_output_tokens":[943718],"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":30,"provider_post_attempts":30,"reasoning_token_observations":30,"reconciliation_get_attempt_observations":30,"requested_max_output_token_observations":30,"requested_max_output_tokens":[943718],"total_output_tokens":294269,"total_reasoning_output_tokens":154600,"total_visible_output_tokens":139669,"visible_token_observations":30},"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":943718,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-wonder","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":69.3986690700849,"score":69.3986690700849},"GB2-02":{"attempts":3,"playable":55.00166099204412,"score":55.00166099204412},"GB2-03":{"attempts":3,"playable":45.554471536188764,"score":45.554471536188764},"GB2-04":{"attempts":3,"playable":58.37032086945252,"score":58.37032086945252},"GB2-05":{"attempts":3,"playable":87.73528716835862,"score":87.73528716835862},"GB2-06":{"attempts":3,"playable":76.80453009537781,"score":76.80453009537781},"GB2-07":{"attempts":3,"playable":71.41218750997895,"score":71.41218750997895},"GB2-08":{"attempts":3,"playable":65.82894418317285,"score":65.82894418317285}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":85.67723495574323,"score":85.67723495574323},"GB2-02":{"attempts":1,"playable":66.73589887844727,"score":66.73589887844727},"GB2-03":{"attempts":1,"playable":83.4078077948239,"score":83.4078077948239},"GB2-04":{"attempts":1,"playable":81.20269299832897,"score":81.20269299832897},"GB2-05":{"attempts":1,"playable":92.88008983338887,"score":92.88008983338887},"GB2-06":{"attempts":1,"playable":83.99726909131363,"score":83.99726909131363},"GB2-07":{"attempts":1,"playable":72.98876238603216,"score":72.98876238603216},"GB2-08":{"attempts":1,"playable":61.343137701058104,"score":61.343137701058104}},"medium":{"GB2-01":{"attempts":1,"playable":53.88276778783554,"score":53.88276778783554},"GB2-02":{"attempts":1,"playable":55.901917993986864,"score":55.901917993986864},"GB2-03":{"attempts":1,"playable":36.40972752118416,"score":36.40972752118416},"GB2-04":{"attempts":1,"playable":39.82479781827604,"score":39.82479781827604},"GB2-05":{"attempts":1,"playable":85.35898835879064,"score":85.35898835879064},"GB2-06":{"attempts":1,"playable":77.00942906687878,"score":77.00942906687878},"GB2-07":{"attempts":1,"playable":87.53479086895358,"score":87.53479086895358},"GB2-08":{"attempts":1,"playable":72.56807214446098,"score":72.56807214446098}},"none":{"GB2-01":{"attempts":1,"playable":68.63600446667594,"score":68.63600446667594},"GB2-02":{"attempts":1,"playable":42.36716610369823,"score":42.36716610369823},"GB2-03":{"attempts":1,"playable":16.845879292558237,"score":16.845879292558237},"GB2-04":{"attempts":1,"playable":54.083471791752544,"score":54.083471791752544},"GB2-05":{"attempts":1,"playable":84.96678331289638,"score":84.96678331289638},"GB2-06":{"attempts":1,"playable":69.40689212794105,"score":69.40689212794105},"GB2-07":{"attempts":1,"playable":53.71300927495108,"score":53.71300927495108},"GB2-08":{"attempts":1,"playable":63.57562270399947,"score":63.57562270399947}}},"id":"meta/muse-wonder","is_recent_addition":false,"last_measured_at":"2026-10-14T17:59:31Z","match_totals_all":{"draws":2049,"losses":2781,"wins":6252},"match_totals_tracks":{"highest":{"draws":475,"losses":580,"wins":2639},"medium":{"draws":607,"losses":1060,"wins":2027},"none":{"draws":967,"losses":1141,"wins":1586}},"model_slug":"meta-muse-wonder","overall":{"max":92.88008983338887,"mean":66.26325892808232,"min":16.845879292558237},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":9,"overall_ranking_status":"ranked","per_game":{"GB2-01":85.67723495574323,"GB2-02":66.73589887844727,"GB2-03":83.4078077948239,"GB2-04":81.20269299832897,"GB2-05":92.88008983338887,"GB2-06":83.99726909131363,"GB2-07":72.98876238603216,"GB2-08":61.343137701058104},"per_game_all":{"GB2-01":69.3986690700849,"GB2-02":55.00166099204412,"GB2-03":45.554471536188764,"GB2-04":58.37032086945252,"GB2-05":87.73528716835862,"GB2-06":76.80453009537781,"GB2-07":71.41218750997895,"GB2-08":65.82894418317285},"per_game_match_totals_all":{"GB2-01":{"draws":161,"losses":358,"wins":885},"GB2-02":{"draws":850,"losses":174,"wins":272},"GB2-03":{"draws":239,"losses":640,"wins":459},"GB2-04":{"draws":529,"losses":310,"wins":505},"GB2-05":{"draws":0,"losses":179,"wins":1273},"GB2-06":{"draws":91,"losses":276,"wins":1001},"GB2-07":{"draws":0,"losses":417,"wins":1005},"GB2-08":{"draws":179,"losses":427,"wins":852}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":66,"wins":397},"GB2-02":{"draws":239,"losses":29,"wins":164},"GB2-03":{"draws":71,"losses":46,"wins":329},"GB2-04":{"draws":54,"losses":61,"wins":333},"GB2-05":{"draws":0,"losses":33,"wins":451},"GB2-06":{"draws":27,"losses":59,"wins":370},"GB2-07":{"draws":0,"losses":131,"wins":343},"GB2-08":{"draws":79,"losses":155,"wins":252}},"medium":{"GB2-01":{"draws":4,"losses":218,"wins":246},"GB2-02":{"draws":272,"losses":60,"wins":100},"GB2-03":{"draws":86,"losses":255,"wins":105},"GB2-04":{"draws":194,"losses":178,"wins":76},"GB2-05":{"draws":0,"losses":72,"wins":412},"GB2-06":{"draws":26,"losses":93,"wins":337},"GB2-07":{"draws":0,"losses":58,"wins":416},"GB2-08":{"draws":25,"losses":126,"wins":335}},"none":{"GB2-01":{"draws":152,"losses":74,"wins":242},"GB2-02":{"draws":339,"losses":85,"wins":8},"GB2-03":{"draws":82,"losses":339,"wins":25},"GB2-04":{"draws":281,"losses":71,"wins":96},"GB2-05":{"draws":0,"losses":74,"wins":410},"GB2-06":{"draws":38,"losses":124,"wins":294},"GB2-07":{"draws":0,"losses":228,"wins":246},"GB2-08":{"draws":75,"losses":146,"wins":265}}},"per_game_raw_elo_all":{"GB2-01":1698.6237242515278,"GB2-02":1517.4952671357762,"GB2-03":1419.7819373296518,"GB2-04":1560.8423725701161,"GB2-05":2196.622195190351,"GB2-06":1914.1833557152222,"GB2-07":1785.6471791576632,"GB2-08":1629.38888355947},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1905.7975768187116,"GB2-02":1613.6794381565571,"GB2-03":1838.3428377479793,"GB2-04":1773.5370947555189,"GB2-05":2416.90255028946,"GB2-06":2053.6969154397625,"GB2-07":1767.5807856069966,"GB2-08":1560.5621702006194},"medium":{"GB2-01":1519.78882316348,"GB2-02":1521.945593940829,"GB2-03":1313.1974634841517,"GB2-04":1399.0812310313784,"GB2-05":2093.1945471951994,"GB2-06":1914.1605126479863,"GB2-07":2092.207872889253,"GB2-08":1735.9612833374274},"none":{"GB2-01":1670.2847727723922,"GB2-02":1416.8607693099427,"GB2-03":1107.8055107568246,"GB2-04":1509.9087919234514,"GB2-05":2079.769488086393,"GB2-06":1774.6926390579176,"GB2-07":1497.1528789767397,"GB2-08":1591.6431971403633}},"per_game_tracks":{"highest":{"GB2-01":85.67723495574323,"GB2-02":66.73589887844727,"GB2-03":83.4078077948239,"GB2-04":81.20269299832897,"GB2-05":92.88008983338887,"GB2-06":83.99726909131363,"GB2-07":72.98876238603216,"GB2-08":61.343137701058104},"medium":{"GB2-01":53.88276778783554,"GB2-02":55.901917993986864,"GB2-03":36.40972752118416,"GB2-04":39.82479781827604,"GB2-05":85.35898835879064,"GB2-06":77.00942906687878,"GB2-07":87.53479086895358,"GB2-08":72.56807214446098},"none":{"GB2-01":68.63600446667594,"GB2-02":42.36716610369823,"GB2-03":16.845879292558237,"GB2-04":54.083471791752544,"GB2-05":84.96678331289638,"GB2-06":69.40689212794105,"GB2-07":53.71300927495108,"GB2-08":63.57562270399947}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":0,"rank_movement_baseline_at":"2026-10-14T17:59:31Z","reasoning":{"highest":78.52911170489202,"medium":63.561311445045824,"none":56.699353634309105},"reasoning_agg":{"highest":{"max":92.88008983338887,"mean":78.52911170489202,"min":61.343137701058104},"medium":{"max":87.53479086895358,"mean":63.561311445045824,"min":36.40972752118416},"none":{"max":84.96678331289638,"mean":56.699353634309105,"min":16.845879292558237}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":21.829758070582912}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3:6c8ebe2f37004c96","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.9384062,"mean":0.549677025,"median":0.477676,"min":0.280382,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":4.3974162},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.23469315999999998,"mean":0.156944395,"median":0.1664265,"min":0.07192,"recorded_attempt_count":10,"run_count":8,"total":1.2555551600000001},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1610404,"mean":0.053977109999999995,"median":0.0318207,"min":0.0217974,"recorded_attempt_count":8,"run_count":8,"total":0.43181688000000007}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.23469315999999998,"mean":0.156944395,"median":0.1664265,"min":0.07192,"recorded_attempt_count":10,"run_count":8,"total":1.2555551600000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1610404,"mean":0.053977109999999995,"median":0.0318207,"min":0.0217974,"recorded_attempt_count":8,"run_count":8,"total":0.43181687999999996},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.9384062,"mean":0.549677025,"median":0.477676,"min":0.280382,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":4.3974162}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.9384062,"mean":0.2535328433333333,"median":0.1720692,"min":0.0217974,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":28,"run_count":24,"total":6.084788240000002},"codegen_latency_ms":{"attempt_count":28,"max_ms":4051923,"mean_ms":1012660.4583333334,"min_ms":28293,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":4051923,"mean_ms":2278758.375,"min_ms":1011583,"run_count":8},"medium":{"attempt_count":10,"max_ms":1900345,"mean_ms":621701.25,"min_ms":106081,"run_count":8},"none":{"attempt_count":8,"max_ms":420991,"mean_ms":137521.75,"min_ms":28293,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":206676,"output_mean":54914.25,"output_min":2671,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":206676,"output_mean":121740.75,"output_min":61533,"run_count":8},"medium":{"attempt_count":10,"output_max":49662,"output_mean":33008.75,"output_min":15862,"run_count":8},"none":{"attempt_count":8,"output_max":33431,"output_mean":9993.25,"output_min":2671,"run_count":8}},"display_name":"GLM-5.3","economics":{"all":68.92498675100913,"highest":83.69693948151648,"medium":71.54403997026198,"none":51.22614554711819},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[131072],"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":29,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"reconciliation_get_attempts":84,"requested_max_output_token_observations":10,"requested_max_output_tokens":[131072],"total_output_tokens":1317942,"total_reasoning_output_tokens":1189870,"total_visible_output_tokens":128072,"visible_token_observations":28},"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":"z-ai","provider_model":"z-ai/glm-5.3","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-01"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":60.307669369232364,"score":40.205112912821576},"GB2-02":{"attempts":3,"playable":57.18217950238684,"score":57.18217950238684},"GB2-03":{"attempts":3,"playable":68.82429685318091,"score":68.82429685318091},"GB2-04":{"attempts":3,"playable":69.49916968071226,"score":69.49916968071226},"GB2-05":{"attempts":3,"playable":72.37046752398872,"score":72.37046752398872},"GB2-06":{"attempts":3,"playable":77.86259517589404,"score":77.86259517589404},"GB2-07":{"attempts":3,"playable":75.63671614766072,"score":75.63671614766072},"GB2-08":{"attempts":3,"playable":61.09948237324047,"score":61.09948237324047}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":73.4914071785553,"score":73.4914071785553},"GB2-03":{"attempts":1,"playable":84.10566465570777,"score":84.10566465570777},"GB2-04":{"attempts":1,"playable":76.67005981880945,"score":76.67005981880945},"GB2-05":{"attempts":1,"playable":89.80328145740647,"score":89.80328145740647},"GB2-06":{"attempts":1,"playable":90.46569539028324,"score":90.46569539028324},"GB2-07":{"attempts":1,"playable":78.74795788028983,"score":78.74795788028983},"GB2-08":{"attempts":1,"playable":92.59450998956325,"score":92.59450998956325}},"medium":{"GB2-01":{"attempts":1,"playable":51.769089349401796,"score":51.769089349401796},"GB2-02":{"attempts":1,"playable":54.40769593971603,"score":54.40769593971603},"GB2-03":{"attempts":1,"playable":79.48394161239362,"score":79.48394161239362},"GB2-04":{"attempts":1,"playable":83.00224230410926,"score":83.00224230410926},"GB2-05":{"attempts":1,"playable":67.40958548787896,"score":67.40958548787896},"GB2-06":{"attempts":1,"playable":92.81995316688595,"score":92.81995316688595},"GB2-07":{"attempts":1,"playable":76.56064319545096,"score":76.56064319545096},"GB2-08":{"attempts":1,"playable":66.89916870625918,"score":66.89916870625918}},"none":{"GB2-01":{"attempts":1,"playable":68.84624938906293,"score":68.84624938906293},"GB2-02":{"attempts":1,"playable":43.64743538888916,"score":43.64743538888916},"GB2-03":{"attempts":1,"playable":42.88328429144135,"score":42.88328429144135},"GB2-04":{"attempts":1,"playable":48.82520691921806,"score":48.82520691921806},"GB2-05":{"attempts":1,"playable":59.89853562668072,"score":59.89853562668072},"GB2-06":{"attempts":1,"playable":50.30213697051295,"score":50.30213697051295},"GB2-07":{"attempts":1,"playable":71.60154736724137,"score":71.60154736724137},"GB2-08":{"attempts":1,"playable":23.804768423898963,"score":23.804768423898963}}},"id":"z-ai/glm-5.3","is_recent_addition":false,"last_measured_at":"2026-10-20T11:34:49Z","match_totals_all":{"draws":2004,"losses":2464,"wins":6145},"match_totals_tracks":{"highest":{"draws":337,"losses":366,"wins":2523},"medium":{"draws":604,"losses":782,"wins":2307},"none":{"draws":1063,"losses":1316,"wins":1315}},"model_slug":"z-ai-glm-5-3","overall":{"max":92.81995316688595,"mean":65.3350025212357,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":10,"overall_ranking_status":"ranked","per_game":{"GB2-02":73.4914071785553,"GB2-03":84.10566465570777,"GB2-04":76.67005981880945,"GB2-05":89.80328145740647,"GB2-06":90.46569539028324,"GB2-07":78.74795788028983,"GB2-08":92.59450998956325},"per_game_all":{"GB2-02":57.18217950238684,"GB2-03":68.82429685318091,"GB2-04":69.49916968071226,"GB2-05":72.37046752398872,"GB2-06":77.86259517589404,"GB2-07":75.63671614766072,"GB2-08":61.09948237324047},"per_game_match_totals_all":{"GB2-01":{"draws":162,"losses":298,"wins":476},"GB2-02":{"draws":838,"losses":151,"wins":307},"GB2-03":{"draws":142,"losses":378,"wins":818},"GB2-04":{"draws":503,"losses":172,"wins":668},"GB2-05":{"draws":0,"losses":405,"wins":1047},"GB2-06":{"draws":52,"losses":283,"wins":1033},"GB2-07":{"draws":0,"losses":353,"wins":1069},"GB2-08":{"draws":307,"losses":424,"wins":727}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":191,"losses":23,"wins":218},"GB2-03":{"draws":4,"losses":76,"wins":366},"GB2-04":{"draws":122,"losses":48,"wins":278},"GB2-05":{"draws":0,"losses":49,"wins":435},"GB2-06":{"draws":20,"losses":32,"wins":404},"GB2-07":{"draws":0,"losses":102,"wins":372},"GB2-08":{"draws":0,"losses":36,"wins":450}},"medium":{"GB2-01":{"draws":86,"losses":187,"wins":195},"GB2-02":{"draws":301,"losses":52,"wins":79},"GB2-03":{"draws":22,"losses":90,"wins":334},"GB2-04":{"draws":83,"losses":38,"wins":326},"GB2-05":{"draws":0,"losses":160,"wins":324},"GB2-06":{"draws":20,"losses":21,"wins":415},"GB2-07":{"draws":0,"losses":113,"wins":361},"GB2-08":{"draws":92,"losses":121,"wins":273}},"none":{"GB2-01":{"draws":76,"losses":111,"wins":281},"GB2-02":{"draws":346,"losses":76,"wins":10},"GB2-03":{"draws":116,"losses":212,"wins":118},"GB2-04":{"draws":298,"losses":86,"wins":64},"GB2-05":{"draws":0,"losses":196,"wins":288},"GB2-06":{"draws":12,"losses":230,"wins":214},"GB2-07":{"draws":0,"losses":138,"wins":336},"GB2-08":{"draws":215,"losses":267,"wins":4}}},"per_game_raw_elo_all":{"GB2-02":1539.017675717071,"GB2-03":1662.887853600815,"GB2-04":1661.6030321863657,"GB2-05":1844.360575083556,"GB2-06":1985.075502172398,"GB2-07":1814.9495142661935,"GB2-08":1673.983418722848},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1680.1800874574299,"GB2-03":1853.0218088029394,"GB2-04":1716.907618493424,"GB2-05":2267.724318988447,"GB2-06":2210.671105434261,"GB2-07":1870.505646348567,"GB2-08":2232.36921486286},"medium":{"GB2-01":1499.4908701054756,"GB2-02":1510.1002588306671,"GB2-03":1765.4676575773428,"GB2-04":1798.9639309455947,"GB2-05":1686.572805746372,"GB2-06":2285.0720825377625,"GB2-07":1829.1095757387468,"GB2-08":1641.1752688742858},"none":{"GB2-01":1672.6223582789503,"GB2-02":1426.772680863115,"GB2-03":1370.1740944221626,"GB2-04":1468.9375471200785,"GB2-05":1578.7846005158483,"GB2-06":1459.4833185451705,"GB2-07":1745.2333207112672,"GB2-08":1148.4057724313982}},"per_game_tracks":{"highest":{"GB2-02":73.4914071785553,"GB2-03":84.10566465570777,"GB2-04":76.67005981880945,"GB2-05":89.80328145740647,"GB2-06":90.46569539028324,"GB2-07":78.74795788028983,"GB2-08":92.59450998956325},"medium":{"GB2-01":51.769089349401796,"GB2-02":54.40769593971603,"GB2-03":79.48394161239362,"GB2-04":83.00224230410926,"GB2-05":67.40958548787896,"GB2-06":92.81995316688595,"GB2-07":76.56064319545096,"GB2-08":66.89916870625918},"none":{"GB2-01":68.84624938906293,"GB2-02":43.64743538888916,"GB2-03":42.88328429144135,"GB2-04":48.82520691921806,"GB2-05":59.89853562668072,"GB2-06":50.30213697051295,"GB2-07":71.60154736724137,"GB2-08":23.804768423898963}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:55:25Z","reasoning":{"highest":73.23482204632693,"medium":71.54403997026198,"none":51.22614554711819},"reasoning_agg":{"highest":{"max":92.59450998956325,"mean":73.23482204632693,"min":0.0},"medium":{"max":92.81995316688595,"mean":71.54403997026198,"min":51.769089349401796},"none":{"max":71.60154736724137,"mean":51.22614554711819,"min":23.804768423898963}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":22.008676499208732}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-7:e41547632cf0ace6","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":1.2177,"mean":0.779445,"median":0.759332,"min":0.571358,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":6.23556},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.576454,"mean":0.39871924999999997,"median":0.380795,"min":0.216934,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":3.1897539999999998},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.143752,"mean":0.082967,"median":0.0730072,"min":0.0533856,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.6637359999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.576454,"mean":0.39871924999999997,"median":0.380795,"min":0.216934,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":3.1897539999999998},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.143752,"mean":0.082967,"median":0.0730072,"min":0.0533856,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.663736},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":1.2177,"mean":0.779445,"median":0.759332,"min":0.571358,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":6.2355599999999995}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":1.2177,"mean":0.4203770833333333,"median":0.380795,"min":0.0533856,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":29},"recorded_attempt_count":29,"run_count":24,"total":10.08905},"codegen_latency_ms":{"attempt_count":29,"max_ms":2516111,"mean_ms":895095.7083333334,"min_ms":107275,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":2516111,"mean_ms":1632486.25,"min_ms":1212881,"run_count":8},"medium":{"attempt_count":9,"max_ms":1551665,"mean_ms":884117.375,"min_ms":472109,"run_count":8},"none":{"attempt_count":10,"max_ms":283828,"mean_ms":168683.5,"min_ms":107275,"run_count":8}},"codegen_output_tokens":{"attempt_count":29,"output_max":195136,"output_mean":67634.29166666667,"output_min":8421,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":195136,"output_mean":126135.375,"output_min":92484,"run_count":8},"medium":{"attempt_count":9,"output_max":95241,"output_mean":63372.625,"output_min":32426,"run_count":8},"none":{"attempt_count":10,"output_max":23276,"output_mean":13394.875,"output_min":8421,"run_count":8}},"display_name":"Grok 4.7","economics":{"all":72.70914511487253,"highest":83.78856722238622,"medium":83.7975899774524,"none":55.18432558396904},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":29,"effective_max_output_tokens":[450000],"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"provider_post_attempt_observations":29,"provider_post_attempts":29,"reasoning_token_observations":29,"reconciliation_get_attempt_observations":29,"requested_max_output_token_observations":29,"requested_max_output_tokens":[450000],"total_output_tokens":1623223,"total_reasoning_output_tokens":1401661,"total_visible_output_tokens":221562,"visible_token_observations":29},"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":450000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.7","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":["GB2-06"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":55.7854275918379,"score":55.7854275918379},"GB2-02":{"attempts":3,"playable":74.04785869993141,"score":74.04785869993141},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":80.66855777011105,"score":53.779038513407365},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":67.69052394393728,"score":45.12701596262485},"GB2-05":{"attempts":3,"playable":76.43220896920843,"score":76.43220896920843},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":86.01901966773465,"score":57.346013111823105},"GB2-07":{"attempts":3,"playable":70.14347144948317,"score":70.14347144948317},"GB2-08":{"attempts":3,"playable":87.1367588639017,"score":87.1367588639017}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":59.47617075447912,"score":59.47617075447912},"GB2-02":{"attempts":1,"playable":88.63323415656338,"score":88.63323415656338},"GB2-03":{"attempts":1,"playable":88.84957873484126,"score":88.84957873484126},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":92.88008983338887,"score":92.88008983338887},"GB2-06":{"attempts":1,"playable":89.82522818284346,"score":89.82522818284346},"GB2-07":{"attempts":1,"playable":78.54894923744821,"score":78.54894923744821},"GB2-08":{"attempts":1,"playable":88.30671965713918,"score":88.30671965713918}},"medium":{"GB2-01":{"attempts":1,"playable":80.06131758810027,"score":80.06131758810027},"GB2-02":{"attempts":1,"playable":80.94521021573577,"score":80.94521021573577},"GB2-03":{"attempts":1,"playable":72.48753680538086,"score":72.48753680538086},"GB2-04":{"attempts":1,"playable":92.62476647096307,"score":92.62476647096307},"GB2-05":{"attempts":1,"playable":93.46367679802134,"score":93.46367679802134},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":75.96474828738522,"score":75.96474828738522},"GB2-08":{"attempts":1,"playable":91.03587367658041,"score":91.03587367658041}},"none":{"GB2-01":{"attempts":1,"playable":27.818794432934297,"score":27.818794432934297},"GB2-02":{"attempts":1,"playable":52.565131727495064,"score":52.565131727495064},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":42.75628141691148,"score":42.75628141691148},"GB2-05":{"attempts":1,"playable":42.95286027621508,"score":42.95286027621508},"GB2-06":{"attempts":1,"playable":82.21281115262583,"score":82.21281115262583},"GB2-07":{"attempts":1,"playable":55.91671682361606,"score":55.91671682361606},"GB2-08":{"attempts":1,"playable":82.06768325798551,"score":82.06768325798551}}},"id":"x-ai/grok-4.7","is_recent_addition":false,"last_measured_at":"2026-10-20T10:52:59Z","match_totals_all":{"draws":944,"losses":2084,"wins":6704},"match_totals_tracks":{"highest":{"draws":137,"losses":468,"wins":2641},"medium":{"draws":191,"losses":444,"wins":2603},"none":{"draws":616,"losses":1172,"wins":1460}},"model_slug":"x-ai-grok-4-7","overall":{"max":93.46367679802134,"mean":64.97472414527725,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":11,"overall_ranking_status":"ranked","per_game":{"GB2-01":59.47617075447912,"GB2-02":88.63323415656338,"GB2-03":88.84957873484126,"GB2-05":92.88008983338887,"GB2-06":89.82522818284346,"GB2-07":78.54894923744821,"GB2-08":88.30671965713918},"per_game_all":{"GB2-01":55.7854275918379,"GB2-02":74.04785869993141,"GB2-05":76.43220896920843,"GB2-07":70.14347144948317,"GB2-08":87.1367588639017},"per_game_match_totals_all":{"GB2-01":{"draws":191,"losses":536,"wins":677},"GB2-02":{"draws":447,"losses":122,"wins":727},"GB2-03":{"draws":92,"losses":143,"wins":657},"GB2-04":{"draws":152,"losses":220,"wins":524},"GB2-05":{"draws":0,"losses":340,"wins":1112},"GB2-06":{"draws":62,"losses":95,"wins":755},"GB2-07":{"draws":0,"losses":436,"wins":986},"GB2-08":{"draws":0,"losses":192,"wins":1266}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":187,"wins":268},"GB2-02":{"draws":46,"losses":27,"wins":359},"GB2-03":{"draws":66,"losses":21,"wins":359},"GB2-05":{"draws":0,"losses":33,"wins":451},"GB2-06":{"draws":12,"losses":39,"wins":405},"GB2-07":{"draws":0,"losses":103,"wins":371},"GB2-08":{"draws":0,"losses":58,"wins":428}},"medium":{"GB2-01":{"draws":31,"losses":80,"wins":357},"GB2-02":{"draws":98,"losses":36,"wins":298},"GB2-03":{"draws":26,"losses":122,"wins":298},"GB2-04":{"draws":36,"losses":16,"wins":396},"GB2-05":{"draws":0,"losses":30,"wins":454},"GB2-07":{"draws":0,"losses":116,"wins":358},"GB2-08":{"draws":0,"losses":44,"wins":442}},"none":{"GB2-01":{"draws":147,"losses":269,"wins":52},"GB2-02":{"draws":303,"losses":59,"wins":70},"GB2-04":{"draws":116,"losses":204,"wins":128},"GB2-05":{"draws":0,"losses":277,"wins":207},"GB2-06":{"draws":50,"losses":56,"wins":350},"GB2-07":{"draws":0,"losses":217,"wins":257},"GB2-08":{"draws":0,"losses":90,"wins":396}}},"per_game_raw_elo_all":{"GB2-01":1549.6966199258775,"GB2-02":1722.4227334014843,"GB2-05":2076.6217282471157,"GB2-07":1736.7588858696374,"GB2-08":2064.319119500628},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1574.5034761105405,"GB2-02":1901.4625294019395,"GB2-03":1973.1619406021878,"GB2-05":2416.90255028946,"GB2-06":2192.7259197542935,"GB2-07":1866.5947515919204,"GB2-08":2088.924455126038},"medium":{"GB2-01":1813.750043665355,"GB2-02":1770.159029782364,"GB2-03":1663.0362730626432,"GB2-04":1992.4152636090275,"GB2-05":2448.9588646969037,"GB2-07":1818.3777299456929,"GB2-08":2175.090979915708},"none":{"GB2-01":1260.8363400017365,"GB2-02":1495.6466410201494,"GB2-04":1422.0138144478688,"GB2-05":1364.0037697549824,"GB2-06":2016.355743179598,"GB2-07":1525.3041760712997,"GB2-08":1928.9419234601385}},"per_game_tracks":{"highest":{"GB2-01":59.47617075447912,"GB2-02":88.63323415656338,"GB2-03":88.84957873484126,"GB2-05":92.88008983338887,"GB2-06":89.82522818284346,"GB2-07":78.54894923744821,"GB2-08":88.30671965713918},"medium":{"GB2-01":80.06131758810027,"GB2-02":80.94521021573577,"GB2-03":72.48753680538086,"GB2-04":92.62476647096307,"GB2-05":93.46367679802134,"GB2-07":75.96474828738522,"GB2-08":91.03587367658041},"none":{"GB2-01":27.818794432934297,"GB2-02":52.565131727495064,"GB2-04":42.75628141691148,"GB2-05":42.95286027621508,"GB2-06":82.21281115262583,"GB2-07":55.91671682361606,"GB2-08":82.06768325798551}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T22:40:21Z","reasoning":{"highest":73.31499631958795,"medium":73.32289123027086,"none":48.28628488597291},"reasoning_agg":{"highest":{"max":92.88008983338887,"mean":73.31499631958795,"min":0.0},"medium":{"max":93.46367679802134,"mean":73.32289123027086,"min":0.0},"none":{"max":82.21281115262583,"mean":48.28628488597291,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":25.036606344297944}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5-5:a3e3cdfd27bf0fcd","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.54817025,"median":0.548798,"min":0.28285,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":4.385361999999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.083848,"mean":0.06079725,"median":0.058081,"min":0.039074,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.486378},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.048946,"mean":0.040937249999999994,"median":0.039029,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.32749799999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.083848,"mean":0.06079725,"median":0.058081,"min":0.039074,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.486378},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.048946,"mean":0.040937249999999994,"median":0.039029,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.327498},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.54817025,"median":0.548798,"min":0.28285,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":4.385362}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.21663491666666665,"median":0.058081,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"run_count":24,"token_priced_attempt_count":28,"total":5.199237999999999},"codegen_output_tokens":{"attempt_count":28,"output_max":70064,"output_mean":18803.166666666668,"output_min":1228,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":70064,"output_mean":51989.0,"output_min":25995,"run_count":8},"medium":{"attempt_count":11,"output_max":4348,"output_mean":2842.75,"output_min":1552,"run_count":8},"none":{"attempt_count":8,"output_max":2376,"output_mean":1577.75,"output_min":1228,"run_count":8}},"display_name":"Claude Sonnet 5.5","economics":{"all":61.61200093360662,"highest":91.55679701872563,"medium":52.132259041756235,"none":41.146946740337995},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[128000],"finish_reason_observations":28,"finish_reasons":["end_turn"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"requested_max_output_token_observations":28,"requested_max_output_tokens":[128000],"total_output_tokens":451276,"total_reasoning_output_tokens":352227,"total_visible_output_tokens":99049,"visible_token_observations":28},"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-sonnet-5-5","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":59.475177237637844,"score":59.475177237637844},"GB2-02":{"attempts":3,"playable":61.464169873325865,"score":61.464169873325865},"GB2-03":{"attempts":3,"playable":58.72330608310398,"score":58.72330608310398},"GB2-04":{"attempts":3,"playable":56.949439040882204,"score":56.949439040882204},"GB2-05":{"attempts":3,"playable":43.583955219542524,"score":43.583955219542524},"GB2-06":{"attempts":3,"playable":61.36472741478506,"score":61.36472741478506},"GB2-07":{"attempts":3,"playable":70.99585310356166,"score":70.99585310356166},"GB2-08":{"attempts":3,"playable":80.33937949601383,"score":80.33937949601383}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":79.22591094943876,"score":79.22591094943876},"GB2-02":{"attempts":1,"playable":95.82151373012108,"score":95.82151373012108},"GB2-03":{"attempts":1,"playable":95.4443982040266,"score":95.4443982040266},"GB2-04":{"attempts":1,"playable":83.98644447674079,"score":83.98644447674079},"GB2-05":{"attempts":1,"playable":97.04162638556379,"score":97.04162638556379},"GB2-06":{"attempts":1,"playable":88.54683212191811,"score":88.54683212191811},"GB2-07":{"attempts":1,"playable":93.55325406983961,"score":93.55325406983961},"GB2-08":{"attempts":1,"playable":98.83439621215632,"score":98.83439621215632}},"medium":{"GB2-01":{"attempts":1,"playable":47.641997522706006,"score":47.641997522706006},"GB2-02":{"attempts":1,"playable":42.4836154135375,"score":42.4836154135375},"GB2-03":{"attempts":1,"playable":31.366014843855535,"score":31.366014843855535},"GB2-04":{"attempts":1,"playable":41.74219235818004,"score":41.74219235818004},"GB2-05":{"attempts":1,"playable":19.38896784670588,"score":19.38896784670588},"GB2-06":{"attempts":1,"playable":77.63049644093736,"score":77.63049644093736},"GB2-07":{"attempts":1,"playable":72.59233269062719,"score":72.59233269062719},"GB2-08":{"attempts":1,"playable":84.21245521750042,"score":84.21245521750042}},"none":{"GB2-01":{"attempts":1,"playable":51.55762324076879,"score":51.55762324076879},"GB2-02":{"attempts":1,"playable":46.087380476319034,"score":46.087380476319034},"GB2-03":{"attempts":1,"playable":49.35950520142979,"score":49.35950520142979},"GB2-04":{"attempts":1,"playable":45.119680287725785,"score":45.119680287725785},"GB2-05":{"attempts":1,"playable":14.321271426357896,"score":14.321271426357896},"GB2-06":{"attempts":1,"playable":17.916853681499692,"score":17.916853681499692},"GB2-07":{"attempts":1,"playable":46.841972550218166,"score":46.841972550218166},"GB2-08":{"attempts":1,"playable":57.97128705838478,"score":57.97128705838478}}},"id":"claude-sonnet-5-5","is_recent_addition":false,"last_measured_at":"2026-10-20T10:52:46Z","match_totals_all":{"draws":1951,"losses":3360,"wins":5771},"match_totals_tracks":{"highest":{"draws":287,"losses":163,"wins":3244},"medium":{"draws":859,"losses":1366,"wins":1469},"none":{"draws":805,"losses":1831,"wins":1058}},"model_slug":"claude-sonnet-5-5","overall":{"max":98.83439621215632,"mean":61.61200093360662,"min":14.321271426357896},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":12,"overall_ranking_status":"ranked","per_game":{"GB2-01":79.22591094943876,"GB2-02":95.82151373012108,"GB2-03":95.4443982040266,"GB2-04":83.98644447674079,"GB2-05":97.04162638556379,"GB2-06":88.54683212191811,"GB2-07":93.55325406983961,"GB2-08":98.83439621215632},"per_game_all":{"GB2-01":59.475177237637844,"GB2-02":61.464169873325865,"GB2-03":58.72330608310398,"GB2-04":56.949439040882204,"GB2-05":43.583955219542524,"GB2-06":61.36472741478506,"GB2-07":70.99585310356166,"GB2-08":80.33937949601383},"per_game_match_totals_all":{"GB2-01":{"draws":198,"losses":481,"wins":725},"GB2-02":{"draws":693,"losses":163,"wins":440},"GB2-03":{"draws":301,"losses":431,"wins":606},"GB2-04":{"draws":622,"losses":282,"wins":440},"GB2-05":{"draws":0,"losses":819,"wins":633},"GB2-06":{"draws":62,"losses":505,"wins":801},"GB2-07":{"draws":0,"losses":423,"wins":999},"GB2-08":{"draws":75,"losses":256,"wins":1127}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":143,"losses":28,"wins":297},"GB2-02":{"draws":20,"losses":7,"wins":405},"GB2-03":{"draws":1,"losses":20,"wins":425},"GB2-04":{"draws":76,"losses":37,"wins":335},"GB2-05":{"draws":0,"losses":12,"wins":472},"GB2-06":{"draws":40,"losses":31,"wins":385},"GB2-07":{"draws":0,"losses":28,"wins":446},"GB2-08":{"draws":7,"losses":0,"wins":479}},"medium":{"GB2-01":{"draws":11,"losses":244,"wins":213},"GB2-02":{"draws":340,"losses":84,"wins":8},"GB2-03":{"draws":195,"losses":222,"wins":29},"GB2-04":{"draws":289,"losses":122,"wins":37},"GB2-05":{"draws":0,"losses":391,"wins":93},"GB2-06":{"draws":16,"losses":95,"wins":345},"GB2-07":{"draws":0,"losses":133,"wins":341},"GB2-08":{"draws":8,"losses":75,"wins":403}},"none":{"GB2-01":{"draws":44,"losses":209,"wins":215},"GB2-02":{"draws":333,"losses":72,"wins":27},"GB2-03":{"draws":105,"losses":189,"wins":152},"GB2-04":{"draws":257,"losses":123,"wins":68},"GB2-05":{"draws":0,"losses":416,"wins":68},"GB2-06":{"draws":6,"losses":379,"wins":71},"GB2-07":{"draws":0,"losses":262,"wins":212},"GB2-08":{"draws":60,"losses":181,"wins":245}}},"per_game_raw_elo_all":{"GB2-01":1586.43108747173,"GB2-02":1665.5586432701045,"GB2-03":1649.4057842190148,"GB2-04":1556.0736293358302,"GB2-05":1542.485400293027,"GB2-06":1682.211086572126,"GB2-07":1842.060418456888,"GB2-08":2059.399933535589},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1801.7134913819227,"GB2-02":2133.3298199569726,"GB2-03":2254.3874341345754,"GB2-04":1813.780589559184,"GB2-05":2704.6602620362037,"GB2-06":2158.980738764998,"GB2-07":2353.9729742678555,"GB2-08":2681.803568558347},"medium":{"GB2-01":1460.1126748380561,"GB2-02":1417.764083768876,"GB2-03":1267.0336991413465,"GB2-04":1414.1159940964542,"GB2-05":1012.0756405220511,"GB2-06":1925.9821562310053,"GB2-07":1761.1181603017924,"GB2-08":1979.8770289366473},"none":{"GB2-01":1497.4670961952113,"GB2-02":1445.582026084465,"GB2-03":1426.796219381122,"GB2-04":1440.3243043518526,"GB2-05":910.7202983208265,"GB2-06":961.6703647203753,"GB2-07":1411.090120801016,"GB2-08":1516.5192031117717}},"per_game_tracks":{"highest":{"GB2-01":79.22591094943876,"GB2-02":95.82151373012108,"GB2-03":95.4443982040266,"GB2-04":83.98644447674079,"GB2-05":97.04162638556379,"GB2-06":88.54683212191811,"GB2-07":93.55325406983961,"GB2-08":98.83439621215632},"medium":{"GB2-01":47.641997522706006,"GB2-02":42.4836154135375,"GB2-03":31.366014843855535,"GB2-04":41.74219235818004,"GB2-05":19.38896784670588,"GB2-06":77.63049644093736,"GB2-07":72.59233269062719,"GB2-08":84.21245521750042},"none":{"GB2-01":51.55762324076879,"GB2-02":46.087380476319034,"GB2-03":49.35950520142979,"GB2-04":45.119680287725785,"GB2-05":14.321271426357896,"GB2-06":17.916853681499692,"GB2-07":46.841972550218166,"GB2-08":57.97128705838478}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T23:00:16Z","reasoning":{"highest":91.55679701872563,"medium":52.132259041756235,"none":41.146946740337995},"reasoning_agg":{"highest":{"max":98.83439621215632,"mean":91.55679701872563,"min":79.22591094943876},"medium":{"max":84.21245521750042,"mean":52.132259041756235,"min":19.38896784670588},"none":{"max":57.97128705838478,"mean":41.146946740337995,"min":14.321271426357896}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":50.40985027838764}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-6:b16b290371c28436","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.23409475,"median":0.240558,"min":0.184404,"recorded_attempt_count":9,"run_count":8,"total":1.872758},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.179588,"mean":0.12726625,"median":0.12371399999999999,"min":0.092184,"recorded_attempt_count":10,"run_count":8,"total":1.01813},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.041774,"mean":0.03185375,"median":0.031432,"min":0.027072,"recorded_attempt_count":8,"run_count":8,"total":0.25483}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.179588,"mean":0.12726625,"median":0.12371399999999999,"min":0.092184,"recorded_attempt_count":10,"run_count":8,"total":1.01813},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.041774,"mean":0.03185375,"median":0.031432,"min":0.027072,"recorded_attempt_count":8,"run_count":8,"total":0.25483},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.23409475,"median":0.240558,"min":0.184404,"recorded_attempt_count":9,"run_count":8,"total":1.872758}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.13107158333333335,"median":0.12371399999999999,"min":0.027072,"recorded_attempt_count":27,"run_count":24,"total":3.145718},"codegen_latency_ms":{"attempt_count":27,"max_ms":669574,"mean_ms":286694.0416666667,"min_ms":31621,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":669574,"mean_ms":551119.125,"min_ms":414817,"run_count":8},"medium":{"attempt_count":10,"max_ms":376458,"mean_ms":270365.25,"min_ms":196147,"run_count":8},"none":{"attempt_count":8,"max_ms":49571,"mean_ms":38597.75,"min_ms":31621,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":43739,"output_mean":18621.333333333332,"output_min":1925,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":43739,"output_mean":35745.125,"output_min":27954,"run_count":8},"medium":{"attempt_count":10,"output_max":24183,"output_mean":17614.25,"output_min":12541,"run_count":8},"none":{"attempt_count":8,"output_max":3323,"output_mean":2504.625,"output_min":1925,"run_count":8}},"display_name":"Grok 4.6","economics":{"all":60.85098105454723,"highest":65.29056884865703,"medium":72.164295856812,"none":45.09807845817268},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"reconciliation_get_attempts":128,"total_output_tokens":446912,"total_reasoning_output_tokens":311255,"total_visible_output_tokens":135657,"visible_token_observations":27},"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-4.6","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":60.135928730282934,"score":60.135928730282934},"GB2-02":{"attempts":3,"playable":60.57335125666728,"score":60.57335125666728},"GB2-03":{"attempts":3,"playable":54.4624074085849,"score":54.4624074085849},"GB2-04":{"attempts":3,"playable":56.49020163568057,"score":56.49020163568057},"GB2-05":{"attempts":3,"playable":72.88211182797271,"score":72.88211182797271},"GB2-06":{"attempts":3,"playable":53.173072309687235,"score":53.173072309687235},"GB2-07":{"attempts":3,"playable":70.01393992405931,"score":70.01393992405931},"GB2-08":{"attempts":3,"playable":59.07683534344292,"score":59.07683534344292}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":50.605794911026955,"score":50.605794911026955},"GB2-02":{"attempts":1,"playable":83.08725535076462,"score":83.08725535076462},"GB2-03":{"attempts":1,"playable":50.93237482346559,"score":50.93237482346559},"GB2-04":{"attempts":1,"playable":59.87144209803317,"score":59.87144209803317},"GB2-05":{"attempts":1,"playable":85.16302198502669,"score":85.16302198502669},"GB2-06":{"attempts":1,"playable":65.7308315036772,"score":65.7308315036772},"GB2-07":{"attempts":1,"playable":75.56762664383982,"score":75.56762664383982},"GB2-08":{"attempts":1,"playable":51.3662034734222,"score":51.3662034734222}},"medium":{"GB2-01":{"attempts":1,"playable":62.953707615284735,"score":62.953707615284735},"GB2-02":{"attempts":1,"playable":54.75274727992973,"score":54.75274727992973},"GB2-03":{"attempts":1,"playable":67.85612837269954,"score":67.85612837269954},"GB2-04":{"attempts":1,"playable":66.50500975285853,"score":66.50500975285853},"GB2-05":{"attempts":1,"playable":82.79034806548603,"score":82.79034806548603},"GB2-06":{"attempts":1,"playable":80.12364263284084,"score":80.12364263284084},"GB2-07":{"attempts":1,"playable":76.56064319545096,"score":76.56064319545096},"GB2-08":{"attempts":1,"playable":85.77213993994556,"score":85.77213993994556}},"none":{"GB2-01":{"attempts":1,"playable":66.8482836645371,"score":66.8482836645371},"GB2-02":{"attempts":1,"playable":43.880051139307476,"score":43.880051139307476},"GB2-03":{"attempts":1,"playable":44.59871902958958,"score":44.59871902958958},"GB2-04":{"attempts":1,"playable":43.09415305615002,"score":43.09415305615002},"GB2-05":{"attempts":1,"playable":50.69296543340541,"score":50.69296543340541},"GB2-06":{"attempts":1,"playable":13.664742792543692,"score":13.664742792543692},"GB2-07":{"attempts":1,"playable":57.91354993288715,"score":57.91354993288715},"GB2-08":{"attempts":1,"playable":40.09216261696101,"score":40.09216261696101}}},"id":"x-ai/grok-4.6","is_recent_addition":false,"last_measured_at":"2026-10-20T11:35:03Z","match_totals_all":{"draws":2843,"losses":3028,"wins":5210},"match_totals_tracks":{"highest":{"draws":829,"losses":911,"wins":1953},"medium":{"draws":717,"losses":692,"wins":2285},"none":{"draws":1297,"losses":1425,"wins":972}},"model_slug":"x-ai-grok-4-6","overall":{"max":85.77213993994556,"mean":60.85098105454724,"min":13.664742792543692},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":13,"overall_ranking_status":"ranked","per_game":{"GB2-01":50.605794911026955,"GB2-02":83.08725535076462,"GB2-03":50.93237482346559,"GB2-04":59.87144209803317,"GB2-05":85.16302198502669,"GB2-06":65.7308315036772,"GB2-07":75.56762664383982,"GB2-08":51.3662034734222},"per_game_all":{"GB2-01":60.135928730282934,"GB2-02":60.57335125666728,"GB2-03":54.4624074085849,"GB2-04":56.49020163568057,"GB2-05":72.88211182797271,"GB2-06":53.173072309687235,"GB2-07":70.01393992405931,"GB2-08":59.07683534344292},"per_game_match_totals_all":{"GB2-01":{"draws":412,"losses":365,"wins":627},"GB2-02":{"draws":676,"losses":186,"wins":433},"GB2-03":{"draws":526,"losses":391,"wins":421},"GB2-04":{"draws":747,"losses":228,"wins":369},"GB2-05":{"draws":0,"losses":398,"wins":1054},"GB2-06":{"draws":58,"losses":623,"wins":687},"GB2-07":{"draws":0,"losses":438,"wins":984},"GB2-08":{"draws":424,"losses":399,"wins":635}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":239,"losses":116,"wins":113},"GB2-02":{"draws":58,"losses":46,"wins":327},"GB2-03":{"draws":87,"losses":191,"wins":168},"GB2-04":{"draws":241,"losses":65,"wins":142},"GB2-05":{"draws":0,"losses":73,"wins":411},"GB2-06":{"draws":32,"losses":145,"wins":279},"GB2-07":{"draws":0,"losses":118,"wins":356},"GB2-08":{"draws":172,"losses":157,"wins":157}},"medium":{"GB2-01":{"draws":120,"losses":117,"wins":231},"GB2-02":{"draws":274,"losses":64,"wins":94},"GB2-03":{"draws":82,"losses":116,"wins":248},"GB2-04":{"draws":221,"losses":45,"wins":182},"GB2-05":{"draws":0,"losses":85,"wins":399},"GB2-06":{"draws":20,"losses":81,"wins":355},"GB2-07":{"draws":0,"losses":113,"wins":361},"GB2-08":{"draws":0,"losses":71,"wins":415}},"none":{"GB2-01":{"draws":53,"losses":132,"wins":283},"GB2-02":{"draws":344,"losses":76,"wins":12},"GB2-03":{"draws":357,"losses":84,"wins":5},"GB2-04":{"draws":285,"losses":118,"wins":45},"GB2-05":{"draws":0,"losses":240,"wins":244},"GB2-06":{"draws":6,"losses":397,"wins":53},"GB2-07":{"draws":0,"losses":207,"wins":267},"GB2-08":{"draws":252,"losses":171,"wins":63}}},"per_game_raw_elo_all":{"GB2-01":1582.9251149018892,"GB2-02":1580.902310803577,"GB2-03":1477.6547873446673,"GB2-04":1531.6699895477834,"GB2-05":1852.6102999971035,"GB2-06":1522.7409528061219,"GB2-07":1730.5414319074378,"GB2-08":1592.2902108684168},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1488.3696114762538,"GB2-02":1801.3126027523713,"GB2-03":1440.732044862331,"GB2-04":1556.5416413926716,"GB2-05":2086.4489982105265,"GB2-06":1710.2504055410152,"GB2-07":1811.3398128258566,"GB2-08":1438.2688916565887},"medium":{"GB2-01":1609.6918726899032,"GB2-02":1512.8247291241155,"GB2-03":1607.1116909739496,"GB2-04":1613.8296681293864,"GB2-05":2010.526413372058,"GB2-06":1974.357213067878,"GB2-07":1829.1095757387468,"GB2-08":2019.292724076693},"none":{"GB2-01":1650.7138605395107,"GB2-02":1428.5696005342438,"GB2-03":1385.1206261977213,"GB2-04":1424.6386591212924,"GB2-05":1460.8554884087264,"GB2-06":883.6152398094728,"GB2-07":1551.1749071577099,"GB2-08":1319.3090168719696}},"per_game_tracks":{"highest":{"GB2-01":50.605794911026955,"GB2-02":83.08725535076462,"GB2-03":50.93237482346559,"GB2-04":59.87144209803317,"GB2-05":85.16302198502669,"GB2-06":65.7308315036772,"GB2-07":75.56762664383982,"GB2-08":51.3662034734222},"medium":{"GB2-01":62.953707615284735,"GB2-02":54.75274727992973,"GB2-03":67.85612837269954,"GB2-04":66.50500975285853,"GB2-05":82.79034806548603,"GB2-06":80.12364263284084,"GB2-07":76.56064319545096,"GB2-08":85.77213993994556},"none":{"GB2-01":66.8482836645371,"GB2-02":43.880051139307476,"GB2-03":44.59871902958958,"GB2-04":43.09415305615002,"GB2-05":50.69296543340541,"GB2-06":13.664742792543692,"GB2-07":57.91354993288715,"GB2-08":40.09216261696101}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T20:28:24Z","reasoning":{"highest":65.29056884865703,"medium":72.164295856812,"none":45.09807845817268},"reasoning_agg":{"highest":{"max":85.16302198502669,"mean":65.29056884865703,"min":50.605794911026955},"medium":{"max":85.77213993994556,"mean":72.164295856812,"min":54.75274727992973},"none":{"max":66.8482836645371,"mean":45.09807845817268,"min":13.664742792543692}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":27.066217398639324}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-8-flash:0c5ad1b0c55c8061","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.14318721034763582,"median":0.1303062996496891,"min":0.10133749410144509,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1454976827810868},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.12249677080183623,"mean":0.07182689102312519,"median":0.06440174762499168,"min":0.044067488277453076,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5746151281850015},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.041197616649628,"mean":0.031941679879238995,"median":0.03128326283110872,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.25553343903391196}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.12249677080183623,"mean":0.07182689102312519,"median":0.06440174762499168,"min":0.044067488277453076,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5746151281850015},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.041197616649628,"mean":0.031941679879238995,"median":0.03128326283110872,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.2555334390339119},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.14318721034763582,"median":0.1303062996496891,"min":0.10133749410144509,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1454976827810865}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.08231859375,"median":0.06440174762499168,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":1.97564625},"codegen_output_tokens":{"attempt_count":25,"output_max":73160,"output_mean":20095.833333333332,"output_min":1712,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":73160,"output_mean":40784.875,"output_min":28671,"run_count":8},"medium":{"attempt_count":8,"output_max":31721,"output_mean":16792.0,"output_min":5265,"run_count":8},"none":{"attempt_count":8,"output_max":3473,"output_mean":2710.625,"output_min":1712,"run_count":8}},"display_name":"Gemini 3.8 Flash","economics":{"all":60.46392515162786,"highest":65.31621110951788,"medium":60.48722541026597,"none":55.58833893509975},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"total_output_tokens":482300,"total_reasoning_output_tokens":300593,"total_visible_output_tokens":181707,"visible_token_observations":25},"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-3.8-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":60.94292528493182,"score":60.94292528493182},"GB2-02":{"attempts":3,"playable":50.1531046789574,"score":50.1531046789574},"GB2-03":{"attempts":3,"playable":69.3231564474975,"score":69.3231564474975},"GB2-04":{"attempts":3,"playable":51.2000938710597,"score":51.2000938710597},"GB2-05":{"attempts":3,"playable":59.405556454086856,"score":59.405556454086856},"GB2-06":{"attempts":3,"playable":80.40368075743635,"score":80.40368075743635},"GB2-07":{"attempts":3,"playable":56.16009605740419,"score":56.16009605740419},"GB2-08":{"attempts":3,"playable":56.12278766164911,"score":56.12278766164911}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":54.93896566533433,"score":54.93896566533433},"GB2-02":{"attempts":1,"playable":69.22134392160535,"score":69.22134392160535},"GB2-03":{"attempts":1,"playable":70.91767753672681,"score":70.91767753672681},"GB2-04":{"attempts":1,"playable":47.927876031493696,"score":47.927876031493696},"GB2-05":{"attempts":1,"playable":66.78501500730421,"score":66.78501500730421},"GB2-06":{"attempts":1,"playable":87.59042676973955,"score":87.59042676973955},"GB2-07":{"attempts":1,"playable":69.026816897973,"score":69.026816897973},"GB2-08":{"attempts":1,"playable":56.12156704596602,"score":56.12156704596602}},"medium":{"GB2-01":{"attempts":1,"playable":71.47284525534819,"score":71.47284525534819},"GB2-02":{"attempts":1,"playable":40.618985057633424,"score":40.618985057633424},"GB2-03":{"attempts":1,"playable":85.0002924910318,"score":85.0002924910318},"GB2-04":{"attempts":1,"playable":59.316379727981364,"score":59.316379727981364},"GB2-05":{"attempts":1,"playable":55.715827177478175,"score":55.715827177478175},"GB2-06":{"attempts":1,"playable":79.49897828946986,"score":79.49897828946986},"GB2-07":{"attempts":1,"playable":57.115500924681164,"score":57.115500924681164},"GB2-08":{"attempts":1,"playable":35.15899435850383,"score":35.15899435850383}},"none":{"GB2-01":{"attempts":1,"playable":56.41696493411293,"score":56.41696493411293},"GB2-02":{"attempts":1,"playable":40.618985057633424,"score":40.618985057633424},"GB2-03":{"attempts":1,"playable":52.05149931473388,"score":52.05149931473388},"GB2-04":{"attempts":1,"playable":46.356025853704054,"score":46.356025853704054},"GB2-05":{"attempts":1,"playable":55.715827177478175,"score":55.715827177478175},"GB2-06":{"attempts":1,"playable":74.12163721309962,"score":74.12163721309962},"GB2-07":{"attempts":1,"playable":42.337970349558404,"score":42.337970349558404},"GB2-08":{"attempts":1,"playable":77.08780158047749,"score":77.08780158047749}}},"id":"google/gemini-3.8-flash","is_recent_addition":false,"last_measured_at":"2026-10-20T11:23:54Z","match_totals_all":{"draws":2490,"losses":3261,"wins":5331},"match_totals_tracks":{"highest":{"draws":535,"losses":1056,"wins":2103},"medium":{"draws":1039,"losses":982,"wins":1673},"none":{"draws":916,"losses":1223,"wins":1555}},"model_slug":"google-gemini-3-8-flash","overall":{"max":87.59042676973955,"mean":60.46392515162787,"min":35.15899435850383},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":14,"overall_ranking_status":"ranked","per_game":{"GB2-01":54.93896566533433,"GB2-02":69.22134392160535,"GB2-03":70.91767753672681,"GB2-04":47.927876031493696,"GB2-05":66.78501500730421,"GB2-06":87.59042676973955,"GB2-07":69.026816897973,"GB2-08":56.12156704596602},"per_game_all":{"GB2-01":60.94292528493182,"GB2-02":50.1531046789574,"GB2-03":69.3231564474975,"GB2-04":51.2000938710597,"GB2-05":59.405556454086856,"GB2-06":80.40368075743635,"GB2-07":56.16009605740419,"GB2-08":56.12278766164911},"per_game_match_totals_all":{"GB2-01":{"draws":293,"losses":413,"wins":698},"GB2-02":{"draws":851,"losses":236,"wins":209},"GB2-03":{"draws":165,"losses":363,"wins":810},"GB2-04":{"draws":648,"losses":349,"wins":347},"GB2-05":{"draws":0,"losses":595,"wins":857},"GB2-06":{"draws":67,"losses":236,"wins":1065},"GB2-07":{"draws":0,"losses":646,"wins":776},"GB2-08":{"draws":466,"losses":423,"wins":569}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":40,"losses":195,"wins":233},"GB2-02":{"draws":175,"losses":50,"wins":207},"GB2-03":{"draws":7,"losses":139,"wins":300},"GB2-04":{"draws":86,"losses":196,"wins":166},"GB2-05":{"draws":0,"losses":163,"wins":321},"GB2-06":{"draws":33,"losses":39,"wins":384},"GB2-07":{"draws":0,"losses":151,"wins":323},"GB2-08":{"draws":194,"losses":123,"wins":169}},"medium":{"GB2-01":{"draws":71,"losses":101,"wins":296},"GB2-02":{"draws":338,"losses":93,"wins":1},"GB2-03":{"draws":79,"losses":34,"wins":333},"GB2-04":{"draws":284,"losses":46,"wins":118},"GB2-05":{"draws":0,"losses":216,"wins":268},"GB2-06":{"draws":18,"losses":85,"wins":353},"GB2-07":{"draws":0,"losses":211,"wins":263},"GB2-08":{"draws":249,"losses":196,"wins":41}},"none":{"GB2-01":{"draws":182,"losses":117,"wins":169},"GB2-02":{"draws":338,"losses":93,"wins":1},"GB2-03":{"draws":79,"losses":190,"wins":177},"GB2-04":{"draws":278,"losses":107,"wins":63},"GB2-05":{"draws":0,"losses":216,"wins":268},"GB2-06":{"draws":16,"losses":112,"wins":328},"GB2-07":{"draws":0,"losses":284,"wins":190},"GB2-08":{"draws":23,"losses":104,"wins":359}}},"per_game_raw_elo_all":{"GB2-01":1592.2997604783534,"GB2-02":1481.1602276732447,"GB2-03":1655.591710282626,"GB2-04":1487.9470847027187,"GB2-05":1575.0562371080568,"GB2-06":1985.8094517763268,"GB2-07":1533.810173096929,"GB2-08":1528.3139780663048},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1529.991665472616,"GB2-02":1636.9885420637365,"GB2-03":1643.2691171406955,"GB2-04":1462.005299971731,"GB2-05":1676.9247778534,"GB2-06":2135.2082607464176,"GB2-07":1705.5191975778419,"GB2-08":1493.6510140500616},"medium":{"GB2-01":1702.5515327703363,"GB2-02":1403.2460704779985,"GB2-03":1872.778024649081,"GB2-04":1551.9637317873467,"GB2-05":1524.1219667353855,"GB2-06":1962.0820449143523,"GB2-07":1540.789234206556,"GB2-08":1269.3393674542144},"none":{"GB2-01":1544.3560831921084,"GB2-02":1403.2460704779985,"GB2-03":1450.727989058102,"GB2-04":1449.8722223490781,"GB2-05":1524.1219667353855,"GB2-06":1860.1380496682104,"GB2-07":1355.122087506389,"GB2-08":1821.9515526946377}},"per_game_tracks":{"highest":{"GB2-01":54.93896566533433,"GB2-02":69.22134392160535,"GB2-03":70.91767753672681,"GB2-04":47.927876031493696,"GB2-05":66.78501500730421,"GB2-06":87.59042676973955,"GB2-07":69.026816897973,"GB2-08":56.12156704596602},"medium":{"GB2-01":71.47284525534819,"GB2-02":40.618985057633424,"GB2-03":85.0002924910318,"GB2-04":59.316379727981364,"GB2-05":55.715827177478175,"GB2-06":79.49897828946986,"GB2-07":57.115500924681164,"GB2-08":35.15899435850383},"none":{"GB2-01":56.41696493411293,"GB2-02":40.618985057633424,"GB2-03":52.05149931473388,"GB2-04":46.356025853704054,"GB2-05":55.715827177478175,"GB2-06":74.12163721309962,"GB2-07":42.337970349558404,"GB2-08":77.08780158047749}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:05:37Z","reasoning":{"highest":65.31621110951788,"medium":60.48722541026597,"none":55.58833893509975},"reasoning_agg":{"highest":{"max":87.59042676973955,"mean":65.31621110951788,"min":47.927876031493696},"medium":{"max":85.0002924910318,"mean":60.48722541026597,"min":35.15899435850383},"none":{"max":77.08780158047749,"mean":55.58833893509975,"min":40.618985057633424}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":9.727872174418131}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-3:47f41b32a19bbda4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.358603,"mean":0.24868390625000003,"median":0.2596235,"min":0.12429875,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.9894712499999998},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.07423675,"mean":0.05217515625,"median":0.050446875,"min":0.04135875,"recorded_attempt_count":8,"run_count":8,"total":0.41740125},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.043892749999999994,"mean":0.023888718750000003,"median":0.020423875,"min":0.017614,"recorded_attempt_count":9,"run_count":8,"total":0.19110975000000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.07423675,"mean":0.05217515625,"median":0.050446875,"min":0.04135875,"recorded_attempt_count":8,"run_count":8,"total":0.41740124999999995},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.043892749999999994,"mean":0.023888718750000003,"median":0.020423875,"min":0.017614,"recorded_attempt_count":9,"run_count":8,"total":0.19110975},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.358603,"mean":0.24868390625000003,"median":0.2596235,"min":0.12429875,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.9894712500000002}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.358603,"mean":0.10824926041666667,"median":0.050446875,"min":0.017614,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":27,"run_count":24,"total":2.5979822500000003},"codegen_latency_ms":{"attempt_count":27,"max_ms":344702,"mean_ms":125679.0,"min_ms":18724,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":344702,"mean_ms":258574.75,"min_ms":141477,"run_count":8},"medium":{"attempt_count":8,"max_ms":148027,"mean_ms":92816.75,"min_ms":70623,"run_count":8},"none":{"attempt_count":9,"max_ms":39588,"mean_ms":25645.5,"min_ms":18724,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":82251,"output_mean":22811.583333333332,"output_min":2043,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":82251,"output_mean":55365.125,"output_min":27171,"run_count":8},"medium":{"attempt_count":8,"output_max":15366,"output_mean":10008.75,"output_min":7655,"run_count":8},"none":{"attempt_count":9,"output_max":5638,"output_mean":3060.875,"output_min":2043,"run_count":8}},"display_name":"Muse Spark 1.3","economics":{"all":59.55168237002285,"highest":70.72972076021328,"medium":66.5669114514288,"none":41.358414898426474},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[943718],"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"reconciliation_get_attempts":79,"requested_max_output_token_observations":10,"requested_max_output_tokens":[943718],"total_output_tokens":547478,"total_reasoning_output_tokens":432530,"total_visible_output_tokens":114948,"visible_token_observations":27},"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":"meta","provider_model":"meta/muse-spark-1.3","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":59.63756176945751,"score":59.63756176945751},"GB2-02":{"attempts":3,"playable":55.68841233379092,"score":55.68841233379092},"GB2-03":{"attempts":3,"playable":67.64329504903542,"score":67.64329504903542},"GB2-04":{"attempts":3,"playable":52.92505498398407,"score":52.92505498398407},"GB2-05":{"attempts":3,"playable":59.48837600894348,"score":59.48837600894348},"GB2-06":{"attempts":3,"playable":69.28405445192006,"score":69.28405445192006},"GB2-07":{"attempts":3,"playable":50.13965494012664,"score":50.13965494012664},"GB2-08":{"attempts":3,"playable":61.607049422924725,"score":61.607049422924725}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":77.44851398498643,"score":77.44851398498643},"GB2-02":{"attempts":1,"playable":62.648988059605855,"score":62.648988059605855},"GB2-03":{"attempts":1,"playable":83.3079628008012,"score":83.3079628008012},"GB2-04":{"attempts":1,"playable":50.95374340030112,"score":50.95374340030112},"GB2-05":{"attempts":1,"playable":79.16632023200127,"score":79.16632023200127},"GB2-06":{"attempts":1,"playable":84.20773742910123,"score":84.20773742910123},"GB2-07":{"attempts":1,"playable":57.714118940419944,"score":57.714118940419944},"GB2-08":{"attempts":1,"playable":70.39038123448921,"score":70.39038123448921}},"medium":{"GB2-01":{"attempts":1,"playable":74.93505852082129,"score":74.93505852082129},"GB2-02":{"attempts":1,"playable":56.705408215797526,"score":56.705408215797526},"GB2-03":{"attempts":1,"playable":63.79284042469114,"score":63.79284042469114},"GB2-04":{"attempts":1,"playable":65.40309120243107,"score":65.40309120243107},"GB2-05":{"attempts":1,"playable":58.225987245264086,"score":58.225987245264086},"GB2-06":{"attempts":1,"playable":81.37584046337942,"score":81.37584046337942},"GB2-07":{"attempts":1,"playable":54.71570120068804,"score":54.71570120068804},"GB2-08":{"attempts":1,"playable":77.38136433835778,"score":77.38136433835778}},"none":{"GB2-01":{"attempts":1,"playable":26.529112802564843,"score":26.529112802564843},"GB2-02":{"attempts":1,"playable":47.71084072596938,"score":47.71084072596938},"GB2-03":{"attempts":1,"playable":55.82908192161388,"score":55.82908192161388},"GB2-04":{"attempts":1,"playable":42.41833034922002,"score":42.41833034922002},"GB2-05":{"attempts":1,"playable":41.0728205495651,"score":41.0728205495651},"GB2-06":{"attempts":1,"playable":42.26858546327951,"score":42.26858546327951},"GB2-07":{"attempts":1,"playable":37.98914467927195,"score":37.98914467927195},"GB2-08":{"attempts":1,"playable":37.049402695927164,"score":37.049402695927164}}},"id":"meta/muse-spark-1.3","is_recent_addition":false,"last_measured_at":"2026-10-20T11:32:13Z","match_totals_all":{"draws":2137,"losses":3553,"wins":5392},"match_totals_tracks":{"highest":{"draws":490,"losses":869,"wins":2335},"medium":{"draws":588,"losses":981,"wins":2125},"none":{"draws":1059,"losses":1703,"wins":932}},"model_slug":"meta-muse-spark-1-3","overall":{"max":84.20773742910123,"mean":59.55168237002285,"min":26.529112802564843},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":15,"overall_ranking_status":"ranked","per_game":{"GB2-01":77.44851398498643,"GB2-02":62.648988059605855,"GB2-03":83.3079628008012,"GB2-04":50.95374340030112,"GB2-05":79.16632023200127,"GB2-06":84.20773742910123,"GB2-07":57.714118940419944,"GB2-08":70.39038123448921},"per_game_all":{"GB2-01":59.63756176945751,"GB2-02":55.68841233379092,"GB2-03":67.64329504903542,"GB2-04":52.92505498398407,"GB2-05":59.48837600894348,"GB2-06":69.28405445192006,"GB2-07":50.13965494012664,"GB2-08":61.607049422924725},"per_game_match_totals_all":{"GB2-01":{"draws":99,"losses":527,"wins":778},"GB2-02":{"draws":857,"losses":162,"wins":277},"GB2-03":{"draws":171,"losses":385,"wins":782},"GB2-04":{"draws":593,"losses":353,"wins":398},"GB2-05":{"draws":0,"losses":593,"wins":859},"GB2-06":{"draws":65,"losses":398,"wins":905},"GB2-07":{"draws":0,"losses":736,"wins":686},"GB2-08":{"draws":352,"losses":399,"wins":707}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":107,"wins":359},"GB2-02":{"draws":249,"losses":42,"wins":141},"GB2-03":{"draws":36,"losses":64,"wins":346},"GB2-04":{"draws":119,"losses":166,"wins":163},"GB2-05":{"draws":0,"losses":103,"wins":381},"GB2-06":{"draws":33,"losses":55,"wins":368},"GB2-07":{"draws":0,"losses":208,"wins":266},"GB2-08":{"draws":51,"losses":124,"wins":311}},"medium":{"GB2-01":{"draws":0,"losses":120,"wins":348},"GB2-02":{"draws":277,"losses":54,"wins":101},"GB2-03":{"draws":56,"losses":148,"wins":242},"GB2-04":{"draws":225,"losses":48,"wins":175},"GB2-05":{"draws":0,"losses":204,"wins":280},"GB2-06":{"draws":16,"losses":77,"wins":363},"GB2-07":{"draws":0,"losses":223,"wins":251},"GB2-08":{"draws":14,"losses":107,"wins":365}},"none":{"GB2-01":{"draws":97,"losses":300,"wins":71},"GB2-02":{"draws":331,"losses":66,"wins":35},"GB2-03":{"draws":79,"losses":173,"wins":194},"GB2-04":{"draws":249,"losses":139,"wins":60},"GB2-05":{"draws":0,"losses":286,"wins":198},"GB2-06":{"draws":16,"losses":266,"wins":174},"GB2-07":{"draws":0,"losses":305,"wins":169},"GB2-08":{"draws":287,"losses":168,"wins":31}}},"per_game_raw_elo_all":{"GB2-01":1589.274029238104,"GB2-02":1521.324946052264,"GB2-03":1628.1381401488788,"GB2-04":1502.912552519537,"GB2-05":1603.0241823374572,"GB2-06":1798.169019147,"GB2-07":1453.0057247026161,"GB2-08":1604.7636473203327},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1777.148963359449,"GB2-02":1577.5272720733012,"GB2-03":1836.2915708035437,"GB2-04":1485.4293522841347,"GB2-05":1912.4908927339682,"GB2-06":2058.2121581595575,"GB2-07":1548.5734365997173,"GB2-08":1697.9115739372792},"medium":{"GB2-01":1744.465057059646,"GB2-02":1528.3703242672718,"GB2-03":1562.9906830068862,"GB2-04":1603.9230407569,"GB2-05":1556.6149399451906,"GB2-06":1999.3379916783801,"GB2-07":1509.915504647683,"GB2-08":1827.8817208112973},"none":{"GB2-01":1246.2080672952172,"GB2-02":1458.0772418162194,"GB2-03":1485.1321666362064,"GB2-04":1419.385264517577,"GB2-05":1339.9667143332126,"GB2-06":1336.956907603062,"GB2-07":1300.5282328604483,"GB2-08":1288.4976472124215}},"per_game_tracks":{"highest":{"GB2-01":77.44851398498643,"GB2-02":62.648988059605855,"GB2-03":83.3079628008012,"GB2-04":50.95374340030112,"GB2-05":79.16632023200127,"GB2-06":84.20773742910123,"GB2-07":57.714118940419944,"GB2-08":70.39038123448921},"medium":{"GB2-01":74.93505852082129,"GB2-02":56.705408215797526,"GB2-03":63.79284042469114,"GB2-04":65.40309120243107,"GB2-05":58.225987245264086,"GB2-06":81.37584046337942,"GB2-07":54.71570120068804,"GB2-08":77.38136433835778},"none":{"GB2-01":26.529112802564843,"GB2-02":47.71084072596938,"GB2-03":55.82908192161388,"GB2-04":42.41833034922002,"GB2-05":41.0728205495651,"GB2-06":42.26858546327951,"GB2-07":37.98914467927195,"GB2-08":37.049402695927164}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":0,"rank_movement_baseline_at":"2026-10-14T17:55:04Z","reasoning":{"highest":70.72972076021328,"medium":66.5669114514288,"none":41.358414898426474},"reasoning_agg":{"highest":{"max":84.20773742910123,"mean":70.72972076021328,"min":50.95374340030112},"medium":{"max":81.37584046337942,"mean":66.5669114514288,"min":54.71570120068804},"none":{"max":55.82908192161388,"mean":41.358414898426474,"min":26.529112802564843}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":29.37130586178681}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-5:a01200a91e174a41","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07455065,"median":0.0607138,"min":0.0448404,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.5964052000000001},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0878628,"mean":0.0635932,"median":0.06199639999999999,"min":0.0498884,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.5087456},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.5947036}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0878628,"mean":0.0635932,"median":0.06199639999999999,"min":0.0498884,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.5087456},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.5947036},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07455065,"median":0.0607138,"min":0.0448404,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.5964052}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07082726666666667,"median":0.0661398,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":34},"recorded_attempt_count":34,"run_count":24,"total":1.6998544},"codegen_latency_ms":{"attempt_count":34,"max_ms":187781,"mean_ms":106806.625,"min_ms":66051,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":187781,"mean_ms":116991.125,"min_ms":74353,"run_count":8},"medium":{"attempt_count":9,"max_ms":137371,"mean_ms":104700.625,"min_ms":79776,"run_count":8},"none":{"attempt_count":14,"max_ms":128385,"mean_ms":98728.125,"min_ms":66051,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":15570,"output_mean":7807.958333333333,"output_min":4284,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":15570,"output_mean":8557.875,"output_min":4867,"run_count":8},"medium":{"attempt_count":9,"output_max":9385,"output_mean":7450.25,"output_min":5674,"run_count":8},"none":{"attempt_count":14,"output_max":10165,"output_mean":7415.75,"output_min":4284,"run_count":8}},"display_name":"Grok 4.5","economics":{"all":58.01749093562081,"highest":63.50179698995503,"medium":61.74969205191261,"none":48.80098376499481},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":34,"finish_reasons":["stop"],"indexed_attempts":34,"output_token_observations":34,"reasoning_token_observations":34,"total_output_tokens":187391,"total_reasoning_output_tokens":5791,"total_visible_output_tokens":181600,"visible_token_observations":34},"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-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":73.66662978224234,"score":73.66662978224234},"GB2-02":{"attempts":3,"playable":51.77229467320169,"score":51.77229467320169},"GB2-03":{"attempts":3,"playable":39.439759355659795,"score":39.439759355659795},"GB2-04":{"attempts":3,"playable":42.98135113649882,"score":42.98135113649882},"GB2-05":{"attempts":3,"playable":61.40156733368537,"score":61.40156733368537},"GB2-06":{"attempts":3,"playable":47.89143402400301,"score":47.89143402400301},"GB2-07":{"attempts":3,"playable":60.95494284017982,"score":60.95494284017982},"GB2-08":{"attempts":3,"playable":86.03194833949567,"score":86.03194833949567}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":84.12204834667513,"score":84.12204834667513},"GB2-02":{"attempts":1,"playable":59.68288574310836,"score":59.68288574310836},"GB2-03":{"attempts":1,"playable":45.73793380980808,"score":45.73793380980808},"GB2-04":{"attempts":1,"playable":43.99475110539615,"score":43.99475110539615},"GB2-05":{"attempts":1,"playable":73.4251514720247,"score":73.4251514720247},"GB2-06":{"attempts":1,"playable":54.8686873485351,"score":54.8686873485351},"GB2-07":{"attempts":1,"playable":56.31654963998211,"score":56.31654963998211},"GB2-08":{"attempts":1,"playable":89.86636845411061,"score":89.86636845411061}},"medium":{"GB2-01":{"attempts":1,"playable":84.32965311212234,"score":84.32965311212234},"GB2-02":{"attempts":1,"playable":52.219228337634405,"score":52.219228337634405},"GB2-03":{"attempts":1,"playable":56.71169666050516,"score":56.71169666050516},"GB2-04":{"attempts":1,"playable":42.305662447831494,"score":42.305662447831494},"GB2-05":{"attempts":1,"playable":67.61770279744185,"score":67.61770279744185},"GB2-06":{"attempts":1,"playable":45.36012528572851,"score":45.36012528572851},"GB2-07":{"attempts":1,"playable":58.5115313465271,"score":58.5115313465271},"GB2-08":{"attempts":1,"playable":86.9419364275101,"score":86.9419364275101}},"none":{"GB2-01":{"attempts":1,"playable":52.54818788792958,"score":52.54818788792958},"GB2-02":{"attempts":1,"playable":43.41476993886233,"score":43.41476993886233},"GB2-03":{"attempts":1,"playable":15.869647596666155,"score":15.869647596666155},"GB2-04":{"attempts":1,"playable":42.643639856268834,"score":42.643639856268834},"GB2-05":{"attempts":1,"playable":43.16184773158957,"score":43.16184773158957},"GB2-06":{"attempts":1,"playable":43.44548943774543,"score":43.44548943774543},"GB2-07":{"attempts":1,"playable":68.03674753403025,"score":68.03674753403025},"GB2-08":{"attempts":1,"playable":81.28754013686628,"score":81.28754013686628}}},"id":"x-ai/grok-4.5","is_recent_addition":false,"last_measured_at":"2026-10-20T11:37:50Z","match_totals_all":{"draws":2353,"losses":3567,"wins":5161},"match_totals_tracks":{"highest":{"draws":631,"losses":1064,"wins":1999},"medium":{"draws":774,"losses":1060,"wins":1860},"none":{"draws":948,"losses":1443,"wins":1302}},"model_slug":"x-ai-grok-4-5","overall":{"max":89.86636845411061,"mean":58.01749093562082,"min":15.869647596666155},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":16,"overall_ranking_status":"ranked","per_game":{"GB2-01":84.12204834667513,"GB2-02":59.68288574310836,"GB2-03":45.73793380980808,"GB2-04":43.99475110539615,"GB2-05":73.4251514720247,"GB2-06":54.8686873485351,"GB2-07":56.31654963998211,"GB2-08":89.86636845411061},"per_game_all":{"GB2-01":73.66662978224234,"GB2-02":51.77229467320169,"GB2-03":39.439759355659795,"GB2-04":42.98135113649882,"GB2-05":61.40156733368537,"GB2-06":47.89143402400301,"GB2-07":60.95494284017982,"GB2-08":86.03194833949567},"per_game_match_totals_all":{"GB2-01":{"draws":360,"losses":197,"wins":846},"GB2-02":{"draws":821,"losses":231,"wins":244},"GB2-03":{"draws":284,"losses":708,"wins":346},"GB2-04":{"draws":830,"losses":368,"wins":146},"GB2-05":{"draws":0,"losses":566,"wins":886},"GB2-06":{"draws":52,"losses":716,"wins":600},"GB2-07":{"draws":0,"losses":575,"wins":847},"GB2-08":{"draws":6,"losses":206,"wins":1246}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":96,"losses":28,"wins":344},"GB2-02":{"draws":219,"losses":70,"wins":143},"GB2-03":{"draws":103,"losses":206,"wins":137},"GB2-04":{"draws":193,"losses":160,"wins":95},"GB2-05":{"draws":0,"losses":131,"wins":353},"GB2-06":{"draws":18,"losses":205,"wins":233},"GB2-07":{"draws":0,"losses":215,"wins":259},"GB2-08":{"draws":2,"losses":49,"wins":435}},"medium":{"GB2-01":{"draws":40,"losses":55,"wins":373},"GB2-02":{"draws":272,"losses":76,"wins":84},"GB2-03":{"draws":115,"losses":151,"wins":180},"GB2-04":{"draws":316,"losses":106,"wins":26},"GB2-05":{"draws":0,"losses":159,"wins":325},"GB2-06":{"draws":27,"losses":246,"wins":183},"GB2-07":{"draws":0,"losses":204,"wins":270},"GB2-08":{"draws":4,"losses":63,"wins":419}},"none":{"GB2-01":{"draws":224,"losses":114,"wins":129},"GB2-02":{"draws":330,"losses":85,"wins":17},"GB2-03":{"draws":66,"losses":351,"wins":29},"GB2-04":{"draws":321,"losses":102,"wins":25},"GB2-05":{"draws":0,"losses":276,"wins":208},"GB2-06":{"draws":7,"losses":265,"wins":184},"GB2-07":{"draws":0,"losses":156,"wins":318},"GB2-08":{"draws":0,"losses":94,"wins":392}}},"per_game_raw_elo_all":{"GB2-01":1755.4939390729098,"GB2-02":1490.171042965427,"GB2-03":1327.562643361361,"GB2-04":1423.756122743933,"GB2-05":1615.270773097154,"GB2-06":1423.1408643387942,"GB2-07":1593.4074455396742,"GB2-08":2032.6816847755226},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1877.9662543971638,"GB2-02":1552.5899449322874,"GB2-03":1395.0519461445472,"GB2-04":1431.6221000192252,"GB2-05":1789.3336765072129,"GB2-06":1530.8857579911178,"GB2-07":1530.4542896952687,"GB2-08":2136.372119696508},"medium":{"GB2-01":1881.5587636019845,"GB2-02":1492.9489095235974,"GB2-03":1493.3538519488966,"GB2-04":1418.508212454619,"GB2-05":1689.8227766068044,"GB2-06":1383.7875321288213,"GB2-07":1559.0007426616567,"GB2-08":2050.4560962752084},"none":{"GB2-01":1506.956799219582,"GB2-02":1424.9742744403968,"GB2-03":1094.2821319906393,"GB2-04":1421.1380557579548,"GB2-05":1366.655866177444,"GB2-06":1354.7493028964436,"GB2-07":1690.7673042620968,"GB2-08":1911.2168383548517}},"per_game_tracks":{"highest":{"GB2-01":84.12204834667513,"GB2-02":59.68288574310836,"GB2-03":45.73793380980808,"GB2-04":43.99475110539615,"GB2-05":73.4251514720247,"GB2-06":54.8686873485351,"GB2-07":56.31654963998211,"GB2-08":89.86636845411061},"medium":{"GB2-01":84.32965311212234,"GB2-02":52.219228337634405,"GB2-03":56.71169666050516,"GB2-04":42.305662447831494,"GB2-05":67.61770279744185,"GB2-06":45.36012528572851,"GB2-07":58.5115313465271,"GB2-08":86.9419364275101},"none":{"GB2-01":52.54818788792958,"GB2-02":43.41476993886233,"GB2-03":15.869647596666155,"GB2-04":42.643639856268834,"GB2-05":43.16184773158957,"GB2-06":43.44548943774543,"GB2-07":68.03674753403025,"GB2-08":81.28754013686628}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:38:09Z","reasoning":{"highest":63.50179698995503,"medium":61.74969205191261,"none":48.80098376499481},"reasoning_agg":{"highest":{"max":89.86636845411061,"mean":63.50179698995503,"min":43.99475110539615},"medium":{"max":86.9419364275101,"mean":61.74969205191261,"min":42.305662447831494},"none":{"max":81.28754013686628,"mean":48.80098376499481,"min":15.869647596666155}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":14.700813224960221}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flashx:8d0d4b30b8e6e2f5","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.09557687,"mean":0.060370179999999996,"median":0.057823150000000004,"min":0.03447845,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.4829614399999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.039202100000000004,"mean":0.026445697500000004,"median":0.025158225,"min":0.015228470000000001,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.21156558},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01270098,"mean":0.0085203375,"median":0.007669445,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.0681627}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.039202100000000004,"mean":0.026445697500000004,"median":0.025158225,"min":0.015228470000000001,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.21156558000000003},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01270098,"mean":0.0085203375,"median":0.007669445,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.06816269999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.09557687,"mean":0.060370179999999996,"median":0.057823150000000004,"min":0.03447845,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.4829614399999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.09557687,"mean":0.03177873833333334,"median":0.025158225,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":29},"recorded_attempt_count":29,"run_count":24,"total":0.76268972},"codegen_latency_ms":{"attempt_count":29,"max_ms":579647,"mean_ms":182597.75,"min_ms":15305,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":579647,"mean_ms":375199.125,"min_ms":217884,"run_count":8},"medium":{"attempt_count":11,"max_ms":196176,"mean_ms":145630.0,"min_ms":61522,"run_count":8},"none":{"attempt_count":10,"max_ms":51111,"mean_ms":26964.125,"min_ms":15305,"run_count":8}},"codegen_output_tokens":{"attempt_count":29,"output_max":74293,"output_mean":22693.125,"output_min":2253,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":74293,"output_mean":46016.5,"output_min":25493,"run_count":8},"medium":{"attempt_count":11,"output_max":25418,"output_mean":18052.125,"output_min":8262,"run_count":8},"none":{"attempt_count":10,"output_max":6651,"output_mean":4010.75,"output_min":2253,"run_count":8}},"display_name":"GLM-5.3 FlashX","economics":{"all":57.512312684738696,"highest":68.32357580110377,"medium":52.28406537179428,"none":51.929296881318024},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":29,"effective_max_output_tokens":[131072],"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"provider_post_attempt_observations":29,"provider_post_attempts":29,"reasoning_token_observations":29,"reconciliation_get_attempt_observations":29,"requested_max_output_token_observations":29,"requested_max_output_tokens":[131072],"total_output_tokens":544635,"total_reasoning_output_tokens":454317,"total_visible_output_tokens":90318,"visible_token_observations":29},"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":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3-flashx","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":62.06930525163538,"score":62.06930525163538},"GB2-02":{"attempts":3,"playable":54.52155784530307,"score":54.52155784530307},"GB2-03":{"attempts":3,"playable":63.56827257936336,"score":63.56827257936336},"GB2-04":{"attempts":3,"playable":62.5927363045627,"score":62.5927363045627},"GB2-05":{"attempts":3,"playable":56.35573201021247,"score":56.35573201021247},"GB2-06":{"attempts":3,"playable":67.22912368922881,"score":67.22912368922881},"GB2-07":{"attempts":3,"playable":65.78642673612892,"score":65.78642673612892},"GB2-08":{"attempts":3,"playable":27.97534706147484,"score":27.97534706147484}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":42.01992788690999,"score":42.01992788690999},"GB2-02":{"attempts":1,"playable":69.55952775832947,"score":69.55952775832947},"GB2-03":{"attempts":1,"playable":84.90102903373923,"score":84.90102903373923},"GB2-04":{"attempts":1,"playable":78.83361282133046,"score":78.83361282133046},"GB2-05":{"attempts":1,"playable":78.55617494027402,"score":78.55617494027402},"GB2-06":{"attempts":1,"playable":81.89874107761575,"score":81.89874107761575},"GB2-07":{"attempts":1,"playable":73.98017687109746,"score":73.98017687109746},"GB2-08":{"attempts":1,"playable":36.83941601953388,"score":36.83941601953388}},"medium":{"GB2-01":{"attempts":1,"playable":78.076142706828,"score":78.076142706828},"GB2-02":{"attempts":1,"playable":52.10389798267272,"score":52.10389798267272},"GB2-03":{"attempts":1,"playable":58.25049435257117,"score":58.25049435257117},"GB2-04":{"attempts":1,"playable":56.42490620385872,"score":56.42490620385872},"GB2-05":{"attempts":1,"playable":40.65526517692817,"score":40.65526517692817},"GB2-06":{"attempts":1,"playable":55.3847041115849,"score":55.3847041115849},"GB2-07":{"attempts":1,"playable":58.5115313465271,"score":58.5115313465271},"GB2-08":{"attempts":1,"playable":18.865581093383458,"score":18.865581093383458}},"none":{"GB2-01":{"attempts":1,"playable":66.11184516116818,"score":66.11184516116818},"GB2-02":{"attempts":1,"playable":41.90124779490702,"score":41.90124779490702},"GB2-03":{"attempts":1,"playable":47.55329435177966,"score":47.55329435177966},"GB2-04":{"attempts":1,"playable":52.519689888498924,"score":52.519689888498924},"GB2-05":{"attempts":1,"playable":49.85575591343522,"score":49.85575591343522},"GB2-06":{"attempts":1,"playable":64.40392587848581,"score":64.40392587848581},"GB2-07":{"attempts":1,"playable":64.8675719907622,"score":64.8675719907622},"GB2-08":{"attempts":1,"playable":28.22104407150718,"score":28.22104407150718}}},"id":"z-ai/glm-5.3-flashx","is_recent_addition":false,"last_measured_at":"2026-10-20T11:20:22Z","match_totals_all":{"draws":2544,"losses":3585,"wins":4953},"match_totals_tracks":{"highest":{"draws":638,"losses":893,"wins":2163},"medium":{"draws":813,"losses":1415,"wins":1466},"none":{"draws":1093,"losses":1277,"wins":1324}},"model_slug":"z-ai-glm-5-3-flashx","overall":{"max":84.90102903373923,"mean":57.512312684738696,"min":18.865581093383458},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":17,"overall_ranking_status":"ranked","per_game":{"GB2-01":42.01992788690999,"GB2-02":69.55952775832947,"GB2-03":84.90102903373923,"GB2-04":78.83361282133046,"GB2-05":78.55617494027402,"GB2-06":81.89874107761575,"GB2-07":73.98017687109746,"GB2-08":36.83941601953388},"per_game_all":{"GB2-01":62.06930525163538,"GB2-02":54.52155784530307,"GB2-03":63.56827257936336,"GB2-04":62.5927363045627,"GB2-05":56.35573201021247,"GB2-06":67.22912368922881,"GB2-07":65.78642673612892,"GB2-08":27.97534706147484},"per_game_match_totals_all":{"GB2-01":{"draws":106,"losses":490,"wins":808},"GB2-02":{"draws":858,"losses":176,"wins":262},"GB2-03":{"draws":154,"losses":448,"wins":736},"GB2-04":{"draws":715,"losses":161,"wins":468},"GB2-05":{"draws":0,"losses":638,"wins":814},"GB2-06":{"draws":67,"losses":428,"wins":873},"GB2-07":{"draws":0,"losses":502,"wins":920},"GB2-08":{"draws":644,"losses":742,"wins":72}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":275,"wins":191},"GB2-02":{"draws":204,"losses":34,"wins":194},"GB2-03":{"draws":6,"losses":71,"wins":369},"GB2-04":{"draws":142,"losses":28,"wins":278},"GB2-05":{"draws":0,"losses":106,"wins":378},"GB2-06":{"draws":29,"losses":68,"wins":359},"GB2-07":{"draws":0,"losses":126,"wins":348},"GB2-08":{"draws":255,"losses":185,"wins":46}},"medium":{"GB2-01":{"draws":6,"losses":102,"wins":360},"GB2-02":{"draws":319,"losses":53,"wins":60},"GB2-03":{"draws":49,"losses":177,"wins":220},"GB2-04":{"draws":260,"losses":71,"wins":117},"GB2-05":{"draws":0,"losses":288,"wins":196},"GB2-06":{"draws":25,"losses":199,"wins":232},"GB2-07":{"draws":0,"losses":204,"wins":270},"GB2-08":{"draws":154,"losses":321,"wins":11}},"none":{"GB2-01":{"draws":98,"losses":113,"wins":257},"GB2-02":{"draws":335,"losses":89,"wins":8},"GB2-03":{"draws":99,"losses":200,"wins":147},"GB2-04":{"draws":313,"losses":62,"wins":73},"GB2-05":{"draws":0,"losses":244,"wins":240},"GB2-06":{"draws":13,"losses":161,"wins":282},"GB2-07":{"draws":0,"losses":172,"wins":302},"GB2-08":{"draws":235,"losses":236,"wins":15}}},"per_game_raw_elo_all":{"GB2-01":1611.590712453386,"GB2-02":1515.1819935651827,"GB2-03":1596.4470485925292,"GB2-04":1589.6447746887382,"GB2-05":1560.9253594971217,"GB2-06":1745.4924696319665,"GB2-07":1662.7201436525418,"GB2-08":1190.5342810325662},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1406.3013954893847,"GB2-02":1640.2530773247229,"GB2-03":1870.5306633760515,"GB2-04":1742.792158501753,"GB2-05":1897.7718222558974,"GB2-06":2009.9368787551211,"GB2-07":1784.033291243827,"GB2-08":1286.3724330913753},"medium":{"GB2-01":1785.6714779725912,"GB2-02":1492.050398189912,"GB2-03":1507.8916239475204,"GB2-04":1528.5086638307328,"GB2-05":1334.5789550647662,"GB2-06":1539.0735989507689,"GB2-07":1559.0007426616567,"GB2-08":1087.8726332073957},"none":{"GB2-01":1642.7992638981823,"GB2-02":1413.2425051809132,"GB2-03":1410.9188584540154,"GB2-04":1497.6335017337292,"GB2-05":1450.4253011707017,"GB2-06":1687.466931190009,"GB2-07":1645.1263970521416,"GB2-08":1197.3577767989273}},"per_game_tracks":{"highest":{"GB2-01":42.01992788690999,"GB2-02":69.55952775832947,"GB2-03":84.90102903373923,"GB2-04":78.83361282133046,"GB2-05":78.55617494027402,"GB2-06":81.89874107761575,"GB2-07":73.98017687109746,"GB2-08":36.83941601953388},"medium":{"GB2-01":78.076142706828,"GB2-02":52.10389798267272,"GB2-03":58.25049435257117,"GB2-04":56.42490620385872,"GB2-05":40.65526517692817,"GB2-06":55.3847041115849,"GB2-07":58.5115313465271,"GB2-08":18.865581093383458},"none":{"GB2-01":66.11184516116818,"GB2-02":41.90124779490702,"GB2-03":47.55329435177966,"GB2-04":52.519689888498924,"GB2-05":49.85575591343522,"GB2-06":64.40392587848581,"GB2-07":64.8675719907622,"GB2-08":28.22104407150718}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:51:36Z","reasoning":{"highest":68.32357580110377,"medium":52.28406537179428,"none":51.929296881318024},"reasoning_agg":{"highest":{"max":84.90102903373923,"mean":68.32357580110377,"min":36.83941601953388},"medium":{"max":78.076142706828,"mean":52.28406537179428,"min":18.865581093383458},"none":{"max":66.11184516116818,"mean":51.929296881318024,"min":28.22104407150718}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":16.394278919785748}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-haiku-5-5:a83d1736bfc7ecfa","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0653315,"mean":0.04782545,"median":0.046146,"min":0.0294405,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.3826036},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0174997,"mean":0.0119476,"median":0.012623549999999999,"min":0.0054094,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.0955808},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0063593,"mean":0.0031203999999999997,"median":0.00236545,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.024963199999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0174997,"mean":0.0119476,"median":0.012623549999999999,"min":0.0054094,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.0955808},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0063593,"mean":0.0031203999999999997,"median":0.00236545,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.0249632},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0653315,"mean":0.04782545,"median":0.046146,"min":0.0294405,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.3826036}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0653315,"mean":0.020964483333333336,"median":0.012623549999999999,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":28},"run_count":24,"token_priced_attempt_count":28,"total":0.5031476},"codegen_output_tokens":{"attempt_count":28,"output_max":128000,"output_mean":38910.541666666664,"output_min":1643,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":128000,"output_mean":92691.0,"output_min":56566,"run_count":8},"medium":{"attempt_count":9,"output_max":32619,"output_mean":20970.375,"output_min":8448,"run_count":8},"none":{"attempt_count":10,"output_max":6434,"output_mean":3070.25,"output_min":1643,"run_count":8}},"display_name":"Claude Haiku 5.5","economics":{"all":56.436977512431085,"highest":74.5450944850528,"medium":57.350741785146006,"none":39.41073076135525},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[128000],"finish_reason_observations":28,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"requested_max_output_token_observations":28,"requested_max_output_tokens":[128000],"total_output_tokens":933853,"total_reasoning_output_tokens":827092,"total_visible_output_tokens":106761,"visible_token_observations":28},"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":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-haiku-5-5","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":7,"first_pass_admitted":7,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"infra_failures_excluded":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-03"],"infra_failures_excluded":1,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":41.270025694614226,"score":41.270025694614226},"GB2-02":{"attempts":3,"playable":57.96282222794272,"score":57.96282222794272},"GB2-03":{"attempts":2,"playable":55.36545700316344,"score":55.36545700316344},"GB2-04":{"attempts":3,"playable":63.002041101438785,"score":63.002041101438785},"GB2-05":{"attempts":3,"playable":53.6982981683018,"score":53.6982981683018},"GB2-06":{"attempts":3,"playable":69.82218546447979,"score":69.82218546447979},"GB2-07":{"attempts":3,"playable":58.2919022729705,"score":58.2919022729705},"GB2-08":{"attempts":3,"playable":51.01156765726975,"score":51.01156765726975}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":42.01992788690999,"score":42.01992788690999},"GB2-02":{"attempts":1,"playable":69.67221557985683,"score":69.67221557985683},"GB2-04":{"attempts":1,"playable":80.55776064507289,"score":80.55776064507289},"GB2-05":{"attempts":1,"playable":86.33480169282974,"score":86.33480169282974},"GB2-06":{"attempts":1,"playable":91.10692876294524,"score":91.10692876294524},"GB2-07":{"attempts":1,"playable":66.25440525035457,"score":66.25440525035457},"GB2-08":{"attempts":1,"playable":85.86962157740032,"score":85.86962157740032}},"medium":{"GB2-01":{"attempts":1,"playable":46.26453886832805,"score":46.26453886832805},"GB2-02":{"attempts":1,"playable":61.96554644322498,"score":61.96554644322498},"GB2-03":{"attempts":1,"playable":67.9622730422806,"score":67.9622730422806},"GB2-04":{"attempts":1,"playable":67.49539001404051,"score":67.49539001404051},"GB2-05":{"attempts":1,"playable":57.80772619999098,"score":57.80772619999098},"GB2-06":{"attempts":1,"playable":68.9980974116821,"score":68.9980974116821},"GB2-07":{"attempts":1,"playable":56.51637535529446,"score":56.51637535529446},"GB2-08":{"attempts":1,"playable":31.79598694632632,"score":31.79598694632632}},"none":{"GB2-01":{"attempts":1,"playable":35.525610328604635,"score":35.525610328604635},"GB2-02":{"attempts":1,"playable":42.250704660746386,"score":42.250704660746386},"GB2-03":{"attempts":1,"playable":42.76864096404629,"score":42.76864096404629},"GB2-04":{"attempts":1,"playable":40.95297264520298,"score":40.95297264520298},"GB2-05":{"attempts":1,"playable":16.952366612084667,"score":16.952366612084667},"GB2-06":{"attempts":1,"playable":49.361530218812035,"score":49.361530218812035},"GB2-07":{"attempts":1,"playable":52.10492621326247,"score":52.10492621326247},"GB2-08":{"attempts":1,"playable":35.3690944480826,"score":35.3690944480826}}},"id":"claude-haiku-5-5","is_recent_addition":false,"last_measured_at":"2026-10-14T17:59:08Z","match_totals_all":{"draws":2431,"losses":3564,"wins":4641},"match_totals_tracks":{"highest":{"draws":362,"losses":663,"wins":2223},"medium":{"draws":893,"losses":1188,"wins":1613},"none":{"draws":1176,"losses":1713,"wins":805}},"model_slug":"claude-haiku-5-5","overall":{"max":91.10692876294524,"mean":57.10218901051801,"min":16.952366612084667},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":18,"overall_ranking_status":"partial","per_game":{"GB2-01":42.01992788690999,"GB2-02":69.67221557985683,"GB2-04":80.55776064507289,"GB2-05":86.33480169282974,"GB2-06":91.10692876294524,"GB2-07":66.25440525035457,"GB2-08":85.86962157740032},"per_game_all":{"GB2-01":41.270025694614226,"GB2-02":57.96282222794272,"GB2-04":63.002041101438785,"GB2-05":53.6982981683018,"GB2-06":69.82218546447979,"GB2-07":58.2919022729705,"GB2-08":51.01156765726975},"per_game_match_totals_all":{"GB2-01":{"draws":239,"losses":719,"wins":446},"GB2-02":{"draws":774,"losses":173,"wins":349},"GB2-03":{"draws":252,"losses":301,"wins":339},"GB2-04":{"draws":582,"losses":221,"wins":541},"GB2-05":{"draws":0,"losses":676,"wins":776},"GB2-06":{"draws":57,"losses":396,"wins":915},"GB2-07":{"draws":0,"losses":615,"wins":807},"GB2-08":{"draws":527,"losses":463,"wins":468}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":32,"losses":260,"wins":176},"GB2-02":{"draws":193,"losses":39,"wins":200},"GB2-04":{"draws":102,"losses":40,"wins":306},"GB2-05":{"draws":0,"losses":67,"wins":417},"GB2-06":{"draws":34,"losses":22,"wins":400},"GB2-07":{"draws":0,"losses":165,"wins":309},"GB2-08":{"draws":1,"losses":70,"wins":415}},"medium":{"GB2-01":{"draws":124,"losses":194,"wins":150},"GB2-02":{"draws":235,"losses":52,"wins":145},"GB2-03":{"draws":87,"losses":113,"wins":246},"GB2-04":{"draws":190,"losses":56,"wins":202},"GB2-05":{"draws":0,"losses":206,"wins":278},"GB2-06":{"draws":6,"losses":142,"wins":308},"GB2-07":{"draws":0,"losses":214,"wins":260},"GB2-08":{"draws":251,"losses":211,"wins":24}},"none":{"GB2-01":{"draws":83,"losses":265,"wins":120},"GB2-02":{"draws":346,"losses":82,"wins":4},"GB2-03":{"draws":165,"losses":188,"wins":93},"GB2-04":{"draws":290,"losses":125,"wins":33},"GB2-05":{"draws":0,"losses":403,"wins":81},"GB2-06":{"draws":17,"losses":232,"wins":207},"GB2-07":{"draws":0,"losses":236,"wins":238},"GB2-08":{"draws":275,"losses":182,"wins":29}}},"per_game_raw_elo_all":{"GB2-01":1398.5580167338721,"GB2-02":1543.0001473373202,"GB2-04":1598.575742940597,"GB2-05":1548.1368563832132,"GB2-06":1813.9617094355954,"GB2-07":1558.227756231947,"GB2-08":1509.4097115260804},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1406.3013954893847,"GB2-02":1641.346220627221,"GB2-04":1764.8859197363404,"GB2-05":2127.9270263259305,"GB2-06":2229.48026227364,"GB2-07":1664.8265121497745,"GB2-08":2021.833277506957},"medium":{"GB2-01":1446.982058943041,"GB2-02":1571.6972561748346,"GB2-03":1608.3186229841579,"GB2-04":1622.895721258378,"GB2-05":1551.1418153892519,"GB2-06":1767.4316434897178,"GB2-07":1533.0335629841932,"GB2-08":1234.9232795577054},"none":{"GB2-01":1342.390595769191,"GB2-02":1415.9569652099042,"GB2-03":1369.1747484742687,"GB2-04":1407.9455878270728,"GB2-05":965.3417274344575,"GB2-06":1444.973222543428,"GB2-07":1476.8231935618737,"GB2-08":1271.4725775135794}},"per_game_tracks":{"highest":{"GB2-01":42.01992788690999,"GB2-02":69.67221557985683,"GB2-04":80.55776064507289,"GB2-05":86.33480169282974,"GB2-06":91.10692876294524,"GB2-07":66.25440525035457,"GB2-08":85.86962157740032},"medium":{"GB2-01":46.26453886832805,"GB2-02":61.96554644322498,"GB2-03":67.9622730422806,"GB2-04":67.49539001404051,"GB2-05":57.80772619999098,"GB2-06":68.9980974116821,"GB2-07":56.51637535529446,"GB2-08":31.79598694632632},"none":{"GB2-01":35.525610328604635,"GB2-02":42.250704660746386,"GB2-03":42.76864096404629,"GB2-04":40.95297264520298,"GB2-05":16.952366612084667,"GB2-06":49.361530218812035,"GB2-07":52.10492621326247,"GB2-08":35.3690944480826}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":74.5450944850528,"medium":57.350741785146006,"none":39.41073076135525},"reasoning_agg":{"highest":{"max":91.10692876294524,"mean":74.5450944850528,"min":42.01992788690999},"medium":{"max":68.9980974116821,"mean":57.350741785146006,"min":31.79598694632632},"none":{"max":52.10492621326247,"mean":39.41073076135525,"min":16.952366612084667}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":35.13436372369755}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flash:ef785d3860d1888f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.014901165624999999,"median":0.013297725,"min":0.0073485,"recorded_attempt_count":9,"run_count":8,"total":0.11920932499999998},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01518705,"mean":0.00578608125,"median":0.0045066875,"min":0.0032555,"recorded_attempt_count":8,"run_count":8,"total":0.04628865},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0140393,"mean":0.0037309874999999996,"median":0.0024275875,"min":0.001111625,"recorded_attempt_count":11,"run_count":8,"total":0.0298479}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01518705,"mean":0.00578608125,"median":0.0045066875,"min":0.0032555,"recorded_attempt_count":8,"run_count":8,"total":0.04628865},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0140393,"mean":0.0037309874999999996,"median":0.0024275875,"min":0.001111625,"recorded_attempt_count":11,"run_count":8,"total":0.029847900000000004},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.014901165624999999,"median":0.013297725,"min":0.0073485,"recorded_attempt_count":9,"run_count":8,"total":0.119209325}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.008139411458333334,"median":0.005035225,"min":0.001111625,"recorded_attempt_count":28,"run_count":24,"total":0.19534587500000003},"codegen_latency_ms":{"attempt_count":28,"max_ms":1214245,"mean_ms":417506.625,"min_ms":32605,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1196482,"mean_ms":748510.375,"min_ms":448704,"run_count":8},"medium":{"attempt_count":8,"max_ms":672648,"mean_ms":296260.625,"min_ms":146516,"run_count":8},"none":{"attempt_count":11,"max_ms":1214245,"mean_ms":207748.875,"min_ms":32605,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":65809,"output_mean":27118.375,"output_min":2294,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":65809,"output_mean":50033.0,"output_min":27276,"run_count":8},"medium":{"attempt_count":8,"output_max":58608,"output_mean":20833.875,"output_min":10904,"run_count":8},"none":{"attempt_count":11,"output_max":54017,"output_mean":10488.25,"output_min":2294,"run_count":8}},"display_name":"GLM-5.3 Flash","economics":{"all":57.07910766741189,"highest":59.39769054315253,"medium":63.96925932410967,"none":47.87037313497346},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"reconciliation_get_attempts":134,"total_output_tokens":650841,"total_reasoning_output_tokens":555865,"total_visible_output_tokens":94976,"visible_token_observations":28},"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":"z-ai","provider_model":"z-ai/glm-5.3-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":58.339862170352255,"score":58.339862170352255},"GB2-02":{"attempts":3,"playable":52.392526824208,"score":52.392526824208},"GB2-03":{"attempts":3,"playable":72.73678156813925,"score":72.73678156813925},"GB2-04":{"attempts":3,"playable":72.69350118990124,"score":72.69350118990124},"GB2-05":{"attempts":3,"playable":53.458452707125566,"score":53.458452707125566},"GB2-06":{"attempts":3,"playable":47.801389975434155,"score":47.801389975434155},"GB2-07":{"attempts":3,"playable":72.46149284084267,"score":72.46149284084267},"GB2-08":{"attempts":3,"playable":26.748854063291958,"score":26.748854063291958}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":66.6378910683406,"score":66.6378910683406},"GB2-02":{"attempts":1,"playable":66.39624705047761,"score":66.39624705047761},"GB2-03":{"attempts":1,"playable":79.07789288736745,"score":79.07789288736745},"GB2-04":{"attempts":1,"playable":78.40162645636329,"score":78.40162645636329},"GB2-05":{"attempts":1,"playable":74.45672038614411,"score":74.45672038614411},"GB2-06":{"attempts":1,"playable":18.152094393631767,"score":18.152094393631767},"GB2-07":{"attempts":1,"playable":69.6208798165654,"score":69.6208798165654},"GB2-08":{"attempts":1,"playable":22.43817228632994,"score":22.43817228632994}},"medium":{"GB2-01":{"attempts":1,"playable":71.68284700913938,"score":71.68284700913938},"GB2-02":{"attempts":1,"playable":45.97132059450513,"score":45.97132059450513},"GB2-03":{"attempts":1,"playable":81.10133343440408,"score":81.10133343440408},"GB2-04":{"attempts":1,"playable":74.60666171540493,"score":74.60666171540493},"GB2-05":{"attempts":1,"playable":48.60003105671666,"score":48.60003105671666},"GB2-06":{"attempts":1,"playable":81.16687131887134,"score":81.16687131887134},"GB2-07":{"attempts":1,"playable":75.56762664383982,"score":75.56762664383982},"GB2-08":{"attempts":1,"playable":33.057382819996036,"score":33.057382819996036}},"none":{"GB2-01":{"attempts":1,"playable":36.698848433576785,"score":36.698848433576785},"GB2-02":{"attempts":1,"playable":44.810012827641245,"score":44.810012827641245},"GB2-03":{"attempts":1,"playable":58.031118382646206,"score":58.031118382646206},"GB2-04":{"attempts":1,"playable":65.07221539793551,"score":65.07221539793551},"GB2-05":{"attempts":1,"playable":37.318606678515934,"score":37.318606678515934},"GB2-06":{"attempts":1,"playable":44.08520421379935,"score":44.08520421379935},"GB2-07":{"attempts":1,"playable":72.19597206212278,"score":72.19597206212278},"GB2-08":{"attempts":1,"playable":24.751007083549897,"score":24.751007083549897}}},"id":"z-ai/glm-5.3-flash","is_recent_addition":false,"last_measured_at":"2026-10-20T11:35:12Z","match_totals_all":{"draws":2256,"losses":3776,"wins":5050},"match_totals_tracks":{"highest":{"draws":423,"losses":1338,"wins":1933},"medium":{"draws":787,"losses":977,"wins":1930},"none":{"draws":1046,"losses":1461,"wins":1187}},"model_slug":"z-ai-glm-5-3-flash","overall":{"max":81.16687131887134,"mean":57.07910766741188,"min":18.152094393631767},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":19,"overall_ranking_status":"ranked","per_game":{"GB2-01":66.6378910683406,"GB2-02":66.39624705047761,"GB2-03":79.07789288736745,"GB2-04":78.40162645636329,"GB2-05":74.45672038614411,"GB2-06":18.152094393631767,"GB2-07":69.6208798165654,"GB2-08":22.43817228632994},"per_game_all":{"GB2-01":58.339862170352255,"GB2-02":52.392526824208,"GB2-03":72.73678156813925,"GB2-04":72.69350118990124,"GB2-05":53.458452707125566,"GB2-06":47.801389975434155,"GB2-07":72.46149284084267,"GB2-08":26.748854063291958},"per_game_match_totals_all":{"GB2-01":{"draws":228,"losses":482,"wins":694},"GB2-02":{"draws":870,"losses":198,"wins":228},"GB2-03":{"draws":129,"losses":334,"wins":875},"GB2-04":{"draws":449,"losses":157,"wins":738},"GB2-05":{"draws":0,"losses":680,"wins":772},"GB2-06":{"draws":81,"losses":692,"wins":595},"GB2-07":{"draws":0,"losses":401,"wins":1021},"GB2-08":{"draws":499,"losses":832,"wins":127}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":157,"wins":306},"GB2-02":{"draws":222,"losses":39,"wins":171},"GB2-03":{"draws":8,"losses":99,"wins":339},"GB2-04":{"draws":128,"losses":37,"wins":283},"GB2-05":{"draws":0,"losses":126,"wins":358},"GB2-06":{"draws":16,"losses":373,"wins":67},"GB2-07":{"draws":0,"losses":148,"wins":326},"GB2-08":{"draws":44,"losses":359,"wins":83}},"medium":{"GB2-01":{"draws":19,"losses":126,"wins":323},"GB2-02":{"draws":320,"losses":79,"wins":33},"GB2-03":{"draws":20,"losses":83,"wins":343},"GB2-04":{"draws":139,"losses":49,"wins":260},"GB2-05":{"draws":0,"losses":250,"wins":234},"GB2-06":{"draws":30,"losses":71,"wins":355},"GB2-07":{"draws":0,"losses":118,"wins":356},"GB2-08":{"draws":259,"losses":201,"wins":26}},"none":{"GB2-01":{"draws":204,"losses":199,"wins":65},"GB2-02":{"draws":328,"losses":80,"wins":24},"GB2-03":{"draws":101,"losses":152,"wins":193},"GB2-04":{"draws":182,"losses":71,"wins":195},"GB2-05":{"draws":0,"losses":304,"wins":180},"GB2-06":{"draws":35,"losses":248,"wins":173},"GB2-07":{"draws":0,"losses":135,"wins":339},"GB2-08":{"draws":196,"losses":272,"wins":18}}},"per_game_raw_elo_all":{"GB2-01":1569.2060865148635,"GB2-02":1497.0041823148342,"GB2-03":1686.0808093569178,"GB2-04":1677.421365770718,"GB2-05":1511.5876784588788,"GB2-06":1441.7602534918326,"GB2-07":1760.1864195129654,"GB2-08":1179.8438033066593},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1648.4444452161974,"GB2-02":1610.5798114357567,"GB2-03":1758.7021743363766,"GB2-04":1737.471423395409,"GB2-05":1809.2425398840048,"GB2-06":965.7116378004962,"GB2-07":1714.5004995970266,"GB2-08":1132.413994150079},"medium":{"GB2-01":1705.0076019196363,"GB2-02":1444.6886537377545,"GB2-03":1793.7381131865563,"GB2-04":1693.8095448138047,"GB2-05":1434.795490953651,"GB2-06":1995.1313824992608,"GB2-07":1811.3398128258566,"GB2-08":1247.905426359034},"none":{"GB2-01":1354.1662124087572,"GB2-02":1435.7440817709912,"GB2-03":1505.802140547821,"GB2-04":1600.983129102941,"GB2-05":1290.7250045389796,"GB2-06":1364.437740175741,"GB2-07":1754.7189461160124,"GB2-08":1159.211989410865}},"per_game_tracks":{"highest":{"GB2-01":66.6378910683406,"GB2-02":66.39624705047761,"GB2-03":79.07789288736745,"GB2-04":78.40162645636329,"GB2-05":74.45672038614411,"GB2-06":18.152094393631767,"GB2-07":69.6208798165654,"GB2-08":22.43817228632994},"medium":{"GB2-01":71.68284700913938,"GB2-02":45.97132059450513,"GB2-03":81.10133343440408,"GB2-04":74.60666171540493,"GB2-05":48.60003105671666,"GB2-06":81.16687131887134,"GB2-07":75.56762664383982,"GB2-08":33.057382819996036},"none":{"GB2-01":36.698848433576785,"GB2-02":44.810012827641245,"GB2-03":58.031118382646206,"GB2-04":65.07221539793551,"GB2-05":37.318606678515934,"GB2-06":44.08520421379935,"GB2-07":72.19597206212278,"GB2-08":24.751007083549897}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:41:30Z","reasoning":{"highest":59.39769054315253,"medium":63.96925932410967,"none":47.87037313497346},"reasoning_agg":{"highest":{"max":79.07789288736745,"mean":59.39769054315253,"min":18.152094393631767},"medium":{"max":81.16687131887134,"mean":63.96925932410967,"min":33.057382819996036},"none":{"max":72.19597206212278,"mean":47.87037313497346,"min":24.751007083549897}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":16.09888618913621}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4:5642a8006ca19523","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":1.51903,"median":1.4938600000000002,"min":1.088255,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":12.15224},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.4120425,"mean":0.283374375,"median":0.26543625,"min":0.2124125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.2669949999999996},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.179715,"mean":0.09608781250000001,"median":0.08063500000000001,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.7687025000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.4120425,"mean":0.283374375,"median":0.26543625,"min":0.2124125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.266995},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.179715,"mean":0.09608781250000001,"median":0.08063500000000001,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.7687025000000001},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":1.51903,"median":1.4938600000000002,"min":1.088255,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":12.15224}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":0.6328307291666667,"median":0.26543625,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":24,"token_priced_attempt_count":27,"total":15.1879375},"codegen_output_tokens":{"attempt_count":27,"output_max":146534,"output_mean":40675.041666666664,"output_min":3180,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":146534,"output_mean":99672.5,"output_min":71368,"run_count":8},"medium":{"attempt_count":8,"output_max":26272,"output_mean":17600.375,"output_min":12941,"run_count":8},"none":{"attempt_count":10,"output_max":8643,"output_mean":4752.25,"output_min":3180,"run_count":8}},"display_name":"GPT-5.4","economics":{"all":59.15753611374335,"highest":72.21984944326559,"medium":56.05270524834249,"none":46.924840734497714},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"total_output_tokens":976201,"total_reasoning_output_tokens":819733,"total_visible_output_tokens":156468,"visible_token_observations":27},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":90.8977065112379,"score":90.8977065112379},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":43.525527788485135,"score":29.017018525656756},"GB2-03":{"attempts":3,"playable":40.090008901271545,"score":40.090008901271545},"GB2-04":{"attempts":3,"playable":43.24332387616667,"score":43.24332387616667},"GB2-05":{"attempts":3,"playable":72.9472159098973,"score":72.9472159098973},"GB2-06":{"attempts":3,"playable":74.85200012802972,"score":74.85200012802972},"GB2-07":{"attempts":3,"playable":47.181108367536375,"score":47.181108367536375},"GB2-08":{"attempts":3,"playable":44.89138910206402,"score":44.89138910206402}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":94.67175383412804,"score":94.67175383412804},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":43.91349499201411,"score":43.91349499201411},"GB2-04":{"attempts":1,"playable":57.204210871611416,"score":57.204210871611416},"GB2-05":{"attempts":1,"playable":86.33480169282974,"score":86.33480169282974},"GB2-06":{"attempts":1,"playable":81.27134229775152,"score":81.27134229775152},"GB2-07":{"attempts":1,"playable":77.35558668748504,"score":77.35558668748504},"GB2-08":{"attempts":1,"playable":64.78775572703928,"score":64.78775572703928}},"medium":{"GB2-01":{"attempts":1,"playable":97.75130853697418,"score":97.75130853697418},"GB2-02":{"attempts":1,"playable":47.015389091617266,"score":47.015389091617266},"GB2-03":{"attempts":1,"playable":43.3415069229021,"score":43.3415069229021},"GB2-04":{"attempts":1,"playable":33.152465166837715,"score":33.152465166837715},"GB2-05":{"attempts":1,"playable":71.56343558164502,"score":71.56343558164502},"GB2-06":{"attempts":1,"playable":79.18699713341948,"score":79.18699713341948},"GB2-07":{"attempts":1,"playable":35.06063951455339,"score":35.06063951455339},"GB2-08":{"attempts":1,"playable":41.349900038790786,"score":41.349900038790786}},"none":{"GB2-01":{"attempts":1,"playable":80.27005716261147,"score":80.27005716261147},"GB2-02":{"attempts":1,"playable":40.035666485353,"score":40.035666485353},"GB2-03":{"attempts":1,"playable":33.01502478889844,"score":33.01502478889844},"GB2-04":{"attempts":1,"playable":39.37329559005088,"score":39.37329559005088},"GB2-05":{"attempts":1,"playable":60.94341045521714,"score":60.94341045521714},"GB2-06":{"attempts":1,"playable":64.09766095291816,"score":64.09766095291816},"GB2-07":{"attempts":1,"playable":29.127098900570697,"score":29.127098900570697},"GB2-08":{"attempts":1,"playable":28.536511540361992,"score":28.536511540361992}}},"id":"gpt-5.4","is_recent_addition":false,"last_measured_at":"2026-10-20T11:35:00Z","match_totals_all":{"draws":2471,"losses":3360,"wins":4819},"match_totals_tracks":{"highest":{"draws":467,"losses":693,"wins":2102},"medium":{"draws":1071,"losses":1126,"wins":1497},"none":{"draws":933,"losses":1541,"wins":1220}},"model_slug":"gpt-5-4","overall":{"max":97.75130853697418,"mean":55.38997141523253,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":20,"overall_ranking_status":"ranked","per_game":{"GB2-01":94.67175383412804,"GB2-03":43.91349499201411,"GB2-04":57.204210871611416,"GB2-05":86.33480169282974,"GB2-06":81.27134229775152,"GB2-07":77.35558668748504,"GB2-08":64.78775572703928},"per_game_all":{"GB2-01":90.8977065112379,"GB2-03":40.090008901271545,"GB2-04":43.24332387616667,"GB2-05":72.9472159098973,"GB2-06":74.85200012802972,"GB2-07":47.181108367536375,"GB2-08":44.89138910206402},"per_game_match_totals_all":{"GB2-01":{"draws":66,"losses":95,"wins":1243},"GB2-02":{"draws":654,"losses":172,"wins":38},"GB2-03":{"draws":486,"losses":603,"wins":249},"GB2-04":{"draws":748,"losses":405,"wins":191},"GB2-05":{"draws":0,"losses":398,"wins":1054},"GB2-06":{"draws":76,"losses":312,"wins":980},"GB2-07":{"draws":0,"losses":775,"wins":647},"GB2-08":{"draws":441,"losses":600,"wins":417}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":18,"wins":437},"GB2-03":{"draws":131,"losses":200,"wins":115},"GB2-04":{"draws":239,"losses":78,"wins":131},"GB2-05":{"draws":0,"losses":67,"wins":417},"GB2-06":{"draws":33,"losses":69,"wins":354},"GB2-07":{"draws":0,"losses":109,"wins":365},"GB2-08":{"draws":51,"losses":152,"wins":283}},"medium":{"GB2-01":{"draws":6,"losses":6,"wins":456},"GB2-02":{"draws":331,"losses":69,"wins":32},"GB2-03":{"draws":196,"losses":170,"wins":80},"GB2-04":{"draws":237,"losses":186,"wins":25},"GB2-05":{"draws":0,"losses":140,"wins":344},"GB2-06":{"draws":29,"losses":81,"wins":346},"GB2-07":{"draws":0,"losses":319,"wins":155},"GB2-08":{"draws":272,"losses":155,"wins":59}},"none":{"GB2-01":{"draws":47,"losses":71,"wins":350},"GB2-02":{"draws":323,"losses":103,"wins":6},"GB2-03":{"draws":159,"losses":233,"wins":54},"GB2-04":{"draws":272,"losses":141,"wins":35},"GB2-05":{"draws":0,"losses":191,"wins":293},"GB2-06":{"draws":14,"losses":162,"wins":280},"GB2-07":{"draws":0,"losses":347,"wins":127},"GB2-08":{"draws":118,"losses":293,"wins":75}}},"per_game_raw_elo_all":{"GB2-01":2098.0425052274986,"GB2-03":1345.2362127132249,"GB2-04":1425.0986735740491,"GB2-05":1825.3814160957763,"GB2-06":1878.4899828634216,"GB2-07":1430.1795241611553,"GB2-08":1380.6889004396846},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2146.5413600658067,"GB2-03":1379.150790344488,"GB2-04":1534.7710853825583,"GB2-05":2127.9270263259305,"GB2-06":1997.2324067994557,"GB2-07":1843.7694651785114,"GB2-08":1609.2340855814612},"medium":{"GB2-01":2330.774654691658,"GB2-02":1452.7241806603793,"GB2-03":1374.1674121735118,"GB2-04":1345.0078175248198,"GB2-05":1755.3208805429808,"GB2-06":1955.992964592284,"GB2-07":1263.0285632676082,"GB2-08":1332.1013925111215},"none":{"GB2-01":1816.8115009250319,"GB2-02":1398.6767889214864,"GB2-03":1282.3904356216744,"GB2-04":1395.517117814769,"GB2-05":1592.8963414184177,"GB2-06":1682.2445771985251,"GB2-07":1183.7405440373466,"GB2-08":1200.7312232264708}},"per_game_tracks":{"highest":{"GB2-01":94.67175383412804,"GB2-03":43.91349499201411,"GB2-04":57.204210871611416,"GB2-05":86.33480169282974,"GB2-06":81.27134229775152,"GB2-07":77.35558668748504,"GB2-08":64.78775572703928},"medium":{"GB2-01":97.75130853697418,"GB2-02":47.015389091617266,"GB2-03":43.3415069229021,"GB2-04":33.152465166837715,"GB2-05":71.56343558164502,"GB2-06":79.18699713341948,"GB2-07":35.06063951455339,"GB2-08":41.349900038790786},"none":{"GB2-01":80.27005716261147,"GB2-02":40.035666485353,"GB2-03":33.01502478889844,"GB2-04":39.37329559005088,"GB2-05":60.94341045521714,"GB2-06":64.09766095291816,"GB2-07":29.127098900570697,"GB2-08":28.536511540361992}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-14T17:26:53Z","reasoning":{"highest":63.19236826285739,"medium":56.05270524834249,"none":46.924840734497714},"reasoning_agg":{"highest":{"max":94.67175383412804,"mean":63.19236826285739,"min":0.0},"medium":{"max":97.75130853697418,"mean":56.05270524834249,"min":33.152465166837715},"none":{"max":80.27005716261147,"mean":46.924840734497714,"min":28.536511540361992}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":16.26752752835968}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max-0902:6d65a4dc2972889b","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.518502,"mean":0.398628,"median":0.380653,"min":0.332482,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":3.1890240000000003},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.30508599999999997,"mean":0.10921525,"median":0.088878,"min":0.054514,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":10,"run_count":8,"total":0.8737219999999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.212408,"mean":0.12122175,"median":0.11379500000000001,"min":0.08249,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.9697739999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.30508599999999997,"mean":0.10921525,"median":0.088878,"min":0.054514,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":10,"run_count":8,"total":0.8737219999999999},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.212408,"mean":0.12122175,"median":0.11379500000000001,"min":0.08249,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.969774},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.518502,"mean":0.398628,"median":0.380653,"min":0.332482,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":3.1890240000000003}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.518502,"mean":0.20968833333333334,"median":0.124697,"min":0.054514,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":19,"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":30,"run_count":24,"total":5.032520000000001},"codegen_latency_ms":{"attempt_count":30,"max_ms":1906796,"mean_ms":726982.5833333334,"min_ms":135091,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":1906796,"mean_ms":1528927.125,"min_ms":1229561,"run_count":8},"medium":{"attempt_count":10,"max_ms":878124,"mean_ms":297986.875,"min_ms":135091,"run_count":8},"none":{"attempt_count":10,"max_ms":640944,"mean_ms":354033.75,"min_ms":208254,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":78760,"output_mean":31343.75,"output_min":6298,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":78760,"output_mean":62794.5,"output_min":52930,"run_count":8},"medium":{"attempt_count":10,"output_max":40870,"output_mean":14338.625,"output_min":6298,"run_count":8},"none":{"attempt_count":10,"output_max":30162,"output_mean":16898.125,"output_min":10952,"run_count":8}},"display_name":"Qwen3.8 Max 0902","economics":{"all":55.049111939210846,"highest":70.11460266920588,"medium":45.20475250128739,"none":49.82798064713928},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":30,"effective_max_output_tokens":[131072],"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":30,"provider_post_attempts":31,"reasoning_token_observations":30,"reconciliation_get_attempt_observations":30,"requested_max_output_token_observations":30,"requested_max_output_tokens":[131072],"total_output_tokens":752250,"total_reasoning_output_tokens":630868,"total_visible_output_tokens":121382,"visible_token_observations":30},"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":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-max-0902","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":47.92934702108003,"score":47.92934702108003},"GB2-02":{"attempts":3,"playable":46.971582056804266,"score":46.971582056804266},"GB2-03":{"attempts":3,"playable":61.69686996156838,"score":61.69686996156838},"GB2-04":{"attempts":3,"playable":56.46895777364628,"score":56.46895777364628},"GB2-05":{"attempts":3,"playable":65.1792408267371,"score":65.1792408267371},"GB2-06":{"attempts":3,"playable":68.25113434852864,"score":68.25113434852864},"GB2-07":{"attempts":3,"playable":51.46547565409549,"score":51.46547565409549},"GB2-08":{"attempts":3,"playable":42.4302878712266,"score":42.4302878712266}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":75.9828635584782,"score":75.9828635584782},"GB2-02":{"attempts":1,"playable":49.56300236613333,"score":49.56300236613333},"GB2-03":{"attempts":1,"playable":71.33722866450711,"score":71.33722866450711},"GB2-04":{"attempts":1,"playable":85.37117754446221,"score":85.37117754446221},"GB2-05":{"attempts":1,"playable":92.68625145888753,"score":92.68625145888753},"GB2-06":{"attempts":1,"playable":63.99556539404529,"score":63.99556539404529},"GB2-07":{"attempts":1,"playable":76.7593334781566,"score":76.7593334781566},"GB2-08":{"attempts":1,"playable":45.22139888897679,"score":45.22139888897679}},"medium":{"GB2-01":{"attempts":1,"playable":26.529112802564843,"score":26.529112802564843},"GB2-02":{"attempts":1,"playable":48.984577700581234,"score":48.984577700581234},"GB2-03":{"attempts":1,"playable":57.262113923501055,"score":57.262113923501055},"GB2-04":{"attempts":1,"playable":46.24367820432267,"score":46.24367820432267},"GB2-05":{"attempts":1,"playable":42.534938107121306,"score":42.534938107121306},"GB2-06":{"attempts":1,"playable":60.008579614554726,"score":60.008579614554726},"GB2-07":{"attempts":1,"playable":37.363645576727194,"score":37.363645576727194},"GB2-08":{"attempts":1,"playable":42.71137408092605,"score":42.71137408092605}},"none":{"GB2-01":{"attempts":1,"playable":41.27606470219706,"score":41.27606470219706},"GB2-02":{"attempts":1,"playable":42.36716610369823,"score":42.36716610369823},"GB2-03":{"attempts":1,"playable":56.491267296696975,"score":56.491267296696975},"GB2-04":{"attempts":1,"playable":37.79201757215395,"score":37.79201757215395},"GB2-05":{"attempts":1,"playable":60.31653291420248,"score":60.31653291420248},"GB2-06":{"attempts":1,"playable":80.74925803698588,"score":80.74925803698588},"GB2-07":{"attempts":1,"playable":40.27344790740269,"score":40.27344790740269},"GB2-08":{"attempts":1,"playable":39.35809064377695,"score":39.35809064377695}}},"id":"qwen/qwen3.8-max-0902","is_recent_addition":false,"last_measured_at":"2026-10-20T11:22:34Z","match_totals_all":{"draws":2932,"losses":3661,"wins":4489},"match_totals_tracks":{"highest":{"draws":747,"losses":762,"wins":2185},"medium":{"draws":995,"losses":1590,"wins":1109},"none":{"draws":1190,"losses":1309,"wins":1195}},"model_slug":"qwen-qwen3-8-max-0902","overall":{"max":92.68625145888753,"mean":55.04911193921085,"min":26.529112802564843},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":21,"overall_ranking_status":"ranked","per_game":{"GB2-01":75.9828635584782,"GB2-02":49.56300236613333,"GB2-03":71.33722866450711,"GB2-04":85.37117754446221,"GB2-05":92.68625145888753,"GB2-06":63.99556539404529,"GB2-07":76.7593334781566,"GB2-08":45.22139888897679},"per_game_all":{"GB2-01":47.92934702108003,"GB2-02":46.971582056804266,"GB2-03":61.69686996156838,"GB2-04":56.46895777364628,"GB2-05":65.1792408267371,"GB2-06":68.25113434852864,"GB2-07":51.46547565409549,"GB2-08":42.4302878712266},"per_game_match_totals_all":{"GB2-01":{"draws":284,"losses":601,"wins":519},"GB2-02":{"draws":948,"losses":230,"wins":118},"GB2-03":{"draws":240,"losses":436,"wins":662},"GB2-04":{"draws":630,"losses":284,"wins":430},"GB2-05":{"draws":0,"losses":507,"wins":945},"GB2-06":{"draws":91,"losses":401,"wins":876},"GB2-07":{"draws":0,"losses":714,"wins":708},"GB2-08":{"draws":739,"losses":488,"wins":231}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":114,"wins":352},"GB2-02":{"draws":297,"losses":75,"wins":60},"GB2-03":{"draws":77,"losses":102,"wins":267},"GB2-04":{"draws":77,"losses":30,"wins":341},"GB2-05":{"draws":0,"losses":34,"wins":450},"GB2-06":{"draws":45,"losses":147,"wins":264},"GB2-07":{"draws":0,"losses":112,"wins":362},"GB2-08":{"draws":249,"losses":148,"wins":89}},"medium":{"GB2-01":{"draws":89,"losses":304,"wins":75},"GB2-02":{"draws":322,"losses":65,"wins":45},"GB2-03":{"draws":82,"losses":165,"wins":199},"GB2-04":{"draws":283,"losses":105,"wins":60},"GB2-05":{"draws":0,"losses":279,"wins":205},"GB2-06":{"draws":14,"losses":182,"wins":260},"GB2-07":{"draws":0,"losses":308,"wins":166},"GB2-08":{"draws":205,"losses":182,"wins":99}},"none":{"GB2-01":{"draws":193,"losses":183,"wins":92},"GB2-02":{"draws":329,"losses":90,"wins":13},"GB2-03":{"draws":81,"losses":169,"wins":196},"GB2-04":{"draws":270,"losses":149,"wins":29},"GB2-05":{"draws":0,"losses":194,"wins":290},"GB2-06":{"draws":32,"losses":72,"wins":352},"GB2-07":{"draws":0,"losses":294,"wins":180},"GB2-08":{"draws":285,"losses":158,"wins":43}}},"per_game_raw_elo_all":{"GB2-01":1467.7153196292827,"GB2-02":1452.3686836879622,"GB2-03":1546.09276408842,"GB2-04":1555.9539802802403,"GB2-05":1783.2256919087397,"GB2-06":1760.3609323759672,"GB2-07":1484.8801232395847,"GB2-08":1343.294789911224},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1757.8271805911668,"GB2-02":1472.3543816874585,"GB2-03":1648.462478180633,"GB2-04":1835.9098645419854,"GB2-05":2406.584151848516,"GB2-06":1680.5066954172821,"GB2-07":1832.7357642132579,"GB2-08":1371.9951745914113},"medium":{"GB2-01":1246.2080672952172,"GB2-02":1467.8909000664848,"GB2-03":1498.5228322278078,"GB2-04":1449.00498947407,"GB2-05":1358.6891764178804,"GB2-06":1613.8045920742813,"GB2-07":1292.5820375528697,"GB2-08":1346.0246480727346},"none":{"GB2-01":1399.1107110014636,"GB2-02":1416.8607693099427,"GB2-03":1491.2929818568186,"GB2-04":1382.947086824666,"GB2-05":1584.403747459823,"GB2-06":1986.771509636338,"GB2-07":1329.3225679526267,"GB2-08":1311.864547069526}},"per_game_tracks":{"highest":{"GB2-01":75.9828635584782,"GB2-02":49.56300236613333,"GB2-03":71.33722866450711,"GB2-04":85.37117754446221,"GB2-05":92.68625145888753,"GB2-06":63.99556539404529,"GB2-07":76.7593334781566,"GB2-08":45.22139888897679},"medium":{"GB2-01":26.529112802564843,"GB2-02":48.984577700581234,"GB2-03":57.262113923501055,"GB2-04":46.24367820432267,"GB2-05":42.534938107121306,"GB2-06":60.008579614554726,"GB2-07":37.363645576727194,"GB2-08":42.71137408092605},"none":{"GB2-01":41.27606470219706,"GB2-02":42.36716610369823,"GB2-03":56.491267296696975,"GB2-04":37.79201757215395,"GB2-05":60.31653291420248,"GB2-06":80.74925803698588,"GB2-07":40.27344790740269,"GB2-08":39.35809064377695}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T22:11:48Z","reasoning":{"highest":70.11460266920588,"medium":45.20475250128739,"none":49.82798064713928},"reasoning_agg":{"highest":{"max":92.68625145888753,"mean":70.11460266920588,"min":45.22139888897679},"medium":{"max":60.008579614554726,"mean":45.20475250128739,"min":26.529112802564843},"none":{"max":80.74925803698588,"mean":49.82798064713928,"min":37.79201757215395}},"reasoning_labels":{"highest":"Xhigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.909850167918492}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-2-4t-a95b:50f9212c2d1a966c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.4317783571024416,"median":0.3306270924500423,"min":0.277380977244658,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.454226856819534},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.17384630544122162,"mean":0.10235142090592425,"median":0.0851321236175097,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.8188113672473941},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2163622471450082,"mean":0.1497312219916341,"median":0.14598267318350014,"min":0.09347384547152984,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1978497759330726}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.17384630544122162,"mean":0.10235142090592425,"median":0.0851321236175097,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.8188113672473941},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2163622471450082,"mean":0.1497312219916341,"median":0.14598267318350014,"min":0.09347384547152984,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1978497759330726},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.4317783571024416,"median":0.3306270924500423,"min":0.277380977244658,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.454226856819534}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":27},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.22795366666666664,"median":0.16679960729572763,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":24,"token_priced_attempt_count":27,"total":5.4708879999999995},"codegen_output_tokens":{"attempt_count":27,"output_max":128921,"output_mean":35057.208333333336,"output_min":6291,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":128921,"output_mean":72806.0,"output_min":45821,"run_count":8},"medium":{"attempt_count":8,"output_max":25498,"output_mean":11826.75,"output_min":6291,"run_count":8},"none":{"attempt_count":9,"output_max":34088,"output_mean":20538.875,"output_min":10484,"run_count":8}},"display_name":"Qwen3.8 2.4T A95B","economics":{"all":54.41936603645973,"highest":69.02230981251466,"medium":43.162916740646416,"none":51.072871556218125},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"total_output_tokens":841373,"total_reasoning_output_tokens":733891,"total_visible_output_tokens":107482,"visible_token_observations":27},"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/qwen3.8-2.4t-a95b","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":49.06912124470347,"score":49.06912124470347},"GB2-02":{"attempts":3,"playable":48.78177689756578,"score":48.78177689756578},"GB2-03":{"attempts":3,"playable":58.81430650791898,"score":58.81430650791898},"GB2-04":{"attempts":3,"playable":44.478427951577885,"score":44.478427951577885},"GB2-05":{"attempts":3,"playable":51.599115304692106,"score":51.599115304692106},"GB2-06":{"attempts":3,"playable":63.20728236928125,"score":63.20728236928125},"GB2-07":{"attempts":3,"playable":48.701617387272336,"score":48.701617387272336},"GB2-08":{"attempts":3,"playable":70.70328062866601,"score":70.70328062866601}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":58.52709121516377,"score":58.52709121516377},"GB2-02":{"attempts":1,"playable":53.83230658171064,"score":53.83230658171064},"GB2-03":{"attempts":1,"playable":82.50780203716772,"score":82.50780203716772},"GB2-04":{"attempts":1,"playable":47.25446018275357,"score":47.25446018275357},"GB2-05":{"attempts":1,"playable":68.65769931935657,"score":68.65769931935657},"GB2-06":{"attempts":1,"playable":80.64492205065594,"score":80.64492205065594},"GB2-07":{"attempts":1,"playable":69.6208798165654,"score":69.6208798165654},"GB2-08":{"attempts":1,"playable":91.13331729674357,"score":91.13331729674357}},"medium":{"GB2-01":{"attempts":1,"playable":51.874815525857464,"score":51.874815525857464},"GB2-02":{"attempts":1,"playable":43.06567904542477,"score":43.06567904542477},"GB2-03":{"attempts":1,"playable":43.227003898484156,"score":43.227003898484156},"GB2-04":{"attempts":1,"playable":39.82479781827604,"score":39.82479781827604},"GB2-05":{"attempts":1,"playable":50.90227178982085,"score":50.90227178982085},"GB2-06":{"attempts":1,"playable":46.206881880944,"score":46.206881880944},"GB2-07":{"attempts":1,"playable":31.683051555324926,"score":31.683051555324926},"GB2-08":{"attempts":1,"playable":38.51883241103909,"score":38.51883241103909}},"none":{"GB2-01":{"attempts":1,"playable":36.80545699308916,"score":36.80545699308916},"GB2-02":{"attempts":1,"playable":49.44734506556192,"score":49.44734506556192},"GB2-03":{"attempts":1,"playable":50.708113588105064,"score":50.708113588105064},"GB2-04":{"attempts":1,"playable":46.356025853704054,"score":46.356025853704054},"GB2-05":{"attempts":1,"playable":35.237374804898906,"score":35.237374804898906},"GB2-06":{"attempts":1,"playable":62.77004317624383,"score":62.77004317624383},"GB2-07":{"attempts":1,"playable":44.80092078992669,"score":44.80092078992669},"GB2-08":{"attempts":1,"playable":82.4576921782154,"score":82.4576921782154}}},"id":"qwen/qwen3.8-2.4t-a95b","is_recent_addition":false,"last_measured_at":"2026-10-20T11:38:38Z","match_totals_all":{"draws":2958,"losses":3700,"wins":4424},"match_totals_tracks":{"highest":{"draws":778,"losses":776,"wins":2140},"medium":{"draws":1273,"losses":1522,"wins":899},"none":{"draws":907,"losses":1402,"wins":1385}},"model_slug":"qwen-qwen3-8-2-4t-a95b","overall":{"max":91.13331729674357,"mean":54.419366036459735,"min":31.683051555324926},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":22,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.52709121516377,"GB2-02":53.83230658171064,"GB2-03":82.50780203716772,"GB2-04":47.25446018275357,"GB2-05":68.65769931935657,"GB2-06":80.64492205065594,"GB2-07":69.6208798165654,"GB2-08":91.13331729674357},"per_game_all":{"GB2-01":49.06912124470347,"GB2-02":48.78177689756578,"GB2-03":58.81430650791898,"GB2-04":44.478427951577885,"GB2-05":51.599115304692106,"GB2-06":63.20728236928125,"GB2-07":48.701617387272336,"GB2-08":70.70328062866601},"per_game_match_totals_all":{"GB2-01":{"draws":564,"losses":446,"wins":394},"GB2-02":{"draws":957,"losses":202,"wins":137},"GB2-03":{"draws":210,"losses":485,"wins":643},"GB2-04":{"draws":858,"losses":334,"wins":152},"GB2-05":{"draws":0,"losses":707,"wins":745},"GB2-06":{"draws":109,"losses":465,"wins":794},"GB2-07":{"draws":0,"losses":755,"wins":667},"GB2-08":{"draws":260,"losses":306,"wins":892}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":142,"losses":127,"wins":199},"GB2-02":{"draws":306,"losses":52,"wins":74},"GB2-03":{"draws":12,"losses":80,"wins":354},"GB2-04":{"draws":274,"losses":105,"wins":69},"GB2-05":{"draws":0,"losses":154,"wins":330},"GB2-06":{"draws":43,"losses":67,"wins":346},"GB2-07":{"draws":0,"losses":148,"wins":326},"GB2-08":{"draws":1,"losses":43,"wins":442}},"medium":{"GB2-01":{"draws":243,"losses":108,"wins":117},"GB2-02":{"draws":325,"losses":89,"wins":18},"GB2-03":{"draws":145,"losses":196,"wins":105},"GB2-04":{"draws":268,"losses":141,"wins":39},"GB2-05":{"draws":0,"losses":239,"wins":245},"GB2-06":{"draws":35,"losses":238,"wins":183},"GB2-07":{"draws":0,"losses":335,"wins":139},"GB2-08":{"draws":257,"losses":176,"wins":53}},"none":{"GB2-01":{"draws":179,"losses":211,"wins":78},"GB2-02":{"draws":326,"losses":61,"wins":45},"GB2-03":{"draws":53,"losses":209,"wins":184},"GB2-04":{"draws":316,"losses":88,"wins":44},"GB2-05":{"draws":0,"losses":314,"wins":170},"GB2-06":{"draws":31,"losses":160,"wins":265},"GB2-07":{"draws":0,"losses":272,"wins":202},"GB2-08":{"draws":2,"losses":87,"wins":397}}},"per_game_raw_elo_all":{"GB2-01":1473.604985915569,"GB2-02":1466.4351590231408,"GB2-03":1544.0582477352411,"GB2-04":1435.253366296173,"GB2-05":1477.43703363259,"GB2-06":1680.3762071446272,"GB2-07":1439.6075037227295,"GB2-08":1806.5947392543676},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1565.0817246191539,"GB2-02":1505.5703326998264,"GB2-03":1820.2675244282245,"GB2-04":1456.8066455080627,"GB2-05":1706.3425197475635,"GB2-06":1984.6922639704885,"GB2-07":1714.5004995970266,"GB2-08":2178.463598547937},"medium":{"GB2-01":1500.5030922101732,"GB2-02":1422.2736922871886,"GB2-03":1373.1696690660337,"GB2-04":1399.0812310313784,"GB2-05":1463.4655166033804,"GB2-06":1396.6729040758423,"GB2-07":1218.5753314635824,"GB2-08":1303.3658125916486},"none":{"GB2-01":1355.23014091738,"GB2-02":1471.4614520824077,"GB2-03":1438.7375497114651,"GB2-04":1449.8722223490781,"GB2-05":1262.5030645468266,"GB2-06":1659.7634533875507,"GB2-07":1385.7466801075798,"GB2-08":1937.9548066235175}},"per_game_tracks":{"highest":{"GB2-01":58.52709121516377,"GB2-02":53.83230658171064,"GB2-03":82.50780203716772,"GB2-04":47.25446018275357,"GB2-05":68.65769931935657,"GB2-06":80.64492205065594,"GB2-07":69.6208798165654,"GB2-08":91.13331729674357},"medium":{"GB2-01":51.874815525857464,"GB2-02":43.06567904542477,"GB2-03":43.227003898484156,"GB2-04":39.82479781827604,"GB2-05":50.90227178982085,"GB2-06":46.206881880944,"GB2-07":31.683051555324926,"GB2-08":38.51883241103909},"none":{"GB2-01":36.80545699308916,"GB2-02":49.44734506556192,"GB2-03":50.708113588105064,"GB2-04":46.356025853704054,"GB2-05":35.237374804898906,"GB2-06":62.77004317624383,"GB2-07":44.80092078992669,"GB2-08":82.4576921782154}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T22:27:00Z","reasoning":{"highest":69.02230981251466,"medium":43.162916740646416,"none":51.072871556218125},"reasoning_agg":{"highest":{"max":91.13331729674357,"mean":69.02230981251466,"min":47.25446018275357},"medium":{"max":51.874815525857464,"mean":43.162916740646416,"min":31.683051555324926},"none":{"max":82.4576921782154,"mean":51.072871556218125,"min":35.237374804898906}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":25.859393071868247}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy4-preview:25dfa6ac02cd1ccf","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.151385561,"mean":0.12117269062500001,"median":0.1216224665,"min":0.099918984,"recorded_attempt_count":9,"run_count":8,"total":0.9693815250000001},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.135826968,"median":0.126875313,"min":0.097439089,"recorded_attempt_count":10,"run_count":8,"total":1.0866157440000002},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.028804516000000002,"mean":0.015939765625,"median":0.0150484685,"min":0.009391185,"recorded_attempt_count":9,"run_count":8,"total":0.127518125}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.135826968,"median":0.126875313,"min":0.097439089,"recorded_attempt_count":10,"run_count":8,"total":1.086615744},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.028804516000000002,"mean":0.015939765625,"median":0.0150484685,"min":0.009391185,"recorded_attempt_count":9,"run_count":8,"total":0.127518125},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.151385561,"mean":0.12117269062500001,"median":0.1216224665,"min":0.099918984,"recorded_attempt_count":9,"run_count":8,"total":0.969381525}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.09097980808333334,"median":0.1119999555,"min":0.009391185,"recorded_attempt_count":28,"run_count":24,"total":2.1835153940000005},"codegen_latency_ms":{"attempt_count":28,"max_ms":1122981,"mean_ms":579882.5416666666,"min_ms":29109,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":995043,"mean_ms":822481.25,"min_ms":674828,"run_count":8},"medium":{"attempt_count":10,"max_ms":1122981,"mean_ms":860540.0,"min_ms":640692,"run_count":8},"none":{"attempt_count":9,"max_ms":99413,"mean_ms":56626.375,"min_ms":29109,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":69581,"output_mean":33844.916666666664,"output_min":1323,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":57331,"output_mean":47325.375,"output_min":39792,"run_count":8},"medium":{"attempt_count":10,"output_max":69581,"output_mean":50814.0,"output_min":36329,"run_count":8},"none":{"attempt_count":9,"output_max":6014,"output_mean":3395.375,"output_min":1323,"run_count":8}},"display_name":"Hy4 Preview","economics":{"all":55.52167074783973,"highest":64.84534922615467,"medium":58.406856855504216,"none":45.10278185897638},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"reconciliation_get_attempts":131,"total_output_tokens":812278,"total_reasoning_output_tokens":673611,"total_visible_output_tokens":138667,"visible_token_observations":28},"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/hy4-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":51.73121919087438,"score":51.73121919087438},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":61.23898048247183,"score":40.825986988314554},"GB2-03":{"attempts":3,"playable":58.91523924206839,"score":58.91523924206839},"GB2-04":{"attempts":3,"playable":44.30127643050357,"score":44.30127643050357},"GB2-05":{"attempts":3,"playable":57.86302515346855,"score":57.86302515346855},"GB2-06":{"attempts":3,"playable":60.31975288746427,"score":60.31975288746427},"GB2-07":{"attempts":3,"playable":61.40130205349127,"score":61.40130205349127},"GB2-08":{"attempts":3,"playable":54.119880277007674,"score":54.119880277007674}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":55.25574526371777,"score":55.25574526371777},"GB2-02":{"attempts":1,"playable":79.06319102608134,"score":79.06319102608134},"GB2-03":{"attempts":1,"playable":72.06983142615508,"score":72.06983142615508},"GB2-04":{"attempts":1,"playable":56.64762580038407,"score":56.64762580038407},"GB2-05":{"attempts":1,"playable":70.31938149407007,"score":70.31938149407007},"GB2-06":{"attempts":1,"playable":80.2278453608523,"score":80.2278453608523},"GB2-07":{"attempts":1,"playable":68.23476209222156,"score":68.23476209222156},"GB2-08":{"attempts":1,"playable":36.944411345755206,"score":36.944411345755206}},"medium":{"GB2-01":{"attempts":1,"playable":53.03750667961113,"score":53.03750667961113},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":40.237651184567675,"score":40.237651184567675},"GB2-04":{"attempts":1,"playable":35.07769682146017,"score":35.07769682146017},"GB2-05":{"attempts":1,"playable":52.15811497181693,"score":52.15811497181693},"GB2-06":{"attempts":1,"playable":60.72520651682459,"score":60.72520651682459},"GB2-07":{"attempts":1,"playable":77.35558668748504,"score":77.35558668748504},"GB2-08":{"attempts":1,"playable":90.25623512676398,"score":90.25623512676398}},"none":{"GB2-01":{"attempts":1,"playable":46.90040562929424,"score":46.90040562929424},"GB2-02":{"attempts":1,"playable":43.41476993886233,"score":43.41476993886233},"GB2-03":{"attempts":1,"playable":64.43823511548239,"score":64.43823511548239},"GB2-04":{"attempts":1,"playable":41.178506669666476,"score":41.178506669666476},"GB2-05":{"attempts":1,"playable":51.111578994518624,"score":51.111578994518624},"GB2-06":{"attempts":1,"playable":40.0062067847159,"score":40.0062067847159},"GB2-07":{"attempts":1,"playable":38.613557380767226,"score":38.613557380767226},"GB2-08":{"attempts":1,"playable":35.15899435850383,"score":35.15899435850383}}},"id":"tencent/hy4-preview","is_recent_addition":false,"last_measured_at":"2026-10-20T11:22:44Z","match_totals_all":{"draws":2551,"losses":3539,"wins":4560},"match_totals_tracks":{"highest":{"draws":965,"losses":865,"wins":1864},"medium":{"draws":508,"losses":1123,"wins":1631},"none":{"draws":1078,"losses":1551,"wins":1065}},"model_slug":"tencent-hy4-preview","overall":{"max":90.25623512676398,"mean":53.68471027789908,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":23,"overall_ranking_status":"ranked","per_game":{"GB2-01":55.25574526371777,"GB2-02":79.06319102608134,"GB2-03":72.06983142615508,"GB2-04":56.64762580038407,"GB2-05":70.31938149407007,"GB2-06":80.2278453608523,"GB2-07":68.23476209222156,"GB2-08":36.944411345755206},"per_game_all":{"GB2-01":51.73121919087438,"GB2-03":58.91523924206839,"GB2-04":44.30127643050357,"GB2-05":57.86302515346855,"GB2-06":60.31975288746427,"GB2-07":61.40130205349127,"GB2-08":54.119880277007674},"per_game_match_totals_all":{"GB2-01":{"draws":335,"losses":523,"wins":546},"GB2-02":{"draws":471,"losses":108,"wins":285},"GB2-03":{"draws":365,"losses":409,"wins":564},"GB2-04":{"draws":766,"losses":382,"wins":196},"GB2-05":{"draws":0,"losses":617,"wins":835},"GB2-06":{"draws":51,"losses":535,"wins":782},"GB2-07":{"draws":0,"losses":566,"wins":856},"GB2-08":{"draws":563,"losses":399,"wins":496}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":231,"losses":98,"wins":139},"GB2-02":{"draws":119,"losses":34,"wins":279},"GB2-03":{"draws":44,"losses":115,"wins":287},"GB2-04":{"draws":238,"losses":81,"wins":129},"GB2-05":{"draws":0,"losses":146,"wins":338},"GB2-06":{"draws":21,"losses":80,"wins":355},"GB2-07":{"draws":0,"losses":155,"wins":319},"GB2-08":{"draws":312,"losses":156,"wins":18}},"medium":{"GB2-01":{"draws":30,"losses":209,"wins":229},"GB2-03":{"draws":231,"losses":166,"wins":49},"GB2-04":{"draws":234,"losses":179,"wins":35},"GB2-05":{"draws":0,"losses":233,"wins":251},"GB2-06":{"draws":13,"losses":179,"wins":264},"GB2-07":{"draws":0,"losses":109,"wins":365},"GB2-08":{"draws":0,"losses":48,"wins":438}},"none":{"GB2-01":{"draws":74,"losses":216,"wins":178},"GB2-02":{"draws":352,"losses":74,"wins":6},"GB2-03":{"draws":90,"losses":128,"wins":228},"GB2-04":{"draws":294,"losses":122,"wins":32},"GB2-05":{"draws":0,"losses":238,"wins":246},"GB2-06":{"draws":17,"losses":276,"wins":163},"GB2-07":{"draws":0,"losses":302,"wins":172},"GB2-08":{"draws":251,"losses":195,"wins":40}}},"per_game_raw_elo_all":{"GB2-01":1499.2537257944705,"GB2-03":1524.8321714594379,"GB2-04":1433.6607084691948,"GB2-05":1559.6770874353103,"GB2-06":1634.9657545473467,"GB2-07":1615.299413757349,"GB2-08":1568.571719291044},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1533.061261494139,"GB2-02":1745.1057599116284,"GB2-03":1657.6855513509374,"GB2-04":1530.2943788975354,"GB2-05":1733.79769285657,"GB2-06":1976.4162674654356,"GB2-07":1693.6969641260628,"GB2-08":1287.4351104932207},"medium":{"GB2-01":1511.6547215090918,"GB2-03":1347.0587445871008,"GB2-04":1360.9764812861754,"GB2-05":1479.1567680074731,"GB2-06":1625.6295965296408,"GB2-07":1843.7694651785114,"GB2-08":2148.9406799256967},"none":{"GB2-01":1453.0451943801806,"GB2-02":1424.9742744403968,"GB2-03":1569.7522184402758,"GB2-04":1409.7112652238734,"GB2-05":1466.076801441888,"GB2-06":1302.8513996469642,"GB2-07":1308.4318119674726,"GB2-08":1269.3393674542144}},"per_game_tracks":{"highest":{"GB2-01":55.25574526371777,"GB2-02":79.06319102608134,"GB2-03":72.06983142615508,"GB2-04":56.64762580038407,"GB2-05":70.31938149407007,"GB2-06":80.2278453608523,"GB2-07":68.23476209222156,"GB2-08":36.944411345755206},"medium":{"GB2-01":53.03750667961113,"GB2-03":40.237651184567675,"GB2-04":35.07769682146017,"GB2-05":52.15811497181693,"GB2-06":60.72520651682459,"GB2-07":77.35558668748504,"GB2-08":90.25623512676398},"none":{"GB2-01":46.90040562929424,"GB2-02":43.41476993886233,"GB2-03":64.43823511548239,"GB2-04":41.178506669666476,"GB2-05":51.111578994518624,"GB2-06":40.0062067847159,"GB2-07":38.613557380767226,"GB2-08":35.15899435850383}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:38:39Z","reasoning":{"highest":64.84534922615467,"medium":51.10599974856619,"none":45.10278185897638},"reasoning_agg":{"highest":{"max":80.2278453608523,"mean":64.84534922615467,"min":36.944411345755206},"medium":{"max":90.25623512676398,"mean":51.10599974856619,"min":0.0},"none":{"max":64.43823511548239,"mean":45.10278185897638,"min":35.15899435850383}},"reasoning_labels":{"highest":"High","medium":"Low","none":"None"},"reasoning_settings":{"balanced":"low","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":19.74256736717829}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-1-flash:c2e28936a24e27ca","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.02640173625,"median":0.026524292999999997,"min":0.018252918,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.21121389},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0294003,"mean":0.0190911675,"median":0.019388559,"min":0.011042118,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.15272934},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.007391933999999999,"mean":0.00359850675,"median":0.003217359,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.028788053999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0294003,"mean":0.0190911675,"median":0.019388559,"min":0.011042118,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.15272934},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.007391933999999999,"mean":0.00359850675,"median":0.003217359,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.028788054},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.02640173625,"median":0.026524292999999997,"min":0.018252918,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.21121389000000002}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.0163638035,"median":0.017740284000000002,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":26},"recorded_attempt_count":26,"run_count":24,"total":0.39273128399999996},"codegen_latency_ms":{"attempt_count":26,"max_ms":176041,"mean_ms":89449.0,"min_ms":6041,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":176041,"mean_ms":153558.625,"min_ms":128316,"run_count":8},"medium":{"attempt_count":9,"max_ms":152315,"mean_ms":102702.875,"min_ms":61501,"run_count":8},"none":{"attempt_count":9,"max_ms":25470,"mean_ms":12085.5,"min_ms":6041,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":50785,"output_mean":25087.541666666668,"output_min":1796,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":50785,"output_mean":42017.75,"output_min":28632,"run_count":8},"medium":{"attempt_count":9,"output_max":44567,"output_mean":29519.625,"output_min":16614,"run_count":8},"none":{"attempt_count":9,"output_max":8282,"output_mean":3725.25,"output_min":1796,"run_count":8}},"display_name":"DeepSeek V4.1 Flash","economics":{"all":53.41311231703446,"highest":68.42903185073722,"medium":55.34217788981988,"none":36.46812721054629},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":26,"effective_max_output_tokens":[384000],"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":26,"output_token_observations":26,"provider_post_attempt_observations":26,"provider_post_attempts":26,"reasoning_token_observations":26,"reconciliation_get_attempt_observations":26,"requested_max_output_token_observations":26,"requested_max_output_tokens":[384000],"total_output_tokens":602101,"total_reasoning_output_tokens":512212,"total_visible_output_tokens":89889,"visible_token_observations":26},"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":384000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4.1-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":58.722709230369595,"score":58.722709230369595},"GB2-02":{"attempts":3,"playable":52.765945853631585,"score":52.765945853631585},"GB2-03":{"attempts":3,"playable":54.86182404031396,"score":54.86182404031396},"GB2-04":{"attempts":3,"playable":50.696718766721496,"score":50.696718766721496},"GB2-05":{"attempts":3,"playable":55.012887365082356,"score":55.012887365082356},"GB2-06":{"attempts":3,"playable":62.50347758940069,"score":62.50347758940069},"GB2-07":{"attempts":3,"playable":56.20734035079777,"score":56.20734035079777},"GB2-08":{"attempts":3,"playable":36.53399533995823,"score":36.53399533995823}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":63.37497300098226,"score":63.37497300098226},"GB2-02":{"attempts":1,"playable":57.50811960461052,"score":57.50811960461052},"GB2-03":{"attempts":1,"playable":60.87114153801437,"score":60.87114153801437},"GB2-04":{"attempts":1,"playable":75.15038740000494,"score":75.15038740000494},"GB2-05":{"attempts":1,"playable":82.19133576376176,"score":82.19133576376176},"GB2-06":{"attempts":1,"playable":82.42232936538578,"score":82.42232936538578},"GB2-07":{"attempts":1,"playable":75.17061333644703,"score":75.17061333644703},"GB2-08":{"attempts":1,"playable":50.74335479669105,"score":50.74335479669105}},"medium":{"GB2-01":{"attempts":1,"playable":67.05866135602744,"score":67.05866135602744},"GB2-02":{"attempts":1,"playable":58.539013295537835,"score":58.539013295537835},"GB2-03":{"attempts":1,"playable":55.27623553161083,"score":55.27623553161083},"GB2-04":{"attempts":1,"playable":38.69579764348235,"score":38.69579764348235},"GB2-05":{"attempts":1,"playable":53.413910681665286,"score":53.413910681665286},"GB2-06":{"attempts":1,"playable":77.42337939611865,"score":77.42337939611865},"GB2-07":{"attempts":1,"playable":68.63078834943678,"score":68.63078834943678},"GB2-08":{"attempts":1,"playable":23.69963686467981,"score":23.69963686467981}},"none":{"GB2-01":{"attempts":1,"playable":45.734493334099085,"score":45.734493334099085},"GB2-02":{"attempts":1,"playable":42.250704660746386,"score":42.250704660746386},"GB2-03":{"attempts":1,"playable":48.43809505131667,"score":48.43809505131667},"GB2-04":{"attempts":1,"playable":38.24397125667721,"score":38.24397125667721},"GB2-05":{"attempts":1,"playable":29.433415649820045,"score":29.433415649820045},"GB2-06":{"attempts":1,"playable":27.664724006697632,"score":27.664724006697632},"GB2-07":{"attempts":1,"playable":24.820619366509476,"score":24.820619366509476},"GB2-08":{"attempts":1,"playable":35.15899435850383,"score":35.15899435850383}}},"id":"deepseek/deepseek-v4.1-flash","is_recent_addition":false,"last_measured_at":"2026-10-20T11:45:46Z","match_totals_all":{"draws":3077,"losses":3771,"wins":4233},"match_totals_tracks":{"highest":{"draws":747,"losses":830,"wins":2117},"medium":{"draws":1142,"losses":1125,"wins":1427},"none":{"draws":1188,"losses":1816,"wins":689}},"model_slug":"deepseek-deepseek-v4-1-flash","overall":{"max":82.42232936538578,"mean":53.41311231703446,"min":23.69963686467981},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":24,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.37497300098226,"GB2-02":57.50811960461052,"GB2-03":60.87114153801437,"GB2-04":75.15038740000494,"GB2-05":82.19133576376176,"GB2-06":82.42232936538578,"GB2-07":75.17061333644703,"GB2-08":50.74335479669105},"per_game_all":{"GB2-01":58.722709230369595,"GB2-02":52.765945853631585,"GB2-03":54.86182404031396,"GB2-04":50.696718766721496,"GB2-05":55.012887365082356,"GB2-06":62.50347758940069,"GB2-07":56.20734035079777,"GB2-08":36.53399533995823},"per_game_match_totals_all":{"GB2-01":{"draws":436,"losses":373,"wins":595},"GB2-02":{"draws":907,"losses":175,"wins":214},"GB2-03":{"draws":283,"losses":508,"wins":546},"GB2-04":{"draws":658,"losses":349,"wins":337},"GB2-05":{"draws":0,"losses":657,"wins":795},"GB2-06":{"draws":88,"losses":480,"wins":800},"GB2-07":{"draws":0,"losses":640,"wins":782},"GB2-08":{"draws":705,"losses":589,"wins":164}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":20,"losses":165,"wins":283},"GB2-02":{"draws":268,"losses":55,"wins":109},"GB2-03":{"draws":51,"losses":164,"wins":231},"GB2-04":{"draws":138,"losses":47,"wins":263},"GB2-05":{"draws":0,"losses":88,"wins":396},"GB2-06":{"draws":28,"losses":66,"wins":362},"GB2-07":{"draws":0,"losses":120,"wins":354},"GB2-08":{"draws":242,"losses":125,"wins":119}},"medium":{"GB2-01":{"draws":271,"losses":22,"wins":175},"GB2-02":{"draws":289,"losses":40,"wins":103},"GB2-03":{"draws":122,"losses":154,"wins":170},"GB2-04":{"draws":238,"losses":161,"wins":49},"GB2-05":{"draws":0,"losses":227,"wins":257},"GB2-06":{"draws":30,"losses":89,"wins":337},"GB2-07":{"draws":0,"losses":153,"wins":321},"GB2-08":{"draws":192,"losses":279,"wins":15}},"none":{"GB2-01":{"draws":145,"losses":186,"wins":137},"GB2-02":{"draws":350,"losses":80,"wins":2},"GB2-03":{"draws":110,"losses":190,"wins":145},"GB2-04":{"draws":282,"losses":141,"wins":25},"GB2-05":{"draws":0,"losses":342,"wins":142},"GB2-06":{"draws":30,"losses":325,"wins":101},"GB2-07":{"draws":0,"losses":367,"wins":107},"GB2-08":{"draws":271,"losses":185,"wins":30}}},"per_game_raw_elo_all":{"GB2-01":1569.6505556319526,"GB2-02":1497.9968707428304,"GB2-03":1477.349943307249,"GB2-04":1492.1551181033349,"GB2-05":1555.6667196389024,"GB2-06":1686.621652762942,"GB2-07":1541.907118272217,"GB2-08":1282.6174183851872},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1614.037365528286,"GB2-02":1534.8322944955478,"GB2-03":1533.345612145722,"GB2-04":1699.761503308181,"GB2-05":1992.9354108503983,"GB2-06":2020.6611422232186,"GB2-07":1804.3902687181849,"GB2-08":1431.3205232831451},"medium":{"GB2-01":1652.989930453965,"GB2-02":1543.2013525230388,"GB2-03":1480.0217153149567,"GB2-04":1390.1490837408435,"GB2-05":1494.922572219597,"GB2-06":1922.0308213794503,"GB2-07":1699.5869556484959,"GB2-08":1147.192364418202},"none":{"GB2-01":1441.9243709136065,"GB2-02":1415.9569652099042,"GB2-03":1418.6825024610675,"GB2-04":1386.55476726098,"GB2-05":1179.1421758467113,"GB2-06":1117.1729946861572,"GB2-07":1121.7441304499707,"GB2-08":1269.3393674542144}},"per_game_tracks":{"highest":{"GB2-01":63.37497300098226,"GB2-02":57.50811960461052,"GB2-03":60.87114153801437,"GB2-04":75.15038740000494,"GB2-05":82.19133576376176,"GB2-06":82.42232936538578,"GB2-07":75.17061333644703,"GB2-08":50.74335479669105},"medium":{"GB2-01":67.05866135602744,"GB2-02":58.539013295537835,"GB2-03":55.27623553161083,"GB2-04":38.69579764348235,"GB2-05":53.413910681665286,"GB2-06":77.42337939611865,"GB2-07":68.63078834943678,"GB2-08":23.69963686467981},"none":{"GB2-01":45.734493334099085,"GB2-02":42.250704660746386,"GB2-03":48.43809505131667,"GB2-04":38.24397125667721,"GB2-05":29.433415649820045,"GB2-06":27.664724006697632,"GB2-07":24.820619366509476,"GB2-08":35.15899435850383}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:51:36Z","reasoning":{"highest":68.42903185073722,"medium":55.34217788981988,"none":36.46812721054629},"reasoning_agg":{"highest":{"max":82.42232936538578,"mean":68.42903185073722,"min":50.74335479669105},"medium":{"max":77.42337939611865,"mean":55.34217788981988,"min":23.69963686467981},"none":{"max":48.43809505131667,"mean":36.46812721054629,"min":24.820619366509476}},"reasoning_labels":{"highest":"Max","medium":"High","none":"None"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":31.960904640190925}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-2:f823de08c5bf7106","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.2224195,"mean":0.1433925625,"median":0.13115787499999998,"min":0.104555,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":1.1471405},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.060198249999999995,"mean":0.047021,"median":0.04824225,"min":0.0324825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.37616800000000006},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.03564825,"mean":0.0239263125,"median":0.02294625,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.1914105}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.060198249999999995,"mean":0.047021,"median":0.04824225,"min":0.0324825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.376168},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.03564825,"mean":0.0239263125,"median":0.02294625,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.1914105},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.2224195,"mean":0.1433925625,"median":0.13115787499999998,"min":0.104555,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":1.1471405}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.2224195,"mean":0.071446625,"median":0.04824225,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":18,"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":27,"run_count":24,"total":1.7147189999999999},"codegen_latency_ms":{"attempt_count":27,"max_ms":194716,"mean_ms":65710.04166666667,"min_ms":14709,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":194716,"mean_ms":132597.5,"min_ms":94687,"run_count":8},"medium":{"attempt_count":9,"max_ms":66794,"mean_ms":45688.625,"min_ms":28293,"run_count":8},"none":{"attempt_count":9,"max_ms":26924,"mean_ms":18844.0,"min_ms":14709,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":46299,"output_mean":14240.0,"output_min":2554,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":46299,"output_mean":31097.375,"output_min":22420,"run_count":8},"medium":{"attempt_count":9,"output_max":11293,"output_mean":8521.75,"output_min":5500,"run_count":8},"none":{"attempt_count":9,"output_max":3991,"output_mean":3100.875,"output_min":2554,"run_count":8}},"display_name":"Muse Spark 1.2","economics":{"all":56.05658606095317,"highest":59.66900041867059,"medium":58.707339966233285,"none":41.79847889506631},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":9,"effective_max_output_tokens":[943718],"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"reconciliation_get_attempts":87,"requested_max_output_token_observations":9,"requested_max_output_tokens":[943718],"total_output_tokens":341760,"total_reasoning_output_tokens":238816,"total_visible_output_tokens":102944,"visible_token_observations":27},"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":"meta","provider_model":"meta/muse-spark-1.2","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"first_pass_admitted":7,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"performance_rejections":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":68.4238125349563,"score":68.4238125349563},"GB2-02":{"attempts":3,"playable":45.580377380912275,"score":45.580377380912275},"GB2-03":{"attempts":3,"playable":52.29822441011714,"score":52.29822441011714},"GB2-04":{"attempts":3,"playable":47.28963561480894,"score":47.28963561480894},"GB2-05":{"attempts":3,"playable":54.59747270038222,"score":54.59747270038222},"GB2-06":{"attempts":2,"playable":22.751453496755822,"score":22.751453496755822},"GB2-07":{"attempts":3,"playable":57.74719013704259,"score":57.74719013704259},"GB2-08":{"attempts":3,"playable":66.45938964845271,"score":66.45938964845271}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":81.62567299651913,"score":81.62567299651913},"GB2-02":{"attempts":1,"playable":48.29001545520104,"score":48.29001545520104},"GB2-03":{"attempts":1,"playable":60.109059106806285,"score":60.109059106806285},"GB2-04":{"attempts":1,"playable":49.94595686061252,"score":49.94595686061252},"GB2-05":{"attempts":1,"playable":61.98786090286942,"score":61.98786090286942},"GB2-06":{"attempts":1,"playable":26.176508714057316,"score":26.176508714057316},"GB2-07":{"attempts":1,"playable":75.17061333644703,"score":75.17061333644703},"GB2-08":{"attempts":1,"playable":74.04631597685199,"score":74.04631597685199}},"medium":{"GB2-01":{"attempts":1,"playable":85.98772839817289,"score":85.98772839817289},"GB2-02":{"attempts":1,"playable":46.89943401659414,"score":46.89943401659414},"GB2-03":{"attempts":1,"playable":50.82026234951344,"score":50.82026234951344},"GB2-04":{"attempts":1,"playable":44.10728525638755,"score":44.10728525638755},"GB2-05":{"attempts":1,"playable":50.065055159003954,"score":50.065055159003954},"GB2-07":{"attempts":1,"playable":64.27297005892744,"score":64.27297005892744},"GB2-08":{"attempts":1,"playable":68.7986445250336,"score":68.7986445250336}},"none":{"GB2-01":{"attempts":1,"playable":37.658036210176874,"score":37.658036210176874},"GB2-02":{"attempts":1,"playable":41.55168267094166,"score":41.55168267094166},"GB2-03":{"attempts":1,"playable":45.9653517740317,"score":45.9653517740317},"GB2-04":{"attempts":1,"playable":47.815664727426764,"score":47.815664727426764},"GB2-05":{"attempts":1,"playable":51.7395020392733,"score":51.7395020392733},"GB2-06":{"attempts":1,"playable":19.32639827945433,"score":19.32639827945433},"GB2-07":{"attempts":1,"playable":33.79798701575328,"score":33.79798701575328},"GB2-08":{"attempts":1,"playable":56.53320844347258,"score":56.53320844347258}}},"id":"meta/muse-spark-1.2","is_recent_addition":false,"last_measured_at":"2026-10-20T11:44:02Z","match_totals_all":{"draws":2233,"losses":3980,"wins":4413},"match_totals_tracks":{"highest":{"draws":629,"losses":1209,"wins":1856},"medium":{"draws":747,"losses":995,"wins":1496},"none":{"draws":857,"losses":1776,"wins":1061}},"model_slug":"meta-muse-spark-1-2","overall":{"max":85.98772839817289,"mean":53.39160642665672,"min":19.32639827945433},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":25,"overall_ranking_status":"ranked","per_game":{"GB2-01":81.62567299651913,"GB2-02":48.29001545520104,"GB2-03":60.109059106806285,"GB2-04":49.94595686061252,"GB2-05":61.98786090286942,"GB2-06":26.176508714057316,"GB2-07":75.17061333644703,"GB2-08":74.04631597685199},"per_game_all":{"GB2-01":68.4238125349563,"GB2-02":45.580377380912275,"GB2-03":52.29822441011714,"GB2-04":47.28963561480894,"GB2-05":54.59747270038222,"GB2-07":57.74719013704259,"GB2-08":66.45938964845271},"per_game_match_totals_all":{"GB2-01":{"draws":183,"losses":360,"wins":861},"GB2-02":{"draws":972,"losses":236,"wins":88},"GB2-03":{"draws":179,"losses":595,"wins":564},"GB2-04":{"draws":807,"losses":322,"wins":215},"GB2-05":{"draws":0,"losses":664,"wins":788},"GB2-06":{"draws":21,"losses":712,"wins":179},"GB2-07":{"draws":0,"losses":620,"wins":802},"GB2-08":{"draws":71,"losses":471,"wins":916}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":87,"wins":379},"GB2-02":{"draws":332,"losses":63,"wins":37},"GB2-03":{"draws":18,"losses":184,"wins":244},"GB2-04":{"draws":248,"losses":106,"wins":94},"GB2-05":{"draws":0,"losses":186,"wins":298},"GB2-06":{"draws":19,"losses":337,"wins":100},"GB2-07":{"draws":0,"losses":120,"wins":354},"GB2-08":{"draws":10,"losses":126,"wins":350}},"medium":{"GB2-01":{"draws":22,"losses":56,"wins":390},"GB2-02":{"draws":324,"losses":73,"wins":35},"GB2-03":{"draws":100,"losses":185,"wins":161},"GB2-04":{"draws":244,"losses":134,"wins":70},"GB2-05":{"draws":0,"losses":243,"wins":241},"GB2-07":{"draws":0,"losses":175,"wins":299},"GB2-08":{"draws":57,"losses":129,"wins":300}},"none":{"GB2-01":{"draws":159,"losses":217,"wins":92},"GB2-02":{"draws":316,"losses":100,"wins":16},"GB2-03":{"draws":61,"losses":226,"wins":159},"GB2-04":{"draws":315,"losses":82,"wins":51},"GB2-05":{"draws":0,"losses":235,"wins":249},"GB2-06":{"draws":2,"losses":375,"wins":79},"GB2-07":{"draws":0,"losses":325,"wins":149},"GB2-08":{"draws":4,"losses":216,"wins":266}}},"per_game_raw_elo_all":{"GB2-01":1704.1995535766343,"GB2-02":1441.6308449833914,"GB2-03":1454.2049535878696,"GB2-04":1457.0808954702914,"GB2-05":1511.3952930852256,"GB2-07":1562.5912972636231,"GB2-08":1644.366013998723},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1837.2655752436724,"GB2-02":1462.5375060862234,"GB2-03":1525.843984023825,"GB2-04":1477.6102456352075,"GB2-05":1607.234725062947,"GB2-06":1094.4377581857693,"GB2-07":1804.3902687181849,"GB2-08":1763.0169260475634},"medium":{"GB2-01":1911.6281185841528,"GB2-02":1451.8317879510382,"GB2-03":1439.7346214468728,"GB2-04":1432.4935494581653,"GB2-05":1453.0316215056675,"GB2-07":1636.7962897661762,"GB2-08":1671.412791853963},"none":{"GB2-01":1363.7049669020776,"GB2-02":1410.5232409129126,"GB2-03":1397.036255292911,"GB2-04":1461.1388913175012,"GB2-05":1473.9195326870622,"GB2-06":985.5692189952265,"GB2-07":1246.587333306508,"GB2-08":1498.668324094642}},"per_game_tracks":{"highest":{"GB2-01":81.62567299651913,"GB2-02":48.29001545520104,"GB2-03":60.109059106806285,"GB2-04":49.94595686061252,"GB2-05":61.98786090286942,"GB2-06":26.176508714057316,"GB2-07":75.17061333644703,"GB2-08":74.04631597685199},"medium":{"GB2-01":85.98772839817289,"GB2-02":46.89943401659414,"GB2-03":50.82026234951344,"GB2-04":44.10728525638755,"GB2-05":50.065055159003954,"GB2-07":64.27297005892744,"GB2-08":68.7986445250336},"none":{"GB2-01":37.658036210176874,"GB2-02":41.55168267094166,"GB2-03":45.9653517740317,"GB2-04":47.815664727426764,"GB2-05":51.7395020392733,"GB2-06":19.32639827945433,"GB2-07":33.79798701575328,"GB2-08":56.53320844347258}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":0,"rank_movement_baseline_at":"2026-10-14T17:59:48Z","reasoning":{"highest":59.66900041867059,"medium":58.707339966233285,"none":41.79847889506631},"reasoning_agg":{"highest":{"max":81.62567299651913,"mean":59.66900041867059,"min":26.176508714057316},"medium":{"max":85.98772839817289,"mean":58.707339966233285,"min":44.10728525638755},"none":{"max":56.53320844347258,"mean":41.79847889506631,"min":19.32639827945433}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":17.870521523604282}},{"canonical_public_row_identity":"publication-row.v1:overall:fireworks-ember-1:3aefb0e11d772bd6","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.508434,"mean":0.298893375,"median":0.3053985,"min":0.149517,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":2.391147},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.20107799999999998,"mean":0.142499625,"median":0.14239200000000002,"min":0.071757,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":1.1399970000000001},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.143745,"mean":0.07283400000000001,"median":0.063006,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.5826720000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.20107799999999998,"mean":0.142499625,"median":0.14239200000000002,"min":0.071757,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":1.1399970000000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.143745,"mean":0.07283400000000001,"median":0.063006,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.582672},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.508434,"mean":0.298893375,"median":0.3053985,"min":0.149517,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":2.391147}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.508434,"mean":0.171409,"median":0.146631,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"recorded_attempt_count":28,"run_count":24,"total":4.113816000000001},"codegen_latency_ms":{"attempt_count":28,"max_ms":413691,"mean_ms":128683.25,"min_ms":28133,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":413691,"mean_ms":243828.625,"min_ms":115297,"run_count":8},"medium":{"attempt_count":10,"max_ms":159798,"mean_ms":101243.125,"min_ms":39983,"run_count":8},"none":{"attempt_count":9,"max_ms":84315,"mean_ms":40978.0,"min_ms":28133,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":30544,"output_mean":9612.333333333334,"output_min":2170,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":30544,"output_mean":18138.375,"output_min":8542,"run_count":8},"medium":{"attempt_count":10,"output_max":11696,"output_mean":7576.625,"output_min":3317,"run_count":8},"none":{"attempt_count":9,"output_max":6625,"output_mean":3122.0,"output_min":2170,"run_count":8}},"display_name":"Ember-1","economics":{"all":52.94124245746951,"highest":65.18493309612018,"medium":54.64540371276745,"none":38.993390563520904},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[262144],"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"requested_max_output_token_observations":28,"requested_max_output_tokens":[262144],"total_output_tokens":230696,"total_reasoning_output_tokens":146257,"total_visible_output_tokens":84439,"visible_token_observations":28},"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":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"fireworks","provider_model":"fireworks/ember-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":60.00936821226497,"score":60.00936821226497},"GB2-02":{"attempts":3,"playable":44.5772660903566,"score":44.5772660903566},"GB2-03":{"attempts":3,"playable":59.841698876920766,"score":59.841698876920766},"GB2-04":{"attempts":3,"playable":44.77021686963682,"score":44.77021686963682},"GB2-05":{"attempts":3,"playable":44.625784106752825,"score":44.625784106752825},"GB2-06":{"attempts":3,"playable":52.67318774669823,"score":52.67318774669823},"GB2-07":{"attempts":3,"playable":59.123999810222905,"score":59.123999810222905},"GB2-08":{"attempts":3,"playable":57.908417946902944,"score":57.908417946902944}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":78.076142706828,"score":78.076142706828},"GB2-02":{"attempts":1,"playable":43.41476993886233,"score":43.41476993886233},"GB2-03":{"attempts":1,"playable":81.10133343440408,"score":81.10133343440408},"GB2-04":{"attempts":1,"playable":40.27616799500331,"score":40.27616799500331},"GB2-05":{"attempts":1,"playable":63.86660963348191,"score":63.86660963348191},"GB2-06":{"attempts":1,"playable":52.90276197567626,"score":52.90276197567626},"GB2-07":{"attempts":1,"playable":76.36198255711318,"score":76.36198255711318},"GB2-08":{"attempts":1,"playable":85.4796965275924,"score":85.4796965275924}},"medium":{"GB2-01":{"attempts":1,"playable":50.71157253248973,"score":50.71157253248973},"GB2-02":{"attempts":1,"playable":45.390827139687964,"score":45.390827139687964},"GB2-03":{"attempts":1,"playable":62.71403962367559,"score":62.71403962367559},"GB2-04":{"attempts":1,"playable":52.74322169139389,"score":52.74322169139389},"GB2-05":{"attempts":1,"playable":47.9722316610349,"score":47.9722316610349},"GB2-06":{"attempts":1,"playable":57.85486889799324,"score":57.85486889799324},"GB2-07":{"attempts":1,"playable":64.27297005892744,"score":64.27297005892744},"GB2-08":{"attempts":1,"playable":55.503498096936795,"score":55.503498096936795}},"none":{"GB2-01":{"attempts":1,"playable":51.24038939747718,"score":51.24038939747718},"GB2-02":{"attempts":1,"playable":44.92620119251952,"score":44.92620119251952},"GB2-03":{"attempts":1,"playable":35.70972357268263,"score":35.70972357268263},"GB2-04":{"attempts":1,"playable":41.291260922513274,"score":41.291260922513274},"GB2-05":{"attempts":1,"playable":22.03851102574167,"score":22.03851102574167},"GB2-06":{"attempts":1,"playable":47.26193236642518,"score":47.26193236642518},"GB2-07":{"attempts":1,"playable":36.73704681462811,"score":36.73704681462811},"GB2-08":{"attempts":1,"playable":32.74205921617964,"score":32.74205921617964}}},"id":"fireworks/ember-1","is_recent_addition":false,"last_measured_at":"2026-10-20T11:41:58Z","match_totals_all":{"draws":3031,"losses":3835,"wins":4216},"match_totals_tracks":{"highest":{"draws":662,"losses":977,"wins":2055},"medium":{"draws":1071,"losses":1190,"wins":1433},"none":{"draws":1298,"losses":1668,"wins":728}},"model_slug":"fireworks-ember-1","overall":{"max":85.4796965275924,"mean":52.941242457469514,"min":22.03851102574167},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":26,"overall_ranking_status":"ranked","per_game":{"GB2-01":78.076142706828,"GB2-02":43.41476993886233,"GB2-03":81.10133343440408,"GB2-04":40.27616799500331,"GB2-05":63.86660963348191,"GB2-06":52.90276197567626,"GB2-07":76.36198255711318,"GB2-08":85.4796965275924},"per_game_all":{"GB2-01":60.00936821226497,"GB2-02":44.5772660903566,"GB2-03":59.841698876920766,"GB2-04":44.77021686963682,"GB2-05":44.625784106752825,"GB2-06":52.67318774669823,"GB2-07":59.123999810222905,"GB2-08":57.908417946902944},"per_game_match_totals_all":{"GB2-01":{"draws":435,"losses":355,"wins":614},"GB2-02":{"draws":982,"losses":244,"wins":70},"GB2-03":{"draws":268,"losses":441,"wins":629},"GB2-04":{"draws":820,"losses":349,"wins":175},"GB2-05":{"draws":0,"losses":808,"wins":644},"GB2-06":{"draws":69,"losses":639,"wins":660},"GB2-07":{"draws":0,"losses":600,"wins":822},"GB2-08":{"draws":457,"losses":399,"wins":602}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":101,"wins":359},"GB2-02":{"draws":332,"losses":84,"wins":16},"GB2-03":{"draws":14,"losses":86,"wins":346},"GB2-04":{"draws":284,"losses":131,"wins":33},"GB2-05":{"draws":0,"losses":177,"wins":307},"GB2-06":{"draws":19,"losses":214,"wins":223},"GB2-07":{"draws":0,"losses":114,"wins":360},"GB2-08":{"draws":5,"losses":70,"wins":411}},"medium":{"GB2-01":{"draws":240,"losses":115,"wins":113},"GB2-02":{"draws":325,"losses":79,"wins":28},"GB2-03":{"draws":36,"losses":163,"wins":247},"GB2-04":{"draws":273,"losses":81,"wins":94},"GB2-05":{"draws":0,"losses":253,"wins":231},"GB2-06":{"draws":17,"losses":191,"wins":248},"GB2-07":{"draws":0,"losses":175,"wins":299},"GB2-08":{"draws":180,"losses":133,"wins":173}},"none":{"GB2-01":{"draws":187,"losses":139,"wins":142},"GB2-02":{"draws":325,"losses":81,"wins":26},"GB2-03":{"draws":218,"losses":192,"wins":36},"GB2-04":{"draws":263,"losses":137,"wins":48},"GB2-05":{"draws":0,"losses":378,"wins":106},"GB2-06":{"draws":33,"losses":234,"wins":189},"GB2-07":{"draws":0,"losses":311,"wins":163},"GB2-08":{"draws":272,"losses":196,"wins":18}}},"per_game_raw_elo_all":{"GB2-01":1589.8280837611644,"GB2-02":1433.9443123216286,"GB2-03":1550.8419962750097,"GB2-04":1437.5366574969473,"GB2-05":1373.4492393945868,"GB2-06":1497.1247973502075,"GB2-07":1582.2981879727915,"GB2-08":1580.8631539179878},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1785.6714779725912,"GB2-02":1424.9742744403968,"GB2-03":1793.7381131865563,"GB2-04":1402.6345039696923,"GB2-05":1633.702015569128,"GB2-06":1499.9297802588017,"GB2-07":1825.508226373387,"GB2-08":2011.7284995680413},"medium":{"GB2-01":1489.3797806622172,"GB2-02":1440.2190847505922,"GB2-03":1551.8691741762045,"GB2-04":1499.3821962534003,"GB2-05":1426.9800628175785,"GB2-06":1578.6736220768255,"GB2-07":1636.7962897661762,"GB2-08":1486.1908944949753},"none":{"GB2-01":1494.4329926486848,"GB2-02":1436.6395777738958,"GB2-03":1306.918701462269,"GB2-04":1410.5932722677485,"GB2-05":1059.6656397970537,"GB2-06":1412.7709897149953,"GB2-07":1284.590047778812,"GB2-08":1244.6700676909472}},"per_game_tracks":{"highest":{"GB2-01":78.076142706828,"GB2-02":43.41476993886233,"GB2-03":81.10133343440408,"GB2-04":40.27616799500331,"GB2-05":63.86660963348191,"GB2-06":52.90276197567626,"GB2-07":76.36198255711318,"GB2-08":85.4796965275924},"medium":{"GB2-01":50.71157253248973,"GB2-02":45.390827139687964,"GB2-03":62.71403962367559,"GB2-04":52.74322169139389,"GB2-05":47.9722316610349,"GB2-06":57.85486889799324,"GB2-07":64.27297005892744,"GB2-08":55.503498096936795},"none":{"GB2-01":51.24038939747718,"GB2-02":44.92620119251952,"GB2-03":35.70972357268263,"GB2-04":41.291260922513274,"GB2-05":22.03851102574167,"GB2-06":47.26193236642518,"GB2-07":36.73704681462811,"GB2-08":32.74205921617964}},"provider_color":"#6720FF","provider_company":"Fireworks AI","provider_key":"fireworks","provider_text_color":"#f8fafc","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:51:25Z","reasoning":{"highest":65.18493309612018,"medium":54.64540371276745,"none":38.993390563520904},"reasoning_agg":{"highest":{"max":85.4796965275924,"mean":65.18493309612018,"min":40.27616799500331},"medium":{"max":64.27297005892744,"mean":54.64540371276745,"min":45.390827139687964},"none":{"max":51.24038939747718,"mean":38.993390563520904,"min":22.03851102574167}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":26.19154253259927}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-ox-alpha:925bbdc6068158b7","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":31,"run_count":28,"total":0.0},"medium":{"admitted_cell_count":26,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":39,"run_count":30,"total":0.0},"none":{"admitted_cell_count":28,"cell_count":8,"cost_basis_counts":{"provider_reported":42},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":42,"run_count":30,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":26,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":39,"run_count":30,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":28,"cell_count":8,"cost_basis_counts":{"provider_reported":42},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":42,"run_count":30,"total":0.0},"historical-provider-setting-intensive":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":31,"run_count":28,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":79,"cell_count":24,"cost_basis_counts":{"provider_reported":112},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":112,"run_count":88,"total":0.0},"codegen_latency_ms":{"attempt_count":112,"max_ms":1487583,"mean_ms":467860.5227272727,"min_ms":38538,"run_count":88},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":31,"max_ms":1487583,"mean_ms":1029047.25,"min_ms":343277,"run_count":28},"medium":{"attempt_count":39,"max_ms":676327,"mean_ms":324151.5,"min_ms":151453,"run_count":30},"none":{"attempt_count":42,"max_ms":287181,"mean_ms":87795.26666666666,"min_ms":38538,"run_count":30}},"codegen_output_tokens":{"attempt_count":112,"output_max":85105,"output_mean":23027.329545454544,"output_min":1660,"run_count":88},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":31,"output_max":85105,"output_mean":50628.67857142857,"output_min":15800,"run_count":28},"medium":{"attempt_count":39,"output_max":33467,"output_mean":16156.733333333334,"output_min":6647,"run_count":30},"none":{"attempt_count":42,"output_max":9871,"output_mean":4136.666666666667,"output_min":1660,"run_count":30}},"display_name":"Ox Alpha","economics":{"all":54.323177874477246,"highest":67.64022168004672,"medium":51.94811721458876,"none":43.38119472879626},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":101,"effective_max_output_tokens":[131072],"finish_reason_observations":110,"finish_reasons":["stop"],"indexed_attempts":114,"output_token_observations":112,"provider_post_attempt_observations":113,"provider_post_attempts":113,"reasoning_token_observations":112,"reconciliation_get_attempt_observations":113,"reconciliation_get_attempts":534,"requested_max_output_token_observations":102,"requested_max_output_tokens":[131072],"total_output_tokens":2026405,"total_visible_output_tokens":2026405,"visible_token_observations":112},"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":"stealth/ox-alpha","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":26,"evaluated_cells":30,"failed_game_aliases":["GB2-01","GB2-03"],"first_pass_admitted":21,"first_pass_rate":0.7241379310344828,"game_attempts":{"GB2-01":{"admitted":2,"model_code_failures":1},"GB2-02":{"admitted":3},"GB2-03":{"admitted":7,"model_code_failures":2},"GB2-04":{"admitted":3},"GB2-05":{"admitted":3},"GB2-06":{"admitted":2,"performance_rejections":1},"GB2-07":{"admitted":3},"GB2-08":{"admitted":3}},"model_code_failure_rate":0.10344827586206896,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1,"repaired_admitted":5,"repaired_rate":0.1724137931034483},"baseline":{"admitted_plugins":28,"evaluated_cells":30,"failed_game_aliases":["GB2-03","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.6333333333333333,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":3},"GB2-03":{"admitted":8,"model_code_failures":1},"GB2-04":{"admitted":3},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":3},"GB2-08":{"admitted":2,"model_code_failures":1}},"model_code_failure_rate":0.06666666666666667,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":9,"repaired_rate":0.3},"intensive":{"admitted_plugins":25,"evaluated_cells":25,"first_pass_admitted":22,"first_pass_rate":0.88,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":2,"infra_failures_excluded":1},"GB2-03":{"admitted":5,"infra_failures_excluded":4},"GB2-04":{"admitted":3},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":3},"GB2-08":{"admitted":3}},"infra_excluded_game_aliases":["GB2-02","GB2-03"],"infra_failures_excluded":5,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.12}},"headline_games_all":{"GB2-01":{"attempts":9,"failed_attempts":1,"playable":54.943694078902894,"score":47.913981183874746},"GB2-02":{"attempts":8,"playable":55.98605985773015,"score":55.98605985773015},"GB2-03":{"attempts":23,"failed_attempts":3,"playable":58.05427419413426,"score":52.104908779490266},"GB2-04":{"attempts":9,"playable":59.77255432964188,"score":59.77255432964188},"GB2-05":{"attempts":9,"playable":54.91903137302625,"score":54.91903137302625},"GB2-06":{"attempts":8,"playable":46.60441896921838,"score":46.60441896921838},"GB2-07":{"attempts":9,"playable":50.6398255880496,"score":50.6398255880496},"GB2-08":{"attempts":9,"failed_attempts":1,"playable":54.128357156826894,"score":50.490353311911655}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":3,"playable":58.789043075528866,"score":58.789043075528866},"GB2-02":{"attempts":2,"playable":74.2152241556405,"score":74.2152241556405},"GB2-03":{"attempts":5,"playable":71.46016824274109,"score":71.46016824274109},"GB2-04":{"attempts":3,"playable":72.11232783272018,"score":72.11232783272018},"GB2-05":{"attempts":3,"playable":62.95106799924048,"score":62.95106799924048},"GB2-06":{"attempts":3,"playable":68.99277931256556,"score":68.99277931256556},"GB2-07":{"attempts":3,"playable":66.58206309176221,"score":66.58206309176221},"GB2-08":{"attempts":3,"playable":71.6516541924911,"score":71.6516541924911}},"medium":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":63.26741605525328,"score":42.17827737016885},"GB2-02":{"attempts":3,"playable":50.13477761489193,"score":50.13477761489193},"GB2-03":{"attempts":9,"failed_attempts":2,"playable":57.93021185572614,"score":45.05683144334255},"GB2-04":{"attempts":3,"playable":57.71806702768231,"score":57.71806702768231},"GB2-05":{"attempts":3,"playable":49.64791785001618,"score":49.64791785001618},"GB2-06":{"attempts":2,"playable":27.759236938095032,"score":27.759236938095032},"GB2-07":{"attempts":3,"playable":45.816489401267226,"score":45.816489401267226},"GB2-08":{"attempts":3,"playable":57.99138267375247,"score":57.99138267375247}},"none":{"GB2-01":{"attempts":3,"playable":42.77462310592653,"score":42.77462310592653},"GB2-02":{"attempts":3,"playable":43.60817780265803,"score":43.60817780265803},"GB2-03":{"attempts":9,"failed_attempts":1,"playable":44.77244248393556,"score":39.79772665238717},"GB2-04":{"attempts":3,"playable":49.48726812852315,"score":49.48726812852315},"GB2-05":{"attempts":3,"playable":52.158108269822094,"score":52.158108269822094},"GB2-06":{"attempts":3,"playable":43.06124065699455,"score":43.06124065699455},"GB2-07":{"attempts":3,"playable":39.520924271119355,"score":39.520924271119355},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":32.742034604237105,"score":21.828023069491405}}},"id":"stealth/ox-alpha","is_recent_addition":false,"last_measured_at":"2026-10-20T11:44:03Z","match_totals_all":{"draws":7992,"losses":13044,"wins":15273},"match_totals_tracks":{"highest":{"draws":1260,"losses":3165,"wins":7116},"medium":{"draws":2706,"losses":4486,"wins":4750},"none":{"draws":4026,"losses":5393,"wins":3407}},"model_slug":"stealth-ox-alpha","overall":{"max":74.2152241556405,"mean":52.303891674117864,"min":21.828023069491405},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":27,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.789043075528866,"GB2-02":74.2152241556405,"GB2-03":69.15194792581691,"GB2-04":69.52328474160564,"GB2-05":62.95106799924048,"GB2-06":72.08854460026902,"GB2-07":66.58206309176221,"GB2-08":67.82059785051017},"per_game_all":{"GB2-01":54.943694078902894,"GB2-02":55.94085162796072,"GB2-03":59.08843711761819,"GB2-04":58.67027724437929,"GB2-05":54.91903137302625,"GB2-06":47.6363407317862,"GB2-07":50.6398255880496,"GB2-08":52.74696523409485},"per_game_match_totals_all":{"GB2-01":{"draws":594,"losses":1461,"wins":1689},"GB2-02":{"draws":2281,"losses":500,"wins":675},"GB2-03":{"draws":1704,"losses":3340,"wins":3875},"GB2-04":{"draws":2129,"losses":605,"wins":1298},"GB2-05":{"draws":0,"losses":1978,"wins":2378},"GB2-06":{"draws":150,"losses":1837,"wins":1661},"GB2-07":{"draws":0,"losses":2168,"wins":2098},"GB2-08":{"draws":1134,"losses":1155,"wins":1599}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":64,"losses":558,"wins":782},"GB2-02":{"draws":316,"losses":72,"wins":476},"GB2-03":{"draws":131,"losses":626,"wins":1472},"GB2-04":{"draws":498,"losses":139,"wins":707},"GB2-05":{"draws":0,"losses":544,"wins":908},"GB2-06":{"draws":89,"losses":390,"wins":889},"GB2-07":{"draws":0,"losses":490,"wins":932},"GB2-08":{"draws":162,"losses":346,"wins":950}},"medium":{"GB2-01":{"draws":192,"losses":255,"wins":489},"GB2-02":{"draws":950,"losses":188,"wins":158},"GB2-03":{"draws":351,"losses":1235,"wins":1536},"GB2-04":{"draws":787,"losses":192,"wins":365},"GB2-05":{"draws":0,"losses":735,"wins":717},"GB2-06":{"draws":26,"losses":659,"wins":227},"GB2-07":{"draws":0,"losses":791,"wins":631},"GB2-08":{"draws":400,"losses":431,"wins":627}},"none":{"GB2-01":{"draws":338,"losses":648,"wins":418},"GB2-02":{"draws":1015,"losses":240,"wins":41},"GB2-03":{"draws":1222,"losses":1479,"wins":867},"GB2-04":{"draws":844,"losses":274,"wins":226},"GB2-05":{"draws":0,"losses":699,"wins":753},"GB2-06":{"draws":35,"losses":788,"wins":545},"GB2-07":{"draws":0,"losses":887,"wins":535},"GB2-08":{"draws":572,"losses":378,"wins":22}}},"per_game_raw_elo_all":{"GB2-01":1532.040985333687,"GB2-02":1534.0164600644905,"GB2-03":1538.2226945696245,"GB2-04":1557.2985246845649,"GB2-05":1517.963962694769,"GB2-06":1420.8519049804481,"GB2-07":1455.3953779458664,"GB2-08":1486.0354186607071},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1570.7751585473668,"GB2-02":1699.703730203843,"GB2-03":1654.9107017554045,"GB2-04":1663.882402941774,"GB2-05":1626.3190656223444,"GB2-06":1846.2135454512195,"GB2-07":1673.7378113371708,"GB2-08":1689.624517955604},"medium":{"GB2-01":1613.7467032822528,"GB2-02":1476.9327780152387,"GB2-03":1574.0608917973152,"GB2-04":1540.6440899146019,"GB2-05":1447.9747271910376,"GB2-06":1065.8310499606084,"GB2-07":1388.301405040121,"GB2-08":1523.820691891979},"none":{"GB2-01":1411.601094171442,"GB2-02":1425.41287197439,"GB2-03":1385.6964901561535,"GB2-04":1467.3690811973188,"GB2-05":1479.5980952709251,"GB2-06":1350.5111195295165,"GB2-07":1304.1469174603073,"GB2-08":1244.661046134538}},"per_game_tracks":{"highest":{"GB2-01":58.789043075528866,"GB2-02":74.2152241556405,"GB2-03":69.15194792581691,"GB2-04":69.52328474160564,"GB2-05":62.95106799924048,"GB2-06":72.08854460026902,"GB2-07":66.58206309176221,"GB2-08":67.82059785051017},"medium":{"GB2-01":63.26741605525328,"GB2-02":50.13477761489193,"GB2-03":63.3853852231098,"GB2-04":57.89545138653938,"GB2-05":49.64791785001618,"GB2-06":27.759236938095032,"GB2-07":45.81648940126721,"GB2-08":57.67826324753726},"none":{"GB2-01":42.77462310592653,"GB2-02":43.47255311334972,"GB2-03":44.72797820392788,"GB2-04":48.59209560499285,"GB2-05":52.158108269822094,"GB2-06":43.06124065699455,"GB2-07":39.520924271119355,"GB2-08":32.742034604237105}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:42:24Z","reasoning":{"highest":68.34429098783625,"medium":47.03787253990207,"none":41.529511494615285},"reasoning_agg":{"highest":{"max":74.2152241556405,"mean":68.34429098783625,"min":58.789043075528866},"medium":{"max":57.99138267375247,"mean":47.03787253990207,"min":27.759236938095032},"none":{"max":52.158108269822094,"mean":41.529511494615285,"min":21.828023069491405}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":26.81477949322096}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-6-flash:bbbf1d6020828606","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":57},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.531673125,"mean":0.4248703476562501,"median":0.446083425,"min":0.28979720625,"recorded_attempt_count":57,"run_count":20,"total":8.014536975},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":44},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07826175,"mean":0.05584070625,"median":0.0541695,"min":0.0411735,"recorded_attempt_count":29,"run_count":16,"total":0.8934513}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":44},"cost_is_complete":false,"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":4.1696877},"historical-provider-setting-baseline":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07826175,"mean":0.05584070625,"median":0.0541695,"min":0.0411735,"recorded_attempt_count":29,"run_count":16,"total":0.8934513},"historical-provider-setting-intensive":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":57},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.531673125,"mean":0.4248703476562501,"median":0.446083425,"min":0.28979720625,"recorded_attempt_count":57,"run_count":20,"total":8.014536975}},"codegen_cost_usd":{"admitted_cell_count":46,"cell_count":24,"cost_basis_counts":{"provider_reported":130},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.531673125,"mean":0.24710551171874998,"median":0.24728879999999998,"min":0.0411735,"recorded_attempt_count":130,"run_count":52,"total":13.077675974999998},"codegen_latency_ms":{"attempt_count":126,"max_ms":348942,"mean_ms":134334.75,"min_ms":17298,"run_count":52},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":53,"max_ms":348942,"mean_ms":213753.4,"min_ms":85578,"run_count":20},"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":130,"output_max":100087,"output_mean":31640.134615384617,"output_min":2060,"run_count":52},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":57,"output_max":100087,"output_mean":54101.95,"output_min":17027,"run_count":20},"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":54.50902606901978,"highest":64.28941728106594,"medium":58.78393236393819,"none":40.453728562055225},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":4,"effective_max_output_tokens":[65536],"finish_reason_observations":126,"finish_reasons":["length","stop"],"indexed_attempts":131,"output_token_observations":130,"provider_post_attempt_observations":4,"provider_post_attempts":4,"reasoning_token_observations":86,"reconciliation_get_attempt_observations":4,"reconciliation_get_attempts":19,"requested_max_output_token_observations":5,"requested_max_output_tokens":[65536],"total_output_tokens":1645287,"total_reasoning_output_tokens":844369,"total_visible_output_tokens":229233,"visible_token_observations":86},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":1,"model_code_failures":1}},"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":12,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.25},"intensive":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":12,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2,"infra_failures_excluded":2},"GB2-03":{"admitted":2,"infra_failures_excluded":1},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2,"infra_failures_excluded":2},"GB2-08":{"admitted":2}},"infra_excluded_game_aliases":["GB2-02","GB2-03","GB2-07"],"infra_failures_excluded":5,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":6,"playable":53.00617622072998,"score":53.00617622072998},"GB2-02":{"attempts":6,"failed_attempts":1,"playable":44.38160453448654,"score":38.059381700932214},"GB2-03":{"attempts":6,"playable":57.60896278966023,"score":57.60896278966023},"GB2-04":{"attempts":6,"playable":48.88214508865408,"score":48.88214508865408},"GB2-05":{"attempts":6,"playable":67.28756051937648,"score":67.28756051937648},"GB2-06":{"attempts":6,"playable":63.38857619323624,"score":63.38857619323624},"GB2-07":{"attempts":6,"playable":48.61086328161139,"score":48.61086328161139},"GB2-08":{"attempts":6,"failed_attempts":1,"playable":52.906319924403306,"score":41.323671454517346}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":55.422068088962384,"score":55.422068088962384},"GB2-02":{"attempts":2,"playable":54.534294838320776,"score":54.534294838320776},"GB2-03":{"attempts":2,"playable":69.54879993765928,"score":69.54879993765928},"GB2-04":{"attempts":2,"playable":62.604714022560046,"score":62.604714022560046},"GB2-05":{"attempts":2,"playable":84.03362006820637,"score":84.03362006820637},"GB2-06":{"attempts":2,"playable":83.41937420896076,"score":83.41937420896076},"GB2-07":{"attempts":2,"playable":50.79341910072915,"score":50.79341910072915},"GB2-08":{"attempts":2,"playable":53.95904798312868,"score":53.95904798312868}},"medium":{"GB2-01":{"attempts":2,"playable":72.24125736001214,"score":72.24125736001214},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":37.93333700132596,"score":18.96666850066298},"GB2-03":{"attempts":2,"playable":47.75148754635672,"score":47.75148754635672},"GB2-04":{"attempts":2,"playable":41.344855376627606,"score":41.344855376627606},"GB2-05":{"attempts":2,"playable":70.2746292082401,"score":70.2746292082401},"GB2-06":{"attempts":2,"playable":83.36968405037838,"score":83.36968405037838},"GB2-07":{"attempts":2,"playable":47.860317549248805,"score":47.860317549248805},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":69.4958908193158,"score":34.7479454096579}},"none":{"GB2-01":{"attempts":2,"playable":31.355203213215418,"score":31.355203213215418},"GB2-02":{"attempts":2,"playable":40.6771817638129,"score":40.6771817638129},"GB2-03":{"attempts":2,"playable":55.52660088496471,"score":55.52660088496471},"GB2-04":{"attempts":2,"playable":42.69686586677458,"score":42.69686586677458},"GB2-05":{"attempts":2,"playable":47.55443228168298,"score":47.55443228168298},"GB2-06":{"attempts":2,"playable":23.376670320369584,"score":23.376670320369584},"GB2-07":{"attempts":2,"playable":47.17885319485622,"score":47.17885319485622},"GB2-08":{"attempts":2,"playable":35.26402097076546,"score":35.26402097076546}}},"id":"google/gemini-3.6-flash","is_recent_addition":false,"last_measured_at":"2026-10-20T11:41:58Z","match_totals_all":{"draws":4928,"losses":7447,"wins":8871},"match_totals_tracks":{"highest":{"draws":1413,"losses":2017,"wins":3958},"medium":{"draws":1299,"losses":2025,"wins":3146},"none":{"draws":2216,"losses":3405,"wins":1767}},"model_slug":"google-gemini-3-6-flash","overall":{"max":84.03362006820637,"mean":52.27091715608975,"min":18.96666850066298},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":28,"overall_ranking_status":"ranked","per_game":{"GB2-01":55.422068088962384,"GB2-02":54.534294838320776,"GB2-03":69.54879993765928,"GB2-04":62.604714022560046,"GB2-05":84.03362006820637,"GB2-06":83.41937420896076,"GB2-07":50.79341910072915,"GB2-08":53.95904798312868},"per_game_all":{"GB2-01":53.00617622072998,"GB2-02":44.38160453448654,"GB2-03":57.60896278966023,"GB2-04":48.88214508865408,"GB2-05":67.28756051937648,"GB2-06":63.38857619323624,"GB2-07":48.61086328161139,"GB2-08":52.906319924403306},"per_game_match_totals_all":{"GB2-01":{"draws":638,"losses":1022,"wins":1148},"GB2-02":{"draws":1503,"losses":449,"wins":208},"GB2-03":{"draws":284,"losses":1077,"wins":1315},"GB2-04":{"draws":1610,"losses":602,"wins":476},"GB2-05":{"draws":0,"losses":955,"wins":1949},"GB2-06":{"draws":150,"losses":944,"wins":1642},"GB2-07":{"draws":0,"losses":1517,"wins":1327},"GB2-08":{"draws":743,"losses":881,"wins":806}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":222,"losses":314,"wins":400},"GB2-02":{"draws":527,"losses":140,"wins":197},"GB2-03":{"draws":48,"losses":274,"wins":570},"GB2-04":{"draws":430,"losses":131,"wins":335},"GB2-05":{"draws":0,"losses":156,"wins":812},"GB2-06":{"draws":23,"losses":140,"wins":749},"GB2-07":{"draws":0,"losses":485,"wins":463},"GB2-08":{"draws":163,"losses":377,"wins":432}},"medium":{"GB2-01":{"draws":246,"losses":141,"wins":549},"GB2-02":{"draws":307,"losses":120,"wins":5},"GB2-03":{"draws":85,"losses":451,"wins":356},"GB2-04":{"draws":553,"losses":260,"wins":83},"GB2-05":{"draws":0,"losses":289,"wins":679},"GB2-06":{"draws":52,"losses":125,"wins":735},"GB2-07":{"draws":0,"losses":513,"wins":435},"GB2-08":{"draws":56,"losses":126,"wins":304}},"none":{"GB2-01":{"draws":170,"losses":567,"wins":199},"GB2-02":{"draws":669,"losses":189,"wins":6},"GB2-03":{"draws":151,"losses":352,"wins":389},"GB2-04":{"draws":627,"losses":211,"wins":58},"GB2-05":{"draws":0,"losses":510,"wins":458},"GB2-06":{"draws":75,"losses":679,"wins":158},"GB2-07":{"draws":0,"losses":519,"wins":429},"GB2-08":{"draws":524,"losses":378,"wins":70}}},"per_game_raw_elo_all":{"GB2-01":1546.2000160308132,"GB2-02":1432.9877491342759,"GB2-03":1509.099035868181,"GB2-04":1471.8393551600032,"GB2-05":1790.7606488079393,"GB2-06":1719.4646611011933,"GB2-07":1433.726528730737,"GB2-08":1483.9030397570405},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1540.8908024376128,"GB2-02":1513.2001706677179,"GB2-03":1626.8054014321697,"GB2-04":1583.229932147142,"GB2-05":2094.8982700985366,"GB2-06":2071.6559267441044,"GB2-07":1460.3752988511387,"GB2-08":1498.4187548867221},"medium":{"GB2-01":1798.7537001519568,"GB2-02":1382.0676245275158,"GB2-03":1417.3353149485122,"GB2-04":1410.8591251901844,"GB2-05":1855.6931846234907,"GB2-06":2041.0286734765218,"GB2-07":1424.5912576925189,"GB2-08":1682.8871013469113},"none":{"GB2-01":1298.9555455028694,"GB2-02":1403.6954522075944,"GB2-03":1483.1563912238616,"GB2-04":1421.429008142683,"GB2-05":1421.6904917017912,"GB2-06":1045.7093830829544,"GB2-07":1416.2130296485539,"GB2-08":1270.403263037488}},"per_game_tracks":{"highest":{"GB2-01":55.422068088962384,"GB2-02":54.534294838320776,"GB2-03":69.54879993765928,"GB2-04":62.604714022560046,"GB2-05":84.03362006820637,"GB2-06":83.41937420896076,"GB2-07":50.79341910072915,"GB2-08":53.95904798312868},"medium":{"GB2-01":72.24125736001214,"GB2-02":37.93333700132596,"GB2-03":47.75148754635672,"GB2-04":41.344855376627606,"GB2-05":70.2746292082401,"GB2-06":83.36968405037838,"GB2-07":47.860317549248805,"GB2-08":69.4958908193158},"none":{"GB2-01":31.355203213215418,"GB2-02":40.6771817638129,"GB2-03":55.52660088496471,"GB2-04":42.69686586677458,"GB2-05":47.55443228168298,"GB2-06":23.376670320369584,"GB2-07":47.17885319485622,"GB2-08":35.26402097076546}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:51:18Z","reasoning":{"highest":64.28941728106594,"medium":52.06960562514808,"none":40.453728562055225},"reasoning_agg":{"highest":{"max":84.03362006820637,"mean":64.28941728106594,"min":50.79341910072915},"medium":{"max":83.36968405037838,"mean":52.06960562514808,"min":18.96666850066298},"none":{"max":55.52660088496471,"mean":40.453728562055225,"min":23.376670320369584}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":23.83568871901071}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-8:9f1d6d50ef1e21fb","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"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-2026-10-09":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.7435250000000002},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"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-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.2628249999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.7435250000000002},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"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-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.2628249999999999},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"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-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":7.449889999999999}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":false,"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-2026-10-09":25},"run_count":24,"token_priced_attempt_count":25,"total":10.45624},"codegen_latency_ms":{"attempt_count":25,"max_ms":604929,"mean_ms":175315.375,"min_ms":28646,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":604929,"mean_ms":421376.5,"min_ms":132563,"run_count":8},"medium":{"attempt_count":8,"max_ms":137577,"mean_ms":68957.5,"min_ms":35597,"run_count":8},"none":{"attempt_count":8,"max_ms":48121,"mean_ms":35612.125,"min_ms":28646,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":52366,"output_mean":14843.708333333334,"output_min":2908,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":52366,"output_mean":34524.125,"output_min":11990,"run_count":8},"medium":{"attempt_count":8,"output_max":11318,"output_mean":6205.25,"output_min":3583,"run_count":8},"none":{"attempt_count":8,"output_max":5116,"output_mean":3801.75,"output_min":2908,"run_count":8}},"display_name":"Claude Opus 4.8","economics":{"all":57.55016505054028,"highest":72.80189638273177,"medium":48.56210191210583,"none":48.796182893702074},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1,"infra_failures_excluded":1},"GB2-02":{"admitted":1,"infra_failures_excluded":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":1,"infra_failures_excluded":1},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"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,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":55.091998546456125,"score":55.091998546456125},"GB2-02":{"attempts":3,"playable":53.31449355297991,"score":53.31449355297991},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":31.129904170537483,"score":10.376634723512494},"GB2-04":{"attempts":3,"playable":51.98505363383192,"score":51.98505363383192},"GB2-05":{"attempts":3,"playable":40.0202996336319,"score":40.0202996336319},"GB2-06":{"attempts":3,"playable":71.0194023395737,"score":71.0194023395737},"GB2-07":{"attempts":3,"playable":65.69625291978858,"score":65.69625291978858},"GB2-08":{"attempts":3,"playable":65.72365472751989,"score":65.72365472751989}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":68.00517283260108,"score":68.00517283260108},"GB2-02":{"attempts":1,"playable":79.17407179391157,"score":79.17407179391157},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":71.0058410594153,"score":71.0058410594153},"GB2-05":{"attempts":1,"playable":49.43716596512116,"score":49.43716596512116},"GB2-06":{"attempts":1,"playable":83.26151422212101,"score":83.26151422212101},"GB2-07":{"attempts":1,"playable":76.7593334781566,"score":76.7593334781566},"GB2-08":{"attempts":1,"playable":81.97017532779569,"score":81.97017532779569}},"medium":{"GB2-01":{"attempts":1,"playable":41.27606470219706,"score":41.27606470219706},"GB2-02":{"attempts":1,"playable":41.90124779490702,"score":41.90124779490702},"GB2-03":{"attempts":1,"playable":31.129904170537483,"score":31.129904170537483},"GB2-04":{"attempts":1,"playable":42.530989492860435,"score":42.530989492860435},"GB2-05":{"attempts":1,"playable":47.9722316610349,"score":47.9722316610349},"GB2-06":{"attempts":1,"playable":80.74925803698588,"score":80.74925803698588},"GB2-07":{"attempts":1,"playable":68.82880188261967,"score":68.82880188261967},"GB2-08":{"attempts":1,"playable":34.10831755570414,"score":34.10831755570414}},"none":{"GB2-01":{"attempts":1,"playable":55.99475810457024,"score":55.99475810457024},"GB2-02":{"attempts":1,"playable":38.86816107012116,"score":38.86816107012116},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":42.41833034922002,"score":42.41833034922002},"GB2-05":{"attempts":1,"playable":22.651501274739637,"score":22.651501274739637},"GB2-06":{"attempts":1,"playable":49.04743475961422,"score":49.04743475961422},"GB2-07":{"attempts":1,"playable":51.50062339858946,"score":51.50062339858946},"GB2-08":{"attempts":1,"playable":81.09247129905982,"score":81.09247129905982}}},"id":"claude-opus-4-8","is_recent_addition":false,"last_measured_at":"2026-10-20T11:44:13Z","match_totals_all":{"draws":2321,"losses":3377,"wins":4492},"match_totals_tracks":{"highest":{"draws":453,"losses":679,"wins":2116},"medium":{"draws":1132,"losses":1372,"wins":1190},"none":{"draws":736,"losses":1326,"wins":1186}},"model_slug":"claude-opus-4-8","overall":{"max":83.26151422212101,"mean":51.653473759661814,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":29,"overall_ranking_status":"ranked","per_game":{"GB2-01":68.00517283260108,"GB2-02":79.17407179391157,"GB2-04":71.0058410594153,"GB2-05":49.43716596512116,"GB2-06":83.26151422212101,"GB2-07":76.7593334781566,"GB2-08":81.97017532779569},"per_game_all":{"GB2-01":55.091998546456125,"GB2-02":53.31449355297991,"GB2-04":51.98505363383192,"GB2-05":40.0202996336319,"GB2-06":71.0194023395737,"GB2-07":65.69625291978858,"GB2-08":65.72365472751989},"per_game_match_totals_all":{"GB2-01":{"draws":233,"losses":526,"wins":645},"GB2-02":{"draws":820,"losses":209,"wins":267},"GB2-03":{"draws":139,"losses":251,"wins":56},"GB2-04":{"draws":791,"losses":266,"wins":287},"GB2-05":{"draws":0,"losses":874,"wins":578},"GB2-06":{"draws":66,"losses":373,"wins":929},"GB2-07":{"draws":0,"losses":503,"wins":919},"GB2-08":{"draws":272,"losses":375,"wins":811}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":62,"losses":122,"wins":284},"GB2-02":{"draws":168,"losses":9,"wins":255},"GB2-04":{"draws":194,"losses":38,"wins":216},"GB2-05":{"draws":0,"losses":246,"wins":238},"GB2-06":{"draws":28,"losses":62,"wins":366},"GB2-07":{"draws":0,"losses":112,"wins":362},"GB2-08":{"draws":1,"losses":90,"wins":395}},"medium":{"GB2-01":{"draws":69,"losses":245,"wins":154},"GB2-02":{"draws":349,"losses":82,"wins":1},"GB2-03":{"draws":139,"losses":251,"wins":56},"GB2-04":{"draws":296,"losses":115,"wins":37},"GB2-05":{"draws":0,"losses":253,"wins":231},"GB2-06":{"draws":10,"losses":83,"wins":363},"GB2-07":{"draws":0,"losses":152,"wins":322},"GB2-08":{"draws":269,"losses":191,"wins":26}},"none":{"GB2-01":{"draws":102,"losses":159,"wins":207},"GB2-02":{"draws":303,"losses":118,"wins":11},"GB2-04":{"draws":301,"losses":113,"wins":34},"GB2-05":{"draws":0,"losses":375,"wins":109},"GB2-06":{"draws":28,"losses":228,"wins":200},"GB2-07":{"draws":0,"losses":239,"wins":235},"GB2-08":{"draws":2,"losses":94,"wins":390}}},"per_game_raw_elo_all":{"GB2-01":1534.2232618998478,"GB2-02":1516.4183326268958,"GB2-04":1498.705294372897,"GB2-05":1314.1536142103616,"GB2-06":1821.6730191757567,"GB2-07":1668.1683652050606,"GB2-08":1697.3996428244654},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1663.3177979460984,"GB2-02":1746.5296725248963,"GB2-04":1656.4687429072426,"GB2-05":1445.2143332958963,"GB2-06":2038.1073732235855,"GB2-07":1832.7357642132579,"GB2-08":1926.704684395979},"medium":{"GB2-01":1399.1107110014636,"GB2-02":1413.2425051809132,"GB2-03":1264.8092388199234,"GB2-04":1420.261875693871,"GB2-05":1426.9800628175785,"GB2-06":1986.771509636338,"GB2-07":1702.5476914342808,"GB2-08":1258.64848514651},"none":{"GB2-01":1540.2412767519818,"GB2-02":1389.4828201748783,"GB2-04":1419.385264517577,"GB2-05":1070.26644651761,"GB2-06":1440.1401746673462,"GB2-07":1469.2216399676431,"GB2-08":1906.8457589309073}},"per_game_tracks":{"highest":{"GB2-01":68.00517283260108,"GB2-02":79.17407179391157,"GB2-04":71.0058410594153,"GB2-05":49.43716596512116,"GB2-06":83.26151422212101,"GB2-07":76.7593334781566,"GB2-08":81.97017532779569},"medium":{"GB2-01":41.27606470219706,"GB2-02":41.90124779490702,"GB2-03":31.129904170537483,"GB2-04":42.530989492860435,"GB2-05":47.9722316610349,"GB2-06":80.74925803698588,"GB2-07":68.82880188261967,"GB2-08":34.10831755570414},"none":{"GB2-01":55.99475810457024,"GB2-02":38.86816107012116,"GB2-04":42.41833034922002,"GB2-05":22.651501274739637,"GB2-06":49.04743475961422,"GB2-07":51.50062339858946,"GB2-08":81.09247129905982}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T22:37:28Z","reasoning":{"highest":63.701659334890294,"medium":48.56210191210583,"none":42.69666003198932},"reasoning_agg":{"highest":{"max":83.26151422212101,"mean":63.701659334890294,"min":0.0},"medium":{"max":80.74925803698588,"mean":48.56210191210583,"min":31.129904170537483},"none":{"max":81.09247129905982,"mean":42.69666003198932,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":21.004999302900977}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash:a48cab159a322be4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.5094276945411561,"mean":0.27056867355814085,"median":0.2333324037943521,"min":0.1875185140307643,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.1645493884651272},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.27117240812024124,"mean":0.1983136265434789,"median":0.18868274576048882,"min":0.15676593388665558,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":1.5865090123478316},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11,"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Combined: Provider-reported + Standard list-price estimate","failed_cell_count":2,"max":0.12650943660072694,"mean":0.07695988119919009,"median":0.07334251535992004,"min":0.043710665151447045,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"recorded_attempt_count":14,"run_count":16,"token_priced_attempt_count":11,"total":1.2313580991870416}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.27117240812024124,"mean":0.1983136265434789,"median":0.18868274576048882,"min":0.15676593388665558,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":1.5865090123478314},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.122172,"mean":0.06676931250000001,"median":0.06893550000000001,"min":0.025422,"recorded_attempt_count":14,"run_count":8,"total":0.5341545},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.13084687320145388,"mean":0.0871504498983802,"median":0.08084431374719805,"min":0.0619993303028941,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.6972035991870416},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.5094276945411561,"mean":0.27056867355814085,"median":0.2333324037943521,"min":0.1875185140307643,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.1645493884651272}},"codegen_cost_usd":{"admitted_cell_count":30,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":32,"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Combined: Provider-reported + Standard list-price estimate","failed_cell_count":2,"max":0.5094276945411561,"mean":0.1819473937669366,"median":0.18692147314407714,"min":0.043710665151447045,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":32},"recorded_attempt_count":14,"run_count":32,"token_priced_attempt_count":32,"total":4.982416499999999},"codegen_output_tokens":{"attempt_count":32,"output_max":60921,"output_mean":18651.916666666668,"output_min":1790,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":60921,"output_mean":31693.5,"output_min":21144,"run_count":8},"medium":{"attempt_count":10,"output_max":28586,"output_mean":21214.875,"output_min":16507,"run_count":8},"none":{"attempt_count":11,"output_max":4623,"output_mean":3047.375,"output_min":1790,"run_count":8}},"display_name":"Gemini 3.5 Flash","economics":{"all":52.59326754539673,"highest":64.21018005668957,"medium":57.23887554372324,"none":36.33074703577737},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":32,"finish_reasons":["stop"],"indexed_attempts":32,"output_token_observations":32,"provider_post_attempt_observations":32,"provider_post_attempts":32,"reasoning_token_observations":32,"reconciliation_get_attempt_observations":32,"total_output_tokens":447646,"total_reasoning_output_tokens":288780,"total_visible_output_tokens":158866,"visible_token_observations":32},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":11,"first_pass_rate":0.6875,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":1,"model_code_failures":1},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.1875},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":4,"playable":71.27274004492487,"score":71.27274004492487},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":49.048574183716305,"score":42.47323127670534},"GB2-03":{"attempts":4,"failed_attempts":1,"playable":55.56124840660326,"score":51.52375572334606},"GB2-04":{"attempts":4,"playable":45.910686543231854,"score":45.910686543231854},"GB2-05":{"attempts":4,"playable":45.37660985700688,"score":45.37660985700688},"GB2-06":{"attempts":4,"playable":63.123333275368886,"score":63.123333275368886},"GB2-07":{"attempts":4,"playable":50.91395172581063,"score":50.91395172581063},"GB2-08":{"attempts":4,"playable":39.538996326511125,"score":39.538996326511125}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":90.51521916038364,"score":90.51521916038364},"GB2-02":{"attempts":1,"playable":62.53512538536123,"score":62.53512538536123},"GB2-03":{"attempts":1,"playable":72.48753680538086,"score":72.48753680538086},"GB2-04":{"attempts":1,"playable":41.40400663982462,"score":41.40400663982462},"GB2-05":{"attempts":1,"playable":52.57672261299705,"score":52.57672261299705},"GB2-06":{"attempts":1,"playable":75.46034712813828,"score":75.46034712813828},"GB2-07":{"attempts":1,"playable":51.90357145244915,"score":51.90357145244915},"GB2-08":{"attempts":1,"playable":66.79891126898163,"score":66.79891126898163}},"medium":{"GB2-01":{"attempts":1,"playable":73.78169573727962,"score":73.78169573727962},"GB2-02":{"attempts":1,"playable":45.158539723721894,"score":45.158539723721894},"GB2-03":{"attempts":1,"playable":69.97125231488576,"score":69.97125231488576},"GB2-04":{"attempts":1,"playable":54.41827852803483,"score":54.41827852803483},"GB2-05":{"attempts":1,"playable":67.40958548787896,"score":67.40958548787896},"GB2-06":{"attempts":1,"playable":73.50485868092147,"score":73.50485868092147},"GB2-07":{"attempts":1,"playable":55.116299873911515,"score":55.116299873911515},"GB2-08":{"attempts":1,"playable":18.55049400315193,"score":18.55049400315193}},"none":{"GB2-01":{"attempts":2,"playable":49.52130523711132,"score":49.52130523711132},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":39.45205744206578,"score":19.72602872103289},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":24.224956099543203,"score":12.112478049771601},"GB2-04":{"attempts":2,"playable":41.90977446183609,"score":41.90977446183609},"GB2-05":{"attempts":2,"playable":16.14352147014463,"score":16.14352147014463},"GB2-06":{"attempts":2,"playable":40.40479401704691,"score":40.40479401704691},"GB2-07":{"attempts":2,"playable":45.721983851071215,"score":45.721983851071215},"GB2-08":{"attempts":2,"playable":33.26758370739982,"score":33.26758370739982}}},"id":"google/gemini-3.5-flash","is_recent_addition":false,"last_measured_at":"2026-10-20T11:45:23Z","match_totals_all":{"draws":3170,"losses":5601,"wins":5127},"match_totals_tracks":{"highest":{"draws":624,"losses":1052,"wins":2018},"medium":{"draws":849,"losses":1204,"wins":1641},"none":{"draws":1697,"losses":3345,"wins":1468}},"model_slug":"google-gemini-3-5-flash","overall":{"max":90.51521916038364,"mean":51.26666309661321,"min":12.112478049771601},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":30,"overall_ranking_status":"ranked","per_game":{"GB2-01":90.51521916038364,"GB2-02":62.53512538536123,"GB2-03":72.48753680538086,"GB2-04":41.40400663982462,"GB2-05":52.57672261299705,"GB2-06":75.46034712813828,"GB2-07":51.90357145244915,"GB2-08":66.79891126898163},"per_game_all":{"GB2-01":71.27274004492487,"GB2-02":49.048574183716305,"GB2-03":55.56124840660326,"GB2-04":45.910686543231854,"GB2-05":45.37660985700688,"GB2-06":63.123333275368886,"GB2-07":50.91395172581063,"GB2-08":39.538996326511125},"per_game_match_totals_all":{"GB2-01":{"draws":203,"losses":550,"wins":1119},"GB2-02":{"draws":935,"losses":209,"wins":152},"GB2-03":{"draws":149,"losses":557,"wins":632},"GB2-04":{"draws":1081,"losses":469,"wins":242},"GB2-05":{"draws":0,"losses":1205,"wins":731},"GB2-06":{"draws":34,"losses":777,"wins":1013},"GB2-07":{"draws":0,"losses":992,"wins":904},"GB2-08":{"draws":768,"losses":842,"wins":334}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":20,"losses":35,"wins":413},"GB2-02":{"draws":238,"losses":48,"wins":146},"GB2-03":{"draws":40,"losses":115,"wins":291},"GB2-04":{"draws":240,"losses":148,"wins":60},"GB2-05":{"draws":0,"losses":231,"wins":253},"GB2-06":{"draws":11,"losses":108,"wins":337},"GB2-07":{"draws":0,"losses":237,"wins":237},"GB2-08":{"draws":75,"losses":130,"wins":281}},"medium":{"GB2-01":{"draws":11,"losses":120,"wins":337},"GB2-02":{"draws":369,"losses":58,"wins":5},"GB2-03":{"draws":42,"losses":126,"wins":278},"GB2-04":{"draws":256,"losses":82,"wins":110},"GB2-05":{"draws":0,"losses":160,"wins":324},"GB2-06":{"draws":12,"losses":117,"wins":327},"GB2-07":{"draws":0,"losses":221,"wins":253},"GB2-08":{"draws":159,"losses":320,"wins":7}},"none":{"GB2-01":{"draws":172,"losses":395,"wins":369},"GB2-02":{"draws":328,"losses":103,"wins":1},"GB2-03":{"draws":67,"losses":316,"wins":63},"GB2-04":{"draws":585,"losses":239,"wins":72},"GB2-05":{"draws":0,"losses":814,"wins":154},"GB2-06":{"draws":11,"losses":552,"wins":349},"GB2-07":{"draws":0,"losses":534,"wins":414},"GB2-08":{"draws":534,"losses":392,"wins":46}}},"per_game_raw_elo_all":{"GB2-01":1739.9480625069762,"GB2-02":1469.6905127874334,"GB2-03":1496.8801755924678,"GB2-04":1446.459067149877,"GB2-05":1373.0522458125354,"GB2-06":1681.8829981870447,"GB2-07":1462.1728213263934,"GB2-08":1324.462514162716},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2011.1241560961178,"GB2-02":1576.5521868057367,"GB2-03":1663.0362730626432,"GB2-04":1411.4747385205646,"GB2-05":1484.4022775344265,"GB2-06":1885.0019417027997,"GB2-07":1474.2882288493392,"GB2-08":1639.6197074636439},"medium":{"GB2-01":1730.1453898902153,"GB2-02":1438.4298063556869,"GB2-03":1631.7772387807552,"GB2-04":1512.5507974037644,"GB2-05":1686.572805746372,"GB2-06":1848.7776115790557,"GB2-07":1515.0354203626625,"GB2-08":1083.710185432731},"none":{"GB2-01":1478.5746415345957,"GB2-02":1394.0895452008763,"GB2-03":1195.8270149340053,"GB2-04":1415.3516655253018,"GB2-05":948.1816541568074,"GB2-06":1311.8694412792788,"GB2-07":1397.1948147671792,"GB2-08":1250.057649591773}},"per_game_tracks":{"highest":{"GB2-01":90.51521916038364,"GB2-02":62.53512538536123,"GB2-03":72.48753680538086,"GB2-04":41.40400663982462,"GB2-05":52.57672261299705,"GB2-06":75.46034712813828,"GB2-07":51.90357145244915,"GB2-08":66.79891126898163},"medium":{"GB2-01":73.78169573727962,"GB2-02":45.158539723721894,"GB2-03":69.97125231488576,"GB2-04":54.41827852803483,"GB2-05":67.40958548787896,"GB2-06":73.50485868092147,"GB2-07":55.116299873911515,"GB2-08":18.55049400315193},"none":{"GB2-01":49.52130523711132,"GB2-02":39.45205744206578,"GB2-03":24.224956099543203,"GB2-04":41.90977446183609,"GB2-05":16.14352147014463,"GB2-06":40.40479401704691,"GB2-07":45.721983851071215,"GB2-08":33.26758370739982}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:15:37Z","reasoning":{"highest":64.21018005668957,"medium":57.23887554372324,"none":32.35093368942681},"reasoning_agg":{"highest":{"max":90.51521916038364,"mean":64.21018005668957,"min":41.40400663982462},"medium":{"max":73.78169573727962,"mean":57.23887554372324,"min":18.55049400315193},"none":{"max":49.52130523711132,"mean":32.35093368942681,"min":12.112478049771601}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":31.859246367262756}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-5:881f6033db92eb7a","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"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-2026-10-09":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":3.542855},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"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-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.13802}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":3.542855},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"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-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.13802},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"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-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":21.885475}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":26},"cost_is_complete":false,"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-2026-10-09":26},"run_count":24,"token_priced_attempt_count":26,"total":26.56635},"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":55.50572526175453,"highest":69.27152738471396,"medium":52.69986726514533,"none":42.857779143422285},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":65.2777460319522,"score":65.2777460319522},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":48.44040878478063,"score":32.29360585652042},"GB2-03":{"attempts":3,"playable":42.800999233901564,"score":42.800999233901564},"GB2-04":{"attempts":3,"playable":39.48436835359029,"score":39.48436835359029},"GB2-05":{"attempts":3,"playable":68.32598056812724,"score":68.32598056812724},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":55.26010576848679,"score":36.84007051232452},"GB2-07":{"attempts":3,"playable":62.54787174623031,"score":62.54787174623031},"GB2-08":{"attempts":3,"playable":54.59738563672558,"score":54.59738563672558}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":79.95693054817052,"score":79.95693054817052},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":50.82026234951344,"score":50.82026234951344},"GB2-04":{"attempts":1,"playable":36.32230510026414,"score":36.32230510026414},"GB2-05":{"attempts":1,"playable":76.71754556719394,"score":76.71754556719394},"GB2-06":{"attempts":1,"playable":81.37584046337942,"score":81.37584046337942},"GB2-07":{"attempts":1,"playable":87.53479086895358,"score":87.53479086895358},"GB2-08":{"attempts":1,"playable":72.17301679552268,"score":72.17301679552268}},"medium":{"GB2-01":{"attempts":1,"playable":65.16473501519636,"score":65.16473501519636},"GB2-02":{"attempts":1,"playable":55.212601205261294,"score":55.212601205261294},"GB2-03":{"attempts":1,"playable":39.5444598317259,"score":39.5444598317259},"GB2-04":{"attempts":1,"playable":40.0504994990073,"score":40.0504994990073},"GB2-05":{"attempts":1,"playable":76.10228116537084,"score":76.10228116537084},"GB2-06":{"attempts":1,"playable":29.14437107359416,"score":29.14437107359416},"GB2-07":{"attempts":1,"playable":61.49526698897012,"score":61.49526698897012},"GB2-08":{"attempts":1,"playable":54.8847233420367,"score":54.8847233420367}},"none":{"GB2-01":{"attempts":1,"playable":50.71157253248973,"score":50.71157253248973},"GB2-02":{"attempts":1,"playable":41.66821636429997,"score":41.66821636429997},"GB2-03":{"attempts":1,"playable":38.03827552046535,"score":38.03827552046535},"GB2-04":{"attempts":1,"playable":42.08030046149943,"score":42.08030046149943},"GB2-05":{"attempts":1,"playable":52.15811497181693,"score":52.15811497181693},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":38.613557380767226,"score":38.613557380767226},"GB2-08":{"attempts":1,"playable":36.73441677261734,"score":36.73441677261734}}},"id":"gpt-5.5","is_recent_addition":false,"last_measured_at":"2026-10-20T11:36:29Z","match_totals_all":{"draws":3116,"losses":3149,"wins":3929},"match_totals_tracks":{"highest":{"draws":660,"losses":690,"wins":1912},"medium":{"draws":1143,"losses":1219,"wins":1332},"none":{"draws":1313,"losses":1240,"wins":685}},"model_slug":"gpt-5-5","overall":{"max":87.53479086895358,"mean":50.27100349242151,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":31,"overall_ranking_status":"ranked","per_game":{"GB2-01":79.95693054817052,"GB2-03":50.82026234951344,"GB2-04":36.32230510026414,"GB2-05":76.71754556719394,"GB2-06":81.37584046337942,"GB2-07":87.53479086895358,"GB2-08":72.17301679552268},"per_game_all":{"GB2-01":65.2777460319522,"GB2-03":42.800999233901564,"GB2-04":39.48436835359029,"GB2-05":68.32598056812724,"GB2-07":62.54787174623031,"GB2-08":54.59738563672558},"per_game_match_totals_all":{"GB2-01":{"draws":663,"losses":166,"wins":575},"GB2-02":{"draws":629,"losses":142,"wins":93},"GB2-03":{"draws":403,"losses":609,"wins":326},"GB2-04":{"draws":797,"losses":431,"wins":116},"GB2-05":{"draws":0,"losses":466,"wins":986},"GB2-06":{"draws":45,"losses":396,"wins":471},"GB2-07":{"draws":0,"losses":549,"wins":873},"GB2-08":{"draws":579,"losses":390,"wins":489}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":116,"losses":38,"wins":314},"GB2-03":{"draws":130,"losses":170,"wins":146},"GB2-04":{"draws":257,"losses":162,"wins":29},"GB2-05":{"draws":0,"losses":115,"wins":369},"GB2-06":{"draws":32,"losses":69,"wins":355},"GB2-07":{"draws":0,"losses":58,"wins":416},"GB2-08":{"draws":125,"losses":78,"wins":283}},"medium":{"GB2-01":{"draws":259,"losses":37,"wins":172},"GB2-02":{"draws":280,"losses":59,"wins":93},"GB2-03":{"draws":151,"losses":209,"wins":86},"GB2-04":{"draws":262,"losses":143,"wins":43},"GB2-05":{"draws":0,"losses":118,"wins":366},"GB2-06":{"draws":13,"losses":327,"wins":116},"GB2-07":{"draws":0,"losses":189,"wins":285},"GB2-08":{"draws":178,"losses":137,"wins":171}},"none":{"GB2-01":{"draws":288,"losses":91,"wins":89},"GB2-02":{"draws":349,"losses":83,"wins":0},"GB2-03":{"draws":122,"losses":230,"wins":94},"GB2-04":{"draws":278,"losses":126,"wins":44},"GB2-05":{"draws":0,"losses":233,"wins":251},"GB2-07":{"draws":0,"losses":302,"wins":172},"GB2-08":{"draws":276,"losses":175,"wins":35}}},"per_game_raw_elo_all":{"GB2-01":1644.7808262484893,"GB2-03":1369.465573522368,"GB2-04":1396.2441516352603,"GB2-05":1725.9920781913236,"GB2-07":1666.4433528931934,"GB2-08":1497.6725192590827},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1812.2273590521786,"GB2-03":1439.7346214468728,"GB2-04":1371.1205292679272,"GB2-05":1856.004267435234,"GB2-06":1999.3379916783801,"GB2-07":2092.207872889253,"GB2-08":1728.900777240795},"medium":{"GB2-01":1632.7353390310723,"GB2-02":1516.4655299343149,"GB2-03":1340.973649403396,"GB2-04":1400.8591792532234,"GB2-05":1842.8151991312643,"GB2-06":1139.6160085497866,"GB2-07":1598.6903738228548,"GB2-08":1478.807178954198},"none":{"GB2-01":1489.3797806622172,"GB2-02":1411.430214719613,"GB2-03":1327.6884497168357,"GB2-04":1416.7527463846307,"GB2-05":1479.1567680074731,"GB2-07":1308.4318119674726,"GB2-08":1285.3096015822553}},"per_game_tracks":{"highest":{"GB2-01":79.95693054817052,"GB2-03":50.82026234951344,"GB2-04":36.32230510026414,"GB2-05":76.71754556719394,"GB2-06":81.37584046337942,"GB2-07":87.53479086895358,"GB2-08":72.17301679552268},"medium":{"GB2-01":65.16473501519636,"GB2-02":55.212601205261294,"GB2-03":39.5444598317259,"GB2-04":40.0504994990073,"GB2-05":76.10228116537084,"GB2-06":29.14437107359416,"GB2-07":61.49526698897012,"GB2-08":54.8847233420367},"none":{"GB2-01":50.71157253248973,"GB2-02":41.66821636429997,"GB2-03":38.03827552046535,"GB2-04":42.08030046149943,"GB2-05":52.15811497181693,"GB2-07":38.613557380767226,"GB2-08":36.73441677261734}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-14T17:58:58Z","reasoning":{"highest":60.61258646162472,"medium":52.69986726514533,"none":37.50055675049449},"reasoning_agg":{"highest":{"max":87.53479086895358,"mean":60.61258646162472,"min":0.0},"medium":{"max":76.10228116537084,"mean":52.69986726514533,"min":29.14437107359416},"none":{"max":52.15811497181693,"mean":37.50055675049449,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":23.112029711130234}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max:61da32d02ed7ac9c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.3468699583333334,"median":0.3476285,"min":0.237408,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":13,"total":4.659586},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.25803,"mean":0.104435,"median":0.081263,"min":0.075542,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.83548},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.173358,"mean":0.1197105,"median":0.119348,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.957684}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.25803,"mean":0.104435,"median":0.081263,"min":0.075542,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.83548},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.173358,"mean":0.1197105,"median":0.119348,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.957684},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.3468699583333334,"median":0.3476285,"min":0.237408,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":13,"total":4.659586}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.19033848611111112,"median":0.13741799999999998,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":30},"recorded_attempt_count":30,"run_count":29,"total":6.45275},"codegen_latency_ms":{"attempt_count":30,"max_ms":1708792,"mean_ms":723489.2413793104,"min_ms":155474,"run_count":29},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":1708792,"mean_ms":1260718.7692307692,"min_ms":853424,"run_count":13},"medium":{"attempt_count":8,"max_ms":700604,"mean_ms":265043.125,"min_ms":183145,"run_count":8},"none":{"attempt_count":8,"max_ms":461859,"mean_ms":308937.375,"min_ms":155474,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":76211,"output_mean":34293.10344827586,"output_min":8500,"run_count":29},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":76211,"output_mean":56804.769230769234,"output_min":37117,"run_count":13},"medium":{"attempt_count":8,"output_max":40473,"output_mean":14733.75,"output_min":10090,"run_count":8},"none":{"attempt_count":8,"output_max":26415,"output_mean":17271.0,"output_min":8500,"run_count":8}},"display_name":"Qwen3.8 Max","economics":{"all":50.85763031487447,"highest":53.93032180177871,"medium":50.598379978253554,"none":48.04418916459115},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":1,"effective_max_output_tokens":[131072],"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":30,"provider_post_attempts":30,"reasoning_token_observations":30,"reconciliation_get_attempt_observations":30,"reconciliation_get_attempts":142,"requested_max_output_token_observations":1,"requested_max_output_tokens":[131072],"total_output_tokens":994500,"total_reasoning_output_tokens":878493,"total_visible_output_tokens":116007,"visible_token_observations":30},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":10,"failed_game_aliases":["GB2-02"],"first_pass_admitted":8,"first_pass_rate":0.8888888888888888,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1,"infra_failures_excluded":1,"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1,"performance_rejections":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-02","GB2-06","GB2-08"],"infra_failures_excluded":3,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-04"],"performance_rejections":1}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":33.589113948943115,"score":33.589113948943115},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":45.26187601751198,"score":36.53945200060854},"GB2-03":{"attempts":3,"playable":50.853152709300254,"score":50.853152709300254},"GB2-04":{"attempts":3,"playable":48.798905226028275,"score":48.798905226028275},"GB2-05":{"attempts":3,"playable":68.8526818987596,"score":68.8526818987596},"GB2-06":{"attempts":3,"playable":40.649172044193826,"score":40.649172044193826},"GB2-07":{"attempts":3,"playable":63.40206015371842,"score":63.40206015371842},"GB2-08":{"attempts":3,"playable":55.45408052054028,"score":55.45408052054028}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":32.7483413402161,"score":32.7483413402161},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":52.334544101420654,"score":26.167272050710327},"GB2-03":{"attempts":1,"playable":58.25049435257117,"score":58.25049435257117},"GB2-04":{"attempts":1,"playable":65.73382942060854,"score":65.73382942060854},"GB2-05":{"attempts":1,"playable":47.762977208309714,"score":47.762977208309714},"GB2-06":{"attempts":1,"playable":51.344441393105214,"score":51.344441393105214},"GB2-07":{"attempts":1,"playable":78.1510316017165,"score":78.1510316017165},"GB2-08":{"attempts":1,"playable":45.11691499628175,"score":45.11691499628175}},"medium":{"GB2-01":{"attempts":1,"playable":41.38235133343958,"score":41.38235133343958},"GB2-02":{"attempts":1,"playable":43.182055003452916,"score":43.182055003452916},"GB2-03":{"attempts":1,"playable":56.27068825486427,"score":56.27068825486427},"GB2-04":{"attempts":1,"playable":38.469900446346955,"score":38.469900446346955},"GB2-05":{"attempts":1,"playable":68.03382244813871,"score":68.03382244813871},"GB2-06":{"attempts":1,"playable":49.98887582223999,"score":49.98887582223999},"GB2-07":{"attempts":1,"playable":39.85917679731602,"score":39.85917679731602},"GB2-08":{"attempts":1,"playable":67.60016972022997,"score":67.60016972022997}},"none":{"GB2-01":{"attempts":1,"playable":26.636649173173655,"score":26.636649173173655},"GB2-02":{"attempts":1,"playable":40.26902894766237,"score":40.26902894766237},"GB2-03":{"attempts":1,"playable":38.03827552046535,"score":38.03827552046535},"GB2-04":{"attempts":1,"playable":42.19298581112933,"score":42.19298581112933},"GB2-05":{"attempts":1,"playable":90.76124603983037,"score":90.76124603983037},"GB2-06":{"attempts":1,"playable":20.614198917236262,"score":20.614198917236262},"GB2-07":{"attempts":1,"playable":72.19597206212278,"score":72.19597206212278},"GB2-08":{"attempts":1,"playable":53.64515684510912,"score":53.64515684510912}}},"id":"qwen/qwen3.8-max","is_recent_addition":false,"last_measured_at":"2026-10-20T11:17:45Z","match_totals_all":{"draws":3015,"losses":4071,"wins":3996},"match_totals_tracks":{"highest":{"draws":909,"losses":1300,"wins":1485},"medium":{"draws":1021,"losses":1365,"wins":1308},"none":{"draws":1085,"losses":1406,"wins":1203}},"model_slug":"qwen-qwen3-8-max","overall":{"max":90.76124603983037,"mean":49.767327312761545,"min":20.614198917236262},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":32,"overall_ranking_status":"ranked","per_game":{"GB2-01":32.7483413402161,"GB2-02":52.334544101420654,"GB2-03":58.25049435257117,"GB2-04":65.73382942060854,"GB2-05":47.762977208309714,"GB2-06":51.344441393105214,"GB2-07":78.1510316017165,"GB2-08":45.11691499628175},"per_game_all":{"GB2-01":33.589113948943115,"GB2-02":45.26187601751198,"GB2-03":50.853152709300254,"GB2-04":48.798905226028275,"GB2-05":68.8526818987596,"GB2-06":40.649172044193826,"GB2-07":63.40206015371842,"GB2-08":55.45408052054028},"per_game_match_totals_all":{"GB2-01":{"draws":355,"losses":769,"wins":280},"GB2-02":{"draws":984,"losses":234,"wins":78},"GB2-03":{"draws":276,"losses":565,"wins":497},"GB2-04":{"draws":773,"losses":318,"wins":253},"GB2-05":{"draws":0,"losses":455,"wins":997},"GB2-06":{"draws":102,"losses":788,"wins":478},"GB2-07":{"draws":0,"losses":536,"wins":886},"GB2-08":{"draws":525,"losses":406,"wins":527}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":89,"losses":275,"wins":104},"GB2-02":{"draws":315,"losses":54,"wins":63},"GB2-03":{"draws":31,"losses":186,"wins":229},"GB2-04":{"draws":188,"losses":65,"wins":195},"GB2-05":{"draws":0,"losses":254,"wins":230},"GB2-06":{"draws":42,"losses":210,"wins":204},"GB2-07":{"draws":0,"losses":105,"wins":369},"GB2-08":{"draws":244,"losses":151,"wins":91}},"medium":{"GB2-01":{"draws":156,"losses":201,"wins":111},"GB2-02":{"draws":350,"losses":76,"wins":6},"GB2-03":{"draws":93,"losses":164,"wins":189},"GB2-04":{"draws":300,"losses":131,"wins":17},"GB2-05":{"draws":0,"losses":157,"wins":327},"GB2-06":{"draws":37,"losses":219,"wins":200},"GB2-07":{"draws":0,"losses":296,"wins":178},"GB2-08":{"draws":85,"losses":121,"wins":280}},"none":{"GB2-01":{"draws":110,"losses":293,"wins":65},"GB2-02":{"draws":319,"losses":104,"wins":9},"GB2-03":{"draws":152,"losses":215,"wins":79},"GB2-04":{"draws":285,"losses":122,"wins":41},"GB2-05":{"draws":0,"losses":44,"wins":440},"GB2-06":{"draws":23,"losses":359,"wins":74},"GB2-07":{"draws":0,"losses":135,"wins":339},"GB2-08":{"draws":196,"losses":134,"wins":156}}},"per_game_raw_elo_all":{"GB2-01":1320.5105332835965,"GB2-02":1439.1762168835348,"GB2-03":1441.6052938738303,"GB2-04":1470.9539028921654,"GB2-05":1810.6578657484795,"GB2-06":1312.3656993609472,"GB2-07":1645.903211446365,"GB2-08":1495.7751239695224},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1313.9502206172,"GB2-02":1493.847780546341,"GB2-03":1507.8916239475204,"GB2-04":1606.8774497131703,"GB2-05":1424.374002390975,"GB2-06":1475.6320907188558,"GB2-07":1858.867453442025,"GB2-08":1370.9044937358003},"medium":{"GB2-01":1400.1396719675854,"GB2-02":1423.174296829968,"GB2-03":1489.2358079571347,"GB2-04":1388.3535492698948,"GB2-05":1696.3756587378923,"GB2-06":1454.6445189121089,"GB2-07":1324.1232347810576,"GB2-08":1652.163612485821},"none":{"GB2-01":1247.4417072660042,"GB2-02":1400.5065732742958,"GB2-03":1327.6884497168357,"GB2-04":1417.6307096934313,"GB2-05":2311.223936116571,"GB2-06":1006.8204884518768,"GB2-07":1754.7189461160124,"GB2-08":1464.2572656869459}},"per_game_tracks":{"highest":{"GB2-01":32.7483413402161,"GB2-02":52.334544101420654,"GB2-03":58.25049435257117,"GB2-04":65.73382942060854,"GB2-05":47.762977208309714,"GB2-06":51.344441393105214,"GB2-07":78.1510316017165,"GB2-08":45.11691499628175},"medium":{"GB2-01":41.38235133343958,"GB2-02":43.182055003452916,"GB2-03":56.27068825486427,"GB2-04":38.469900446346955,"GB2-05":68.03382244813871,"GB2-06":49.98887582223999,"GB2-07":39.85917679731602,"GB2-08":67.60016972022997},"none":{"GB2-01":26.636649173173655,"GB2-02":40.26902894766237,"GB2-03":38.03827552046535,"GB2-04":42.19298581112933,"GB2-05":90.76124603983037,"GB2-06":20.614198917236262,"GB2-07":72.19597206212278,"GB2-08":53.64515684510912}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-14T17:24:33Z","reasoning":{"highest":50.65941279543991,"medium":50.598379978253554,"none":48.04418916459115},"reasoning_agg":{"highest":{"max":78.1510316017165,"mean":50.65941279543991,"min":26.167272050710327},"medium":{"max":68.03382244813871,"mean":50.598379978253554,"min":38.469900446346955},"none":{"max":90.76124603983037,"mean":48.04418916459115,"min":20.614198917236262}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":2.61522363084876}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-luna:4805358587e278d4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.0117399875,"median":0.011861425,"min":0.0087063,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.0939199},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0044690500000000005,"mean":0.0038361124999999998,"median":0.0037657374999999996,"min":0.00283105,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.030688900000000005},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.007622525,"mean":0.0031813812500000004,"median":0.0022472374999999998,"min":0.00169605,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":0.02545105}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0044690500000000005,"mean":0.0038361124999999998,"median":0.0037657374999999996,"min":0.00283105,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.030688900000000005},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.007622525,"mean":0.0031813812500000004,"median":0.0022472374999999998,"min":0.00169605,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":0.02545105},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.0117399875,"median":0.011861425,"min":0.0087063,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.0939199}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.00625249375,"median":0.0043227375,"min":0.00169605,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":16,"boardgame-list-prices-2026-10-09":11},"run_count":24,"token_priced_attempt_count":27,"total":0.15005985000000002},"codegen_latency_ms":{"attempt_count":11,"max_ms":86701,"mean_ms":33803.25,"min_ms":21457,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":11,"max_ms":86701,"mean_ms":33803.25,"min_ms":21457,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":26534,"output_mean":10296.416666666666,"output_min":1575,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":26534,"output_mean":21543.25,"output_min":15583,"run_count":8},"medium":{"attempt_count":8,"output_max":6895,"output_mean":5735.5,"output_min":3866,"run_count":8},"none":{"attempt_count":11,"output_max":9509,"output_mean":3610.5,"output_min":1575,"run_count":8}},"display_name":"GPT-6 Luna","economics":{"all":48.84184311939819,"highest":57.668167016175076,"medium":44.08364196259764,"none":44.773720379421846},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"effective_max_output_tokens":[65536,128000],"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"requested_max_output_token_observations":27,"requested_max_output_tokens":[65536,128000],"total_output_tokens":247114,"total_reasoning_output_tokens":163396,"total_visible_output_tokens":83718,"visible_token_observations":27},"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-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":38.66993242673803,"score":38.66993242673803},"GB2-02":{"attempts":3,"playable":50.559399598646735,"score":50.559399598646735},"GB2-03":{"attempts":3,"playable":48.78957636347053,"score":48.78957636347053},"GB2-04":{"attempts":3,"playable":53.233040829496396,"score":53.233040829496396},"GB2-05":{"attempts":3,"playable":47.075043828744406,"score":47.075043828744406},"GB2-06":{"attempts":3,"playable":64.26557735640033,"score":64.26557735640033},"GB2-07":{"attempts":3,"playable":41.83048991730961,"score":41.83048991730961},"GB2-08":{"attempts":3,"playable":46.311684634379475,"score":46.311684634379475}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":29.964740313617273,"score":29.964740313617273},"GB2-02":{"attempts":1,"playable":63.10426044931666,"score":63.10426044931666},"GB2-03":{"attempts":1,"playable":49.24688648743102,"score":49.24688648743102},"GB2-04":{"attempts":1,"playable":64.18921667871949,"score":64.18921667871949},"GB2-05":{"attempts":1,"playable":54.87884402711515,"score":54.87884402711515},"GB2-06":{"attempts":1,"playable":86.31859296959385,"score":86.31859296959385},"GB2-07":{"attempts":1,"playable":38.613557380767226,"score":38.613557380767226},"GB2-08":{"attempts":1,"playable":75.02923782283995,"score":75.02923782283995}},"medium":{"GB2-01":{"attempts":1,"playable":38.297139526736814,"score":38.297139526736814},"GB2-02":{"attempts":1,"playable":44.57759803665907,"score":44.57759803665907},"GB2-03":{"attempts":1,"playable":51.15649082894886,"score":51.15649082894886},"GB2-04":{"attempts":1,"playable":51.17757957609639,"score":51.17757957609639},"GB2-05":{"attempts":1,"playable":50.69296543340539,"score":50.69296543340539},"GB2-06":{"attempts":1,"playable":34.307531302188934,"score":34.307531302188934},"GB2-07":{"attempts":1,"playable":53.71300927495108,"score":53.71300927495108},"GB2-08":{"attempts":1,"playable":28.746821721794646,"score":28.746821721794646}},"none":{"GB2-01":{"attempts":1,"playable":47.747917439860004,"score":47.747917439860004},"GB2-02":{"attempts":1,"playable":43.99634030996448,"score":43.99634030996448},"GB2-03":{"attempts":1,"playable":45.9653517740317,"score":45.9653517740317},"GB2-04":{"attempts":1,"playable":44.33232623367333,"score":44.33232623367333},"GB2-05":{"attempts":1,"playable":35.653322025712676,"score":35.653322025712676},"GB2-06":{"attempts":1,"playable":72.17060779741821,"score":72.17060779741821},"GB2-07":{"attempts":1,"playable":33.16490309621053,"score":33.16490309621053},"GB2-08":{"attempts":1,"playable":35.15899435850383,"score":35.15899435850383}}},"id":"gpt-6-luna","is_recent_addition":false,"last_measured_at":"2026-10-20T11:14:17Z","match_totals_all":{"draws":2933,"losses":4372,"wins":3777},"match_totals_tracks":{"highest":{"draws":541,"losses":1344,"wins":1809},"medium":{"draws":1162,"losses":1545,"wins":987},"none":{"draws":1230,"losses":1483,"wins":981}},"model_slug":"gpt-6-luna","overall":{"max":86.31859296959385,"mean":48.841843119398185,"min":28.746821721794646},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":33,"overall_ranking_status":"ranked","per_game":{"GB2-01":29.964740313617273,"GB2-02":63.10426044931666,"GB2-03":49.24688648743102,"GB2-04":64.18921667871949,"GB2-05":54.87884402711515,"GB2-06":86.31859296959385,"GB2-07":38.613557380767226,"GB2-08":75.02923782283995},"per_game_all":{"GB2-01":38.66993242673803,"GB2-02":50.559399598646735,"GB2-03":48.78957636347053,"GB2-04":53.233040829496396,"GB2-05":47.075043828744406,"GB2-06":64.26557735640033,"GB2-07":41.83048991730961,"GB2-08":46.311684634379475},"per_game_match_totals_all":{"GB2-01":{"draws":434,"losses":658,"wins":312},"GB2-02":{"draws":966,"losses":174,"wins":156},"GB2-03":{"draws":194,"losses":635,"wins":509},"GB2-04":{"draws":771,"losses":260,"wins":313},"GB2-05":{"draws":0,"losses":772,"wins":680},"GB2-06":{"draws":65,"losses":469,"wins":834},"GB2-07":{"draws":0,"losses":858,"wins":564},"GB2-08":{"draws":503,"losses":546,"wins":409}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":332,"wins":135},"GB2-02":{"draws":251,"losses":39,"wins":142},"GB2-03":{"draws":22,"losses":231,"wins":193},"GB2-04":{"draws":212,"losses":60,"wins":176},"GB2-05":{"draws":0,"losses":220,"wins":264},"GB2-06":{"draws":23,"losses":50,"wins":383},"GB2-07":{"draws":0,"losses":302,"wins":172},"GB2-08":{"draws":32,"losses":110,"wins":344}},"medium":{"GB2-01":{"draws":177,"losses":205,"wins":86},"GB2-02":{"draws":360,"losses":65,"wins":7},"GB2-03":{"draws":89,"losses":189,"wins":168},"GB2-04":{"draws":267,"losses":91,"wins":90},"GB2-05":{"draws":0,"losses":240,"wins":244},"GB2-06":{"draws":21,"losses":300,"wins":135},"GB2-07":{"draws":0,"losses":228,"wins":246},"GB2-08":{"draws":248,"losses":227,"wins":11}},"none":{"GB2-01":{"draws":256,"losses":121,"wins":91},"GB2-02":{"draws":355,"losses":70,"wins":7},"GB2-03":{"draws":83,"losses":215,"wins":148},"GB2-04":{"draws":292,"losses":109,"wins":47},"GB2-05":{"draws":0,"losses":312,"wins":172},"GB2-06":{"draws":21,"losses":119,"wins":316},"GB2-07":{"draws":0,"losses":328,"wins":146},"GB2-08":{"draws":223,"losses":209,"wins":54}}},"per_game_raw_elo_all":{"GB2-01":1371.863387900776,"GB2-02":1481.6205171724023,"GB2-03":1421.8556632852017,"GB2-04":1504.8720883938538,"GB2-05":1414.170261721432,"GB2-06":1715.6060164924572,"GB2-07":1347.9511684433244,"GB2-08":1417.9618466974232},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1284.447430149914,"GB2-02":1581.4417471116926,"GB2-03":1425.8027448593605,"GB2-04":1593.2113435854003,"GB2-05":1513.4508507073165,"GB2-06":2105.1393544558287,"GB2-07":1308.4318119674726,"GB2-08":1781.5732725498374},"medium":{"GB2-01":1370.0208112144937,"GB2-02":1433.9522753316842,"GB2-03":1442.7279897033336,"GB2-04":1487.1693573218072,"GB2-05":1460.8554884087262,"GB2-06":1217.2837923950283,"GB2-07":1497.1528789767397,"GB2-08":1202.9729000882176},"none":{"GB2-01":1461.12192233792,"GB2-02":1429.4675290738298,"GB2-03":1397.036255292911,"GB2-04":1434.2355642743532,"GB2-05":1268.2044460482537,"GB2-06":1824.3949026265147,"GB2-07":1238.2688143857604,"GB2-08":1269.3393674542144}},"per_game_tracks":{"highest":{"GB2-01":29.964740313617273,"GB2-02":63.10426044931666,"GB2-03":49.24688648743102,"GB2-04":64.18921667871949,"GB2-05":54.87884402711515,"GB2-06":86.31859296959385,"GB2-07":38.613557380767226,"GB2-08":75.02923782283995},"medium":{"GB2-01":38.297139526736814,"GB2-02":44.57759803665907,"GB2-03":51.15649082894886,"GB2-04":51.17757957609639,"GB2-05":50.69296543340539,"GB2-06":34.307531302188934,"GB2-07":53.71300927495108,"GB2-08":28.746821721794646},"none":{"GB2-01":47.747917439860004,"GB2-02":43.99634030996448,"GB2-03":45.9653517740317,"GB2-04":44.33232623367333,"GB2-05":35.653322025712676,"GB2-06":72.17060779741821,"GB2-07":33.16490309621053,"GB2-08":35.15899435850383}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T22:57:22Z","reasoning":{"highest":57.668167016175076,"medium":44.08364196259764,"none":44.773720379421846},"reasoning_agg":{"highest":{"max":86.31859296959385,"mean":57.668167016175076,"min":29.964740313617273},"medium":{"max":53.71300927495108,"mean":44.08364196259764,"min":28.746821721794646},"none":{"max":72.17060779741821,"mean":44.773720379421846,"min":33.16490309621053}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":13.584525053577437}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3:f253398d34d2d321","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.6877614000000001,"mean":0.46446825,"median":0.4896297,"min":0.2393742,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":3.715746},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.4398702,"mean":0.29041619999999996,"median":0.301782,"min":0.095232,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":16},"recorded_attempt_count":16,"run_count":8,"total":2.3233295999999997},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.1077678,"mean":0.076003275,"median":0.070269,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.6080262}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.4398702,"mean":0.29041619999999996,"median":0.301782,"min":0.095232,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":16},"recorded_attempt_count":16,"run_count":8,"total":2.3233296},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.1077678,"mean":0.076003275,"median":0.070269,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.6080262000000001},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.6877614000000001,"mean":0.46446825,"median":0.4896297,"min":0.2393742,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":3.715746}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.6877614000000001,"mean":0.27696257500000004,"median":0.2537256,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":35},"recorded_attempt_count":35,"run_count":24,"total":6.6471018000000015},"codegen_latency_ms":{"attempt_count":35,"max_ms":754602,"mean_ms":294629.0833333333,"min_ms":64944,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":415982,"mean_ms":310768.0,"min_ms":108461,"run_count":8},"medium":{"attempt_count":16,"max_ms":754602,"mean_ms":479215.25,"min_ms":119309,"run_count":8},"none":{"attempt_count":9,"max_ms":115016,"mean_ms":93904.0,"min_ms":64944,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":41670,"output_mean":16512.916666666668,"output_min":2237,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":41670,"output_mean":28939.0,"output_min":14510,"run_count":8},"medium":{"attempt_count":16,"output_max":27465,"output_mean":17219.125,"output_min":4345,"run_count":8},"none":{"attempt_count":9,"output_max":4534,"output_mean":3380.625,"output_min":2237,"run_count":8}},"display_name":"Kimi K3","economics":{"all":50.922754201072095,"highest":51.44557353947902,"medium":49.77311212450976,"none":51.63506845493232},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[262144],"finish_reason_observations":35,"finish_reasons":["length","stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":10,"provider_post_attempts":13,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":10,"requested_max_output_token_observations":10,"requested_max_output_tokens":[262144],"total_output_tokens":396310,"total_reasoning_output_tokens":285325,"total_visible_output_tokens":110985,"visible_token_observations":35},"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-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":42.62030828568442,"score":42.62030828568442},"GB2-02":{"attempts":3,"playable":42.59992651241634,"score":42.59992651241634},"GB2-03":{"attempts":3,"playable":64.85970272065144,"score":64.85970272065144},"GB2-04":{"attempts":3,"playable":49.34477318338515,"score":49.34477318338515},"GB2-05":{"attempts":3,"playable":56.82958533609749,"score":56.82958533609749},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":51.00331059468796,"score":34.002207063125304},"GB2-07":{"attempts":3,"playable":48.95556484169166,"score":48.95556484169166},"GB2-08":{"attempts":3,"playable":51.24941852757815,"score":51.24941852757815}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":6.404133826586545,"score":6.404133826586545},"GB2-02":{"attempts":1,"playable":43.29841864347721,"score":43.29841864347721},"GB2-03":{"attempts":1,"playable":77.34451242559989,"score":77.34451242559989},"GB2-04":{"attempts":1,"playable":53.413549747227506,"score":53.413549747227506},"GB2-05":{"attempts":1,"playable":62.40550919894259,"score":62.40550919894259},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":93.55325406983961,"score":93.55325406983961},"GB2-08":{"attempts":1,"playable":23.69963686467981,"score":23.69963686467981}},"medium":{"GB2-01":{"attempts":1,"playable":69.58197550460926,"score":69.58197550460926},"GB2-02":{"attempts":1,"playable":42.01774548023428,"score":42.01774548023428},"GB2-03":{"attempts":1,"playable":67.53745067607339,"score":67.53745067607339},"GB2-04":{"attempts":1,"playable":48.040077408044546,"score":48.040077408044546},"GB2-05":{"attempts":1,"playable":52.367419631871705,"score":52.367419631871705},"GB2-06":{"attempts":1,"playable":55.694067412401715,"score":55.694067412401715},"GB2-07":{"attempts":1,"playable":25.686787637593177,"score":25.686787637593177},"GB2-08":{"attempts":1,"playable":37.259373245250075,"score":37.259373245250075}},"none":{"GB2-01":{"attempts":1,"playable":51.874815525857464,"score":51.874815525857464},"GB2-02":{"attempts":1,"playable":42.4836154135375,"score":42.4836154135375},"GB2-03":{"attempts":1,"playable":49.69714506028106,"score":49.69714506028106},"GB2-04":{"attempts":1,"playable":46.580692394883414,"score":46.580692394883414},"GB2-05":{"attempts":1,"playable":55.715827177478175,"score":55.715827177478175},"GB2-06":{"attempts":1,"playable":46.312553776974205,"score":46.312553776974205},"GB2-07":{"attempts":1,"playable":27.626652817642196,"score":27.626652817642196},"GB2-08":{"attempts":1,"playable":92.78924547280458,"score":92.78924547280458}}},"id":"moonshotai/kimi-k3","is_recent_addition":false,"last_measured_at":"2026-10-20T11:22:04Z","match_totals_all":{"draws":2760,"losses":3967,"wins":3899},"match_totals_tracks":{"highest":{"draws":753,"losses":1228,"wins":1257},"medium":{"draws":1094,"losses":1367,"wins":1233},"none":{"draws":913,"losses":1372,"wins":1409}},"model_slug":"moonshotai-kimi-k3","overall":{"max":93.55325406983961,"mean":48.807685808828744,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":34,"overall_ranking_status":"ranked","per_game":{"GB2-01":6.404133826586545,"GB2-02":43.29841864347721,"GB2-03":77.34451242559989,"GB2-04":53.413549747227506,"GB2-05":62.40550919894259,"GB2-07":93.55325406983961,"GB2-08":23.69963686467981},"per_game_all":{"GB2-01":42.62030828568442,"GB2-02":42.59992651241634,"GB2-03":64.85970272065144,"GB2-04":49.34477318338515,"GB2-05":56.82958533609749,"GB2-07":48.95556484169166,"GB2-08":51.24941852757815},"per_game_match_totals_all":{"GB2-01":{"draws":338,"losses":647,"wins":419},"GB2-02":{"draws":975,"losses":273,"wins":48},"GB2-03":{"draws":184,"losses":418,"wins":736},"GB2-04":{"draws":740,"losses":328,"wins":276},"GB2-05":{"draws":0,"losses":632,"wins":820},"GB2-06":{"draws":62,"losses":434,"wins":416},"GB2-07":{"draws":0,"losses":745,"wins":677},"GB2-08":{"draws":461,"losses":490,"wins":507}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":437,"wins":23},"GB2-02":{"draws":307,"losses":97,"wins":28},"GB2-03":{"draws":31,"losses":96,"wins":319},"GB2-04":{"draws":227,"losses":101,"wins":120},"GB2-05":{"draws":0,"losses":184,"wins":300},"GB2-07":{"draws":0,"losses":28,"wins":446},"GB2-08":{"draws":180,"losses":285,"wins":21}},"medium":{"GB2-01":{"draws":83,"losses":104,"wins":281},"GB2-02":{"draws":326,"losses":93,"wins":13},"GB2-03":{"draws":65,"losses":126,"wins":255},"GB2-04":{"draws":305,"losses":86,"wins":57},"GB2-05":{"draws":0,"losses":232,"wins":252},"GB2-06":{"draws":34,"losses":193,"wins":229},"GB2-07":{"draws":0,"losses":363,"wins":111},"GB2-08":{"draws":281,"losses":170,"wins":35}},"none":{"GB2-01":{"draws":247,"losses":106,"wins":115},"GB2-02":{"draws":342,"losses":83,"wins":7},"GB2-03":{"draws":88,"losses":196,"wins":162},"GB2-04":{"draws":208,"losses":141,"wins":99},"GB2-05":{"draws":0,"losses":216,"wins":268},"GB2-06":{"draws":28,"losses":241,"wins":187},"GB2-07":{"draws":0,"losses":354,"wins":120},"GB2-08":{"draws":0,"losses":35,"wins":451}}},"per_game_raw_elo_all":{"GB2-01":1360.2178801962764,"GB2-02":1418.6621384266125,"GB2-03":1588.1405942225065,"GB2-04":1473.0385849741513,"GB2-05":1539.646628767803,"GB2-07":1550.4212146710436,"GB2-08":1559.304570971366},"per_game_raw_elo_tracks":{"highest":{"GB2-01":899.2838821828099,"GB2-02":1424.0744873329763,"GB2-03":1731.1373617755578,"GB2-04":1504.6376910899507,"GB2-05":1613.0395000745293,"GB2-07":2353.9729742678555,"GB2-08":1147.192364418202},"medium":{"GB2-01":1680.866666195846,"GB2-02":1414.1478441779848,"GB2-03":1603.5064599220082,"GB2-04":1462.87171549051,"GB2-05":1481.7784194934934,"GB2-06":1543.9957422795626,"GB2-07":1134.6163034813717,"GB2-08":1290.6223520916576},"none":{"GB2-01":1500.5030922101732,"GB2-02":1417.764083768876,"GB2-03":1429.7779609699537,"GB2-04":1451.6063483419928,"GB2-05":1524.1219667353855,"GB2-06":1398.283025251779,"GB2-07":1162.6743662639035,"GB2-08":2240.0989964042383}},"per_game_tracks":{"highest":{"GB2-01":6.404133826586545,"GB2-02":43.29841864347721,"GB2-03":77.34451242559989,"GB2-04":53.413549747227506,"GB2-05":62.40550919894259,"GB2-07":93.55325406983961,"GB2-08":23.69963686467981},"medium":{"GB2-01":69.58197550460926,"GB2-02":42.01774548023428,"GB2-03":67.53745067607339,"GB2-04":48.040077408044546,"GB2-05":52.367419631871705,"GB2-06":55.694067412401715,"GB2-07":25.686787637593177,"GB2-08":37.259373245250075},"none":{"GB2-01":51.874815525857464,"GB2-02":42.4836154135375,"GB2-03":49.69714506028106,"GB2-04":46.580692394883414,"GB2-05":55.715827177478175,"GB2-06":46.312553776974205,"GB2-07":27.626652817642196,"GB2-08":92.78924547280458}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:55:39Z","reasoning":{"highest":45.01487684704414,"medium":49.77311212450976,"none":51.63506845493232},"reasoning_agg":{"highest":{"max":93.55325406983961,"mean":45.01487684704414,"min":0.0},"medium":{"max":69.58197550460926,"mean":49.77311212450976,"min":25.686787637593177},"none":{"max":92.78924547280458,"mean":51.63506845493232,"min":27.626652817642196}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":6.620191607888181}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-5:b25498cf4a1e2d4f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":17},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.512955,"mean":0.43048093750000005,"median":0.4308725,"min":0.32672249999999997,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8,"boardgame-list-prices-2026-10-09":9},"run_count":16,"token_priced_attempt_count":17,"total":6.887695000000001},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.266665,"mean":0.20888499999999996,"median":0.20905875000000002,"min":0.14104,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8,"boardgame-list-prices-2026-10-09":8},"run_count":16,"token_priced_attempt_count":16,"total":3.34216},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.9739300000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"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":1.42452},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.9739300000000001},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"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":4.709264999999999},"historical-thinking-budget-setting":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":17},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.30059250000000004,"mean":0.256004375,"median":0.25514000000000003,"min":0.2090225,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":17},"run_count":16,"token_priced_attempt_count":17,"total":4.09607}},"codegen_cost_usd":{"admitted_cell_count":39,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":41},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.512955,"mean":0.2537023958333333,"median":0.20905875000000002,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":16,"boardgame-list-prices-2026-10-09":25},"run_count":40,"token_priced_attempt_count":41,"total":11.203784999999998},"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":50.02625226471754,"highest":50.15588367827256,"medium":52.20129103301632,"none":47.72158208286376},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":5,"playable":47.07687240044158,"score":47.07687240044158},"GB2-02":{"attempts":5,"playable":44.093176928685146,"score":44.093176928685146},"GB2-03":{"attempts":4,"playable":47.326754345005185,"score":47.326754345005185},"GB2-04":{"attempts":5,"playable":43.633212609573924,"score":43.633212609573924},"GB2-05":{"attempts":5,"playable":46.36903374840015,"score":46.36903374840015},"GB2-06":{"attempts":5,"playable":47.93706355381226,"score":47.93706355381226},"GB2-07":{"attempts":5,"playable":45.622852864033696,"score":45.622852864033696},"GB2-08":{"attempts":5,"playable":67.45975426357728,"score":67.45975426357728}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":50.10947726073738,"score":50.10947726073738},"GB2-02":{"attempts":2,"playable":43.821887849426815,"score":43.821887849426815},"GB2-03":{"attempts":1,"playable":49.80961952189805,"score":49.80961952189805},"GB2-04":{"attempts":2,"playable":41.12207427063058,"score":41.12207427063058},"GB2-05":{"attempts":2,"playable":47.55489801989091,"score":47.55489801989091},"GB2-06":{"attempts":2,"playable":51.2211971324097,"score":51.2211971324097},"GB2-07":{"attempts":2,"playable":55.39239470322069,"score":55.39239470322069},"GB2-08":{"attempts":2,"playable":57.45267271469531,"score":57.45267271469531}},"medium":{"GB2-01":{"attempts":2,"playable":47.18990801296199,"score":47.18990801296199},"GB2-02":{"attempts":2,"playable":43.88004489996955,"score":43.88004489996955},"GB2-03":{"attempts":2,"playable":49.86092606317697,"score":49.86092606317697},"GB2-04":{"attempts":2,"playable":41.17662907629388,"score":41.17662907629388},"GB2-05":{"attempts":2,"playable":44.626172727915886,"score":44.626172727915886},"GB2-06":{"attempts":2,"playable":47.33588873973642,"score":47.33588873973642},"GB2-07":{"attempts":2,"playable":49.36905381853366,"score":49.36905381853366},"GB2-08":{"attempts":2,"playable":66.86066066617977,"score":66.86066066617977}},"none":{"GB2-01":{"attempts":1,"playable":43.93123192762538,"score":43.93123192762538},"GB2-02":{"attempts":1,"playable":44.57759803665907,"score":44.57759803665907},"GB2-03":{"attempts":1,"playable":42.30971744994054,"score":42.30971744994054},"GB2-04":{"attempts":1,"playable":48.60093448179732,"score":48.60093448179732},"GB2-05":{"attempts":1,"playable":46.92603049739365,"score":46.92603049739365},"GB2-06":{"attempts":1,"playable":45.25410478929066,"score":45.25410478929066},"GB2-07":{"attempts":1,"playable":32.10711007034676,"score":32.10711007034676},"GB2-08":{"attempts":1,"playable":78.06592940985675,"score":78.06592940985675}}},"id":"claude-opus-4-5","is_recent_addition":false,"last_measured_at":"2026-10-20T11:39:05Z","match_totals_all":{"draws":2994,"losses":4190,"wins":3898},"match_totals_tracks":{"highest":{"draws":1000,"losses":1394,"wins":1300},"medium":{"draws":932,"losses":1345,"wins":1417},"none":{"draws":1062,"losses":1451,"wins":1181}},"model_slug":"claude-opus-4-5","overall":{"max":78.06592940985675,"mean":48.68984008919116,"min":32.10711007034676},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":35,"overall_ranking_status":"ranked","per_game":{"GB2-01":73.15227521117475,"GB2-02":43.64743538888916,"GB2-03":49.80961952189805,"GB2-04":41.51674379958626,"GB2-05":51.32088668051307,"GB2-06":55.07515682860483,"GB2-07":49.88553597598052,"GB2-08":36.83941601953388},"per_game_all":{"GB2-01":58.325905431192325,"GB2-02":44.0737912451709,"GB2-03":46.70834823177332,"GB2-04":44.554067413941226,"GB2-05":48.460724282210805,"GB2-06":50.696612637091,"GB2-07":42.741117487354444,"GB2-08":64.64945138900634},"per_game_match_totals_all":{"GB2-01":{"draws":389,"losses":402,"wins":613},"GB2-02":{"draws":1025,"losses":229,"wins":42},"GB2-03":{"draws":361,"losses":579,"wins":398},"GB2-04":{"draws":854,"losses":335,"wins":155},"GB2-05":{"draws":0,"losses":752,"wins":700},"GB2-06":{"draws":78,"losses":663,"wins":627},"GB2-07":{"draws":0,"losses":845,"wins":577},"GB2-08":{"draws":287,"losses":385,"wins":786}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":55,"losses":101,"wins":312},"GB2-02":{"draws":350,"losses":74,"wins":8},"GB2-03":{"draws":67,"losses":206,"wins":173},"GB2-04":{"draws":253,"losses":141,"wins":54},"GB2-05":{"draws":0,"losses":237,"wins":247},"GB2-06":{"draws":32,"losses":197,"wins":227},"GB2-07":{"draws":0,"losses":247,"wins":227},"GB2-08":{"draws":243,"losses":191,"wins":52}},"medium":{"GB2-01":{"draws":118,"losses":142,"wins":208},"GB2-02":{"draws":339,"losses":78,"wins":15},"GB2-03":{"draws":133,"losses":181,"wins":132},"GB2-04":{"draws":309,"losses":104,"wins":35},"GB2-05":{"draws":0,"losses":257,"wins":227},"GB2-06":{"draws":30,"losses":214,"wins":212},"GB2-07":{"draws":0,"losses":265,"wins":209},"GB2-08":{"draws":3,"losses":104,"wins":379}},"none":{"GB2-01":{"draws":216,"losses":159,"wins":93},"GB2-02":{"draws":336,"losses":77,"wins":19},"GB2-03":{"draws":161,"losses":192,"wins":93},"GB2-04":{"draws":292,"losses":90,"wins":66},"GB2-05":{"draws":0,"losses":258,"wins":226},"GB2-06":{"draws":16,"losses":252,"wins":188},"GB2-07":{"draws":0,"losses":333,"wins":141},"GB2-08":{"draws":41,"losses":90,"wins":355}}},"per_game_raw_elo_all":{"GB2-01":1568.6677047739447,"GB2-02":1430.0641617562096,"GB2-03":1403.610262390005,"GB2-04":1435.897670766145,"GB2-05":1433.0608861145245,"GB2-06":1466.1454728658582,"GB2-07":1358.910746487518,"GB2-08":1663.5163929070113},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1722.488560430691,"GB2-02":1426.772680863115,"GB2-03":1430.772349799,"GB2-04":1412.3556741604834,"GB2-05":1468.6894762297427,"GB2-06":1534.1585968692557,"GB2-07":1448.988906026532,"GB2-08":1286.3724330913753},"medium":{"GB2-01":1558.835287990106,"GB2-02":1429.4675290738298,"GB2-03":1414.8854949221086,"GB2-04":1428.1331374660363,"GB2-05":1416.551325680638,"GB2-06":1482.1016396980042,"GB2-07":1403.4985221319878,"GB2-08":1862.2941704509108},"none":{"GB2-01":1424.679265901037,"GB2-02":1433.9522753316842,"GB2-03":1365.172942448906,"GB2-04":1467.2042006719155,"GB2-05":1413.9418564331927,"GB2-06":1382.1761820303143,"GB2-07":1224.2448113040346,"GB2-08":1841.882575178748}},"per_game_tracks":{"highest":{"GB2-01":73.15227521117475,"GB2-02":43.64743538888916,"GB2-03":49.80961952189805,"GB2-04":41.51674379958626,"GB2-05":51.32088668051307,"GB2-06":55.07515682860483,"GB2-07":49.88553597598052,"GB2-08":36.83941601953388},"medium":{"GB2-01":57.894209154776846,"GB2-02":43.99634030996448,"GB2-03":48.00570772348137,"GB2-04":43.544523960440095,"GB2-05":47.13525566872569,"GB2-06":51.760576293377525,"GB2-07":46.23070641573607,"GB2-08":79.04300873762841},"none":{"GB2-01":43.93123192762538,"GB2-02":44.57759803665907,"GB2-03":42.30971744994054,"GB2-04":48.60093448179732,"GB2-05":46.92603049739365,"GB2-06":45.25410478929066,"GB2-07":32.10711007034676,"GB2-08":78.06592940985675}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:29:54Z","reasoning":{"highest":49.56052768411368,"medium":48.787410500596025,"none":47.72158208286376},"reasoning_agg":{"highest":{"max":57.45267271469531,"mean":49.56052768411368,"min":41.12207427063058},"medium":{"max":66.86066066617977,"mean":48.787410500596025,"min":41.17662907629388},"none":{"max":78.06592940985675,"mean":47.72158208286376,"min":32.10711007034676}},"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":{"reasoning_variance":1.8389456012499181}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5:8583d72c67ca4ec4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.35099375,"median":0.321349,"min":0.220732,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.8079499999999995},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.08884,"mean":0.06562375000000001,"median":0.062855,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5249900000000001},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.07847,"mean":0.06167125,"median":0.061313,"min":0.051588,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.49337}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.08884,"mean":0.06562375000000001,"median":0.062855,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5249900000000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.07847,"mean":0.06167125,"median":0.061313,"min":0.051588,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.49337000000000003},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.35099375,"median":0.321349,"min":0.220732,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.8079499999999995}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.15942958333333332,"median":0.068377,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":3.826309999999999},"codegen_output_tokens":{"attempt_count":24,"output_max":47973,"output_mean":13430.583333333334,"output_min":2639,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":47973,"output_mean":32587.0,"output_min":19731,"run_count":8},"medium":{"attempt_count":8,"output_max":5918,"output_mean":4050.0,"output_min":2639,"run_count":8},"none":{"attempt_count":8,"output_max":4635,"output_mean":3654.75,"output_min":2807,"run_count":8}},"display_name":"Claude Sonnet 5","economics":{"all":48.038572872656864,"highest":56.62982199550634,"medium":43.8398560190796,"none":43.64604060338464},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":24,"effective_max_output_tokens":[128000],"finish_reason_observations":24,"finish_reasons":["end_turn"],"indexed_attempts":24,"output_token_observations":24,"provider_post_attempt_observations":24,"provider_post_attempts":24,"reasoning_token_observations":24,"reconciliation_get_attempt_observations":24,"requested_max_output_token_observations":24,"requested_max_output_tokens":[128000],"total_output_tokens":322334,"total_reasoning_output_tokens":243107,"total_visible_output_tokens":79227,"visible_token_observations":24},"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-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":53.237373170042396,"score":53.237373170042396},"GB2-02":{"attempts":3,"playable":43.026588278541176,"score":43.026588278541176},"GB2-03":{"attempts":3,"playable":52.776947697945786,"score":52.776947697945786},"GB2-04":{"attempts":3,"playable":47.24555374903605,"score":47.24555374903605},"GB2-05":{"attempts":3,"playable":40.506563225845234,"score":40.506563225845234},"GB2-06":{"attempts":3,"playable":38.97001724246144,"score":38.97001724246144},"GB2-07":{"attempts":3,"playable":51.13170050333857,"score":51.13170050333857},"GB2-08":{"attempts":3,"playable":57.413839114044265,"score":57.413839114044265}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":64.2173388084373,"score":64.2173388084373},"GB2-02":{"attempts":1,"playable":42.01774548023428,"score":42.01774548023428},"GB2-03":{"attempts":1,"playable":60.109059106806285,"score":60.109059106806285},"GB2-04":{"attempts":1,"playable":53.86020995550423,"score":53.86020995550423},"GB2-05":{"attempts":1,"playable":55.29734874817114,"score":55.29734874817114},"GB2-06":{"attempts":1,"playable":28.803691637114987,"score":28.803691637114987},"GB2-07":{"attempts":1,"playable":67.6407109287227,"score":67.6407109287227},"GB2-08":{"attempts":1,"playable":81.09247129905982,"score":81.09247129905982}},"medium":{"GB2-01":{"attempts":1,"playable":46.26453886832805,"score":46.26453886832805},"GB2-02":{"attempts":1,"playable":43.99634030996448,"score":43.99634030996448},"GB2-03":{"attempts":1,"playable":41.620283286326895,"score":41.620283286326895},"GB2-04":{"attempts":1,"playable":44.78229823545388,"score":44.78229823545388},"GB2-05":{"attempts":1,"playable":43.161847731589596,"score":43.161847731589596},"GB2-06":{"attempts":1,"playable":39.8979422444374,"score":39.8979422444374},"GB2-07":{"attempts":1,"playable":50.69375106673961,"score":50.69375106673961},"GB2-08":{"attempts":1,"playable":40.301846409796916,"score":40.301846409796916}},"none":{"GB2-01":{"attempts":1,"playable":49.23024183336186,"score":49.23024183336186},"GB2-02":{"attempts":1,"playable":43.06567904542477,"score":43.06567904542477},"GB2-03":{"attempts":1,"playable":56.601500700704165,"score":56.601500700704165},"GB2-04":{"attempts":1,"playable":43.09415305615002,"score":43.09415305615002},"GB2-05":{"attempts":1,"playable":23.060493197774957,"score":23.060493197774957},"GB2-06":{"attempts":1,"playable":48.20841784583191,"score":48.20841784583191},"GB2-07":{"attempts":1,"playable":35.06063951455339,"score":35.06063951455339},"GB2-08":{"attempts":1,"playable":50.84719963327608,"score":50.84719963327608}}},"id":"claude-sonnet-5","is_recent_addition":false,"last_measured_at":"2026-10-20T11:20:03Z","match_totals_all":{"draws":2878,"losses":4478,"wins":3726},"match_totals_tracks":{"highest":{"draws":755,"losses":1261,"wins":1678},"medium":{"draws":1118,"losses":1573,"wins":1003},"none":{"draws":1005,"losses":1644,"wins":1045}},"model_slug":"claude-sonnet-5","overall":{"max":81.09247129905982,"mean":48.03857287265686,"min":23.060493197774957},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":36,"overall_ranking_status":"ranked","per_game":{"GB2-01":64.2173388084373,"GB2-02":42.01774548023428,"GB2-03":60.109059106806285,"GB2-04":53.86020995550423,"GB2-05":55.29734874817114,"GB2-06":28.803691637114987,"GB2-07":67.6407109287227,"GB2-08":81.09247129905982},"per_game_all":{"GB2-01":53.237373170042396,"GB2-02":43.026588278541176,"GB2-03":52.776947697945786,"GB2-04":47.24555374903605,"GB2-05":40.506563225845234,"GB2-06":38.97001724246144,"GB2-07":51.13170050333857,"GB2-08":57.413839114044265},"per_game_match_totals_all":{"GB2-01":{"draws":220,"losses":559,"wins":625},"GB2-02":{"draws":1032,"losses":239,"wins":25},"GB2-03":{"draws":295,"losses":530,"wins":513},"GB2-04":{"draws":828,"losses":312,"wins":204},"GB2-05":{"draws":0,"losses":867,"wins":585},"GB2-06":{"draws":52,"losses":840,"wins":476},"GB2-07":{"draws":0,"losses":720,"wins":702},"GB2-08":{"draws":451,"losses":411,"wins":596}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":50,"losses":146,"wins":272},"GB2-02":{"draws":338,"losses":87,"wins":7},"GB2-03":{"draws":94,"losses":146,"wins":206},"GB2-04":{"draws":253,"losses":86,"wins":109},"GB2-05":{"draws":0,"losses":218,"wins":266},"GB2-06":{"draws":16,"losses":327,"wins":113},"GB2-07":{"draws":0,"losses":158,"wins":316},"GB2-08":{"draws":4,"losses":93,"wins":389}},"medium":{"GB2-01":{"draws":92,"losses":210,"wins":166},"GB2-02":{"draws":355,"losses":70,"wins":7},"GB2-03":{"draws":111,"losses":220,"wins":115},"GB2-04":{"draws":282,"losses":112,"wins":54},"GB2-05":{"draws":0,"losses":276,"wins":208},"GB2-06":{"draws":18,"losses":276,"wins":162},"GB2-07":{"draws":0,"losses":243,"wins":231},"GB2-08":{"draws":260,"losses":166,"wins":60}},"none":{"GB2-01":{"draws":78,"losses":203,"wins":187},"GB2-02":{"draws":339,"losses":82,"wins":11},"GB2-03":{"draws":90,"losses":164,"wins":192},"GB2-04":{"draws":293,"losses":114,"wins":41},"GB2-05":{"draws":0,"losses":373,"wins":111},"GB2-06":{"draws":18,"losses":237,"wins":201},"GB2-07":{"draws":0,"losses":319,"wins":155},"GB2-08":{"draws":187,"losses":152,"wins":147}}},"per_game_raw_elo_all":{"GB2-01":1515.0058868179683,"GB2-02":1421.9630218463344,"GB2-03":1459.107524968902,"GB2-04":1456.8349605774329,"GB2-05":1320.8981929368558,"GB2-06":1287.6467425707795,"GB2-07":1469.0219936570804,"GB2-08":1553.5861752540188},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1622.7883705090753,"GB2-02":1414.1478441779848,"GB2-03":1525.843984023825,"GB2-04":1508.149905521151,"GB2-05":1518.7779061188305,"GB2-06":1134.4601932791065,"GB2-07":1684.937678680947,"GB2-08":1906.8457589309073},"medium":{"GB2-01":1446.982058943041,"GB2-02":1429.4675290738298,"GB2-03":1359.1556420111306,"GB2-04":1437.7163170898555,"GB2-05":1366.6558661774443,"GB2-06":1301.2220147154699,"GB2-07":1459.0997390226867,"GB2-08":1321.4380361127508},"none":{"GB2-01":1475.2472310017888,"GB2-02":1422.2736922871886,"GB2-03":1492.3229488717511,"GB2-04":1424.6386591212924,"GB2-05":1077.2608065142927,"GB2-06":1427.2580197177622,"GB2-07":1263.0285632676082,"GB2-08":1432.474730718399}},"per_game_tracks":{"highest":{"GB2-01":64.2173388084373,"GB2-02":42.01774548023428,"GB2-03":60.109059106806285,"GB2-04":53.86020995550423,"GB2-05":55.29734874817114,"GB2-06":28.803691637114987,"GB2-07":67.6407109287227,"GB2-08":81.09247129905982},"medium":{"GB2-01":46.26453886832805,"GB2-02":43.99634030996448,"GB2-03":41.620283286326895,"GB2-04":44.78229823545388,"GB2-05":43.161847731589596,"GB2-06":39.8979422444374,"GB2-07":50.69375106673961,"GB2-08":40.301846409796916},"none":{"GB2-01":49.23024183336186,"GB2-02":43.06567904542477,"GB2-03":56.601500700704165,"GB2-04":43.09415305615002,"GB2-05":23.060493197774957,"GB2-06":48.20841784583191,"GB2-07":35.06063951455339,"GB2-08":50.84719963327608}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T22:53:55Z","reasoning":{"highest":56.62982199550634,"medium":43.8398560190796,"none":43.64604060338464},"reasoning_agg":{"highest":{"max":81.09247129905982,"mean":56.62982199550634,"min":28.803691637114987},"medium":{"max":50.69375106673961,"mean":43.8398560190796,"min":39.8979422444374},"none":{"max":56.601500700704165,"mean":43.64604060338464,"min":23.060493197774957}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":12.9837813921217}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-terra:3102bc1eaa5e56ef","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.45800250000000003,"mean":0.38340421874999997,"median":0.38428625,"min":0.302056875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.06723375},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.146648125,"mean":0.09696234375000001,"median":0.09060875000000002,"min":0.083821875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.7756987499999999},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.136415,"mean":0.07671781250000001,"median":0.0705246875,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6137425}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.146648125,"mean":0.09696234375000001,"median":0.09060875000000002,"min":0.083821875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.7756987499999999},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.136415,"mean":0.07671781250000001,"median":0.0705246875,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6137425000000001},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.45800250000000003,"mean":0.38340421874999997,"median":0.38428625,"min":0.302056875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.0672337499999998}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.45800250000000003,"mean":0.18569479166666666,"median":0.091314375,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":28},"run_count":24,"token_priced_attempt_count":28,"total":4.456675000000001},"codegen_output_tokens":{"attempt_count":28,"output_max":28998,"output_mean":10500.666666666666,"output_min":2419,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":28998,"output_mean":23512.0,"output_min":18631,"run_count":8},"medium":{"attempt_count":9,"output_max":6917,"output_mean":4677.5,"output_min":3936,"run_count":8},"none":{"attempt_count":9,"output_max":6065,"output_mean":3312.5,"output_min":2419,"run_count":8}},"display_name":"GPT-5.6 Terra","economics":{"all":48.414700621599,"highest":54.47650160025032,"medium":50.46743483268853,"none":41.37641280472268},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"total_output_tokens":252016,"total_reasoning_output_tokens":152800,"total_visible_output_tokens":99216,"visible_token_observations":28},"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-5.6-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-05"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":68.02245511786872,"score":68.02245511786872},"GB2-02":{"attempts":3,"playable":49.769407425997606,"score":49.769407425997606},"GB2-03":{"attempts":3,"playable":34.80741888711343,"score":34.80741888711343},"GB2-04":{"attempts":3,"playable":43.84448173624176,"score":43.84448173624176},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":56.23883402149532,"score":37.49255601433021},"GB2-06":{"attempts":3,"playable":52.33572172648409,"score":52.33572172648409},"GB2-07":{"attempts":3,"playable":45.14614055810827,"score":45.14614055810827},"GB2-08":{"attempts":3,"playable":44.977278899379115,"score":44.977278899379115}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":71.68284700913938,"score":71.68284700913938},"GB2-02":{"attempts":1,"playable":59.3398990024055,"score":59.3398990024055},"GB2-03":{"attempts":1,"playable":37.92217387510583,"score":37.92217387510583},"GB2-04":{"attempts":1,"playable":43.09415305615002,"score":43.09415305615002},"GB2-05":{"attempts":1,"playable":55.506591423978314,"score":55.506591423978314},"GB2-06":{"attempts":1,"playable":79.60302371557374,"score":79.60302371557374},"GB2-07":{"attempts":1,"playable":44.80092078992667,"score":44.80092078992667},"GB2-08":{"attempts":1,"playable":43.86240392972311,"score":43.86240392972311}},"medium":{"GB2-01":{"attempts":1,"playable":77.76236875722358,"score":77.76236875722358},"GB2-02":{"attempts":1,"playable":45.50695161028554,"score":45.50695161028554},"GB2-03":{"attempts":1,"playable":33.132558435116685,"score":33.132558435116685},"GB2-04":{"attempts":1,"playable":43.544523960440095,"score":43.544523960440095},"GB2-05":{"attempts":1,"playable":56.97107661901234,"score":56.97107661901234},"GB2-06":{"attempts":1,"playable":39.5728496232157,"score":39.5728496232157},"GB2-07":{"attempts":1,"playable":61.296631884081854,"score":61.296631884081854},"GB2-08":{"attempts":1,"playable":45.95251777213249,"score":45.95251777213249}},"none":{"GB2-01":{"attempts":1,"playable":54.622149587243165,"score":54.622149587243165},"GB2-02":{"attempts":1,"playable":44.46137166530179,"score":44.46137166530179},"GB2-03":{"attempts":1,"playable":33.36752435111778,"score":33.36752435111778},"GB2-04":{"attempts":1,"playable":44.89476819213515,"score":44.89476819213515},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":37.83129184066284,"score":37.83129184066284},"GB2-07":{"attempts":1,"playable":29.34086900031628,"score":29.34086900031628},"GB2-08":{"attempts":1,"playable":45.11691499628175,"score":45.11691499628175}}},"id":"gpt-5.6-terra","is_recent_addition":false,"last_measured_at":"2026-10-20T11:37:59Z","match_totals_all":{"draws":3143,"losses":3971,"wins":3484},"match_totals_tracks":{"highest":{"draws":946,"losses":1257,"wins":1491},"medium":{"draws":977,"losses":1385,"wins":1332},"none":{"draws":1220,"losses":1329,"wins":661}},"model_slug":"gpt-5-6-terra","overall":{"max":79.60302371557374,"mean":47.0494325456904,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":37,"overall_ranking_status":"ranked","per_game":{"GB2-01":71.68284700913938,"GB2-02":59.3398990024055,"GB2-03":37.92217387510583,"GB2-04":43.09415305615002,"GB2-05":55.506591423978314,"GB2-06":79.60302371557374,"GB2-07":44.80092078992667,"GB2-08":43.86240392972311},"per_game_all":{"GB2-01":68.02245511786872,"GB2-02":49.769407425997606,"GB2-03":34.80741888711343,"GB2-04":43.84448173624176,"GB2-06":52.33572172648409,"GB2-07":45.14614055810827,"GB2-08":44.977278899379115},"per_game_match_totals_all":{"GB2-01":{"draws":219,"losses":349,"wins":836},"GB2-02":{"draws":945,"losses":195,"wins":156},"GB2-03":{"draws":497,"losses":666,"wins":175},"GB2-04":{"draws":829,"losses":357,"wins":158},"GB2-05":{"draws":0,"losses":427,"wins":541},"GB2-06":{"draws":87,"losses":631,"wins":650},"GB2-07":{"draws":0,"losses":808,"wins":614},"GB2-08":{"draws":566,"losses":538,"wins":354}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":63,"losses":104,"wins":301},"GB2-02":{"draws":244,"losses":59,"wins":129},"GB2-03":{"draws":143,"losses":220,"wins":83},"GB2-04":{"draws":295,"losses":113,"wins":40},"GB2-05":{"draws":0,"losses":217,"wins":267},"GB2-06":{"draws":35,"losses":76,"wins":345},"GB2-07":{"draws":0,"losses":272,"wins":202},"GB2-08":{"draws":166,"losses":196,"wins":124}},"medium":{"GB2-01":{"draws":3,"losses":105,"wins":360},"GB2-02":{"draws":342,"losses":70,"wins":20},"GB2-03":{"draws":194,"losses":215,"wins":37},"GB2-04":{"draws":235,"losses":141,"wins":72},"GB2-05":{"draws":0,"losses":210,"wins":274},"GB2-06":{"draws":51,"losses":261,"wins":144},"GB2-07":{"draws":0,"losses":190,"wins":284},"GB2-08":{"draws":152,"losses":193,"wins":141}},"none":{"GB2-01":{"draws":153,"losses":140,"wins":175},"GB2-02":{"draws":359,"losses":66,"wins":7},"GB2-03":{"draws":160,"losses":231,"wins":55},"GB2-04":{"draws":299,"losses":103,"wins":46},"GB2-06":{"draws":1,"losses":294,"wins":161},"GB2-07":{"draws":0,"losses":346,"wins":128},"GB2-08":{"draws":248,"losses":149,"wins":89}}},"per_game_raw_elo_all":{"GB2-01":1671.1083147466354,"GB2-02":1474.6440469401189,"GB2-03":1298.5899549031658,"GB2-04":1430.4525576535486,"GB2-06":1510.2017855924817,"GB2-07":1389.4866756233587,"GB2-08":1369.4789427428666},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1705.0076019196363,"GB2-02":1549.7628034822194,"GB2-03":1326.6601463376599,"GB2-04":1424.6386591212924,"GB2-05":1521.4477333848008,"GB2-06":1964.1187528728399,"GB2-07":1385.7466801075796,"GB2-08":1357.8779785529446},"medium":{"GB2-01":1781.391064934977,"GB2-02":1441.113392927429,"GB2-03":1283.4739034973695,"GB2-04":1428.1331374660363,"GB2-05":1540.2687630819958,"GB2-06":1296.3306507517777,"GB2-07":1596.0115126312962,"GB2-08":1379.6543559398544},"none":{"GB2-01":1526.926277385293,"GB2-02":1433.0559444107084,"GB2-03":1285.6358148744685,"GB2-04":1438.5858763733165,"GB2-06":1270.1559531528271,"GB2-07":1186.701834131201,"GB2-08":1370.9044937358003}},"per_game_tracks":{"highest":{"GB2-01":71.68284700913938,"GB2-02":59.3398990024055,"GB2-03":37.92217387510583,"GB2-04":43.09415305615002,"GB2-05":55.506591423978314,"GB2-06":79.60302371557374,"GB2-07":44.80092078992667,"GB2-08":43.86240392972311},"medium":{"GB2-01":77.76236875722358,"GB2-02":45.50695161028554,"GB2-03":33.132558435116685,"GB2-04":43.544523960440095,"GB2-05":56.97107661901234,"GB2-06":39.5728496232157,"GB2-07":61.296631884081854,"GB2-08":45.95251777213249},"none":{"GB2-01":54.622149587243165,"GB2-02":44.46137166530179,"GB2-03":33.36752435111778,"GB2-04":44.89476819213515,"GB2-06":37.83129184066284,"GB2-07":29.34086900031628,"GB2-08":45.11691499628175}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-14T17:24:56Z","reasoning":{"highest":54.47650160025032,"medium":50.46743483268853,"none":36.20436120413235},"reasoning_agg":{"highest":{"max":79.60302371557374,"mean":54.47650160025032,"min":37.92217387510583},"medium":{"max":77.76236875722358,"mean":50.46743483268853,"min":33.132558435116685},"none":{"max":54.622149587243165,"mean":36.20436120413235,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":18.272140396117976}},{"canonical_public_row_identity":"publication-row.v1:overall:gemini-3-1-pro-preview:aa95c9efa1088490","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.46894399999999997,"mean":0.3240465,"median":0.32247400000000004,"min":0.095864,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.5923720000000006},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.10957599999999999,"mean":0.08025825,"median":0.080065,"min":0.052756,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.6420659999999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.06018799999999999,"mean":0.04587999999999999,"median":0.044081999999999996,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.36704}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.10957599999999999,"mean":0.08025825,"median":0.080065,"min":0.052756,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.6420659999999999},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.06018799999999999,"mean":0.04587999999999999,"median":0.044081999999999996,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.36704000000000003},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.46894399999999997,"mean":0.3240465,"median":0.32247400000000004,"min":0.095864,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.592372}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.46894399999999997,"mean":0.15006158333333333,"median":0.080065,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"run_count":24,"token_priced_attempt_count":28,"total":3.601478},"codegen_latency_ms":{"attempt_count":28,"max_ms":255692,"mean_ms":76920.70833333333,"min_ms":12384,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":255692,"mean_ms":175619.75,"min_ms":52003,"run_count":8},"medium":{"attempt_count":8,"max_ms":58005,"mean_ms":37933.625,"min_ms":21700,"run_count":8},"none":{"attempt_count":9,"max_ms":20748,"mean_ms":17208.75,"min_ms":12384,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":36035,"output_mean":10826.541666666666,"output_min":1554,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":36035,"output_mean":24993.125,"output_min":6631,"run_count":8},"medium":{"attempt_count":8,"output_max":7812,"output_mean":5238.375,"output_min":2903,"run_count":8},"none":{"attempt_count":9,"output_max":3115,"output_mean":2248.125,"output_min":1554,"run_count":8}},"display_name":"Gemini 3.1 Pro Preview","economics":{"all":46.468661358203924,"highest":66.1424077873,"medium":42.854278097330536,"none":30.40929818998127},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[65536],"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"requested_max_output_token_observations":28,"requested_max_output_tokens":[65536],"total_output_tokens":259837,"total_reasoning_output_tokens":197903,"total_visible_output_tokens":61934,"visible_token_observations":28},"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":65536,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"gemini-3.1-pro-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"google","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":50.224552623274896,"score":50.224552623274896},"GB2-02":{"attempts":3,"playable":43.49205578790016,"score":43.49205578790016},"GB2-03":{"attempts":3,"playable":54.430741775180934,"score":54.430741775180934},"GB2-04":{"attempts":3,"playable":56.768160801281006,"score":56.768160801281006},"GB2-05":{"attempts":3,"playable":39.48692748899275,"score":39.48692748899275},"GB2-06":{"attempts":3,"playable":20.90667365614851,"score":20.90667365614851},"GB2-07":{"attempts":3,"playable":56.39863808643506,"score":56.39863808643506},"GB2-08":{"attempts":3,"playable":50.04154064641815,"score":50.04154064641815}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":74.7254143109904,"score":74.7254143109904},"GB2-02":{"attempts":1,"playable":42.832890281616656,"score":42.832890281616656},"GB2-03":{"attempts":1,"playable":67.21840820109549,"score":67.21840820109549},"GB2-04":{"attempts":1,"playable":81.41746705727853,"score":81.41746705727853},"GB2-05":{"attempts":1,"playable":85.16302198502669,"score":85.16302198502669},"GB2-06":{"attempts":1,"playable":19.091799332456365,"score":19.091799332456365},"GB2-07":{"attempts":1,"playable":74.57528651068932,"score":74.57528651068932},"GB2-08":{"attempts":1,"playable":84.11497461924645,"score":84.11497461924645}},"medium":{"GB2-01":{"attempts":1,"playable":34.7784723804558,"score":34.7784723804558},"GB2-02":{"attempts":1,"playable":44.57759803665907,"score":44.57759803665907},"GB2-03":{"attempts":1,"playable":67.43114366760072,"score":67.43114366760072},"GB2-04":{"attempts":1,"playable":46.356025853704054,"score":46.356025853704054},"GB2-05":{"attempts":1,"playable":17.5607518555301,"score":17.5607518555301},"GB2-06":{"attempts":1,"playable":29.371228253085143,"score":29.371228253085143},"GB2-07":{"attempts":1,"playable":70.01694551542973,"score":70.01694551542973},"GB2-08":{"attempts":1,"playable":32.74205921617964,"score":32.74205921617964}},"none":{"GB2-01":{"attempts":1,"playable":41.1697711783785,"score":41.1697711783785},"GB2-02":{"attempts":1,"playable":43.06567904542477,"score":43.06567904542477},"GB2-03":{"attempts":1,"playable":28.642673456846595,"score":28.642673456846595},"GB2-04":{"attempts":1,"playable":42.530989492860435,"score":42.530989492860435},"GB2-05":{"attempts":1,"playable":15.737008626421453,"score":15.737008626421453},"GB2-06":{"attempts":1,"playable":14.256993382904012,"score":14.256993382904012},"GB2-07":{"attempts":1,"playable":24.603682233186106,"score":24.603682233186106},"GB2-08":{"attempts":1,"playable":33.26758810382834,"score":33.26758810382834}}},"id":"gemini-3.1-pro-preview","is_recent_addition":false,"last_measured_at":"2026-10-20T11:42:10Z","match_totals_all":{"draws":2738,"losses":4704,"wins":3640},"match_totals_tracks":{"highest":{"draws":482,"losses":1032,"wins":2180},"medium":{"draws":1123,"losses":1609,"wins":962},"none":{"draws":1133,"losses":2063,"wins":498}},"model_slug":"gemini-3-1-pro-preview","overall":{"max":85.16302198502669,"mean":46.46866135820394,"min":14.256993382904012},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":38,"overall_ranking_status":"ranked","per_game":{"GB2-01":74.7254143109904,"GB2-02":42.832890281616656,"GB2-03":67.21840820109549,"GB2-04":81.41746705727853,"GB2-05":85.16302198502669,"GB2-06":19.091799332456365,"GB2-07":74.57528651068932,"GB2-08":84.11497461924645},"per_game_all":{"GB2-01":50.224552623274896,"GB2-02":43.49205578790016,"GB2-03":54.430741775180934,"GB2-04":56.768160801281006,"GB2-05":39.48692748899275,"GB2-06":20.90667365614851,"GB2-07":56.39863808643506,"GB2-08":50.04154064641815},"per_game_match_totals_all":{"GB2-01":{"draws":260,"losses":581,"wins":563},"GB2-02":{"draws":1046,"losses":226,"wins":24},"GB2-03":{"draws":248,"losses":526,"wins":564},"GB2-04":{"draws":622,"losses":285,"wins":437},"GB2-05":{"draws":0,"losses":882,"wins":570},"GB2-06":{"draws":20,"losses":1097,"wins":251},"GB2-07":{"draws":0,"losses":637,"wins":785},"GB2-08":{"draws":542,"losses":470,"wins":446}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":20,"losses":111,"wins":337},"GB2-02":{"draws":341,"losses":82,"wins":9},"GB2-03":{"draws":28,"losses":146,"wins":272},"GB2-04":{"draws":90,"losses":42,"wins":316},"GB2-05":{"draws":0,"losses":73,"wins":411},"GB2-06":{"draws":2,"losses":376,"wins":78},"GB2-07":{"draws":0,"losses":123,"wins":351},"GB2-08":{"draws":1,"losses":79,"wins":406}},"medium":{"GB2-01":{"draws":162,"losses":229,"wins":77},"GB2-02":{"draws":348,"losses":71,"wins":13},"GB2-03":{"draws":78,"losses":120,"wins":248},"GB2-04":{"draws":250,"losses":121,"wins":77},"GB2-05":{"draws":0,"losses":400,"wins":84},"GB2-06":{"draws":15,"losses":325,"wins":116},"GB2-07":{"draws":0,"losses":146,"wins":328},"GB2-08":{"draws":270,"losses":197,"wins":19}},"none":{"GB2-01":{"draws":78,"losses":241,"wins":149},"GB2-02":{"draws":357,"losses":73,"wins":2},"GB2-03":{"draws":142,"losses":260,"wins":44},"GB2-04":{"draws":282,"losses":122,"wins":44},"GB2-05":{"draws":0,"losses":409,"wins":75},"GB2-06":{"draws":3,"losses":396,"wins":57},"GB2-07":{"draws":0,"losses":368,"wins":106},"GB2-08":{"draws":271,"losses":194,"wins":21}}},"per_game_raw_elo_all":{"GB2-01":1491.5790325617854,"GB2-02":1425.5657219789282,"GB2-03":1481.0509627669069,"GB2-04":1548.8677295900934,"GB2-05":1334.8306856475667,"GB2-06":1006.6255547516386,"GB2-07":1544.384193354923,"GB2-08":1490.7380361906062},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1741.8330624964296,"GB2-02":1420.471198317911,"GB2-03":1599.9241119041387,"GB2-04":1776.469090727331,"GB2-05":2086.4489982105265,"GB2-06":981.6416693870235,"GB2-07":1794.1230333016174,"GB2-08":1977.4851055163576},"medium":{"GB2-01":1334.8228837880629,"GB2-02":1433.9522753316842,"GB2-03":1602.3098305472663,"GB2-04":1449.8722223490781,"GB2-05":977.3157128485295,"GB2-06":1143.045934332552,"GB2-07":1720.5459375794921,"GB2-08":1244.6700676909472},"none":{"GB2-01":1398.0811514008642,"GB2-02":1422.2736922871886,"GB2-03":1240.9189458493158,"GB2-04":1420.261875693871,"GB2-05":940.727345883644,"GB2-06":895.1890605353406,"GB2-07":1118.4836091836594,"GB2-08":1250.0589353645134}},"per_game_tracks":{"highest":{"GB2-01":74.7254143109904,"GB2-02":42.832890281616656,"GB2-03":67.21840820109549,"GB2-04":81.41746705727853,"GB2-05":85.16302198502669,"GB2-06":19.091799332456365,"GB2-07":74.57528651068932,"GB2-08":84.11497461924645},"medium":{"GB2-01":34.7784723804558,"GB2-02":44.57759803665907,"GB2-03":67.43114366760072,"GB2-04":46.356025853704054,"GB2-05":17.5607518555301,"GB2-06":29.371228253085143,"GB2-07":70.01694551542973,"GB2-08":32.74205921617964},"none":{"GB2-01":41.1697711783785,"GB2-02":43.06567904542477,"GB2-03":28.642673456846595,"GB2-04":42.530989492860435,"GB2-05":15.737008626421453,"GB2-06":14.256993382904012,"GB2-07":24.603682233186106,"GB2-08":33.26758810382834}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:45:13Z","reasoning":{"highest":66.1424077873,"medium":42.854278097330536,"none":30.40929818998127},"reasoning_agg":{"highest":{"max":85.16302198502669,"mean":66.1424077873,"min":19.091799332456365},"medium":{"max":70.01694551542973,"mean":42.854278097330536,"min":17.5607518555301},"none":{"max":43.06567904542477,"mean":30.40929818998127,"min":14.256993382904012}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":35.73310959731873}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-2:e81535a3e8cbf684","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.1808710912875,"median":0.13158330000000001,"min":0.0448038366,"recorded_attempt_count":9,"run_count":8,"total":1.4469687303},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.14635563000000001,"mean":0.0939111476625,"median":0.10304704349999999,"min":0.032703412,"recorded_attempt_count":26,"run_count":16,"total":1.5025783626},"none":{"admitted_cell_count":24,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.03729904666666666,"mean":0.023546225995833333,"median":0.024102434966666666,"min":0.013816857666666668,"recorded_attempt_count":37,"run_count":24,"total":0.5651094239000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.23894740000000003,"mean":0.121926546075,"median":0.109979,"min":0.0289264146,"recorded_attempt_count":10,"run_count":8,"total":0.9754123686},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.14831665,"mean":0.06589574925,"median":0.044104765,"min":0.0155414,"recorded_attempt_count":16,"run_count":8,"total":0.527165994},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.047757869999999994,"mean":0.022448211274999998,"median":0.017169796,"min":0.0106770175,"recorded_attempt_count":24,"run_count":16,"total":0.35917138039999996},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.050486600000000006,"mean":0.0257422554375,"median":0.02408436405,"min":0.0093287,"recorded_attempt_count":13,"run_count":8,"total":0.2059380435},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.1808710912875,"median":0.13158330000000001,"min":0.0448038366,"recorded_attempt_count":9,"run_count":8,"total":1.4469687303}},"codegen_cost_usd":{"admitted_cell_count":48,"cell_count":24,"cost_basis_counts":{"provider_reported":72},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.09944282164861112,"median":0.056673037849999996,"min":0.013816857666666668,"recorded_attempt_count":72,"run_count":48,"total":3.5146565168},"codegen_latency_ms":{"attempt_count":32,"max_ms":882507,"mean_ms":240683.0,"min_ms":16088,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":882507,"mean_ms":333475.125,"min_ms":88401,"run_count":8},"medium":{"attempt_count":10,"max_ms":677392,"mean_ms":353638.875,"min_ms":112475,"run_count":8},"none":{"attempt_count":13,"max_ms":79329,"mean_ms":34935.0,"min_ms":16088,"run_count":8}},"codegen_output_tokens":{"attempt_count":32,"output_max":130069,"output_mean":34536.041666666664,"output_min":1442,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":130069,"output_mean":52728.5,"output_min":20107,"run_count":8},"medium":{"attempt_count":10,"output_max":83540,"output_mean":46751.875,"output_min":17329,"run_count":8},"none":{"attempt_count":13,"output_max":8574,"output_mean":4127.75,"output_min":1442,"run_count":8}},"display_name":"GLM-5.2","economics":{"all":44.39542160233486,"highest":44.13129210999335,"medium":48.183300995411905,"none":40.87167170159932},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":32,"finish_reasons":["stop"],"indexed_attempts":32,"output_token_observations":32,"provider_post_attempt_observations":32,"provider_post_attempts":32,"reasoning_token_observations":32,"reconciliation_get_attempt_observations":32,"reconciliation_get_attempts":148,"total_output_tokens":828865,"total_reasoning_output_tokens":728689,"total_visible_output_tokens":100176,"visible_token_observations":32},"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":"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":6,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":10,"repaired_rate":0.625},"baseline":{"admitted_plugins":24,"evaluated_cells":24,"first_pass_admitted":13,"first_pass_rate":0.5416666666666666,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":3},"GB2-03":{"admitted":3},"GB2-04":{"admitted":3},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":3},"GB2-08":{"admitted":3}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":11,"repaired_rate":0.4583333333333333},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":6,"playable":40.51338126218118,"score":40.51338126218118},"GB2-02":{"attempts":6,"playable":50.74424496580213,"score":50.74424496580213},"GB2-03":{"attempts":6,"playable":35.945536850832184,"score":35.945536850832184},"GB2-04":{"attempts":6,"playable":49.76342106553988,"score":49.76342106553988},"GB2-05":{"attempts":6,"playable":49.38828848916086,"score":49.38828848916086},"GB2-06":{"attempts":6,"playable":55.91985230960154,"score":55.91985230960154},"GB2-07":{"attempts":6,"playable":39.19594443366145,"score":39.19594443366145},"GB2-08":{"attempts":6,"playable":35.507298032020685,"score":35.507298032020685}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":53.98840627356537,"score":53.98840627356537},"GB2-02":{"attempts":1,"playable":62.07949751536973,"score":62.07949751536973},"GB2-03":{"attempts":1,"playable":36.9921235769783,"score":36.9921235769783},"GB2-04":{"attempts":1,"playable":58.760991706604635,"score":58.760991706604635},"GB2-05":{"attempts":1,"playable":59.062366824010496,"score":59.062366824010496},"GB2-06":{"attempts":1,"playable":41.946663551663576,"score":41.946663551663576},"GB2-07":{"attempts":1,"playable":10.106500772761303,"score":10.106500772761303},"GB2-08":{"attempts":1,"playable":30.1137866589934,"score":30.1137866589934}},"medium":{"GB2-01":{"attempts":2,"playable":39.34789324373638,"score":39.34789324373638},"GB2-02":{"attempts":2,"playable":48.91312859190987,"score":48.91312859190987},"GB2-03":{"attempts":2,"playable":30.408589579462905,"score":30.408589579462905},"GB2-04":{"attempts":2,"playable":47.84844167979981,"score":47.84844167979981},"GB2-05":{"attempts":2,"playable":54.041686154551094,"score":54.041686154551094},"GB2-06":{"attempts":2,"playable":78.89108462512189,"score":78.89108462512189},"GB2-07":{"attempts":2,"playable":59.58198711418237,"score":59.58198711418237},"GB2-08":{"attempts":2,"playable":26.43359697453093,"score":26.43359697453093}},"none":{"GB2-01":{"attempts":3,"playable":28.203844269241788,"score":28.203844269241788},"GB2-02":{"attempts":3,"playable":41.24010879012682,"score":41.24010879012682},"GB2-03":{"attempts":3,"playable":40.43589739605533,"score":40.43589739605533},"GB2-04":{"attempts":3,"playable":42.68082981021519,"score":42.68082981021519},"GB2-05":{"attempts":3,"playable":35.06081248892097,"score":35.06081248892097},"GB2-06":{"attempts":3,"playable":46.92180875201916,"score":46.92180875201916},"GB2-07":{"attempts":3,"playable":47.89934541404068,"score":47.89934541404068},"GB2-08":{"attempts":3,"playable":49.97451046253773,"score":49.97451046253773}}},"id":"z-ai/glm-5.2","is_recent_addition":false,"last_measured_at":"2026-10-20T11:36:34Z","match_totals_all":{"draws":6502,"losses":9432,"wins":6230},"match_totals_tracks":{"highest":{"draws":1063,"losses":1596,"wins":1035},"medium":{"draws":2297,"losses":2770,"wins":2321},"none":{"draws":3142,"losses":5066,"wins":2874}},"model_slug":"z-ai-glm-5-2","overall":{"max":78.89108462512189,"mean":44.62224592609999,"min":10.106500772761303},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":39,"overall_ranking_status":"ranked","per_game":{"GB2-01":53.98840627356537,"GB2-02":62.07949751536973,"GB2-03":36.9921235769783,"GB2-04":58.760991706604635,"GB2-05":59.062366824010496,"GB2-06":41.946663551663576,"GB2-07":10.106500772761303,"GB2-08":30.1137866589934},"per_game_all":{"GB2-01":40.68691661362448,"GB2-02":50.85757361362613,"GB2-03":35.56141842452681,"GB2-04":49.7133769531469,"GB2-05":48.1501431189507,"GB2-06":55.919852309601545,"GB2-07":38.766793753181595,"GB2-08":35.507298032020685},"per_game_match_totals_all":{"GB2-01":{"draws":715,"losses":1461,"wins":632},"GB2-02":{"draws":1885,"losses":457,"wins":250},"GB2-03":{"draws":994,"losses":1287,"wins":395},"GB2-04":{"draws":1530,"losses":691,"wins":467},"GB2-05":{"draws":0,"losses":1594,"wins":1310},"GB2-06":{"draws":128,"losses":1157,"wins":1451},"GB2-07":{"draws":0,"losses":1599,"wins":1245},"GB2-08":{"draws":1250,"losses":1186,"wins":480}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":175,"losses":132,"wins":161},"GB2-02":{"draws":214,"losses":62,"wins":156},"GB2-03":{"draws":159,"losses":216,"wins":71},"GB2-04":{"draws":215,"losses":83,"wins":150},"GB2-05":{"draws":0,"losses":200,"wins":284},"GB2-06":{"draws":25,"losses":263,"wins":168},"GB2-07":{"draws":0,"losses":433,"wins":41},"GB2-08":{"draws":275,"losses":207,"wins":4}},"medium":{"GB2-01":{"draws":260,"losses":447,"wins":229},"GB2-02":{"draws":655,"losses":125,"wins":84},"GB2-03":{"draws":384,"losses":455,"wins":53},"GB2-04":{"draws":513,"losses":222,"wins":161},"GB2-05":{"draws":0,"losses":448,"wins":520},"GB2-06":{"draws":41,"losses":174,"wins":697},"GB2-07":{"draws":0,"losses":397,"wins":551},"GB2-08":{"draws":444,"losses":502,"wins":26}},"none":{"GB2-01":{"draws":280,"losses":882,"wins":242},"GB2-02":{"draws":1016,"losses":270,"wins":10},"GB2-03":{"draws":451,"losses":616,"wins":271},"GB2-04":{"draws":802,"losses":386,"wins":156},"GB2-05":{"draws":0,"losses":946,"wins":506},"GB2-06":{"draws":62,"losses":720,"wins":586},"GB2-07":{"draws":0,"losses":769,"wins":653},"GB2-08":{"draws":531,"losses":477,"wins":450}}},"per_game_raw_elo_all":{"GB2-01":1389.7336789535277,"GB2-02":1483.634994676563,"GB2-03":1304.691139302851,"GB2-04":1476.4092205754805,"GB2-05":1419.2209106209984,"GB2-06":1569.584687258038,"GB2-07":1274.7068187522618,"GB2-08":1292.6110805313344},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1520.8072371486178,"GB2-02":1572.6655558820726,"GB2-03":1318.3971502400752,"GB2-04":1547.409326260419,"GB2-05":1567.6414137196207,"GB2-06":1332.0966419584076,"GB2-07":838.712893237883,"GB2-08":1217.4136691648166},"medium":{"GB2-01":1378.999141002425,"GB2-02":1467.5260284126628,"GB2-03":1257.2792327218317,"GB2-04":1461.5697252758432,"GB2-05":1502.9031936923811,"GB2-06":1959.1728238592352,"GB2-07":1575.9012215106877,"GB2-08":1177.038894019247},"none":{"GB2-01":1269.3946587095406,"GB2-02":1410.7133997349538,"GB2-03":1338.3970349466463,"GB2-04":1420.2486101901793,"GB2-05":1187.1181244509933,"GB2-06":1417.4845959564718,"GB2-07":1409.506341508215,"GB2-08":1483.3806784099395}},"per_game_tracks":{"highest":{"GB2-01":53.98840627356537,"GB2-02":62.07949751536973,"GB2-03":36.9921235769783,"GB2-04":58.760991706604635,"GB2-05":59.062366824010496,"GB2-06":41.946663551663576,"GB2-07":10.106500772761303,"GB2-08":30.1137866589934},"medium":{"GB2-01":39.34789324373638,"GB2-02":48.91312859190987,"GB2-03":30.408589579462905,"GB2-04":47.84844167979981,"GB2-05":54.041686154551094,"GB2-06":78.89108462512189,"GB2-07":59.58198711418237,"GB2-08":26.43359697453093},"none":{"GB2-01":28.724450323571713,"GB2-02":41.580094733598784,"GB2-03":39.283542117139234,"GB2-04":42.53069747303624,"GB2-05":31.346376378290543,"GB2-06":46.92180875201917,"GB2-07":46.6118933726011,"GB2-08":49.97451046253773}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":1,"rank_movement_baseline_at":"2026-10-13T21:16:30Z","reasoning":{"highest":44.13129210999335,"medium":48.183300995411905,"none":41.55214467289471},"reasoning_agg":{"highest":{"max":62.07949751536973,"mean":44.13129210999335,"min":10.106500772761303},"medium":{"max":78.89108462512189,"mean":48.183300995411905,"min":26.43359697453093},"none":{"max":49.97451046253773,"mean":41.55214467289471,"min":28.203844269241788}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":6.631156322517192}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro-0813:e630610a8ce59c4d","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28337826924,"mean":0.14657020603499998,"median":0.140081106,"min":0.07036986,"recorded_attempt_count":10,"run_count":8,"total":1.1725616482799999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.18085216,"mean":0.12355654023,"median":0.14129957716,"min":0.04648314,"recorded_attempt_count":9,"run_count":8,"total":0.9884523218400001},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0508167,"mean":0.02704530848,"median":0.020221080000000002,"min":0.01808105112,"recorded_attempt_count":12,"run_count":8,"total":0.21636246784000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.18085216,"mean":0.12355654023,"median":0.14129957716,"min":0.04648314,"recorded_attempt_count":9,"run_count":8,"total":0.98845232184},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0508167,"mean":0.02704530848,"median":0.020221080000000002,"min":0.01808105112,"recorded_attempt_count":12,"run_count":8,"total":0.21636246784},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28337826924,"mean":0.14657020603499998,"median":0.140081106,"min":0.07036986,"recorded_attempt_count":10,"run_count":8,"total":1.17256164828}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.28337826924,"mean":0.09905735158166666,"median":0.10177922040000001,"min":0.01808105112,"recorded_attempt_count":31,"run_count":24,"total":2.3773764379599998},"codegen_latency_ms":{"attempt_count":31,"max_ms":1461124,"mean_ms":482100.7083333333,"min_ms":19301,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":1461124,"mean_ms":902169.625,"min_ms":499972,"run_count":8},"medium":{"attempt_count":9,"max_ms":676490,"mean_ms":489467.75,"min_ms":326732,"run_count":8},"none":{"attempt_count":12,"max_ms":131002,"mean_ms":54664.75,"min_ms":19301,"run_count":8}},"codegen_output_tokens":{"attempt_count":31,"output_max":106197,"output_mean":33246.666666666664,"output_min":2345,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":106197,"output_mean":60744.125,"output_min":32963,"run_count":8},"medium":{"attempt_count":9,"output_max":42157,"output_mean":35085.125,"output_min":20989,"run_count":8},"none":{"attempt_count":12,"output_max":10866,"output_mean":3910.75,"output_min":2345,"run_count":8}},"display_name":"DeepSeek V4 Pro 0813","economics":{"all":47.62672712050974,"highest":56.32584171392987,"medium":46.87641686846795,"none":39.271224121727506},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":31,"finish_reasons":["stop"],"indexed_attempts":31,"output_token_observations":31,"provider_post_attempt_observations":31,"provider_post_attempts":31,"reasoning_token_observations":31,"reconciliation_get_attempt_observations":31,"reconciliation_get_attempts":150,"total_output_tokens":797920,"total_reasoning_output_tokens":686933,"total_visible_output_tokens":110987,"visible_token_observations":31},"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-0813","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-05"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":43.67061129975838,"score":43.67061129975838},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.1322737963081,"score":28.088182530872064},"GB2-03":{"attempts":3,"playable":47.88290534236402,"score":47.88290534236402},"GB2-04":{"attempts":3,"playable":40.87119878284775,"score":40.87119878284775},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":59.84988881387794,"score":39.899925875918626},"GB2-06":{"attempts":3,"playable":56.16772089895969,"score":56.16772089895969},"GB2-07":{"attempts":3,"playable":59.225197678555,"score":59.225197678555},"GB2-08":{"attempts":3,"playable":37.94272872057365,"score":37.94272872057365}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":43.506677631679686,"score":43.506677631679686},"GB2-02":{"attempts":1,"playable":44.2288811072632,"score":44.2288811072632},"GB2-03":{"attempts":1,"playable":64.11571519587511,"score":64.11571519587511},"GB2-04":{"attempts":1,"playable":43.65709428159629,"score":43.65709428159629},"GB2-05":{"attempts":1,"playable":75.07457335895464,"score":75.07457335895464},"GB2-06":{"attempts":1,"playable":68.58942473097892,"score":68.58942473097892},"GB2-07":{"attempts":1,"playable":79.74350802911847,"score":79.74350802911847},"GB2-08":{"attempts":1,"playable":31.690859375972636,"score":31.690859375972636}},"medium":{"GB2-01":{"attempts":1,"playable":52.08625421902925,"score":52.08625421902925},"GB2-02":{"attempts":1,"playable":40.035666485353,"score":40.035666485353},"GB2-03":{"attempts":1,"playable":42.42450082772572,"score":42.42450082772572},"GB2-04":{"attempts":1,"playable":34.51166905360669,"score":34.51166905360669},"GB2-05":{"attempts":1,"playable":44.62520426880125,"score":44.62520426880125},"GB2-06":{"attempts":1,"playable":38.26791925637799,"score":38.26791925637799},"GB2-07":{"attempts":1,"playable":73.98017687109746,"score":73.98017687109746},"GB2-08":{"attempts":1,"playable":49.07994396575226,"score":49.07994396575226}},"none":{"GB2-01":{"attempts":1,"playable":35.418902048566196,"score":35.418902048566196},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":37.108500003491244,"score":37.108500003491244},"GB2-04":{"attempts":1,"playable":44.444833013340265,"score":44.444833013340265},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":61.64581870952218,"score":61.64581870952218},"GB2-07":{"attempts":1,"playable":23.951908135449084,"score":23.951908135449084},"GB2-08":{"attempts":1,"playable":33.057382819996036,"score":33.057382819996036}}},"id":"deepseek/deepseek-v4-pro-0813","is_recent_addition":false,"last_measured_at":"2026-10-20T11:42:11Z","match_totals_all":{"draws":2542,"losses":4125,"wins":3499},"match_totals_tracks":{"highest":{"draws":724,"losses":1290,"wins":1680},"medium":{"draws":946,"losses":1532,"wins":1216},"none":{"draws":872,"losses":1303,"wins":603}},"model_slug":"deepseek-deepseek-v4-pro-0813","overall":{"max":79.74350802911847,"mean":44.21855889123115,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":40,"overall_ranking_status":"ranked","per_game":{"GB2-01":43.506677631679686,"GB2-02":44.2288811072632,"GB2-03":64.11571519587511,"GB2-04":43.65709428159629,"GB2-05":75.07457335895464,"GB2-06":68.58942473097892,"GB2-07":79.74350802911847,"GB2-08":31.690859375972636},"per_game_all":{"GB2-01":43.67061129975838,"GB2-03":47.88290534236402,"GB2-04":40.87119878284775,"GB2-06":56.16772089895969,"GB2-07":59.225197678555,"GB2-08":37.94272872057365},"per_game_match_totals_all":{"GB2-01":{"draws":373,"losses":618,"wins":413},"GB2-02":{"draws":648,"losses":187,"wins":29},"GB2-03":{"draws":251,"losses":616,"wins":471},"GB2-04":{"draws":732,"losses":445,"wins":167},"GB2-05":{"draws":0,"losses":392,"wins":576},"GB2-06":{"draws":31,"losses":605,"wins":732},"GB2-07":{"draws":0,"losses":594,"wins":828},"GB2-08":{"draws":507,"losses":668,"wins":283}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":14,"losses":262,"wins":192},"GB2-02":{"draws":339,"losses":77,"wins":16},"GB2-03":{"draws":23,"losses":163,"wins":260},"GB2-04":{"draws":228,"losses":144,"wins":76},"GB2-05":{"draws":0,"losses":123,"wins":361},"GB2-06":{"draws":12,"losses":141,"wins":303},"GB2-07":{"draws":0,"losses":97,"wins":377},"GB2-08":{"draws":108,"losses":283,"wins":95}},"medium":{"GB2-01":{"draws":263,"losses":97,"wins":108},"GB2-02":{"draws":309,"losses":110,"wins":13},"GB2-03":{"draws":40,"losses":252,"wins":154},"GB2-04":{"draws":173,"losses":212,"wins":63},"GB2-05":{"draws":0,"losses":269,"wins":215},"GB2-06":{"draws":15,"losses":285,"wins":156},"GB2-07":{"draws":0,"losses":126,"wins":348},"GB2-08":{"draws":146,"losses":181,"wins":159}},"none":{"GB2-01":{"draws":96,"losses":259,"wins":113},"GB2-03":{"draws":188,"losses":201,"wins":57},"GB2-04":{"draws":331,"losses":89,"wins":28},"GB2-06":{"draws":4,"losses":179,"wins":273},"GB2-07":{"draws":0,"losses":371,"wins":103},"GB2-08":{"draws":253,"losses":204,"wins":29}}},"per_game_raw_elo_all":{"GB2-01":1421.4829819832987,"GB2-03":1417.3235376334942,"GB2-04":1406.8102961452553,"GB2-06":1559.2782274491603,"GB2-07":1594.397897935264,"GB2-08":1298.2638736795636},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1420.607520746461,"GB2-02":1431.262375744063,"GB2-03":1566.3628114652183,"GB2-04":1429.0058715880014,"GB2-05":1821.572488377008,"GB2-06":1760.1962797700758,"GB2-07":1890.56611416368,"GB2-08":1233.8361796685492},"medium":{"GB2-01":1502.528246247236,"GB2-02":1398.6767889214864,"GB2-03":1366.174081212224,"GB2-04":1356.3188686264023,"GB2-05":1385.1343991171714,"GB2-06":1276.7141544852752,"GB2-07":1784.033291243827,"GB2-08":1413.0500150111075},"none":{"GB2-01":1341.3131789561994,"GB2-03":1319.4337202230397,"GB2-04":1435.1061482213624,"GB2-06":1640.9242480921303,"GB2-07":1108.5942883982839,"GB2-08":1247.905426359034}},"per_game_tracks":{"highest":{"GB2-01":43.506677631679686,"GB2-02":44.2288811072632,"GB2-03":64.11571519587511,"GB2-04":43.65709428159629,"GB2-05":75.07457335895464,"GB2-06":68.58942473097892,"GB2-07":79.74350802911847,"GB2-08":31.690859375972636},"medium":{"GB2-01":52.08625421902925,"GB2-02":40.035666485353,"GB2-03":42.42450082772572,"GB2-04":34.51166905360669,"GB2-05":44.62520426880125,"GB2-06":38.26791925637799,"GB2-07":73.98017687109746,"GB2-08":49.07994396575226},"none":{"GB2-01":35.418902048566196,"GB2-03":37.108500003491244,"GB2-04":44.444833013340265,"GB2-06":61.64581870952218,"GB2-07":23.951908135449084,"GB2-08":33.057382819996036}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":1,"rank_movement_baseline_at":"2026-10-15T06:26:40Z","reasoning":{"highest":56.32584171392987,"medium":46.87641686846795,"none":29.453418091295628},"reasoning_agg":{"highest":{"max":79.74350802911847,"mean":56.32584171392987,"min":31.690859375972636},"medium":{"max":73.98017687109746,"mean":46.87641686846795,"min":34.51166905360669},"none":{"max":61.64581870952218,"mean":29.453418091295628,"min":0.0}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":26.87242362263424}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro:3f7b3092f4efde2e","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.176790095,"mean":0.114196574281125,"median":0.09418628700000001,"min":0.06074422244,"recorded_attempt_count":11,"run_count":8,"total":0.9135725942490001},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.06923239834,"mean":0.046577516286750005,"median":0.0458058365,"min":0.023862969,"recorded_attempt_count":12,"run_count":8,"total":0.372620130294},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.03845835,"mean":0.025296556802625002,"median":0.02540433020275,"min":0.014466934,"recorded_attempt_count":12,"run_count":8,"total":0.202372454421}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.06923239834,"mean":0.046577516286750005,"median":0.0458058365,"min":0.023862969,"recorded_attempt_count":12,"run_count":8,"total":0.37262013029400004},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.03845835,"mean":0.025296556802625002,"median":0.02540433020275,"min":0.014466934,"recorded_attempt_count":12,"run_count":8,"total":0.20237245442100002},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.176790095,"mean":0.114196574281125,"median":0.09418628700000001,"min":0.06074422244,"recorded_attempt_count":11,"run_count":8,"total":0.913572594249}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.176790095,"mean":0.062023549123500006,"median":0.0458058365,"min":0.014466934,"recorded_attempt_count":35,"run_count":24,"total":1.4885651789640004},"codegen_latency_ms":{"attempt_count":35,"max_ms":1560134,"mean_ms":432334.7916666667,"min_ms":52746,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":1560134,"mean_ms":818090.375,"min_ms":426935,"run_count":8},"medium":{"attempt_count":12,"max_ms":673313,"mean_ms":392142.875,"min_ms":86869,"run_count":8},"none":{"attempt_count":12,"max_ms":170011,"mean_ms":86771.125,"min_ms":52746,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":74570,"output_mean":21422.416666666668,"output_min":2493,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":74570,"output_mean":43080.25,"output_min":21434,"run_count":8},"medium":{"attempt_count":12,"output_max":23131,"output_mean":16655.5,"output_min":5286,"run_count":8},"none":{"attempt_count":12,"output_max":8274,"output_mean":4531.5,"output_min":2493,"run_count":8}},"display_name":"DeepSeek V4 Pro","economics":{"all":46.80944331673643,"highest":48.72994730736378,"medium":53.7039265501177,"none":39.31458413400366},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":35,"finish_reasons":["stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":35,"provider_post_attempts":35,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":35,"reconciliation_get_attempts":166,"total_output_tokens":514138,"total_reasoning_output_tokens":410486,"total_visible_output_tokens":103652,"visible_token_observations":35},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.5},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":39.91733152369647,"score":39.91733152369647},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.53723149584549,"score":28.35815433056366},"GB2-03":{"attempts":3,"playable":39.423250285725366,"score":39.423250285725366},"GB2-04":{"attempts":3,"playable":44.781468613925426,"score":44.781468613925426},"GB2-05":{"attempts":3,"playable":43.17143024733418,"score":43.17143024733418},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":63.85702648546362,"score":42.57135099030908},"GB2-07":{"attempts":3,"playable":66.83134045991856,"score":66.83134045991856},"GB2-08":{"attempts":3,"playable":46.731838769818495,"score":46.731838769818495}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":26.529112802564843,"score":26.529112802564843},"GB2-02":{"attempts":1,"playable":45.73916193781219,"score":45.73916193781219},"GB2-03":{"attempts":1,"playable":47.10030914439933,"score":47.10030914439933},"GB2-04":{"attempts":1,"playable":46.805320428724514,"score":46.805320428724514},"GB2-05":{"attempts":1,"playable":45.25256780459805,"score":45.25256780459805},"GB2-06":{"attempts":1,"playable":78.77138068387647,"score":78.77138068387647},"GB2-07":{"attempts":1,"playable":74.57528651068932,"score":74.57528651068932},"GB2-08":{"attempts":1,"playable":25.066439146245518,"score":25.066439146245518}},"medium":{"GB2-01":{"attempts":1,"playable":63.90147748365587,"score":63.90147748365587},"GB2-02":{"attempts":1,"playable":39.33530105387879,"score":39.33530105387879},"GB2-03":{"attempts":1,"playable":28.2861574213354,"score":28.2861574213354},"GB2-04":{"attempts":1,"playable":43.20675917937842,"score":43.20675917937842},"GB2-05":{"attempts":1,"playable":49.85575591343522,"score":49.85575591343522},"GB2-06":{"attempts":1,"playable":48.94267228705076,"score":48.94267228705076},"GB2-07":{"attempts":1,"playable":71.40343369244843,"score":71.40343369244843},"GB2-08":{"attempts":1,"playable":84.69985536975864,"score":84.69985536975864}},"none":{"GB2-01":{"attempts":1,"playable":29.321404284868706,"score":29.321404284868706},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":42.88328429144135,"score":42.88328429144135},"GB2-04":{"attempts":1,"playable":44.33232623367333,"score":44.33232623367333},"GB2-05":{"attempts":1,"playable":34.40596702396929,"score":34.40596702396929},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":54.51530117661794,"score":54.51530117661794},"GB2-08":{"attempts":1,"playable":30.429221793451333,"score":30.429221793451333}}},"id":"deepseek/deepseek-v4-pro","is_recent_addition":false,"last_measured_at":"2026-10-20T11:30:11Z","match_totals_all":{"draws":2476,"losses":4181,"wins":3537},"match_totals_tracks":{"highest":{"draws":910,"losses":1484,"wins":1300},"medium":{"draws":729,"losses":1370,"wins":1595},"none":{"draws":837,"losses":1327,"wins":642}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":84.69985536975864,"mean":43.973270652661405,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":41,"overall_ranking_status":"ranked","per_game":{"GB2-01":26.529112802564843,"GB2-02":45.73916193781219,"GB2-03":47.10030914439933,"GB2-04":46.805320428724514,"GB2-05":45.25256780459805,"GB2-06":78.77138068387647,"GB2-07":74.57528651068932,"GB2-08":25.066439146245518},"per_game_all":{"GB2-01":39.91733152369647,"GB2-03":39.423250285725366,"GB2-04":44.781468613925426,"GB2-05":43.17143024733418,"GB2-07":66.83134045991856,"GB2-08":46.731838769818495},"per_game_match_totals_all":{"GB2-01":{"draws":197,"losses":758,"wins":449},"GB2-02":{"draws":641,"losses":187,"wins":36},"GB2-03":{"draws":392,"losses":658,"wins":288},"GB2-04":{"draws":842,"losses":338,"wins":164},"GB2-05":{"draws":0,"losses":828,"wins":624},"GB2-06":{"draws":22,"losses":329,"wins":561},"GB2-07":{"draws":0,"losses":486,"wins":936},"GB2-08":{"draws":382,"losses":597,"wins":479}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":41,"losses":328,"wins":99},"GB2-02":{"draws":324,"losses":78,"wins":30},"GB2-03":{"draws":147,"losses":178,"wins":121},"GB2-04":{"draws":268,"losses":110,"wins":70},"GB2-05":{"draws":0,"losses":266,"wins":218},"GB2-06":{"draws":13,"losses":91,"wins":352},"GB2-07":{"draws":0,"losses":123,"wins":351},"GB2-08":{"draws":117,"losses":310,"wins":59}},"medium":{"GB2-01":{"draws":35,"losses":155,"wins":278},"GB2-02":{"draws":317,"losses":109,"wins":6},"GB2-03":{"draws":93,"losses":286,"wins":67},"GB2-04":{"draws":274,"losses":123,"wins":51},"GB2-05":{"draws":0,"losses":244,"wins":240},"GB2-06":{"draws":9,"losses":238,"wins":209},"GB2-07":{"draws":0,"losses":139,"wins":335},"GB2-08":{"draws":1,"losses":76,"wins":409}},"none":{"GB2-01":{"draws":121,"losses":275,"wins":72},"GB2-03":{"draws":152,"losses":194,"wins":100},"GB2-04":{"draws":300,"losses":105,"wins":43},"GB2-05":{"draws":0,"losses":318,"wins":166},"GB2-07":{"draws":0,"losses":224,"wins":250},"GB2-08":{"draws":264,"losses":211,"wins":11}}},"per_game_raw_elo_all":{"GB2-01":1381.0539633450041,"GB2-03":1338.1817497994352,"GB2-04":1437.6961578968082,"GB2-05":1364.8161016737681,"GB2-07":1681.1941049483394,"GB2-08":1458.4816709725117},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1246.2080672952172,"GB2-02":1442.9013976328413,"GB2-03":1406.9528785644811,"GB2-04":1453.3400804253079,"GB2-05":1393.0141114642481,"GB2-06":1947.9214982264505,"GB2-07":1794.1230333016174,"GB2-08":1162.7707013613856},"medium":{"GB2-01":1619.4971005813861,"GB2-02":1393.1698080350175,"GB2-03":1237.4182764116617,"GB2-04":1425.512828990763,"GB2-05":1450.4253011707017,"GB2-06":1438.52947660883,"GB2-07":1742.1003942748193,"GB2-08":1991.9573605339147},"none":{"GB2-01":1277.4567221584089,"GB2-03":1370.1740944221626,"GB2-04":1434.2355642743532,"GB2-05":1251.0088923863545,"GB2-07":1507.3588872685818,"GB2-08":1220.7169510222352}},"per_game_tracks":{"highest":{"GB2-01":26.529112802564843,"GB2-02":45.73916193781219,"GB2-03":47.10030914439933,"GB2-04":46.805320428724514,"GB2-05":45.25256780459805,"GB2-06":78.77138068387647,"GB2-07":74.57528651068932,"GB2-08":25.066439146245518},"medium":{"GB2-01":63.90147748365587,"GB2-02":39.33530105387879,"GB2-03":28.2861574213354,"GB2-04":43.20675917937842,"GB2-05":49.85575591343522,"GB2-06":48.94267228705076,"GB2-07":71.40343369244843,"GB2-08":84.69985536975864},"none":{"GB2-01":29.321404284868706,"GB2-03":42.88328429144135,"GB2-04":44.33232623367333,"GB2-05":34.40596702396929,"GB2-07":54.51530117661794,"GB2-08":30.429221793451333}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-14T17:24:18Z","reasoning":{"highest":48.72994730736378,"medium":53.7039265501177,"none":29.48593810050274},"reasoning_agg":{"highest":{"max":78.77138068387647,"mean":48.72994730736378,"min":25.066439146245518},"medium":{"max":84.69985536975864,"mean":53.7039265501177,"min":28.2861574213354},"none":{"max":54.51530117661794,"mean":29.48593810050274,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.21798844961496}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5:0486b73521227988","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.45464499999999997,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":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},"cost_is_complete":false,"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-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":1.42050125},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":12},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.15380375000000002,"mean":0.09741312500000002,"median":0.090410625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12},"run_count":8,"token_priced_attempt_count":12,"total":0.779305}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"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-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":1.42050125},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":12},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.15380375000000002,"mean":0.09741312500000002,"median":0.090410625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12},"run_count":8,"token_priced_attempt_count":12,"total":0.7793050000000001},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.45464499999999997,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":2.2561125}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":31},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":0.45464499999999997,"mean":0.18566328125000006,"median":0.17276625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12,"boardgame-list-prices-2026-10-09":19},"run_count":24,"token_priced_attempt_count":31,"total":4.45591875},"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":{"all":44.08983226473309,"highest":49.7853941734894,"medium":42.53188970633532,"none":41.73430175813005},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"first_pass_admitted":4,"first_pass_rate":0.6666666666666666,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"performance_rejections":1},"GB2-05":{"admitted":1},"GB2-06":{"performance_rejections":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-04","GB2-06"],"performance_rejections":2,"repaired_admitted":2,"repaired_rate":0.3333333333333333},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":43.60141444804657,"score":43.60141444804657},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":40.559749689277055,"score":27.039833126184703},"GB2-03":{"attempts":3,"playable":27.925692636923156,"score":27.925692636923156},"GB2-04":{"attempts":2,"playable":41.5162247059574,"score":41.5162247059574},"GB2-05":{"attempts":3,"playable":61.60288960963256,"score":61.60288960963256},"GB2-06":{"attempts":2,"playable":60.45637955978876,"score":60.45637955978876},"GB2-07":{"attempts":3,"playable":52.37147258344147,"score":52.37147258344147},"GB2-08":{"attempts":3,"playable":34.94769204562169,"score":34.94769204562169}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":40.21281479320935,"score":40.21281479320935},"GB2-02":{"attempts":1,"playable":42.01774548023428,"score":42.01774548023428},"GB2-03":{"attempts":1,"playable":36.293145628718385,"score":36.293145628718385},"GB2-04":{"attempts":1,"playable":40.27616799500331,"score":40.27616799500331},"GB2-05":{"attempts":1,"playable":76.10228116537084,"score":76.10228116537084},"GB2-06":{"attempts":1,"playable":71.76059401821166,"score":71.76059401821166},"GB2-07":{"attempts":1,"playable":53.31143609255761,"score":53.31143609255761},"GB2-08":{"attempts":1,"playable":38.308968214609784,"score":38.308968214609784}},"medium":{"GB2-01":{"attempts":1,"playable":20.378998498634317,"score":20.378998498634317},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":31.24797627398688,"score":31.24797627398688},"GB2-04":{"attempts":1,"playable":42.75628141691148,"score":42.75628141691148},"GB2-05":{"attempts":1,"playable":60.94341045521714,"score":60.94341045521714},"GB2-06":{"attempts":1,"playable":49.15216510136586,"score":49.15216510136586},"GB2-07":{"attempts":1,"playable":62.28947011253836,"score":62.28947011253836},"GB2-08":{"attempts":1,"playable":30.954926085693206,"score":30.954926085693206}},"none":{"GB2-01":{"attempts":1,"playable":70.21243005229606,"score":70.21243005229606},"GB2-02":{"attempts":1,"playable":39.10175389831983,"score":39.10175389831983},"GB2-03":{"attempts":1,"playable":16.23595600806419,"score":16.23595600806419},"GB2-05":{"attempts":1,"playable":47.762977208309714,"score":47.762977208309714},"GB2-07":{"attempts":1,"playable":41.51351154522843,"score":41.51351154522843},"GB2-08":{"attempts":1,"playable":35.57918183656208,"score":35.57918183656208}}},"id":"gpt-5","is_recent_addition":false,"last_measured_at":"2026-10-20T11:21:10Z","match_totals_all":{"draws":2552,"losses":4192,"wins":3002},"match_totals_tracks":{"highest":{"draws":1110,"losses":1342,"wins":1242},"medium":{"draws":740,"losses":1547,"wins":975},"none":{"draws":702,"losses":1303,"wins":785}},"model_slug":"gpt-5","overall":{"max":76.10228116537084,"mean":42.91169980822095,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":42,"overall_ranking_status":"partial","per_game":{"GB2-01":40.21281479320935,"GB2-02":42.01774548023428,"GB2-03":36.293145628718385,"GB2-04":40.27616799500331,"GB2-05":76.10228116537084,"GB2-06":71.76059401821166,"GB2-07":53.31143609255761,"GB2-08":38.308968214609784},"per_game_all":{"GB2-01":43.60141444804657,"GB2-03":27.925692636923156,"GB2-05":61.60288960963256,"GB2-07":52.37147258344147,"GB2-08":34.94769204562169},"per_game_match_totals_all":{"GB2-01":{"draws":188,"losses":710,"wins":506},"GB2-02":{"draws":649,"losses":200,"wins":15},"GB2-03":{"draws":382,"losses":810,"wins":146},"GB2-04":{"draws":544,"losses":263,"wins":89},"GB2-05":{"draws":0,"losses":563,"wins":889},"GB2-06":{"draws":32,"losses":357,"wins":523},"GB2-07":{"draws":0,"losses":703,"wins":719},"GB2-08":{"draws":757,"losses":586,"wins":115}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":75,"losses":247,"wins":146},"GB2-02":{"draws":330,"losses":91,"wins":11},"GB2-03":{"draws":141,"losses":228,"wins":77},"GB2-04":{"draws":300,"losses":123,"wins":25},"GB2-05":{"draws":0,"losses":118,"wins":366},"GB2-06":{"draws":13,"losses":125,"wins":318},"GB2-07":{"draws":0,"losses":230,"wins":244},"GB2-08":{"draws":251,"losses":180,"wins":55}},"medium":{"GB2-01":{"draws":58,"losses":348,"wins":62},"GB2-03":{"draws":172,"losses":234,"wins":40},"GB2-04":{"draws":244,"losses":140,"wins":64},"GB2-05":{"draws":0,"losses":191,"wins":293},"GB2-06":{"draws":19,"losses":232,"wins":205},"GB2-07":{"draws":0,"losses":185,"wins":289},"GB2-08":{"draws":247,"losses":217,"wins":22}},"none":{"GB2-01":{"draws":55,"losses":115,"wins":298},"GB2-02":{"draws":319,"losses":109,"wins":4},"GB2-03":{"draws":69,"losses":348,"wins":29},"GB2-05":{"draws":0,"losses":254,"wins":230},"GB2-07":{"draws":0,"losses":288,"wins":186},"GB2-08":{"draws":259,"losses":189,"wins":38}}},"per_game_raw_elo_all":{"GB2-01":1415.6946605037956,"GB2-03":1225.8341328296979,"GB2-05":1620.0285143135523,"GB2-07":1482.1196680936953,"GB2-08":1267.0156882431993},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1388.7865880757017,"GB2-02":1414.1478441779848,"GB2-03":1312.1540485580147,"GB2-04":1402.6345039696923,"GB2-05":1842.8151991312643,"GB2-06":1816.9535573322032,"GB2-07":1492.0610768799636,"GB2-08":1301.2419463161098},"medium":{"GB2-01":1170.2830160443573,"GB2-03":1265.9224827888725,"GB2-04":1422.0138144478688,"GB2-05":1592.8963414184177,"GB2-06":1441.7510249892111,"GB2-07":1609.4593331179533,"GB2-08":1226.2007189338674},"none":{"GB2-01":1688.0143773913283,"GB2-02":1391.3279468860167,"GB2-03":1099.4258671422062,"GB2-05":1424.374002390975,"GB2-07":1344.8385942831687,"GB2-08":1273.604399479621}},"per_game_tracks":{"highest":{"GB2-01":40.21281479320935,"GB2-02":42.01774548023428,"GB2-03":36.293145628718385,"GB2-04":40.27616799500331,"GB2-05":76.10228116537084,"GB2-06":71.76059401821166,"GB2-07":53.31143609255761,"GB2-08":38.308968214609784},"medium":{"GB2-01":20.378998498634317,"GB2-03":31.24797627398688,"GB2-04":42.75628141691148,"GB2-05":60.94341045521714,"GB2-06":49.15216510136586,"GB2-07":62.28947011253836,"GB2-08":30.954926085693206},"none":{"GB2-01":70.21243005229606,"GB2-02":39.10175389831983,"GB2-03":16.23595600806419,"GB2-05":47.762977208309714,"GB2-07":41.51351154522843,"GB2-08":35.57918183656208}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":49.7853941734894,"medium":37.215403493043404,"none":41.73430175813005},"reasoning_agg":{"highest":{"max":76.10228116537084,"mean":49.7853941734894,"min":36.293145628718385},"medium":{"max":62.28947011253836,"mean":37.215403493043404,"min":0.0},"none":{"max":70.21243005229606,"mean":41.73430175813005,"min":16.23595600806419}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":12.569990680445997}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-luna:0f2b44abb61ff1a1","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.030833324999999998,"median":0.031411375,"min":0.0247604,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.2466666},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.011164349999999998,"mean":0.00631805625,"median":0.005847,"min":0.00434295,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.05054445},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0057713,"mean":0.004598475,"median":0.0045067,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.0367878}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.011164349999999998,"mean":0.00631805625,"median":0.005847,"min":0.00434295,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.050544450000000005},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0057713,"mean":0.004598475,"median":0.0045067,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.036787799999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.030833324999999998,"median":0.031411375,"min":0.0247604,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.2466666}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.01391661875,"median":0.00586915,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":0.33399885},"codegen_output_tokens":{"attempt_count":25,"output_max":29793,"output_mean":9924.083333333334,"output_min":1845,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":29793,"output_mean":24080.5,"output_min":19109,"run_count":8},"medium":{"attempt_count":9,"output_max":6277,"output_mean":3473.625,"output_min":2113,"run_count":8},"none":{"attempt_count":8,"output_max":2721,"output_mean":2218.125,"output_min":1845,"run_count":8}},"display_name":"GPT-5.6 Luna","economics":{"all":41.65260836668773,"highest":55.803810868464694,"medium":43.296109931383135,"none":25.857904300215345},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"total_output_tokens":238178,"total_reasoning_output_tokens":167062,"total_visible_output_tokens":71116,"visible_token_observations":25},"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-5.6-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":51.35744419355416,"score":51.35744419355416},"GB2-02":{"attempts":3,"playable":43.685787539816765,"score":43.685787539816765},"GB2-03":{"attempts":3,"playable":38.44552208731011,"score":38.44552208731011},"GB2-04":{"attempts":3,"playable":41.99913412858553,"score":41.99913412858553},"GB2-05":{"attempts":3,"playable":39.80509494639045,"score":39.80509494639045},"GB2-06":{"attempts":3,"playable":52.92013414534026,"score":52.92013414534026},"GB2-07":{"attempts":3,"playable":39.23371231016119,"score":39.23371231016119},"GB2-08":{"attempts":3,"playable":25.774037582343357,"score":25.774037582343357}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":82.35469070548879,"score":82.35469070548879},"GB2-02":{"attempts":1,"playable":44.92620119251952,"score":44.92620119251952},"GB2-03":{"attempts":1,"playable":41.620283286326895,"score":41.620283286326895},"GB2-04":{"attempts":1,"playable":38.35693984005379,"score":38.35693984005379},"GB2-05":{"attempts":1,"playable":50.69296543340541,"score":50.69296543340541},"GB2-06":{"attempts":1,"playable":82.84169884246968,"score":82.84169884246968},"GB2-07":{"attempts":1,"playable":72.79053853408634,"score":72.79053853408634},"GB2-08":{"attempts":1,"playable":32.84716911336711,"score":32.84716911336711}},"medium":{"GB2-01":{"attempts":1,"playable":46.26453886832805,"score":46.26453886832805},"GB2-02":{"attempts":1,"playable":43.53110886291607,"score":43.53110886291607},"GB2-03":{"attempts":1,"playable":44.59871902958958,"score":44.59871902958958},"GB2-04":{"attempts":1,"playable":47.815664727426764,"score":47.815664727426764},"GB2-05":{"attempts":1,"playable":45.25256780459805,"score":45.25256780459805},"GB2-06":{"attempts":1,"playable":56.826904261094754,"score":56.826904261094754},"GB2-07":{"attempts":1,"playable":29.127098900570697,"score":29.127098900570697},"GB2-08":{"attempts":1,"playable":32.952276996541194,"score":32.952276996541194}},"none":{"GB2-01":{"attempts":1,"playable":25.45310300684563,"score":25.45310300684563},"GB2-02":{"attempts":1,"playable":42.600052564014696,"score":42.600052564014696},"GB2-03":{"attempts":1,"playable":29.117563946013863,"score":29.117563946013863},"GB2-04":{"attempts":1,"playable":39.82479781827604,"score":39.82479781827604},"GB2-05":{"attempts":1,"playable":23.469751601167886,"score":23.469751601167886},"GB2-06":{"attempts":1,"playable":19.091799332456365,"score":19.091799332456365},"GB2-07":{"attempts":1,"playable":15.783499495826515,"score":15.783499495826515},"GB2-08":{"attempts":1,"playable":11.522666637121777,"score":11.522666637121777}}},"id":"gpt-5.6-luna","is_recent_addition":false,"last_measured_at":"2026-10-20T11:34:53Z","match_totals_all":{"draws":3299,"losses":4973,"wins":2810},"match_totals_tracks":{"highest":{"draws":1127,"losses":1103,"wins":1464},"medium":{"draws":1144,"losses":1584,"wins":966},"none":{"draws":1028,"losses":2286,"wins":380}},"model_slug":"gpt-5-6-luna","overall":{"max":82.84169884246968,"mean":41.65260836668773,"min":11.522666637121777},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":43,"overall_ranking_status":"ranked","per_game":{"GB2-01":82.35469070548879,"GB2-02":44.92620119251952,"GB2-03":41.620283286326895,"GB2-04":38.35693984005379,"GB2-05":50.69296543340541,"GB2-06":82.84169884246968,"GB2-07":72.79053853408634,"GB2-08":32.84716911336711},"per_game_all":{"GB2-01":51.35744419355416,"GB2-02":43.685787539816765,"GB2-03":38.44552208731011,"GB2-04":41.99913412858553,"GB2-05":39.80509494639045,"GB2-06":52.92013414534026,"GB2-07":39.23371231016119,"GB2-08":25.774037582343357},"per_game_match_totals_all":{"GB2-01":{"draws":156,"losses":616,"wins":632},"GB2-02":{"draws":1023,"losses":235,"wins":38},"GB2-03":{"draws":532,"losses":601,"wins":205},"GB2-04":{"draws":864,"losses":364,"wins":116},"GB2-05":{"draws":0,"losses":877,"wins":575},"GB2-06":{"draws":81,"losses":619,"wins":668},"GB2-07":{"draws":0,"losses":887,"wins":535},"GB2-08":{"draws":643,"losses":774,"wins":41}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":84,"wins":383},"GB2-02":{"draws":327,"losses":80,"wins":25},"GB2-03":{"draws":189,"losses":181,"wins":76},"GB2-04":{"draws":267,"losses":148,"wins":33},"GB2-05":{"draws":0,"losses":240,"wins":244},"GB2-06":{"draws":40,"losses":58,"wins":358},"GB2-07":{"draws":0,"losses":132,"wins":342},"GB2-08":{"draws":303,"losses":180,"wins":3}},"medium":{"GB2-01":{"draws":62,"losses":225,"wins":181},"GB2-02":{"draws":347,"losses":76,"wins":9},"GB2-03":{"draws":145,"losses":190,"wins":111},"GB2-04":{"draws":313,"losses":83,"wins":52},"GB2-05":{"draws":0,"losses":266,"wins":218},"GB2-06":{"draws":17,"losses":196,"wins":243},"GB2-07":{"draws":0,"losses":347,"wins":127},"GB2-08":{"draws":260,"losses":201,"wins":25}},"none":{"GB2-01":{"draws":93,"losses":307,"wins":68},"GB2-02":{"draws":349,"losses":79,"wins":4},"GB2-03":{"draws":198,"losses":230,"wins":18},"GB2-04":{"draws":284,"losses":133,"wins":31},"GB2-05":{"draws":0,"losses":371,"wins":113},"GB2-06":{"draws":24,"losses":365,"wins":67},"GB2-07":{"draws":0,"losses":408,"wins":66},"GB2-08":{"draws":80,"losses":393,"wins":13}}},"per_game_raw_elo_all":{"GB2-01":1509.8027333738821,"GB2-02":1427.0600553477982,"GB2-03":1329.9421444305938,"GB2-04":1415.891564118175,"GB2-05":1312.6893996968906,"GB2-06":1524.3628888724736,"GB2-07":1305.4406027209711,"GB2-08":1155.7357904818803},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1848.711722159639,"GB2-02":1436.6395777738958,"GB2-03":1359.1556420111306,"GB2-04":1387.4545700056453,"GB2-05":1460.8554884087264,"GB2-06":2029.3378450122948,"GB2-07":1764.3413772264344,"GB2-08":1245.7492209433503},"medium":{"GB2-01":1446.982058943041,"GB2-02":1425.873668759836,"GB2-03":1385.1206261977213,"GB2-04":1461.1388913175012,"GB2-05":1393.0141114642481,"GB2-06":1562.109152218103,"GB2-07":1183.7405440373466,"GB2-08":1246.8276685590758},"none":{"GB2-01":1233.7144190189663,"GB2-02":1418.666919509663,"GB2-03":1245.5501650829297,"GB2-04":1399.0812310313784,"GB2-05":1084.1985992176974,"GB2-06":981.6416693870235,"GB2-07":968.2398868991326,"GB2-08":974.630481943215}},"per_game_tracks":{"highest":{"GB2-01":82.35469070548879,"GB2-02":44.92620119251952,"GB2-03":41.620283286326895,"GB2-04":38.35693984005379,"GB2-05":50.69296543340541,"GB2-06":82.84169884246968,"GB2-07":72.79053853408634,"GB2-08":32.84716911336711},"medium":{"GB2-01":46.26453886832805,"GB2-02":43.53110886291607,"GB2-03":44.59871902958958,"GB2-04":47.815664727426764,"GB2-05":45.25256780459805,"GB2-06":56.826904261094754,"GB2-07":29.127098900570697,"GB2-08":32.952276996541194},"none":{"GB2-01":25.45310300684563,"GB2-02":42.600052564014696,"GB2-03":29.117563946013863,"GB2-04":39.82479781827604,"GB2-05":23.469751601167886,"GB2-06":19.091799332456365,"GB2-07":15.783499495826515,"GB2-08":11.522666637121777}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T22:57:21Z","reasoning":{"highest":55.803810868464694,"medium":43.296109931383135,"none":25.857904300215345},"reasoning_agg":{"highest":{"max":82.84169884246968,"mean":55.803810868464694,"min":32.84716911336711},"medium":{"max":56.826904261094754,"mean":43.296109931383135,"min":29.127098900570697},"none":{"max":42.600052564014696,"mean":25.857904300215345,"min":11.522666637121777}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":29.94590656824935}},{"canonical_public_row_identity":"publication-row.v1:overall:o3:e111031353bc7327","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"estimated":32,"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840574999999999,"min":0.0773785,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.927552},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"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-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.390976},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.08754999999999999,"mean":0.04313775,"median":0.033532,"min":0.030172,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.34510199999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"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-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.39097600000000005},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.08754999999999999,"mean":0.04313775,"median":0.033532,"min":0.030172,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.345102},"historical-provider-setting-intensive":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"estimated":32,"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840574999999999,"min":0.0773785,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.927552}},"codegen_cost_usd":{"admitted_cell_count":33,"cell_count":24,"cost_basis_counts":{"estimated":32,"local_standard_estimate":26},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":15,"max":0.1097735,"mean":0.06116525,"median":0.054719000000000004,"min":0.030172,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":58},"recorded_attempt_count":32,"run_count":48,"token_priced_attempt_count":26,"total":3.66363},"codegen_latency_ms":{"attempt_count":26,"max_ms":79649,"mean_ms":37254.041666666664,"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":10,"max_ms":74310,"mean_ms":41174.25,"min_ms":21597,"run_count":8}},"codegen_output_tokens":{"attempt_count":58,"output_max":15813,"output_mean":7191.916666666667,"output_min":1943,"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":10,"output_max":6022,"output_mean":2920.75,"output_min":1943,"run_count":8}},"display_name":"o3","economics":{"all":46.672840722881666,"highest":48.302906443152345,"medium":46.17212106801713,"none":42.464764595431845},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[100000],"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":82,"output_token_observations":58,"provider_post_attempt_observations":10,"provider_post_attempts":10,"reasoning_token_observations":10,"reconciliation_get_attempt_observations":10,"requested_max_output_token_observations":10,"requested_max_output_tokens":[100000],"total_output_tokens":345212,"total_reasoning_output_tokens":5824,"total_visible_output_tokens":17542,"visible_token_observations":10},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":19,"evaluated_cells":32,"failed_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.6785714285714286,"game_attempts":{"GB2-01":{"admitted":3,"model_code_failures":1},"GB2-02":{"performance_rejections":4},"GB2-03":{"admitted":1,"model_code_failures":3},"GB2-04":{"model_code_failures":4},"GB2-05":{"admitted":4},"GB2-06":{"admitted":4},"GB2-07":{"admitted":4},"GB2-08":{"admitted":3,"model_code_failures":1}},"model_code_failure_rate":0.32142857142857145,"model_code_failures":9,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-02"],"performance_rejections":4}},"headline_games_all":{"GB2-01":{"attempts":6,"failed_attempts":1,"playable":45.7418154303235,"score":40.71583624073296},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":42.832890281616656,"score":21.416445140808328},"GB2-03":{"attempts":6,"failed_attempts":4,"playable":39.009720511311585,"score":17.079049447703735},"GB2-04":{"attempts":6,"failed_attempts":4,"playable":42.811669841503374,"score":28.541113227668916},"GB2-05":{"attempts":6,"playable":48.444966086933526,"score":48.444966086933526},"GB2-06":{"attempts":6,"playable":45.04770177500351,"score":45.04770177500351},"GB2-07":{"attempts":6,"playable":47.07899889691188,"score":47.07899889691188},"GB2-08":{"attempts":6,"failed_attempts":1,"playable":43.0713234279852,"score":39.035723389270736}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":60.3117502750864,"score":45.2338127063148},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":35.70972357268263,"score":8.927430893170657},"GB2-04":{"attempts":4,"failed_attempts":4,"score":0.0},"GB2-05":{"attempts":4,"playable":48.97091292078867,"score":48.97091292078867},"GB2-06":{"attempts":4,"playable":41.360962083898585,"score":41.360962083898585},"GB2-07":{"attempts":4,"playable":43.098695350132004,"score":43.098695350132004},"GB2-08":{"attempts":4,"failed_attempts":1,"playable":48.42720046457364,"score":36.320400348430226}},"medium":{"GB2-01":{"attempts":1,"playable":38.19064169039569,"score":38.19064169039569},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":41.178506669666476,"score":41.178506669666476},"GB2-05":{"attempts":1,"playable":45.46171355019105,"score":45.46171355019105},"GB2-06":{"attempts":1,"playable":45.78381345051227,"score":45.78381345051227},"GB2-07":{"attempts":1,"playable":59.109065822758886,"score":59.109065822758886},"GB2-08":{"attempts":1,"playable":47.308985224578365,"score":47.308985224578365}},"none":{"GB2-01":{"attempts":1,"playable":38.72305432548841,"score":38.72305432548841},"GB2-02":{"attempts":1,"playable":42.832890281616656,"score":42.832890281616656},"GB2-03":{"attempts":1,"playable":42.30971744994054,"score":42.30971744994054},"GB2-04":{"attempts":1,"playable":44.444833013340265,"score":44.444833013340265},"GB2-05":{"attempts":1,"playable":50.90227178982085,"score":50.90227178982085},"GB2-06":{"attempts":1,"playable":47.99832979059968,"score":47.99832979059968},"GB2-07":{"attempts":1,"playable":39.02923551784475,"score":39.02923551784475},"GB2-08":{"attempts":1,"playable":33.47778459480361,"score":33.47778459480361}}},"id":"o3","is_recent_addition":false,"last_measured_at":"2026-10-20T11:12:27Z","match_totals_all":{"draws":2370,"losses":7405,"wins":5699},"match_totals_tracks":{"highest":{"draws":817,"losses":4447,"wins":3700},"medium":{"draws":516,"losses":1291,"wins":1009},"none":{"draws":1037,"losses":1667,"wins":990}},"model_slug":"o3","overall":{"max":59.109065822758886,"mean":36.360438194183224,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":44,"overall_ranking_status":"ranked","per_game":{"GB2-01":60.3117502750864,"GB2-03":35.70972357268263,"GB2-05":52.474101669154905,"GB2-06":43.29283858300147,"GB2-07":43.098695350132004,"GB2-08":54.93032920885664},"per_game_all":{"GB2-01":45.7418154303235,"GB2-05":49.612695669722264,"GB2-06":45.69166060803781,"GB2-07":47.07899889691188,"GB2-08":45.23903300941287},"per_game_match_totals_all":{"GB2-01":{"draws":268,"losses":1020,"wins":1052},"GB2-02":{"draws":349,"losses":78,"wins":5},"GB2-03":{"draws":241,"losses":453,"wins":198},"GB2-04":{"draws":545,"losses":251,"wins":100},"GB2-05":{"draws":0,"losses":1497,"wins":1407},"GB2-06":{"draws":62,"losses":1580,"wins":1094},"GB2-07":{"draws":0,"losses":1620,"wins":1224},"GB2-08":{"draws":905,"losses":906,"wins":619}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":139,"losses":499,"wins":766},"GB2-03":{"draws":118,"losses":242,"wins":86},"GB2-05":{"draws":0,"losses":993,"wins":943},"GB2-06":{"draws":27,"losses":1093,"wins":704},"GB2-07":{"draws":0,"losses":1119,"wins":777},"GB2-08":{"draws":533,"losses":501,"wins":424}},"medium":{"GB2-01":{"draws":90,"losses":249,"wins":129},"GB2-04":{"draws":306,"losses":116,"wins":26},"GB2-05":{"draws":0,"losses":265,"wins":219},"GB2-06":{"draws":27,"losses":244,"wins":185},"GB2-07":{"draws":0,"losses":201,"wins":273},"GB2-08":{"draws":93,"losses":216,"wins":177}},"none":{"GB2-01":{"draws":39,"losses":272,"wins":157},"GB2-02":{"draws":349,"losses":78,"wins":5},"GB2-03":{"draws":123,"losses":211,"wins":112},"GB2-04":{"draws":239,"losses":135,"wins":74},"GB2-05":{"draws":0,"losses":239,"wins":245},"GB2-06":{"draws":8,"losses":243,"wins":205},"GB2-07":{"draws":0,"losses":300,"wins":174},"GB2-08":{"draws":279,"losses":189,"wins":18}}},"per_game_raw_elo_all":{"GB2-01":1442.5997809396306,"GB2-05":1447.685409218966,"GB2-06":1388.7889937080256,"GB2-07":1414.513003471815,"GB2-08":1389.124760133004},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1584.6153542774857,"GB2-03":1306.918701462269,"GB2-05":1483.9544452966195,"GB2-06":1352.0972584829278,"GB2-07":1362.9997283630612,"GB2-08":1521.1613225195097},"medium":{"GB2-01":1368.9704452520893,"GB2-04":1409.7112652238734,"GB2-05":1395.6362657568977,"GB2-06":1390.2313113730754,"GB2-07":1566.860578920202,"GB2-08":1394.0030850549897},"none":{"GB2-01":1374.2135432893172,"GB2-02":1420.471198317911,"GB2-03":1365.172942448906,"GB2-04":1435.1061482213624,"GB2-05":1463.4655166033804,"GB2-06":1424.0384112680742,"GB2-07":1313.6787031321821,"GB2-08":1252.209872824512}},"per_game_tracks":{"highest":{"GB2-01":60.3117502750864,"GB2-03":35.70972357268263,"GB2-05":52.474101669154905,"GB2-06":43.29283858300147,"GB2-07":43.098695350132004,"GB2-08":54.93032920885664},"medium":{"GB2-01":38.19064169039569,"GB2-04":41.178506669666476,"GB2-05":45.46171355019105,"GB2-06":45.78381345051227,"GB2-07":59.109065822758886,"GB2-08":47.308985224578365},"none":{"GB2-01":38.72305432548841,"GB2-02":42.832890281616656,"GB2-03":42.30971744994054,"GB2-04":44.444833013340265,"GB2-05":50.90227178982085,"GB2-06":47.99832979059968,"GB2-07":39.02923551784475,"GB2-08":33.47778459480361}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:38:16Z","reasoning":{"highest":31.987459186104985,"medium":34.62909080101284,"none":42.464764595431845},"reasoning_agg":{"highest":{"max":48.97091292078867,"mean":31.987459186104985,"min":0.0},"medium":{"max":59.109065822758886,"mean":34.62909080101284,"min":0.0},"none":{"max":50.90227178982085,"mean":42.464764595431845,"min":33.47778459480361}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.47730540932686}},{"canonical_public_row_identity":"publication-row.v1:overall:bytedance-seed-seed-2-0-code:417d288b9594825c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.075846,"mean":0.050721249999999996,"median":0.04471025,"min":0.0372345,"recorded_attempt_count":11,"run_count":8,"total":0.40577},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.071558,"mean":0.053513000000000005,"median":0.0517895,"min":0.034152,"recorded_attempt_count":14,"run_count":8,"total":0.42810399999999993},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.030187,"mean":0.020951124999999998,"median":0.0183875,"min":0.0121355,"recorded_attempt_count":9,"run_count":8,"total":0.16760899999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.071558,"mean":0.053513000000000005,"median":0.0517895,"min":0.034152,"recorded_attempt_count":14,"run_count":8,"total":0.42810399999999993},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.030187,"mean":0.020951124999999998,"median":0.0183875,"min":0.0121355,"recorded_attempt_count":9,"run_count":8,"total":0.167609},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.075846,"mean":0.050721249999999996,"median":0.04471025,"min":0.0372345,"recorded_attempt_count":11,"run_count":8,"total":0.40576999999999996}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.075846,"mean":0.041728458333333336,"median":0.04202725,"min":0.0121355,"recorded_attempt_count":34,"run_count":24,"total":1.001483},"codegen_latency_ms":{"attempt_count":34,"max_ms":395404,"mean_ms":199903.16666666666,"min_ms":55601,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":395404,"mean_ms":251379.375,"min_ms":180439,"run_count":8},"medium":{"attempt_count":14,"max_ms":353826,"mean_ms":258198.75,"min_ms":158866,"run_count":8},"none":{"attempt_count":9,"max_ms":131809,"mean_ms":90131.375,"min_ms":55601,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":22808,"output_mean":12018.333333333334,"output_min":2752,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":22808,"output_mean":15068.125,"output_min":11085,"run_count":8},"medium":{"attempt_count":14,"output_max":21381,"output_mean":15556.75,"output_min":10057,"run_count":8},"none":{"attempt_count":9,"output_max":8609,"output_mean":5430.125,"output_min":2752,"run_count":8}},"display_name":"Seed 2.0 Code","economics":{"all":39.400979251776796,"highest":41.69541117591993,"medium":45.9041129291832,"none":29.7538285402816},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":34,"finish_reasons":["stop"],"indexed_attempts":34,"output_token_observations":34,"provider_post_attempt_observations":34,"provider_post_attempts":34,"reasoning_token_observations":34,"reconciliation_get_attempt_observations":34,"reconciliation_get_attempts":157,"total_output_tokens":288440,"total_reasoning_output_tokens":204471,"total_visible_output_tokens":83969,"visible_token_observations":34},"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":"bytedance-seed","provider_model":"bytedance-seed/seed-2.0-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":2,"first_pass_rate":0.25,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":38.217658076561285,"score":38.217658076561285},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":39.918915642425674,"score":26.612610428283784},"GB2-03":{"attempts":3,"playable":42.72423649927404,"score":42.72423649927404},"GB2-04":{"attempts":3,"playable":40.538776047704964,"score":40.538776047704964},"GB2-05":{"attempts":3,"playable":38.611123372034356,"score":38.611123372034356},"GB2-06":{"attempts":3,"playable":17.441148680810716,"score":17.441148680810716},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":37.056710938389706,"score":24.70447395892647},"GB2-08":{"attempts":3,"playable":58.87293283427539,"score":58.87293283427539}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":40.53186376581151,"score":40.53186376581151},"GB2-02":{"attempts":1,"playable":40.26902894766237,"score":40.26902894766237},"GB2-03":{"attempts":1,"playable":42.65396260046989,"score":42.65396260046989},"GB2-04":{"attempts":1,"playable":38.808734192147654,"score":38.808734192147654},"GB2-05":{"attempts":1,"playable":50.483660294564714,"score":50.483660294564714},"GB2-06":{"attempts":1,"playable":19.795186035547452,"score":19.795186035547452},"GB2-07":{"attempts":1,"playable":45.41429428775638,"score":45.41429428775638},"GB2-08":{"attempts":1,"playable":55.60655928339949,"score":55.60655928339949}},"medium":{"GB2-01":{"attempts":1,"playable":50.50001249296818,"score":50.50001249296818},"GB2-02":{"attempts":1,"playable":39.56880233718898,"score":39.56880233718898},"GB2-03":{"attempts":1,"playable":40.12220594818917,"score":40.12220594818917},"GB2-04":{"attempts":1,"playable":40.61460813983791,"score":40.61460813983791},"GB2-05":{"attempts":1,"playable":48.60003105671666,"score":48.60003105671666},"GB2-06":{"attempts":1,"playable":14.493770736299494,"score":14.493770736299494},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":87.429359793082,"score":87.429359793082}},"none":{"GB2-01":{"attempts":1,"playable":23.621097970904177,"score":23.621097970904177},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":45.39654094916306,"score":45.39654094916306},"GB2-04":{"attempts":1,"playable":42.19298581112933,"score":42.19298581112933},"GB2-05":{"attempts":1,"playable":16.7496787648217,"score":16.7496787648217},"GB2-06":{"attempts":1,"playable":18.034489270585198,"score":18.034489270585198},"GB2-07":{"attempts":1,"playable":28.69912758902304,"score":28.69912758902304},"GB2-08":{"attempts":1,"playable":33.58287942634469,"score":33.58287942634469}}},"id":"bytedance-seed/seed-2.0-code","is_recent_addition":false,"last_measured_at":"2026-10-20T11:22:36Z","match_totals_all":{"draws":2737,"losses":4948,"wins":2491},"match_totals_tracks":{"highest":{"draws":1165,"losses":1621,"wins":908},"medium":{"draws":762,"losses":1384,"wins":1074},"none":{"draws":810,"losses":1943,"wins":509}},"model_slug":"bytedance-seed-seed-2-0-code","overall":{"max":87.429359793082,"mean":35.96536998723388,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":45,"overall_ranking_status":"ranked","per_game":{"GB2-01":40.53186376581151,"GB2-02":40.26902894766237,"GB2-03":42.65396260046989,"GB2-04":38.808734192147654,"GB2-05":50.483660294564714,"GB2-06":19.795186035547452,"GB2-07":45.41429428775638,"GB2-08":55.60655928339949},"per_game_all":{"GB2-01":38.217658076561285,"GB2-03":42.72423649927404,"GB2-04":40.538776047704964,"GB2-05":38.611123372034356,"GB2-06":17.441148680810716,"GB2-08":58.87293283427539},"per_game_match_totals_all":{"GB2-01":{"draws":360,"losses":701,"wins":343},"GB2-02":{"draws":648,"losses":206,"wins":10},"GB2-03":{"draws":310,"losses":657,"wins":371},"GB2-04":{"draws":893,"losses":369,"wins":82},"GB2-05":{"draws":0,"losses":895,"wins":557},"GB2-06":{"draws":8,"losses":1148,"wins":212},"GB2-07":{"draws":0,"losses":618,"wins":330},"GB2-08":{"draws":518,"losses":354,"wins":586}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":188,"losses":189,"wins":91},"GB2-02":{"draws":329,"losses":99,"wins":4},"GB2-03":{"draws":120,"losses":211,"wins":115},"GB2-04":{"draws":289,"losses":135,"wins":24},"GB2-05":{"draws":0,"losses":241,"wins":243},"GB2-06":{"draws":2,"losses":373,"wins":81},"GB2-07":{"draws":0,"losses":269,"wins":205},"GB2-08":{"draws":237,"losses":104,"wins":145}},"medium":{"GB2-01":{"draws":62,"losses":205,"wins":201},"GB2-02":{"draws":319,"losses":107,"wins":6},"GB2-03":{"draws":96,"losses":234,"wins":116},"GB2-04":{"draws":283,"losses":130,"wins":35},"GB2-05":{"draws":0,"losses":250,"wins":234},"GB2-06":{"draws":1,"losses":396,"wins":59},"GB2-08":{"draws":1,"losses":62,"wins":423}},"none":{"GB2-01":{"draws":110,"losses":307,"wins":51},"GB2-03":{"draws":94,"losses":212,"wins":140},"GB2-04":{"draws":321,"losses":104,"wins":23},"GB2-05":{"draws":0,"losses":404,"wins":80},"GB2-06":{"draws":5,"losses":379,"wins":72},"GB2-07":{"draws":0,"losses":349,"wins":125},"GB2-08":{"draws":280,"losses":188,"wins":18}}},"per_game_raw_elo_all":{"GB2-01":1363.6678045634899,"GB2-03":1368.765275666998,"GB2-04":1404.6563768037995,"GB2-05":1284.781705551156,"GB2-06":952.2658230118996,"GB2-08":1601.5415029725164},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1391.8906852388682,"GB2-02":1400.5065732742958,"GB2-03":1368.17497224144,"GB2-04":1391.0456619731683,"GB2-05":1458.246584286411,"GB2-06":993.363301522623,"GB2-07":1393.3622685126227,"GB2-08":1487.428862699637},"medium":{"GB2-01":1487.3595816642905,"GB2-02":1395.0085032498407,"GB2-03":1346.0463996855215,"GB2-04":1405.2927587447987,"GB2-05":1434.795490953651,"GB2-06":899.7400773941482,"GB2-08":2063.9112303331085},"none":{"GB2-01":1211.753146787311,"GB2-03":1392.0744550740328,"GB2-04":1417.6307096934313,"GB2-05":961.3030414134053,"GB2-06":963.6940901189275,"GB2-07":1177.7830455509798,"GB2-08":1253.284415884804}},"per_game_tracks":{"highest":{"GB2-01":40.53186376581151,"GB2-02":40.26902894766237,"GB2-03":42.65396260046989,"GB2-04":38.808734192147654,"GB2-05":50.483660294564714,"GB2-06":19.795186035547452,"GB2-07":45.41429428775638,"GB2-08":55.60655928339949},"medium":{"GB2-01":50.50001249296818,"GB2-02":39.56880233718898,"GB2-03":40.12220594818917,"GB2-04":40.61460813983791,"GB2-05":48.60003105671666,"GB2-06":14.493770736299494,"GB2-08":87.429359793082},"none":{"GB2-01":23.621097970904177,"GB2-03":45.39654094916306,"GB2-04":42.19298581112933,"GB2-05":16.7496787648217,"GB2-06":18.034489270585198,"GB2-07":28.69912758902304,"GB2-08":33.58287942634469}},"provider_color":"#F44336","provider_company":"ByteDance","provider_key":"bytedance-seed","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:41:24Z","reasoning":{"highest":41.69541117591993,"medium":40.1660988130353,"none":26.0345999727464},"reasoning_agg":{"highest":{"max":55.60655928339949,"mean":41.69541117591993,"min":19.795186035547452},"medium":{"max":87.429359793082,"mean":40.1660988130353,"min":0.0},"none":{"max":45.39654094916306,"mean":26.0345999727464,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":15.66081120317353}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-27b:46d75de3b4280668","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3521656,"mean":0.19569013062499999,"median":0.187188825,"min":0.119031025,"recorded_attempt_count":11,"run_count":8,"total":1.565521045},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.06623293499999999,"mean":0.04480870625,"median":0.0402421875,"min":0.0205156,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.35846965},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.028626384999999997,"mean":0.021101813124999997,"median":0.024224999999999997,"min":0.00651321,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.168814505}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.06623293499999999,"mean":0.04480870625,"median":0.0402421875,"min":0.0205156,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.35846965000000003},"historical-provider-setting-baseline":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.028626384999999997,"mean":0.021101813124999997,"median":0.024224999999999997,"min":0.00651321,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.168814505},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3521656,"mean":0.19569013062499999,"median":0.187188825,"min":0.119031025,"recorded_attempt_count":11,"run_count":8,"total":1.5655210449999999}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":24,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.3521656,"mean":0.08720021666666666,"median":0.0402421875,"min":0.00651321,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"recorded_attempt_count":38,"run_count":24,"total":2.0928052000000004},"codegen_latency_ms":{"attempt_count":38,"max_ms":2128037,"mean_ms":537328.375,"min_ms":33625,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":2128037,"mean_ms":1259891.875,"min_ms":809012,"run_count":8},"medium":{"attempt_count":13,"max_ms":394009,"mean_ms":249918.25,"min_ms":106640,"run_count":8},"none":{"attempt_count":14,"max_ms":139550,"mean_ms":102175.0,"min_ms":33625,"run_count":8}},"codegen_output_tokens":{"attempt_count":38,"output_max":142524,"output_mean":33293.458333333336,"output_min":2177,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":142524,"output_mean":77872.0,"output_min":45409,"run_count":8},"medium":{"attempt_count":13,"output_max":24263,"output_mean":15845.5,"output_min":6781,"run_count":8},"none":{"attempt_count":14,"output_max":9194,"output_mean":6162.875,"output_min":2177,"run_count":8}},"display_name":"Qwen3.8 27B","economics":{"all":45.4932006841819,"highest":59.82531133882714,"medium":46.52912805720205,"none":35.17496973566356},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"effective_max_output_tokens":[131072],"finish_reason_observations":38,"finish_reasons":["stop"],"indexed_attempts":38,"output_token_observations":38,"provider_post_attempt_observations":38,"provider_post_attempts":41,"reasoning_token_observations":38,"reconciliation_get_attempt_observations":38,"reconciliation_get_attempts":53,"requested_max_output_token_observations":27,"requested_max_output_tokens":[131072],"total_output_tokens":799043,"total_reasoning_output_tokens":636129,"total_visible_output_tokens":162914,"visible_token_observations":38},"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/qwen3.8-27b","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":["GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":2,"first_pass_rate":0.25,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.5,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":50.67742544331375,"score":50.67742544331375},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.36716003714194,"score":28.24477335809463},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":45.67208269274842,"score":30.448055128498947},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":55.74868458373541,"score":37.165789722490274},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":59.48047218142314,"score":39.65364812094876},"GB2-06":{"attempts":3,"playable":40.30897592505004,"score":40.30897592505004},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":49.431762816038606,"score":32.954508544025735},"GB2-08":{"attempts":3,"failed_attempts":2,"playable":46.996114648765065,"score":15.665371549588356}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":74.8302397535435,"score":74.8302397535435},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":71.3340312615993,"score":71.3340312615993},"GB2-05":{"attempts":1,"playable":59.68951458505206,"score":59.68951458505206},"GB2-06":{"attempts":1,"playable":28.34872283440046,"score":28.34872283440046},"GB2-07":{"attempts":1,"playable":77.75324494960249,"score":77.75324494960249},"GB2-08":{"attempts":1,"playable":46.996114648765065,"score":46.996114648765065}},"medium":{"GB2-01":{"attempts":1,"playable":52.8261482000463,"score":52.8261482000463},"GB2-02":{"attempts":1,"playable":42.250704660746386,"score":42.250704660746386},"GB2-03":{"attempts":1,"playable":48.23169961099186,"score":48.23169961099186},"GB2-04":{"attempts":1,"playable":40.163337905871515,"score":40.163337905871515},"GB2-05":{"attempts":1,"playable":59.27142977779422,"score":59.27142977779422},"GB2-06":{"attempts":1,"playable":61.850295562489364,"score":61.850295562489364},"GB2-07":{"attempts":1,"playable":21.11028068247472,"score":21.11028068247472},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"playable":24.375888376351465,"score":24.375888376351465},"GB2-02":{"attempts":1,"playable":42.4836154135375,"score":42.4836154135375},"GB2-03":{"attempts":1,"playable":43.112465774504976,"score":43.112465774504976},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":30.7279093782603,"score":30.7279093782603},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"qwen/qwen3.8-27b","is_recent_addition":false,"last_measured_at":"2026-10-14T17:59:10Z","match_totals_all":{"draws":1812,"losses":3224,"wins":2790},"match_totals_tracks":{"highest":{"draws":310,"losses":1004,"wins":1502},"medium":{"draws":918,"losses":1304,"wins":986},"none":{"draws":584,"losses":916,"wins":302}},"model_slug":"qwen-qwen3-8-27b","overall":{"max":77.75324494960249,"mean":34.38981847400131,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":46,"overall_ranking_status":"partial","per_game":{"GB2-01":74.8302397535435,"GB2-04":71.3340312615993,"GB2-05":59.68951458505206,"GB2-06":28.34872283440046,"GB2-07":77.75324494960249,"GB2-08":46.996114648765065},"per_game_all":{"GB2-01":50.67742544331375,"GB2-06":40.30897592505004},"per_game_match_totals_all":{"GB2-01":{"draws":244,"losses":582,"wins":578},"GB2-02":{"draws":692,"losses":163,"wins":9},"GB2-03":{"draws":255,"losses":388,"wins":249},"GB2-04":{"draws":420,"losses":197,"wins":279},"GB2-05":{"draws":0,"losses":396,"wins":572},"GB2-06":{"draws":53,"losses":817,"wins":498},"GB2-07":{"draws":0,"losses":491,"wins":457},"GB2-08":{"draws":148,"losses":190,"wins":148}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":9,"losses":116,"wins":343},"GB2-04":{"draws":135,"losses":66,"wins":247},"GB2-05":{"draws":0,"losses":197,"wins":287},"GB2-06":{"draws":18,"losses":328,"wins":110},"GB2-07":{"draws":0,"losses":107,"wins":367},"GB2-08":{"draws":148,"losses":190,"wins":148}},"medium":{"GB2-01":{"draws":104,"losses":173,"wins":191},"GB2-02":{"draws":346,"losses":82,"wins":4},"GB2-03":{"draws":161,"losses":166,"wins":119},"GB2-04":{"draws":285,"losses":131,"wins":32},"GB2-05":{"draws":0,"losses":199,"wins":285},"GB2-06":{"draws":22,"losses":169,"wins":265},"GB2-07":{"draws":0,"losses":384,"wins":90}},"none":{"GB2-01":{"draws":131,"losses":293,"wins":44},"GB2-02":{"draws":346,"losses":81,"wins":5},"GB2-03":{"draws":94,"losses":222,"wins":130},"GB2-06":{"draws":13,"losses":320,"wins":123}}},"per_game_raw_elo_all":{"GB2-01":1491.2285965312785,"GB2-06":1311.804487511679},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1743.1474321753813,"GB2-04":1659.7376963876363,"GB2-05":1575.98720538982,"GB2-06":1127.5645659192107,"GB2-07":1851.2609804324409,"GB2-08":1390.676422999513},"medium":{"GB2-01":1509.6245707082765,"GB2-02":1415.9569652099042,"GB2-03":1416.8692746386585,"GB2-04":1401.7471641870025,"GB2-05":1570.4158023713994,"GB2-06":1644.3374268554348,"GB2-07":1063.6275861306992},"none":{"GB2-01":1220.9137867101776,"GB2-02":1417.764083768876,"GB2-03":1372.17154290952,"GB2-06":1163.5114697603917}},"per_game_tracks":{"highest":{"GB2-01":74.8302397535435,"GB2-04":71.3340312615993,"GB2-05":59.68951458505206,"GB2-06":28.34872283440046,"GB2-07":77.75324494960249,"GB2-08":46.996114648765065},"medium":{"GB2-01":52.8261482000463,"GB2-02":42.250704660746386,"GB2-03":48.23169961099186,"GB2-04":40.163337905871515,"GB2-05":59.27142977779422,"GB2-06":61.850295562489364,"GB2-07":21.11028068247472},"none":{"GB2-01":24.375888376351465,"GB2-02":42.4836154135375,"GB2-03":43.112465774504976,"GB2-06":30.7279093782603}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":44.86898350412036,"medium":40.7129870500518,"none":17.58748486783178},"reasoning_agg":{"highest":{"max":77.75324494960249,"mean":44.86898350412036,"min":0.0},"medium":{"max":61.850295562489364,"mean":40.7129870500518,"min":0.0},"none":{"max":43.112465774504976,"mean":17.58748486783178,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":27.28149863628858}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-flash:bc29f998e211af2f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01423672,"mean":0.0073094338874999994,"median":0.0062260825200000005,"min":0.004397959999999999,"recorded_attempt_count":13,"run_count":8,"total":0.0584754711},"medium":{"admitted_cell_count":22,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.008042989573333334,"mean":0.0037891845841666666,"median":0.0032265161666666666,"min":0.002126702,"recorded_attempt_count":36,"run_count":24,"total":0.09094043002000002},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00200925116,"mean":0.0013339496149999998,"median":0.0012586017,"min":0.0008945895,"recorded_attempt_count":10,"run_count":8,"total":0.010671596920000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01663094,"mean":0.00499588742,"median":0.0034890575,"min":0.00258188,"recorded_attempt_count":12,"run_count":8,"total":0.03996709936000001},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.004911942999999999,"mean":0.0031858331662499998,"median":0.002947833025,"min":0.001831717,"recorded_attempt_count":24,"run_count":16,"total":0.05097333066},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00200925116,"mean":0.0013339496149999998,"median":0.0012586017,"min":0.0008945895,"recorded_attempt_count":10,"run_count":8,"total":0.010671596919999998},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01423672,"mean":0.0073094338874999994,"median":0.0062260825200000005,"min":0.004397959999999999,"recorded_attempt_count":13,"run_count":8,"total":0.0584754711}},"codegen_cost_usd":{"admitted_cell_count":36,"cell_count":24,"cost_basis_counts":{"provider_reported":59},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01423672,"mean":0.004144189362222222,"median":0.0032265161666666666,"min":0.0008945895,"recorded_attempt_count":59,"run_count":40,"total":0.16008749804},"codegen_latency_ms":{"attempt_count":35,"max_ms":2156476,"mean_ms":402937.5,"min_ms":36579,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":13,"max_ms":2156476,"mean_ms":830597.625,"min_ms":100447,"run_count":8},"medium":{"attempt_count":12,"max_ms":572210,"mean_ms":258473.0,"min_ms":66883,"run_count":8},"none":{"attempt_count":10,"max_ms":286097,"mean_ms":119741.875,"min_ms":36579,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":54472,"output_mean":14159.166666666666,"output_min":1979,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":13,"output_max":47250,"output_mean":26393.0,"output_min":7308,"run_count":8},"medium":{"attempt_count":12,"output_max":54472,"output_mean":12951.25,"output_min":5048,"run_count":8},"none":{"attempt_count":10,"output_max":4856,"output_mean":3133.25,"output_min":1979,"run_count":8}},"display_name":"DeepSeek V4 Flash","economics":{"all":37.566372143968046,"highest":41.516286014330085,"medium":37.15862290783301,"none":35.48863819857725},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":35,"finish_reasons":["stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":35,"provider_post_attempts":35,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":35,"reconciliation_get_attempts":166,"total_output_tokens":339820,"total_reasoning_output_tokens":258096,"total_visible_output_tokens":81724,"visible_token_observations":35},"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-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":22,"evaluated_cells":22,"first_pass_admitted":15,"first_pass_rate":0.6818181818181818,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":3},"GB2-03":{"admitted":2,"infra_failures_excluded":1},"GB2-04":{"admitted":2,"infra_failures_excluded":1},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":3},"GB2-08":{"admitted":3}},"infra_excluded_game_aliases":["GB2-03","GB2-04"],"infra_failures_excluded":2,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.3181818181818182},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-05"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":5,"playable":24.94403744405855,"score":24.94403744405855},"GB2-02":{"attempts":5,"playable":41.61425959835939,"score":41.61425959835939},"GB2-03":{"attempts":4,"playable":37.64475838690311,"score":37.64475838690311},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":41.40343968891005,"score":27.602293125940033},"GB2-05":{"attempts":5,"failed_attempts":1,"playable":35.50871662704829,"score":23.672477751365523},"GB2-06":{"attempts":5,"playable":55.1142086555653,"score":55.1142086555653},"GB2-07":{"attempts":5,"playable":28.170213858296204,"score":28.170213858296204},"GB2-08":{"attempts":5,"playable":34.0362001949056,"score":34.0362001949056}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":15.709716312200175,"score":15.709716312200175},"GB2-02":{"attempts":1,"playable":42.94929079597173,"score":42.94929079597173},"GB2-03":{"attempts":1,"playable":34.42319523116485,"score":34.42319523116485},"GB2-04":{"attempts":1,"playable":42.08030046149943,"score":42.08030046149943},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":81.89874107761575,"score":81.89874107761575},"GB2-07":{"attempts":1,"playable":39.444440666154506,"score":39.444440666154506},"GB2-08":{"attempts":1,"playable":34.10831755570414,"score":34.10831755570414}},"medium":{"GB2-01":{"attempts":3,"playable":38.41863634478289,"score":38.41863634478289},"GB2-02":{"attempts":3,"playable":39.75925688822895,"score":39.75925688822895},"GB2-03":{"attempts":2,"playable":43.7366050405458,"score":43.7366050405458},"GB2-04":{"attempts":2,"playable":40.72657891632067,"score":40.72657891632067},"GB2-05":{"attempts":3,"playable":26.183120561817066,"score":26.183120561817066},"GB2-06":{"attempts":3,"playable":26.205589993823313,"score":26.205589993823313},"GB2-07":{"attempts":3,"playable":25.49824396720292,"score":25.49824396720292},"GB2-08":{"attempts":3,"playable":38.83284584310818,"score":38.83284584310818}},"none":{"GB2-01":{"attempts":1,"playable":20.70375967519258,"score":20.70375967519258},"GB2-02":{"attempts":1,"playable":42.134231110877494,"score":42.134231110877494},"GB2-03":{"attempts":1,"playable":34.77447488899868,"score":34.77447488899868},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":44.834312692279504,"score":44.834312692279504},"GB2-06":{"attempts":1,"playable":57.238294895256836,"score":57.238294895256836},"GB2-07":{"attempts":1,"playable":19.567956941531186,"score":19.567956941531186},"GB2-08":{"attempts":1,"playable":29.167437185904454,"score":29.167437185904454}}},"id":"deepseek/deepseek-v4-flash","is_recent_addition":false,"last_measured_at":"2026-10-20T11:29:56Z","match_totals_all":{"draws":4603,"losses":8627,"wins":3414},"match_totals_tracks":{"highest":{"draws":1104,"losses":1376,"wins":730},"medium":{"draws":2724,"losses":5492,"wins":1972},"none":{"draws":775,"losses":1759,"wins":712}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":81.89874107761575,"mean":34.099806126924214,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":47,"overall_ranking_status":"ranked","per_game":{"GB2-01":15.709716312200175,"GB2-02":42.94929079597173,"GB2-03":34.42319523116485,"GB2-04":42.08030046149943,"GB2-06":81.89874107761575,"GB2-07":39.444440666154506,"GB2-08":34.10831755570414},"per_game_all":{"GB2-01":24.533873154992392,"GB2-02":41.76362841358545,"GB2-03":37.64475838690311,"GB2-06":57.087442416862444,"GB2-07":29.089354685936314,"GB2-08":35.279175805528546},"per_game_match_totals_all":{"GB2-01":{"draws":378,"losses":1462,"wins":500},"GB2-02":{"draws":1637,"losses":486,"wins":37},"GB2-03":{"draws":526,"losses":881,"wins":377},"GB2-04":{"draws":892,"losses":361,"wins":91},"GB2-05":{"draws":0,"losses":1344,"wins":592},"GB2-06":{"draws":56,"losses":1289,"wins":935},"GB2-07":{"draws":0,"losses":1778,"wins":592},"GB2-08":{"draws":1114,"losses":1026,"wins":290}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":99,"losses":349,"wins":20},"GB2-02":{"draws":324,"losses":90,"wins":18},"GB2-03":{"draws":135,"losses":239,"wins":72},"GB2-04":{"draws":268,"losses":131,"wins":49},"GB2-06":{"draws":27,"losses":69,"wins":360},"GB2-07":{"draws":0,"losses":298,"wins":176},"GB2-08":{"draws":251,"losses":200,"wins":35}},"medium":{"GB2-01":{"draws":178,"losses":788,"wins":438},"GB2-02":{"draws":964,"losses":315,"wins":17},"GB2-03":{"draws":261,"losses":402,"wins":229},"GB2-04":{"draws":624,"losses":230,"wins":42},"GB2-05":{"draws":0,"losses":1076,"wins":376},"GB2-06":{"draws":16,"losses":1024,"wins":328},"GB2-07":{"draws":0,"losses":1089,"wins":333},"GB2-08":{"draws":681,"losses":568,"wins":209}},"none":{"GB2-01":{"draws":101,"losses":325,"wins":42},"GB2-02":{"draws":349,"losses":81,"wins":2},"GB2-03":{"draws":130,"losses":240,"wins":76},"GB2-05":{"draws":0,"losses":268,"wins":216},"GB2-06":{"draws":13,"losses":196,"wins":247},"GB2-07":{"draws":0,"losses":391,"wins":83},"GB2-08":{"draws":182,"losses":258,"wins":46}}},"per_game_raw_elo_all":{"GB2-01":1208.4830863243972,"GB2-02":1412.079252017622,"GB2-03":1323.7886778504337,"GB2-06":1583.678082719629,"GB2-07":1169.9357248350561,"GB2-08":1271.3142883799094},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1102.2761419175633,"GB2-02":1421.3726630230817,"GB2-03":1295.2853847029332,"GB2-04":1416.7527463846307,"GB2-06":2009.9368787551211,"GB2-07":1318.9088919535798,"GB2-08":1258.64848514651},"medium":{"GB2-01":1348.560813836502,"GB2-02":1399.8124325271497,"GB2-03":1377.6058893648874,"GB2-04":1406.1194949519713,"GB2-05":1181.8779820653876,"GB2-06":1172.3741826273365,"GB2-07":1153.1691733807404,"GB2-08":1347.8548658996733},"none":{"GB2-01":1174.6123032191263,"GB2-02":1415.0526605026348,"GB2-03":1298.4747594834803,"GB2-05":1387.7632975530944,"GB2-06":1568.723186776429,"GB2-07":1037.7291091708485,"GB2-08":1207.4395140935449}},"per_game_tracks":{"highest":{"GB2-01":15.709716312200175,"GB2-02":42.94929079597173,"GB2-03":34.42319523116485,"GB2-04":42.08030046149943,"GB2-06":81.89874107761575,"GB2-07":39.444440666154506,"GB2-08":34.10831755570414},"medium":{"GB2-01":37.18814347758441,"GB2-02":40.207363333907125,"GB2-03":43.7366050405458,"GB2-04":40.72657891632067,"GB2-05":32.46756209149107,"GB2-06":32.125291277714744,"GB2-07":28.255666450123243,"GB2-08":42.56177267497704},"none":{"GB2-01":20.70375967519258,"GB2-02":42.134231110877494,"GB2-03":34.77447488899868,"GB2-05":44.834312692279504,"GB2-06":57.238294895256836,"GB2-07":19.567956941531186,"GB2-08":29.167437185904454}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T22:40:34Z","reasoning":{"highest":36.32675026253882,"medium":34.920109694478725,"none":31.05255842375509},"reasoning_agg":{"highest":{"max":81.89874107761575,"mean":36.32675026253882,"min":0.0},"medium":{"max":43.7366050405458,"mean":34.920109694478725,"min":25.49824396720292},"none":{"max":57.238294895256836,"mean":31.05255842375509,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":5.274191838783732}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash-lite:f78f5f2f111ce853","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"cost_is_complete":false,"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":0.9722945000000001},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"cost_is_complete":false,"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":0.6081093},"none":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":false,"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_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"cost_is_complete":false,"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":0.6081093},"historical-provider-setting-baseline":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":false,"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":0.2715711},"historical-provider-setting-intensive":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"cost_is_complete":false,"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":0.9722945000000001}},"codegen_cost_usd":{"admitted_cell_count":43,"cell_count":24,"cost_basis_counts":{"provider_reported":132},"cost_is_complete":false,"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":1.8519748999999999},"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":37.60933294596757,"highest":38.477715595415724,"medium":31.405219787595332,"none":42.945063454891645},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":1,"model_code_failures":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":15,"evaluated_cells":16,"failed_game_aliases":["GB2-03"],"first_pass_admitted":9,"first_pass_rate":0.5625,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":1,"model_code_failures":1},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0625,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"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,"game_attempts":{"GB2-01":{"admitted":1,"model_code_failures":1},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.0625}},"headline_games_all":{"GB2-01":{"attempts":6,"failed_attempts":1,"playable":37.88494454824042,"score":31.94622619423158},"GB2-02":{"attempts":6,"failed_attempts":2,"playable":43.27736402539819,"score":28.43756099748437},"GB2-03":{"attempts":6,"failed_attempts":1,"playable":47.894311216679085,"score":38.71850509515395},"GB2-04":{"attempts":6,"playable":43.42776238342038,"score":43.42776238342038},"GB2-05":{"attempts":6,"playable":15.437951641179367,"score":15.437951641179367},"GB2-06":{"attempts":6,"playable":37.8813783716081,"score":37.8813783716081},"GB2-07":{"attempts":6,"failed_attempts":1,"playable":42.46920958340624,"score":39.060814598480476},"GB2-08":{"attempts":6,"playable":32.60174179780875,"score":32.60174179780875}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":35.63231012405303,"score":17.816155062026514},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":44.92620119251952,"score":22.46310059625976},"GB2-03":{"attempts":2,"playable":47.06567629391702,"score":47.06567629391702},"GB2-04":{"attempts":2,"playable":39.88035752813174,"score":39.88035752813174},"GB2-05":{"attempts":2,"playable":18.3729711622035,"score":18.3729711622035},"GB2-06":{"attempts":2,"playable":43.362401817285175,"score":43.362401817285175},"GB2-07":{"attempts":2,"playable":45.10402205041221,"score":45.10402205041221},"GB2-08":{"attempts":2,"playable":33.47778459480361,"score":33.47778459480361}},"medium":{"GB2-01":{"attempts":2,"playable":41.1697711783785,"score":41.1697711783785},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":44.112616974963444,"score":22.056308487481722},"GB2-03":{"attempts":2,"playable":41.56242062696943,"score":41.56242062696943},"GB2-04":{"attempts":2,"playable":42.86837881806345,"score":42.86837881806345},"GB2-05":{"attempts":2,"playable":15.939467359773172,"score":15.939467359773172},"GB2-06":{"attempts":2,"playable":14.078876341837255,"score":14.078876341837255},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":20.450369909554578,"score":10.225184954777289},"GB2-08":{"attempts":2,"playable":31.059857091222824,"score":31.059857091222824}},"none":{"GB2-01":{"attempts":2,"playable":36.85275234228973,"score":36.85275234228973},"GB2-02":{"attempts":2,"playable":40.793273908711626,"score":40.793273908711626},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":55.054836729150814,"score":27.527418364575407},"GB2-04":{"attempts":2,"playable":47.53455080406596,"score":47.53455080406596},"GB2-05":{"attempts":2,"playable":12.001416401561425,"score":12.001416401561425},"GB2-06":{"attempts":2,"playable":56.202856955701876,"score":56.202856955701876},"GB2-07":{"attempts":2,"playable":61.85323679025192,"score":61.85323679025192},"GB2-08":{"attempts":2,"playable":33.26758370739982,"score":33.26758370739982}}},"id":"google/gemini-3.5-flash-lite","is_recent_addition":false,"last_measured_at":"2026-10-20T11:45:46Z","match_totals_all":{"draws":5180,"losses":9887,"wins":4359},"match_totals_tracks":{"highest":{"draws":1387,"losses":3099,"wins":1516},"medium":{"draws":1788,"losses":3667,"wins":1027},"none":{"draws":2005,"losses":3121,"wins":1816}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":61.85323679025192,"mean":33.43899263492087,"min":10.225184954777289},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":48,"overall_ranking_status":"ranked","per_game":{"GB2-01":35.63231012405303,"GB2-02":44.92620119251952,"GB2-03":47.06567629391702,"GB2-04":39.88035752813174,"GB2-05":18.3729711622035,"GB2-06":43.362401817285175,"GB2-07":45.10402205041221,"GB2-08":33.47778459480361},"per_game_all":{"GB2-01":37.88494454824042,"GB2-02":43.27736402539819,"GB2-03":47.894311216679085,"GB2-04":43.42776238342038,"GB2-05":15.437951641179367,"GB2-06":37.8813783716081,"GB2-07":42.46920958340624,"GB2-08":32.60174179780875},"per_game_match_totals_all":{"GB2-01":{"draws":421,"losses":1256,"wins":663},"GB2-02":{"draws":1364,"losses":331,"wins":33},"GB2-03":{"draws":497,"losses":1021,"wins":712},"GB2-04":{"draws":1664,"losses":722,"wins":302},"GB2-05":{"draws":0,"losses":2463,"wins":441},"GB2-06":{"draws":45,"losses":1719,"wins":972},"GB2-07":{"draws":0,"losses":1302,"wins":1068},"GB2-08":{"draws":1189,"losses":1073,"wins":168}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":94,"losses":259,"wins":115},"GB2-02":{"draws":323,"losses":82,"wins":27},"GB2-03":{"draws":134,"losses":435,"wins":323},"GB2-04":{"draws":531,"losses":284,"wins":81},"GB2-05":{"draws":0,"losses":792,"wins":176},"GB2-06":{"draws":30,"losses":515,"wins":367},"GB2-07":{"draws":0,"losses":541,"wins":407},"GB2-08":{"draws":275,"losses":191,"wins":20}},"medium":{"GB2-01":{"draws":156,"losses":482,"wins":298},"GB2-02":{"draws":364,"losses":65,"wins":3},"GB2-03":{"draws":283,"losses":410,"wins":199},"GB2-04":{"draws":600,"losses":223,"wins":73},"GB2-05":{"draws":0,"losses":816,"wins":152},"GB2-06":{"draws":5,"losses":794,"wins":113},"GB2-07":{"draws":0,"losses":387,"wins":87},"GB2-08":{"draws":380,"losses":490,"wins":102}},"none":{"GB2-01":{"draws":171,"losses":515,"wins":250},"GB2-02":{"draws":677,"losses":184,"wins":3},"GB2-03":{"draws":80,"losses":176,"wins":190},"GB2-04":{"draws":533,"losses":215,"wins":148},"GB2-05":{"draws":0,"losses":855,"wins":113},"GB2-06":{"draws":10,"losses":410,"wins":492},"GB2-07":{"draws":0,"losses":374,"wins":574},"GB2-08":{"draws":534,"losses":392,"wins":46}}},"per_game_raw_elo_all":{"GB2-01":1365.5110599914613,"GB2-02":1423.8609562766906,"GB2-03":1414.8570059440224,"GB2-04":1427.097190433383,"GB2-05":930.8499143495528,"GB2-06":1268.4848162244782,"GB2-07":1351.0744619751797,"GB2-08":1243.1337045808652},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1343.466819217614,"GB2-02":1436.6395777738958,"GB2-03":1407.9401482498427,"GB2-04":1399.4552207107317,"GB2-05":992.8764862459918,"GB2-06":1361.5155933651095,"GB2-07":1389.5044884749896,"GB2-08":1252.209872824512},"medium":{"GB2-01":1398.0811514008642,"GB2-02":1430.3651173422625,"GB2-03":1358.647692423426,"GB2-04":1422.8648193900574,"GB2-05":944.8820082561122,"GB2-06":891.4279357695156,"GB2-07":1052.6906403139787,"GB2-08":1227.1335913263104},"none":{"GB2-01":1354.9852093559055,"GB2-02":1404.5781737139127,"GB2-03":1477.9831771587983,"GB2-04":1458.971531199361,"GB2-05":854.7912485465542,"GB2-06":1552.51091953881,"GB2-07":1611.0282571365706,"GB2-08":1250.057649591773}},"per_game_tracks":{"highest":{"GB2-01":35.63231012405303,"GB2-02":44.92620119251952,"GB2-03":47.06567629391702,"GB2-04":39.88035752813174,"GB2-05":18.3729711622035,"GB2-06":43.362401817285175,"GB2-07":45.10402205041221,"GB2-08":33.47778459480361},"medium":{"GB2-01":41.1697711783785,"GB2-02":44.112616974963444,"GB2-03":41.56242062696943,"GB2-04":42.86837881806345,"GB2-05":15.939467359773172,"GB2-06":14.078876341837255,"GB2-07":20.450369909554578,"GB2-08":31.059857091222824},"none":{"GB2-01":36.85275234228973,"GB2-02":40.793273908711626,"GB2-03":55.054836729150814,"GB2-04":47.53455080406596,"GB2-05":12.001416401561425,"GB2-06":56.202856955701876,"GB2-07":61.85323679025192,"GB2-08":33.26758370739982}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:33:40Z","reasoning":{"highest":33.44280863812994,"medium":27.370033107312956,"none":39.504136159319714},"reasoning_agg":{"highest":{"max":47.06567629391702,"mean":33.44280863812994,"min":17.816155062026514},"medium":{"max":42.86837881806345,"mean":27.370033107312956,"min":10.225184954777289},"none":{"max":61.85323679025192,"mean":39.504136159319714,"min":12.001416401561425}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":12.134103052006758}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-space-bunny-alpha:ac228f4ce33a4444","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":15},"recorded_attempt_count":15,"run_count":8,"total":0.0},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.0},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":16},"recorded_attempt_count":16,"run_count":8,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":16},"recorded_attempt_count":16,"run_count":8,"total":0.0},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":15},"recorded_attempt_count":15,"run_count":8,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":19,"cell_count":24,"cost_basis_counts":{"provider_reported":42},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":42},"recorded_attempt_count":42,"run_count":24,"total":0.0},"codegen_latency_ms":{"attempt_count":42,"max_ms":537122,"mean_ms":137533.5,"min_ms":13879,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":15,"max_ms":537122,"mean_ms":335588.75,"min_ms":221492,"run_count":8},"medium":{"attempt_count":11,"max_ms":84351,"mean_ms":41299.125,"min_ms":13879,"run_count":8},"none":{"attempt_count":16,"max_ms":68645,"mean_ms":35712.625,"min_ms":19448,"run_count":8}},"codegen_output_tokens":{"attempt_count":42,"output_max":39424,"output_mean":14219.625,"output_min":2263,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":15,"output_max":39424,"output_mean":32529.75,"output_min":24807,"run_count":8},"medium":{"attempt_count":11,"output_max":9849,"output_mean":5340.25,"output_min":2263,"run_count":8},"none":{"attempt_count":16,"output_max":8167,"output_mean":4788.875,"output_min":2672,"run_count":8}},"display_name":"Space Bunny Alpha","economics":{"all":40.455471946002994,"highest":47.76121554353386,"medium":41.004020918030456,"none":37.77299863217675},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":42,"effective_max_output_tokens":[262144],"finish_reason_observations":42,"finish_reasons":["stop"],"indexed_attempts":42,"output_token_observations":42,"provider_post_attempt_observations":42,"provider_post_attempts":42,"reasoning_token_observations":42,"reconciliation_get_attempt_observations":42,"requested_max_output_token_observations":42,"requested_max_output_tokens":[262144],"total_output_tokens":341271,"total_visible_output_tokens":341271,"visible_token_observations":42},"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":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"stealth/space-bunny-alpha","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":["GB2-08"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-06"],"first_pass_admitted":1,"first_pass_rate":0.125,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.125,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":56.3541510230606,"score":37.56943401537374},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.19234694656345,"score":28.128231297708965},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":41.47736019576577,"score":27.651573463843846},"GB2-04":{"attempts":3,"playable":41.29005040876019,"score":41.29005040876019},"GB2-05":{"attempts":3,"playable":34.189702010463726,"score":34.189702010463726},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":49.34947006930476,"score":32.89964671286984},"GB2-07":{"attempts":3,"playable":45.88666341878507,"score":45.88666341878507},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":28.693763748530362,"score":19.129175832353575}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":63.90147748365587,"score":63.90147748365587},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":38.808734192147654,"score":38.808734192147654},"GB2-05":{"attempts":1,"playable":45.46171355019105,"score":45.46171355019105},"GB2-06":{"attempts":1,"playable":40.33070372736698,"score":40.33070372736698},"GB2-07":{"attempts":1,"playable":74.57528651068932,"score":74.57528651068932},"GB2-08":{"attempts":1,"playable":23.48937779715225,"score":23.48937779715225}},"medium":{"GB2-01":{"attempts":1,"playable":48.80682456246534,"score":48.80682456246534},"GB2-02":{"attempts":1,"playable":42.71647752882692,"score":42.71647752882692},"GB2-03":{"attempts":1,"playable":46.07900752229306,"score":46.07900752229306},"GB2-04":{"attempts":1,"playable":41.629472379739354,"score":41.629472379739354},"GB2-05":{"attempts":1,"playable":13.109431189976348,"score":13.109431189976348},"GB2-06":{"attempts":1,"playable":58.36823641124253,"score":58.36823641124253},"GB2-07":{"attempts":1,"playable":36.318696831669634,"score":36.318696831669634},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":41.66821636429997,"score":41.66821636429997},"GB2-03":{"attempts":1,"playable":36.87571286923848,"score":36.87571286923848},"GB2-04":{"attempts":1,"playable":43.431944654393554,"score":43.431944654393554},"GB2-05":{"attempts":1,"playable":43.99796129122379,"score":43.99796129122379},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":26.76600691399625,"score":26.76600691399625},"GB2-08":{"attempts":1,"playable":33.89814969990847,"score":33.89814969990847}}},"id":"stealth/space-bunny-alpha","is_recent_addition":false,"last_measured_at":"2026-10-20T11:30:53Z","match_totals_all":{"draws":2504,"losses":3968,"wins":2322},"match_totals_tracks":{"highest":{"draws":634,"losses":1182,"wins":1000},"medium":{"draws":838,"losses":1533,"wins":837},"none":{"draws":1032,"losses":1253,"wins":485}},"model_slug":"stealth-space-bunny-alpha","overall":{"max":74.57528651068932,"mean":33.34305964501987,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":49,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.90147748365587,"GB2-04":38.808734192147654,"GB2-05":45.46171355019105,"GB2-06":40.33070372736698,"GB2-07":74.57528651068932,"GB2-08":23.48937779715225},"per_game_all":{"GB2-04":41.29005040876019,"GB2-05":34.189702010463726,"GB2-07":45.88666341878507},"per_game_match_totals_all":{"GB2-01":{"draws":223,"losses":305,"wins":408},"GB2-02":{"draws":689,"losses":166,"wins":9},"GB2-03":{"draws":212,"losses":446,"wins":234},"GB2-04":{"draws":875,"losses":368,"wins":101},"GB2-05":{"draws":0,"losses":959,"wins":493},"GB2-06":{"draws":14,"losses":473,"wins":425},"GB2-07":{"draws":0,"losses":794,"wins":628},"GB2-08":{"draws":491,"losses":457,"wins":24}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":141,"losses":102,"wins":225},"GB2-04":{"draws":271,"losses":144,"wins":33},"GB2-05":{"draws":0,"losses":265,"wins":219},"GB2-06":{"draws":8,"losses":279,"wins":169},"GB2-07":{"draws":0,"losses":123,"wins":351},"GB2-08":{"draws":214,"losses":269,"wins":3}},"medium":{"GB2-01":{"draws":82,"losses":203,"wins":183},"GB2-02":{"draws":348,"losses":79,"wins":5},"GB2-03":{"draws":96,"losses":208,"wins":142},"GB2-04":{"draws":306,"losses":114,"wins":28},"GB2-05":{"draws":0,"losses":422,"wins":62},"GB2-06":{"draws":6,"losses":194,"wins":256},"GB2-07":{"draws":0,"losses":313,"wins":161}},"none":{"GB2-02":{"draws":341,"losses":87,"wins":4},"GB2-03":{"draws":116,"losses":238,"wins":92},"GB2-04":{"draws":298,"losses":110,"wins":40},"GB2-05":{"draws":0,"losses":272,"wins":212},"GB2-07":{"draws":0,"losses":358,"wins":116},"GB2-08":{"draws":277,"losses":188,"wins":21}}},"per_game_raw_elo_all":{"GB2-04":1410.513936646741,"GB2-05":1218.8482421612816,"GB2-07":1407.9024759261526},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1619.4971005813861,"GB2-04":1391.0456619731683,"GB2-05":1395.6362657568977,"GB2-06":1307.7364308000626,"GB2-07":1794.1230333016174,"GB2-08":1144.7575294081257},"medium":{"GB2-01":1471.2116376456609,"GB2-02":1419.5692874129504,"GB2-03":1398.0282374979201,"GB2-04":1413.2360893219495,"GB2-05":883.6761494839095,"GB2-06":1586.9938772693606,"GB2-07":1279.2349844207502},"none":{"GB2-02":1411.430214719613,"GB2-03":1317.3594786100866,"GB2-04":1427.2600586451053,"GB2-05":1377.2323112430379,"GB2-07":1150.34941005609,"GB2-08":1256.504526044892}},"per_game_tracks":{"highest":{"GB2-01":63.90147748365587,"GB2-04":38.808734192147654,"GB2-05":45.46171355019105,"GB2-06":40.33070372736698,"GB2-07":74.57528651068932,"GB2-08":23.48937779715225},"medium":{"GB2-01":48.80682456246534,"GB2-02":42.71647752882692,"GB2-03":46.07900752229306,"GB2-04":41.629472379739354,"GB2-05":13.109431189976348,"GB2-06":58.36823641124253,"GB2-07":36.318696831669634},"none":{"GB2-02":41.66821636429997,"GB2-03":36.87571286923848,"GB2-04":43.431944654393554,"GB2-05":43.99796129122379,"GB2-07":26.76600691399625,"GB2-08":33.89814969990847}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T23:03:06Z","reasoning":{"highest":35.82091165765039,"medium":35.87851830327665,"none":28.32974897413256},"reasoning_agg":{"highest":{"max":74.57528651068932,"mean":35.82091165765039,"min":0.0},"medium":{"max":58.36823641124253,"mean":35.87851830327665,"min":0.0},"none":{"max":43.99796129122379,"mean":28.32974897413256,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":7.54876932914409}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling-small:bafcffdaa4610350","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.06806129999999999,"mean":0.037113121874999995,"median":0.0310111,"min":0.0230335,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":10,"total":0.38761484999999996},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01196465,"mean":0.00854730625,"median":0.008640199999999999,"min":0.00555765,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":15},"recorded_attempt_count":15,"run_count":9,"total":0.07763975},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.014791950000000002,"mean":0.007616140625,"median":0.005694875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":9,"total":0.072064}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01196465,"mean":0.00854730625,"median":0.008640199999999999,"min":0.00555765,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":15},"recorded_attempt_count":15,"run_count":9,"total":0.07763975},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.014791950000000002,"mean":0.007616140625,"median":0.005694875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":9,"total":0.072064},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.06806129999999999,"mean":0.037113121874999995,"median":0.0310111,"min":0.0230335,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":10,"total":0.38761485}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":43},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.06806129999999999,"mean":0.01775885625,"median":0.0102184875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":43},"recorded_attempt_count":43,"run_count":28,"total":0.5373185999999999},"codegen_latency_ms":{"attempt_count":43,"max_ms":599272,"mean_ms":125847.07142857143,"min_ms":18961,"run_count":28},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":599272,"mean_ms":283663.1,"min_ms":69866,"run_count":10},"medium":{"attempt_count":15,"max_ms":68712,"mean_ms":42566.11111111111,"min_ms":22862,"run_count":9},"none":{"attempt_count":14,"max_ms":63236,"mean_ms":33776.88888888889,"min_ms":18961,"run_count":9}},"codegen_output_tokens":{"attempt_count":43,"output_max":49133,"output_mean":11683.67857142857,"output_min":894,"run_count":28},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":49133,"output_mean":28182.1,"output_min":11882,"run_count":10},"medium":{"attempt_count":15,"output_max":4066,"output_mean":2679.6666666666665,"output_min":1736,"run_count":9},"none":{"attempt_count":14,"output_max":5147,"output_mean":2356.1111111111113,"output_min":894,"run_count":9}},"display_name":"Inkling Small","economics":{"all":34.03537094586968,"highest":38.995213224186415,"medium":31.694445821606607,"none":31.416453791816043},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":43,"finish_reasons":["stop"],"indexed_attempts":43,"output_token_observations":43,"provider_post_attempt_observations":43,"provider_post_attempts":43,"reasoning_token_observations":43,"reconciliation_get_attempt_observations":43,"reconciliation_get_attempts":203,"total_output_tokens":327143,"total_reasoning_output_tokens":261125,"total_visible_output_tokens":66018,"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":"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":"thinkingmachines","provider_model":"thinkingmachines/inkling-small","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":4,"first_pass_rate":0.4444444444444444,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.4444444444444444},"baseline":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-06"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.3333333333333333},"intensive":{"admitted_plugins":8,"evaluated_cells":10,"failed_game_aliases":["GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.6666666666666666,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1,"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"performance_rejections":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1,"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":21.411347097254993,"score":21.411347097254993},"GB2-02":{"attempts":3,"playable":41.823566641822566,"score":41.823566641822566},"GB2-03":{"attempts":3,"playable":47.40902657727573,"score":47.40902657727573},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":43.88169002779879,"score":36.83074628649354},"GB2-05":{"attempts":3,"playable":19.15179329692795,"score":19.15179329692795},"GB2-06":{"attempts":5,"failed_attempts":2,"playable":29.477890437209727,"score":23.78040534230912},"GB2-07":{"attempts":3,"playable":35.57992519972033,"score":35.57992519972033},"GB2-08":{"attempts":3,"playable":33.547728288947404,"score":33.547728288947404}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":32.32052274155014,"score":32.32052274155014},"GB2-02":{"attempts":1,"playable":42.01774548023428,"score":42.01774548023428},"GB2-03":{"attempts":1,"playable":45.624171627892096,"score":45.624171627892096},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":42.305662447831494,"score":21.152831223915747},"GB2-05":{"attempts":1,"playable":42.11708978710608,"score":42.11708978710608},"GB2-06":{"attempts":1,"playable":54.248760742225535,"score":54.248760742225535},"GB2-07":{"attempts":1,"playable":18.904203079136312,"score":18.904203079136312},"GB2-08":{"attempts":1,"playable":34.423549887515314,"score":34.423549887515314}},"medium":{"GB2-01":{"attempts":1,"playable":9.5878133761572,"score":9.5878133761572},"GB2-02":{"attempts":1,"playable":41.78473808093344,"score":41.78473808093344},"GB2-03":{"attempts":1,"playable":39.89121144342992,"score":39.89121144342992},"GB2-04":{"attempts":1,"playable":45.23212237917734,"score":45.23212237917734},"GB2-05":{"attempts":1,"playable":9.883634248381743,"score":9.883634248381743},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":17.446013397304412,"score":8.723006698652206},"GB2-07":{"attempts":1,"playable":55.516636005784825,"score":55.516636005784825},"GB2-08":{"attempts":1,"playable":34.213397641683954,"score":34.213397641683954}},"none":{"GB2-01":{"attempts":1,"playable":22.325705174057642,"score":22.325705174057642},"GB2-02":{"attempts":1,"playable":41.66821636429997,"score":41.66821636429997},"GB2-03":{"attempts":1,"playable":56.71169666050516,"score":56.71169666050516},"GB2-04":{"attempts":1,"playable":44.10728525638755,"score":44.10728525638755},"GB2-05":{"attempts":1,"playable":5.454655855296023,"score":5.454655855296023},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":16.738897172099232,"score":8.369448586049616},"GB2-07":{"attempts":1,"playable":32.31893651423984,"score":32.31893651423984},"GB2-08":{"attempts":1,"playable":32.00623733764294,"score":32.00623733764294}}},"id":"thinkingmachines/inkling-small","is_recent_addition":false,"last_measured_at":"2026-10-20T11:42:18Z","match_totals_all":{"draws":3379,"losses":5814,"wins":1889},"match_totals_tracks":{"highest":{"draws":1141,"losses":1745,"wins":808},"medium":{"draws":1069,"losses":2049,"wins":576},"none":{"draws":1169,"losses":2020,"wins":505}},"model_slug":"thinkingmachines-inkling-small","overall":{"max":56.71169666050516,"mean":32.441817341343956,"min":5.454655855296023},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":50,"overall_ranking_status":"ranked","per_game":{"GB2-01":32.32052274155014,"GB2-02":42.01774548023428,"GB2-03":45.624171627892096,"GB2-04":42.305662447831494,"GB2-05":42.11708978710608,"GB2-06":54.248760742225535,"GB2-07":18.904203079136312,"GB2-08":34.423549887515314},"per_game_all":{"GB2-01":21.411347097254993,"GB2-02":41.823566641822566,"GB2-03":47.40902657727573,"GB2-04":43.88169002779879,"GB2-05":19.15179329692795,"GB2-06":29.477890437209727,"GB2-07":35.57992519972033,"GB2-08":33.547728288947404},"per_game_match_totals_all":{"GB2-01":{"draws":250,"losses":991,"wins":163},"GB2-02":{"draws":1047,"losses":247,"wins":2},"GB2-03":{"draws":389,"losses":555,"wins":394},"GB2-04":{"draws":870,"losses":336,"wins":138},"GB2-05":{"draws":0,"losses":1179,"wins":273},"GB2-06":{"draws":18,"losses":979,"wins":371},"GB2-07":{"draws":0,"losses":945,"wins":477},"GB2-08":{"draws":805,"losses":582,"wins":71}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":131,"losses":256,"wins":81},"GB2-02":{"draws":352,"losses":80,"wins":0},"GB2-03":{"draws":84,"losses":216,"wins":146},"GB2-04":{"draws":282,"losses":123,"wins":43},"GB2-05":{"draws":0,"losses":281,"wins":203},"GB2-06":{"draws":14,"losses":210,"wins":232},"GB2-07":{"draws":0,"losses":394,"wins":80},"GB2-08":{"draws":278,"losses":185,"wins":23}},"medium":{"GB2-01":{"draws":57,"losses":398,"wins":13},"GB2-02":{"draws":350,"losses":82,"wins":0},"GB2-03":{"draws":118,"losses":224,"wins":104},"GB2-04":{"draws":276,"losses":113,"wins":59},"GB2-05":{"draws":0,"losses":438,"wins":46},"GB2-06":{"draws":2,"losses":383,"wins":71},"GB2-07":{"draws":0,"losses":219,"wins":255},"GB2-08":{"draws":266,"losses":192,"wins":28}},"none":{"GB2-01":{"draws":62,"losses":337,"wins":69},"GB2-02":{"draws":345,"losses":85,"wins":2},"GB2-03":{"draws":187,"losses":115,"wins":144},"GB2-04":{"draws":312,"losses":100,"wins":36},"GB2-05":{"draws":0,"losses":460,"wins":24},"GB2-06":{"draws":2,"losses":386,"wins":68},"GB2-07":{"draws":0,"losses":332,"wins":142},"GB2-08":{"draws":261,"losses":205,"wins":20}}},"per_game_raw_elo_all":{"GB2-01":1163.6906476851136,"GB2-02":1412.6382304360693,"GB2-03":1410.4776645435861,"GB2-04":1430.7316510619673,"GB2-05":937.1893046427496,"GB2-06":1138.555049728329,"GB2-07":1257.8105638492498,"GB2-08":1252.8917055777058},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1309.487502221421,"GB2-02":1414.1478441779848,"GB2-03":1394.0595971564885,"GB2-04":1418.508212454619,"GB2-05":1353.3599402882091,"GB2-06":1521.0847011838848,"GB2-07":1026.200553561312,"GB2-08":1261.8605519911894},"medium":{"GB2-01":985.9596024876771,"GB2-02":1412.33663241061,"GB2-03":1344.0195445253737,"GB2-04":1441.1931912731175,"GB2-05":803.2778470075806,"GB2-06":953.5115340189197,"GB2-07":1520.164766497361,"GB2-08":1259.7196754588515},"none":{"GB2-01":1195.6248383462425,"GB2-02":1411.430214719613,"GB2-03":1493.3538519488966,"GB2-04":1432.4935494581653,"GB2-05":654.9301266324593,"GB2-06":941.0689139821825,"GB2-07":1227.0663714890763,"GB2-08":1237.0948892830766}},"per_game_tracks":{"highest":{"GB2-01":32.32052274155014,"GB2-02":42.01774548023428,"GB2-03":45.624171627892096,"GB2-04":42.305662447831494,"GB2-05":42.11708978710608,"GB2-06":54.248760742225535,"GB2-07":18.904203079136312,"GB2-08":34.423549887515314},"medium":{"GB2-01":9.5878133761572,"GB2-02":41.78473808093344,"GB2-03":39.89121144342992,"GB2-04":45.23212237917734,"GB2-05":9.883634248381743,"GB2-06":17.446013397304412,"GB2-07":55.516636005784825,"GB2-08":34.213397641683954},"none":{"GB2-01":22.325705174057642,"GB2-02":41.66821636429997,"GB2-03":56.71169666050516,"GB2-04":44.10728525638755,"GB2-05":5.454655855296023,"GB2-06":16.738897172099232,"GB2-07":32.31893651423984,"GB2-08":32.00623733764294}},"provider_color":"#31373D","provider_company":"Thinking Machines","provider_key":"thinkingmachines","provider_text_color":"#f8fafc","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:06:26Z","reasoning":{"highest":36.35110932119694,"medium":30.60406998427508,"none":30.370272718559843},"reasoning_agg":{"highest":{"max":54.248760742225535,"mean":36.35110932119694,"min":18.904203079136312},"medium":{"max":55.516636005784825,"mean":30.60406998427508,"min":8.723006698652206},"none":{"max":56.71169666050516,"mean":30.370272718559843,"min":5.454655855296023}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":5.980836602637094}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-glimmer-30b:77cc296015f7d9bb","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02351982,"mean":0.019656965,"median":0.019640945,"min":0.01650772,"recorded_attempt_count":11,"run_count":8,"total":0.15725572},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0138593,"mean":0.00832475125,"median":0.006849235,"min":0.00556902,"recorded_attempt_count":10,"run_count":8,"total":0.06659801},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01024177,"mean":0.0073127075,"median":0.007628165,"min":0.00402612,"recorded_attempt_count":13,"run_count":8,"total":0.05850166}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0138593,"mean":0.00832475125,"median":0.006849235,"min":0.00556902,"recorded_attempt_count":10,"run_count":8,"total":0.06659801},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01024177,"mean":0.0073127075,"median":0.007628165,"min":0.00402612,"recorded_attempt_count":13,"run_count":8,"total":0.058501660000000004},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02351982,"mean":0.019656965,"median":0.019640945,"min":0.01650772,"recorded_attempt_count":11,"run_count":8,"total":0.15725572}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.02351982,"mean":0.011764807916666668,"median":0.0084872,"min":0.00402612,"recorded_attempt_count":34,"run_count":24,"total":0.28235539000000004},"codegen_latency_ms":{"attempt_count":34,"max_ms":380009,"mean_ms":93239.75,"min_ms":17041,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":380009,"mean_ms":168796.875,"min_ms":74942,"run_count":8},"medium":{"attempt_count":10,"max_ms":111336,"mean_ms":66228.375,"min_ms":28934,"run_count":8},"none":{"attempt_count":13,"max_ms":72200,"mean_ms":44694.0,"min_ms":17041,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":16539,"output_mean":6423.083333333333,"output_min":1715,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":16539,"output_mean":12718.0,"output_min":9279,"run_count":8},"medium":{"attempt_count":10,"output_max":6754,"output_mean":3630.75,"output_min":2165,"run_count":8},"none":{"attempt_count":13,"output_max":4210,"output_mean":2920.5,"output_min":1715,"run_count":8}},"display_name":"Muse Glimmer 30B","economics":{"all":35.03403403983146,"highest":41.26530643167188,"medium":31.804036679247282,"none":31.796883831962102},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":34,"finish_reasons":["stop"],"indexed_attempts":34,"output_token_observations":34,"provider_post_attempt_observations":34,"provider_post_attempts":34,"reasoning_token_observations":34,"reconciliation_get_attempt_observations":34,"reconciliation_get_attempts":164,"total_output_tokens":154154,"total_reasoning_output_tokens":105962,"total_visible_output_tokens":48432,"visible_token_observations":34},"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":"meta","provider_model":"meta/muse-glimmer-30b","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-06"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":30.094589031107233,"score":30.094589031107233},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":43.12385471972447,"score":28.749236479816314},"GB2-03":{"attempts":3,"playable":40.0373498000295,"score":40.0373498000295},"GB2-04":{"attempts":3,"playable":46.01702325020955,"score":46.01702325020955},"GB2-05":{"attempts":3,"playable":23.105172743066035,"score":23.105172743066035},"GB2-06":{"attempts":3,"failed_attempts":2,"playable":17.21041929103866,"score":5.7368064303462205},"GB2-07":{"attempts":3,"playable":37.61241950856569,"score":37.61241950856569},"GB2-08":{"attempts":3,"playable":33.33764990601077,"score":33.33764990601077}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":31.361704408399504,"score":31.361704408399504},"GB2-02":{"attempts":1,"playable":42.94929079597173,"score":42.94929079597173},"GB2-03":{"attempts":1,"playable":37.45742344810872,"score":37.45742344810872},"GB2-04":{"attempts":1,"playable":48.93732795009696,"score":48.93732795009696},"GB2-05":{"attempts":1,"playable":46.716813708255856,"score":46.716813708255856},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":48.061897239178755,"score":48.061897239178755},"GB2-08":{"attempts":1,"playable":33.37268747169157,"score":33.37268747169157}},"medium":{"GB2-01":{"attempts":1,"playable":22.649730174781443,"score":22.649730174781443},"GB2-02":{"attempts":1,"playable":43.29841864347721,"score":43.29841864347721},"GB2-03":{"attempts":1,"playable":39.31311902907769,"score":39.31311902907769},"GB2-04":{"attempts":1,"playable":45.68179714613813,"score":45.68179714613813},"GB2-05":{"attempts":1,"playable":15.332284146393214,"score":15.332284146393214},"GB2-06":{"attempts":1,"playable":17.21041929103866,"score":17.21041929103866},"GB2-07":{"attempts":1,"playable":37.36364557672718,"score":37.36364557672718},"GB2-08":{"attempts":1,"playable":33.58287942634469,"score":33.58287942634469}},"none":{"GB2-01":{"attempts":1,"playable":36.272332510140764,"score":36.272332510140764},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":43.3415069229021,"score":43.3415069229021},"GB2-04":{"attempts":1,"playable":43.431944654393554,"score":43.431944654393554},"GB2-05":{"attempts":1,"playable":7.266420374549029,"score":7.266420374549029},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":27.411715709791117,"score":27.411715709791117},"GB2-08":{"attempts":1,"playable":33.057382819996036,"score":33.057382819996036}}},"id":"meta/muse-glimmer-30b","is_recent_addition":false,"last_measured_at":"2026-10-20T11:17:08Z","match_totals_all":{"draws":3094,"losses":4952,"wins":1691},"match_totals_tracks":{"highest":{"draws":1142,"losses":1378,"wins":717},"medium":{"draws":1149,"losses":2009,"wins":536},"none":{"draws":803,"losses":1565,"wins":438}},"model_slug":"meta-muse-glimmer-30b","overall":{"max":48.93732795009696,"mean":30.586280893643917,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":51,"overall_ranking_status":"ranked","per_game":{"GB2-01":31.361704408399504,"GB2-02":42.94929079597173,"GB2-03":37.45742344810872,"GB2-04":48.93732795009696,"GB2-05":46.716813708255856,"GB2-07":48.061897239178755,"GB2-08":33.37268747169157},"per_game_all":{"GB2-01":30.094589031107233,"GB2-03":40.0373498000295,"GB2-04":46.01702325020955,"GB2-05":23.105172743066035,"GB2-07":37.61241950856569,"GB2-08":33.33764990601077},"per_game_match_totals_all":{"GB2-01":{"draws":305,"losses":842,"wins":256},"GB2-02":{"draws":711,"losses":147,"wins":6},"GB2-03":{"draws":396,"losses":649,"wins":293},"GB2-04":{"draws":891,"losses":297,"wins":156},"GB2-05":{"draws":0,"losses":1121,"wins":331},"GB2-06":{"draws":2,"losses":384,"wins":70},"GB2-07":{"draws":0,"losses":919,"wins":503},"GB2-08":{"draws":789,"losses":593,"wins":76}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":128,"losses":261,"wins":78},"GB2-02":{"draws":350,"losses":77,"wins":5},"GB2-03":{"draws":143,"losses":222,"wins":81},"GB2-04":{"draws":263,"losses":103,"wins":82},"GB2-05":{"draws":0,"losses":259,"wins":225},"GB2-07":{"draws":0,"losses":256,"wins":218},"GB2-08":{"draws":258,"losses":200,"wins":28}},"medium":{"GB2-01":{"draws":89,"losses":322,"wins":57},"GB2-02":{"draws":361,"losses":70,"wins":1},"GB2-03":{"draws":115,"losses":228,"wins":103},"GB2-04":{"draws":308,"losses":95,"wins":45},"GB2-05":{"draws":0,"losses":411,"wins":73},"GB2-06":{"draws":2,"losses":384,"wins":70},"GB2-07":{"draws":0,"losses":308,"wins":166},"GB2-08":{"draws":274,"losses":191,"wins":21}},"none":{"GB2-01":{"draws":88,"losses":259,"wins":121},"GB2-03":{"draws":138,"losses":199,"wins":109},"GB2-04":{"draws":320,"losses":99,"wins":29},"GB2-05":{"draws":0,"losses":451,"wins":33},"GB2-07":{"draws":0,"losses":355,"wins":119},"GB2-08":{"draws":257,"losses":202,"wins":27}}},"per_game_raw_elo_all":{"GB2-01":1283.0017586794113,"GB2-03":1345.214513596738,"GB2-04":1447.2437197738836,"GB2-05":1022.4556689931642,"GB2-07":1292.8170227152698,"GB2-08":1250.7748533431102},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1299.395396458381,"GB2-02":1421.3726630230817,"GB2-03":1322.5369739688429,"GB2-04":1469.8043305492176,"GB2-05":1411.3312271278876,"GB2-07":1426.2552658238576,"GB2-08":1251.1347177854918},"medium":{"GB2-01":1199.7100643802523,"GB2-02":1424.0744873329763,"GB2-03":1338.9391546478591,"GB2-04":1444.6667701273284,"GB2-05":932.3060234233931,"GB2-06":949.392192466611,"GB2-07":1292.5820375528695,"GB2-08":1253.284415884804},"none":{"GB2-01":1349.899815199601,"GB2-03":1374.1674121735118,"GB2-04":1427.2600586451053,"GB2-05":723.7297564282118,"GB2-07":1159.6137647690828,"GB2-08":1247.905426359034}},"per_game_tracks":{"highest":{"GB2-01":31.361704408399504,"GB2-02":42.94929079597173,"GB2-03":37.45742344810872,"GB2-04":48.93732795009696,"GB2-05":46.716813708255856,"GB2-07":48.061897239178755,"GB2-08":33.37268747169157},"medium":{"GB2-01":22.649730174781443,"GB2-02":43.29841864347721,"GB2-03":39.31311902907769,"GB2-04":45.68179714613813,"GB2-05":15.332284146393214,"GB2-06":17.21041929103866,"GB2-07":37.36364557672718,"GB2-08":33.58287942634469},"none":{"GB2-01":36.272332510140764,"GB2-03":43.3415069229021,"GB2-04":43.431944654393554,"GB2-05":7.266420374549029,"GB2-07":27.411715709791117,"GB2-08":33.057382819996036}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":0,"rank_movement_baseline_at":"2026-10-13T22:51:01Z","reasoning":{"highest":36.107143127712895,"medium":31.804036679247282,"none":23.847662873971576},"reasoning_agg":{"highest":{"max":48.93732795009696,"mean":36.107143127712895,"min":0.0},"medium":{"max":45.68179714613813,"mean":31.804036679247282,"min":15.332284146393214},"none":{"max":43.431944654393554,"mean":23.847662873971576,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":12.25948025374132}},{"canonical_public_row_identity":"publication-row.v1:overall:openai-gpt-oss-120b:62cf2f5dff5e8c28","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.015120192000000001,"mean":0.0074424702499999995,"median":0.006876,"min":0.00134592,"recorded_attempt_count":11,"run_count":8,"total":0.059539762},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00145295,"mean":0.001135709125,"median":0.001180259,"min":0.00078534,"recorded_attempt_count":10,"run_count":8,"total":0.009085673},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.002555,"mean":0.001231986375,"median":0.0010393855,"min":0.00046744,"recorded_attempt_count":12,"run_count":8,"total":0.009855890999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00145295,"mean":0.001135709125,"median":0.001180259,"min":0.00078534,"recorded_attempt_count":10,"run_count":8,"total":0.009085673},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.002555,"mean":0.001231986375,"median":0.0010393855,"min":0.00046744,"recorded_attempt_count":12,"run_count":8,"total":0.009855891},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.015120192000000001,"mean":0.0074424702499999995,"median":0.006876,"min":0.00134592,"recorded_attempt_count":11,"run_count":8,"total":0.059539762}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":33},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.015120192000000001,"mean":0.0032700552500000003,"median":0.0013951725,"min":0.00046744,"recorded_attempt_count":33,"run_count":24,"total":0.078481326},"codegen_latency_ms":{"attempt_count":33,"max_ms":1105859,"mean_ms":161415.45833333334,"min_ms":22661,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":1105859,"mean_ms":300420.375,"min_ms":56038,"run_count":8},"medium":{"attempt_count":10,"max_ms":291211,"mean_ms":111417.625,"min_ms":22661,"run_count":8},"none":{"attempt_count":12,"max_ms":151123,"mean_ms":72408.375,"min_ms":26216,"run_count":8}},"codegen_output_tokens":{"attempt_count":33,"output_max":63626,"output_mean":9305.125,"output_min":1487,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":63626,"output_mean":22255.875,"output_min":2344,"run_count":8},"medium":{"attempt_count":10,"output_max":5420,"output_mean":3175.75,"output_min":2107,"run_count":8},"none":{"attempt_count":12,"output_max":4178,"output_mean":2483.75,"output_min":1487,"run_count":8}},"display_name":"GPT-OSS 120B","economics":{"all":34.62791134179391,"highest":40.159484395007645,"medium":31.251890738905075,"none":32.6759249041017},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":33,"finish_reasons":["stop"],"indexed_attempts":33,"output_token_observations":33,"provider_post_attempt_observations":33,"provider_post_attempts":33,"reasoning_token_observations":33,"reconciliation_get_attempt_observations":33,"reconciliation_get_attempts":158,"total_output_tokens":223323,"total_reasoning_output_tokens":139050,"total_visible_output_tokens":87482,"visible_token_observations":33},"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":"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-04","GB2-06"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-01"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":38.77419860616891,"score":25.84946573744594},"GB2-02":{"attempts":3,"playable":43.41450601072089,"score":43.41450601072089},"GB2-03":{"attempts":3,"playable":39.205999044632264,"score":39.205999044632264},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":40.72632608611751,"score":27.150884057411673},"GB2-05":{"attempts":3,"playable":29.765093339359584,"score":29.765093339359584},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":24.38367329471142,"score":16.255782196474282},"GB2-07":{"attempts":3,"playable":28.152256034525333,"score":28.152256034525333},"GB2-08":{"attempts":3,"playable":32.60170227973147,"score":32.60170227973147}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":44.34513267976285,"score":44.34513267976285},"GB2-03":{"attempts":1,"playable":45.9653517740317,"score":45.9653517740317},"GB2-04":{"attempts":1,"playable":42.530989492860435,"score":42.530989492860435},"GB2-05":{"attempts":1,"playable":58.225987245264086,"score":58.225987245264086},"GB2-06":{"attempts":1,"playable":22.246661626259176,"score":22.246661626259176},"GB2-07":{"attempts":1,"playable":34.21938852053058,"score":34.21938852053058},"GB2-08":{"attempts":1,"playable":33.58287942634469,"score":33.58287942634469}},"medium":{"GB2-01":{"attempts":1,"playable":36.272332510140764,"score":36.272332510140764},"GB2-02":{"attempts":1,"playable":42.4836154135375,"score":42.4836154135375},"GB2-03":{"attempts":1,"playable":35.47611581624766,"score":35.47611581624766},"GB2-04":{"attempts":1,"playable":38.92166267937459,"score":38.92166267937459},"GB2-05":{"attempts":1,"playable":15.332284146393214,"score":15.332284146393214},"GB2-06":{"attempts":1,"playable":26.52068496316367,"score":26.52068496316367},"GB2-07":{"attempts":1,"playable":21.11028068247472,"score":21.11028068247472},"GB2-08":{"attempts":1,"playable":33.89814969990847,"score":33.89814969990847}},"none":{"GB2-01":{"attempts":1,"playable":41.27606470219706,"score":41.27606470219706},"GB2-02":{"attempts":1,"playable":43.41476993886233,"score":43.41476993886233},"GB2-03":{"attempts":1,"playable":36.176529543617434,"score":36.176529543617434},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":15.737008626421453,"score":15.737008626421453},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":29.127098900570697,"score":29.127098900570697},"GB2-08":{"attempts":1,"playable":30.324077712941243,"score":30.324077712941243}}},"id":"openai/gpt-oss-120b","is_recent_addition":false,"last_measured_at":"2026-10-20T11:17:40Z","match_totals_all":{"draws":2795,"losses":5119,"wins":1796},"match_totals_tracks":{"highest":{"draws":872,"losses":1548,"wins":806},"medium":{"draws":1121,"losses":2044,"wins":529},"none":{"draws":802,"losses":1527,"wins":461}},"model_slug":"openai-gpt-oss-120b","overall":{"max":58.225987245264086,"mean":30.29946108753768,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":52,"overall_ranking_status":"ranked","per_game":{"GB2-02":44.34513267976285,"GB2-03":45.9653517740317,"GB2-04":42.530989492860435,"GB2-05":58.225987245264086,"GB2-06":22.246661626259176,"GB2-07":34.21938852053058,"GB2-08":33.58287942634469},"per_game_all":{"GB2-02":43.41450601072089,"GB2-03":39.205999044632264,"GB2-05":29.765093339359584,"GB2-07":28.152256034525333,"GB2-08":32.60170227973147},"per_game_match_totals_all":{"GB2-01":{"draws":163,"losses":501,"wins":272},"GB2-02":{"draws":1060,"losses":220,"wins":16},"GB2-03":{"draws":333,"losses":691,"wins":314},"GB2-04":{"draws":594,"losses":245,"wins":57},"GB2-05":{"draws":0,"losses":1024,"wins":428},"GB2-06":{"draws":11,"losses":703,"wins":198},"GB2-07":{"draws":0,"losses":1054,"wins":368},"GB2-08":{"draws":634,"losses":681,"wins":143}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":348,"losses":72,"wins":12},"GB2-03":{"draws":111,"losses":201,"wins":134},"GB2-04":{"draws":292,"losses":117,"wins":39},"GB2-05":{"draws":0,"losses":204,"wins":280},"GB2-06":{"draws":3,"losses":362,"wins":91},"GB2-07":{"draws":0,"losses":323,"wins":151},"GB2-08":{"draws":118,"losses":269,"wins":99}},"medium":{"GB2-01":{"draws":86,"losses":260,"wins":122},"GB2-02":{"draws":350,"losses":79,"wins":3},"GB2-03":{"draws":114,"losses":245,"wins":87},"GB2-04":{"draws":302,"losses":128,"wins":18},"GB2-05":{"draws":0,"losses":411,"wins":73},"GB2-06":{"draws":8,"losses":341,"wins":107},"GB2-07":{"draws":0,"losses":384,"wins":90},"GB2-08":{"draws":261,"losses":196,"wins":29}},"none":{"GB2-01":{"draws":77,"losses":241,"wins":150},"GB2-02":{"draws":362,"losses":69,"wins":1},"GB2-03":{"draws":108,"losses":245,"wins":93},"GB2-05":{"draws":0,"losses":409,"wins":75},"GB2-07":{"draws":0,"losses":347,"wins":127},"GB2-08":{"draws":255,"losses":216,"wins":15}}},"per_game_raw_elo_all":{"GB2-02":1424.9658909539492,"GB2-03":1337.6538068475259,"GB2-05":1143.216103084076,"GB2-07":1166.4879568396593,"GB2-08":1243.1353069010695},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1432.1593146525747,"GB2-03":1397.036255292911,"GB2-04":1420.261875693871,"GB2-05":1556.6149399451906,"GB2-06":1033.1246316767965,"GB2-07":1252.0957403509324,"GB2-08":1253.284415884804},"medium":{"GB2-01":1349.899815199601,"GB2-02":1417.764083768876,"GB2-03":1304.8157280665482,"GB2-04":1391.9414627783788,"GB2-05":932.3060234233931,"GB2-06":1099.7131259332907,"GB2-07":1063.6275861306992,"GB2-08":1256.504526044892},"none":{"GB2-01":1399.1107110014636,"GB2-02":1424.9742744403968,"GB2-03":1311.1094371831182,"GB2-05":940.727345883644,"GB2-07":1183.7405440373466,"GB2-08":1219.6169787735125}},"per_game_tracks":{"highest":{"GB2-02":44.34513267976285,"GB2-03":45.9653517740317,"GB2-04":42.530989492860435,"GB2-05":58.225987245264086,"GB2-06":22.246661626259176,"GB2-07":34.21938852053058,"GB2-08":33.58287942634469},"medium":{"GB2-01":36.272332510140764,"GB2-02":42.4836154135375,"GB2-03":35.47611581624766,"GB2-04":38.92166267937459,"GB2-05":15.332284146393214,"GB2-06":26.52068496316367,"GB2-07":21.11028068247472,"GB2-08":33.89814969990847},"none":{"GB2-01":41.27606470219706,"GB2-02":43.41476993886233,"GB2-03":36.176529543617434,"GB2-05":15.737008626421453,"GB2-07":29.127098900570697,"GB2-08":30.324077712941243}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:42:03Z","reasoning":{"highest":35.13954884563169,"medium":31.251890738905075,"none":24.506943678076272},"reasoning_agg":{"highest":{"max":58.225987245264086,"mean":35.13954884563169,"min":0.0},"medium":{"max":42.4836154135375,"mean":31.251890738905075,"min":15.332284146393214},"none":{"max":43.41476993886233,"mean":24.506943678076272,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.632605167555415}},{"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:7bf75f6ebf97c516","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.065385,"mean":0.03551179375,"median":0.032728425,"min":0.0200767,"recorded_attempt_count":21,"run_count":9,"total":0.3177278},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.13485595000000003,"mean":0.031792056250000006,"median":0.0158481,"min":0.0111232,"recorded_attempt_count":14,"run_count":9,"total":0.38919240000000005}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":21},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.065385,"mean":0.03551179375,"median":0.032728425,"min":0.0200767,"recorded_attempt_count":21,"run_count":9,"total":0.31772780000000006},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.13485595000000003,"mean":0.031792056250000006,"median":0.0158481,"min":0.0111232,"recorded_attempt_count":14,"run_count":9,"total":0.38919240000000005},"historical-provider-setting-intensive":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0456916,"mean":0.031545040625,"median":0.035551075,"min":0.01864685,"recorded_attempt_count":35,"run_count":16,"total":0.50472065}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":70},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.13485595000000003,"mean":0.03294963020833334,"median":0.02851355,"min":0.0111232,"recorded_attempt_count":70,"run_count":34,"total":1.21164085},"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":38.524272625989084,"highest":34.28193236549964,"medium":39.45000419842667,"none":35.236104535741454},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":7,"failed_game_aliases":["GB2-03","GB2-04"],"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"infra_failures_excluded":2},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-05"],"infra_failures_excluded":2,"model_code_failure_rate":0.2857142857142857,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":5,"repaired_rate":0.7142857142857143},"baseline":{"admitted_plugins":7,"evaluated_cells":9,"failed_game_aliases":["GB2-02","GB2-07"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1,"model_code_failures":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.2222222222222222,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.2222222222222222},"intensive":{"admitted_plugins":9,"evaluated_cells":14,"failed_game_aliases":["GB2-01","GB2-03","GB2-07"],"first_pass_admitted":2,"first_pass_rate":0.14285714285714285,"game_attempts":{"GB2-01":{"admitted":1,"model_code_failures":1},"GB2-02":{"admitted":2},"GB2-03":{"model_code_failures":2},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"model_code_failures":2},"GB2-08":{"admitted":2}},"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.35714285714285715,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.5}},"headline_games_all":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":45.60301120209763,"score":41.36082736762336},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":41.08521620236074,"score":27.39014413490716},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":31.601991317737806,"score":10.533997105912603},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":41.460289533241124,"score":27.640193022160748},"GB2-05":{"attempts":3,"playable":45.88482460132006,"score":45.88482460132006},"GB2-06":{"attempts":3,"playable":35.774175678652874,"score":35.774175678652874},"GB2-07":{"attempts":5,"failed_attempts":3,"playable":7.2066206549190195,"score":4.00991012346746},"GB2-08":{"attempts":4,"playable":34.19563099721673,"score":34.19563099721673}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":25.45310300684563,"score":12.726551503422815},"GB2-02":{"attempts":2,"playable":40.85185294718475,"score":40.85185294718475},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":1,"playable":40.95297264520298,"score":40.95297264520298},"GB2-05":{"attempts":2,"playable":30.19951389075772,"score":30.19951389075772},"GB2-06":{"attempts":1,"playable":33.86314730550888,"score":33.86314730550888},"GB2-07":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-08":{"attempts":2,"playable":34.37100439749791,"score":34.37100439749791}},"medium":{"GB2-01":{"attempts":1,"playable":56.41696493411293,"score":56.41696493411293},"GB2-02":{"attempts":1,"playable":41.31857945753672,"score":41.31857945753672},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":57.546656775667714,"score":57.546656775667714},"GB2-07":{"attempts":1,"playable":9.646219430966719,"score":9.646219430966719},"GB2-08":{"attempts":1,"playable":32.32160039384927,"score":32.32160039384927}},"none":{"GB2-01":{"attempts":1,"playable":54.93896566533433,"score":54.93896566533433},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":31.601991317737806,"score":31.601991317737806},"GB2-04":{"attempts":1,"playable":41.96760642127926,"score":41.96760642127926},"GB2-05":{"attempts":1,"playable":61.57013531188241,"score":61.57013531188241},"GB2-06":{"attempts":1,"playable":15.912722954782046,"score":15.912722954782046},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":4.76702187887132,"score":2.38351093943566},"GB2-08":{"attempts":1,"playable":35.89428820030302,"score":35.89428820030302}}},"id":"nvidia/nemotron-3-ultra-550b-a55b","is_recent_addition":false,"last_measured_at":"2026-10-20T11:23:06Z","match_totals_all":{"draws":3162,"losses":4790,"wins":1802},"match_totals_tracks":{"highest":{"draws":1639,"losses":1964,"wins":573},"medium":{"draws":698,"losses":1088,"wins":530},"none":{"draws":825,"losses":1738,"wins":699}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":61.57013531188241,"mean":27.610952454996276,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings","generation_incomplete"],"overall_official_rank":53,"overall_ranking_status":"partial","per_game":{"GB2-01":25.45310300684563,"GB2-02":40.85185294718475,"GB2-04":40.95297264520298,"GB2-05":30.19951389075772,"GB2-06":33.86314730550888,"GB2-08":34.37100439749791},"per_game_all":{"GB2-01":45.60301120209763,"GB2-06":35.774175678652874,"GB2-08":34.19563099721673},"per_game_match_totals_all":{"GB2-01":{"draws":257,"losses":648,"wins":499},"GB2-02":{"draws":1010,"losses":276,"wins":10},"GB2-03":{"draws":171,"losses":233,"wins":42},"GB2-04":{"draws":631,"losses":220,"wins":45},"GB2-05":{"draws":0,"losses":865,"wins":587},"GB2-06":{"draws":44,"losses":882,"wins":442},"GB2-07":{"draws":0,"losses":891,"wins":57},"GB2-08":{"draws":1049,"losses":775,"wins":120}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":95,"losses":306,"wins":67},"GB2-02":{"draws":666,"losses":189,"wins":9},"GB2-04":{"draws":318,"losses":111,"wins":19},"GB2-05":{"draws":0,"losses":677,"wins":291},"GB2-06":{"draws":27,"losses":299,"wins":130},"GB2-08":{"draws":533,"losses":382,"wins":57}},"medium":{"GB2-01":{"draws":92,"losses":162,"wins":214},"GB2-02":{"draws":344,"losses":87,"wins":1},"GB2-06":{"draws":12,"losses":195,"wins":249},"GB2-07":{"draws":0,"losses":435,"wins":39},"GB2-08":{"draws":250,"losses":209,"wins":27}},"none":{"GB2-01":{"draws":70,"losses":180,"wins":218},"GB2-03":{"draws":171,"losses":233,"wins":42},"GB2-04":{"draws":313,"losses":109,"wins":26},"GB2-05":{"draws":0,"losses":188,"wins":296},"GB2-06":{"draws":5,"losses":388,"wins":63},"GB2-07":{"draws":0,"losses":456,"wins":18},"GB2-08":{"draws":266,"losses":184,"wins":36}}},"per_game_raw_elo_all":{"GB2-01":1436.0207225612303,"GB2-06":1236.840443241642,"GB2-08":1259.4899527100863},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1233.7144190189663,"GB2-02":1405.0487287962314,"GB2-04":1407.9455878270728,"GB2-05":1182.1259703264489,"GB2-06":1210.6173003453457,"GB2-08":1261.3240032910585},"medium":{"GB2-01":1544.3560831921084,"GB2-02":1408.707579929197,"GB2-06":1573.6938971308282,"GB2-07":826.1022996071234,"GB2-08":1240.3460787859824},"none":{"GB2-01":1529.991665472616,"GB2-03":1269.2501416839302,"GB2-04":1415.8743126403042,"GB2-05":1601.4704940534818,"GB2-06":926.2101322487524,"GB2-07":651.3371718688962,"GB2-08":1276.7997760532176}},"per_game_tracks":{"highest":{"GB2-01":25.45310300684563,"GB2-02":40.85185294718475,"GB2-04":40.95297264520298,"GB2-05":30.19951389075772,"GB2-06":33.86314730550888,"GB2-08":34.37100439749791},"medium":{"GB2-01":56.41696493411293,"GB2-02":41.31857945753672,"GB2-06":57.546656775667714,"GB2-07":9.646219430966719,"GB2-08":32.32160039384927},"none":{"GB2-01":54.93896566533433,"GB2-03":31.601991317737806,"GB2-04":41.96760642127926,"GB2-05":61.57013531188241,"GB2-06":15.912722954782046,"GB2-07":4.76702187887132,"GB2-08":35.89428820030302}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":24.120630336196882,"medium":28.17857442744762,"none":30.53365260134431},"reasoning_agg":{"highest":{"max":40.95297264520298,"mean":24.120630336196882,"min":0.0},"medium":{"max":57.546656775667714,"mean":28.17857442744762,"min":0.0},"none":{"max":61.57013531188241,"mean":30.53365260134431,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":6.413022265147429}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling:05dc2b52c65a627c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":60},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.261503015,"mean":0.224623670625,"median":0.22750746833333335,"min":0.17735088333333335,"recorded_attempt_count":60,"run_count":22,"total":4.90638056},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.04901556,"mean":0.031135205,"median":0.02897688,"min":0.01737051,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.24908164000000002},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":false,"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":0.58845395}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.04901556,"mean":0.031135205,"median":0.02897688,"min":0.01737051,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.24908164},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":false,"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":0.58845395},"historical-provider-setting-intensive":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":60},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.261503015,"mean":0.224623670625,"median":0.22750746833333335,"min":0.17735088333333335,"recorded_attempt_count":60,"run_count":22,"total":4.906380560000001}},"codegen_cost_usd":{"admitted_cell_count":32,"cell_count":24,"cost_basis_counts":{"provider_reported":112},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.261503015,"mean":0.09751241583333332,"median":0.042993304999999996,"min":0.01737051,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":112,"run_count":46,"total":5.7439161499999996},"codegen_latency_ms":{"attempt_count":112,"max_ms":712912,"mean_ms":234938.63043478262,"min_ms":16322,"run_count":46},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":60,"max_ms":712912,"mean_ms":442344.0909090909,"min_ms":125659,"run_count":22},"medium":{"attempt_count":13,"max_ms":52676,"mean_ms":32623.625,"min_ms":16322,"run_count":8},"none":{"attempt_count":39,"max_ms":118093,"mean_ms":50913.625,"min_ms":20774,"run_count":16}},"codegen_output_tokens":{"attempt_count":112,"output_max":80000,"output_mean":26608.978260869564,"output_min":1372,"run_count":46},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":60,"output_max":80000,"output_mean":50498.318181818184,"output_min":12059,"run_count":22},"medium":{"attempt_count":13,"output_max":9117,"output_mean":4863.875,"output_min":2632,"run_count":8},"none":{"attempt_count":39,"output_max":11313,"output_mean":4633.6875,"output_min":1372,"run_count":16}},"display_name":"Inkling","economics":{"all":31.674341776053307,"highest":39.33129603788025,"medium":25.401256528873954,"none":38.0875441543065},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":20,"effective_max_output_tokens":[262144],"finish_reason_observations":112,"finish_reasons":["length","stop"],"indexed_attempts":112,"output_token_observations":112,"provider_post_attempt_observations":20,"provider_post_attempts":23,"reasoning_token_observations":85,"reconciliation_get_attempt_observations":20,"reconciliation_get_attempts":33,"requested_max_output_token_observations":20,"requested_max_output_tokens":[262144],"total_output_tokens":1224013,"total_reasoning_output_tokens":793927,"total_visible_output_tokens":126602,"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":"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":"thinkingmachines","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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","GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"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,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"model_code_failures":1},"GB2-07":{"admitted":1,"model_code_failures":1},"GB2-08":{"admitted":1,"model_code_failures":1}},"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.3125},"intensive":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-04","GB2-06"],"first_pass_admitted":9,"first_pass_rate":0.5625,"game_attempts":{"GB2-01":{"admitted":2,"infra_failures_excluded":1},"GB2-02":{"admitted":2,"infra_failures_excluded":1},"GB2-03":{"admitted":2,"infra_failures_excluded":1},"GB2-04":{"admitted":1,"infra_failures_excluded":1,"model_code_failures":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"model_code_failures":1},"GB2-07":{"admitted":2,"infra_failures_excluded":1},"GB2-08":{"admitted":2,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-07","GB2-08"],"infra_failures_excluded":6,"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.3125}},"headline_games_all":{"GB2-01":{"attempts":5,"playable":25.640038480230036,"score":25.640038480230036},"GB2-02":{"attempts":5,"failed_attempts":2,"playable":43.06537790002693,"score":21.39691007680004},"GB2-03":{"attempts":5,"playable":44.282370728392884,"score":44.282370728392884},"GB2-04":{"attempts":5,"failed_attempts":1,"playable":41.77863026647469,"score":34.50244788620864},"GB2-05":{"attempts":5,"playable":19.3547512841421,"score":19.3547512841421},"GB2-06":{"attempts":5,"failed_attempts":2,"playable":35.3538717434922,"score":21.7325453894895},"GB2-07":{"attempts":5,"failed_attempts":1,"playable":23.636388153587916,"score":19.753276488422447},"GB2-08":{"attempts":5,"failed_attempts":2,"playable":57.74467647086216,"score":26.33599173246599}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":39.962858718204004,"score":39.962858718204004},"GB2-02":{"attempts":2,"playable":42.250704660746386,"score":42.250704660746386},"GB2-03":{"attempts":2,"playable":47.89249698138576,"score":47.89249698138576},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.65709428159629,"score":21.828547140798143},"GB2-05":{"attempts":2,"playable":16.040733964329057,"score":16.040733964329057},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":53.83502995605499,"score":26.917514978027494},"GB2-07":{"attempts":2,"playable":28.484852287653844,"score":28.484852287653844},"GB2-08":{"attempts":2,"playable":42.52659745307162,"score":42.52659745307162}},"medium":{"GB2-01":{"attempts":1,"playable":17.124259454020994,"score":17.124259454020994},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":36.526275206237635,"score":36.526275206237635},"GB2-04":{"attempts":1,"playable":41.178506669666476,"score":41.178506669666476},"GB2-05":{"attempts":1,"playable":14.119198554741105,"score":14.119198554741105},"GB2-06":{"attempts":1,"playable":24.333657106460397,"score":24.333657106460397},"GB2-07":{"attempts":1,"playable":19.1256421821171,"score":19.1256421821171},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":2,"playable":19.832997268465114,"score":19.832997268465114},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.880051139307476,"score":21.940025569653738},"GB2-03":{"attempts":2,"playable":48.42833999755525,"score":48.42833999755525},"GB2-04":{"attempts":2,"playable":40.500289848161316,"score":40.500289848161316},"GB2-05":{"attempts":2,"playable":27.904321333356148,"score":27.904321333356148},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":27.892928167961212,"score":13.946464083980606},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":23.2986699909928,"score":11.6493349954964},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":72.9627554886527,"score":36.48137774432635}}},"id":"thinkingmachines/inkling","is_recent_addition":false,"last_measured_at":"2026-10-20T11:13:27Z","match_totals_all":{"draws":3891,"losses":7905,"wins":3004},"match_totals_tracks":{"highest":{"draws":1794,"losses":3242,"wins":1448},"medium":{"draws":624,"losses":1811,"wins":341},"none":{"draws":1473,"losses":2852,"wins":1215}},"model_slug":"thinkingmachines-inkling","overall":{"max":48.42833999755525,"mean":26.624791508268956,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":54,"overall_ranking_status":"ranked","per_game":{"GB2-01":39.962858718204004,"GB2-02":42.250704660746386,"GB2-03":47.89249698138576,"GB2-04":43.65709428159629,"GB2-05":16.040733964329057,"GB2-06":53.83502995605499,"GB2-07":28.484852287653844,"GB2-08":42.52659745307162},"per_game_all":{"GB2-01":25.640038480230036,"GB2-03":44.282370728392884,"GB2-04":41.77863026647469,"GB2-05":19.3547512841421,"GB2-06":35.3538717434922,"GB2-07":23.636388153587916},"per_game_match_totals_all":{"GB2-01":{"draws":584,"losses":1430,"wins":326},"GB2-02":{"draws":1050,"losses":233,"wins":13},"GB2-03":{"draws":703,"losses":931,"wins":596},"GB2-04":{"draws":1144,"losses":499,"wins":149},"GB2-05":{"draws":0,"losses":1931,"wins":489},"GB2-06":{"draws":29,"losses":898,"wins":441},"GB2-07":{"draws":0,"losses":1467,"wins":429},"GB2-08":{"draws":381,"losses":516,"wins":561}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":262,"losses":440,"wins":234},"GB2-02":{"draws":690,"losses":165,"wins":9},"GB2-03":{"draws":186,"losses":403,"wins":303},"GB2-04":{"draws":284,"losses":116,"wins":48},"GB2-05":{"draws":0,"losses":815,"wins":153},"GB2-06":{"draws":12,"losses":213,"wins":231},"GB2-07":{"draws":0,"losses":700,"wins":248},"GB2-08":{"draws":360,"losses":390,"wins":222}},"medium":{"GB2-01":{"draws":54,"losses":365,"wins":49},"GB2-03":{"draws":271,"losses":162,"wins":13},"GB2-04":{"draws":296,"losses":121,"wins":31},"GB2-05":{"draws":0,"losses":417,"wins":67},"GB2-06":{"draws":3,"losses":353,"wins":100},"GB2-07":{"draws":0,"losses":393,"wins":81}},"none":{"GB2-01":{"draws":268,"losses":625,"wins":43},"GB2-02":{"draws":360,"losses":68,"wins":4},"GB2-03":{"draws":246,"losses":366,"wins":280},"GB2-04":{"draws":564,"losses":262,"wins":70},"GB2-05":{"draws":0,"losses":699,"wins":269},"GB2-06":{"draws":14,"losses":332,"wins":110},"GB2-07":{"draws":0,"losses":374,"wins":100},"GB2-08":{"draws":21,"losses":126,"wins":339}}},"per_game_raw_elo_all":{"GB2-01":1222.7593397105281,"GB2-03":1383.326151346313,"GB2-04":1414.3378165645584,"GB2-05":1001.8070209551902,"GB2-06":1233.7250250128452,"GB2-07":1101.1298330036773},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1382.831996505365,"GB2-02":1415.9569652099042,"GB2-03":1413.894066546337,"GB2-04":1429.0058715880014,"GB2-05":946.939243090346,"GB2-06":1514.5643699697914,"GB2-07":1174.7802269195574,"GB2-08":1350.187318131393},"medium":{"GB2-01":1124.1798813631447,"GB2-03":1314.2396980424076,"GB2-04":1409.7112652238734,"GB2-05":906.3046500855279,"GB2-06":1065.9672043568307,"GB2-07":1030.0741049042842},"none":{"GB2-01":1161.266141263075,"GB2-02":1428.5696005342438,"GB2-03":1421.844689450195,"GB2-04":1404.2963128818,"GB2-05":1152.1771696896967,"GB2-06":1120.6435007119132,"GB2-07":1098.5351671871904,"GB2-08":1743.086242175381}},"per_game_tracks":{"highest":{"GB2-01":39.962858718204004,"GB2-02":42.250704660746386,"GB2-03":47.89249698138576,"GB2-04":43.65709428159629,"GB2-05":16.040733964329057,"GB2-06":53.83502995605499,"GB2-07":28.484852287653844,"GB2-08":42.52659745307162},"medium":{"GB2-01":17.124259454020994,"GB2-03":36.526275206237635,"GB2-04":41.178506669666476,"GB2-05":14.119198554741105,"GB2-06":24.333657106460397,"GB2-07":19.1256421821171},"none":{"GB2-01":19.832997268465114,"GB2-02":43.880051139307476,"GB2-03":48.42833999755525,"GB2-04":40.500289848161316,"GB2-05":27.904321333356148,"GB2-06":27.892928167961212,"GB2-07":23.2986699909928,"GB2-08":72.9627554886527}},"provider_color":"#31373D","provider_company":"Thinking Machines","provider_key":"thinkingmachines","provider_text_color":"#f8fafc","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:55:39Z","reasoning":{"highest":33.238038273027044,"medium":19.050942396655465,"none":27.585393855124362},"reasoning_agg":{"highest":{"max":47.89249698138576,"mean":33.238038273027044,"min":16.040733964329057},"medium":{"max":41.178506669666476,"mean":19.050942396655465,"min":0.0},"none":{"max":48.42833999755525,"mean":27.585393855124362,"min":11.6493349954964}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":14.187095876371579}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-3-7-flash:c772c6115b8fc654","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"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":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0442025,"mean":0.017142385,"median":0.01322286,"min":0.01037917,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.13713908},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.02271207,"mean":0.0141778,"median":0.011690184999999999,"min":0.00650197,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.11342239999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0442025,"mean":0.017142385,"median":0.01322286,"min":0.01037917,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.13713908},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.02271207,"mean":0.0141778,"median":0.011690184999999999,"min":0.00650197,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.1134224},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"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}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":24,"cost_basis_counts":{"provider_reported":46},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.11219570000000001,"mean":0.030692482499999996,"median":0.01928415,"min":0.00650197,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":26},"recorded_attempt_count":46,"run_count":24,"total":0.7366195800000002},"codegen_latency_ms":{"attempt_count":46,"max_ms":511905,"mean_ms":147013.95833333334,"min_ms":23584,"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":13,"max_ms":348782,"mean_ms":92838.875,"min_ms":39705,"run_count":8},"none":{"attempt_count":13,"max_ms":194018,"mean_ms":63357.25,"min_ms":23584,"run_count":8}},"codegen_output_tokens":{"attempt_count":46,"output_max":93362,"output_mean":24067.583333333332,"output_min":4359,"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":13,"output_max":33638,"output_mean":12726.0,"output_min":7627,"run_count":8},"none":{"attempt_count":13,"output_max":17245,"output_mean":10160.0,"output_min":4359,"run_count":8}},"display_name":"Step 3.7 Flash","economics":{"all":31.84023729136864,"highest":27.592114849703442,"medium":35.106530921421616,"none":40.91579565869437},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":26,"effective_max_output_tokens":[230400],"finish_reason_observations":46,"finish_reasons":["stop"],"indexed_attempts":46,"output_token_observations":46,"provider_post_attempt_observations":26,"provider_post_attempts":26,"reasoning_token_observations":26,"reconciliation_get_attempt_observations":26,"requested_max_output_token_observations":26,"requested_max_output_tokens":[230400],"total_output_tokens":577622,"total_visible_output_tokens":183088,"visible_token_observations":26},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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","GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-05","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-04"],"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":17.528190378300398,"score":17.528190378300398},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":43.64743538888916,"score":14.54914512962972},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":35.763458824328225,"score":23.842305882885483},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":39.71193458741103,"score":13.23731152913701},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":44.63227220463322,"score":29.754848136422144},"GB2-06":{"attempts":3,"playable":42.53049041283919,"score":42.53049041283919},"GB2-07":{"attempts":3,"playable":35.46203108296634,"score":35.46203108296634},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":31.690783036336114,"score":21.127188690890744}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":9.5878133761572,"score":9.5878133761572},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":37.943657728753365,"score":37.943657728753365},"GB2-06":{"attempts":1,"playable":33.08336169424091,"score":33.08336169424091},"GB2-07":{"attempts":1,"playable":24.603682233186106,"score":24.603682233186106},"GB2-08":{"attempts":1,"playable":32.74205921617964,"score":32.74205921617964}},"medium":{"GB2-01":{"attempts":1,"playable":10.355356939998487,"score":10.355356939998487},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":33.837050247481926,"score":33.837050247481926},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":51.32088668051307,"score":51.32088668051307},"GB2-06":{"attempts":1,"playable":45.04194413788909,"score":45.04194413788909},"GB2-07":{"attempts":1,"playable":39.44444066615452,"score":39.44444066615452},"GB2-08":{"attempts":1,"playable":30.639506856492588,"score":30.639506856492588}},"none":{"GB2-01":{"attempts":1,"playable":32.6414008187455,"score":32.6414008187455},"GB2-02":{"attempts":1,"playable":43.64743538888916,"score":43.64743538888916},"GB2-03":{"attempts":1,"playable":37.68986740117452,"score":37.68986740117452},"GB2-04":{"attempts":1,"playable":39.71193458741103,"score":39.71193458741103},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":49.466165406387574,"score":49.466165406387574},"GB2-07":{"attempts":1,"playable":42.337970349558404,"score":42.337970349558404},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"stepfun/step-3.7-flash","is_recent_addition":false,"last_measured_at":"2026-10-20T11:06:29Z","match_totals_all":{"draws":1681,"losses":4434,"wins":1791},"match_totals_tracks":{"highest":{"draws":311,"losses":1588,"wins":469},"medium":{"draws":478,"losses":1631,"wins":705},"none":{"draws":892,"losses":1215,"wins":617}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":51.32088668051307,"mean":24.75393890538388,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":55,"overall_ranking_status":"ranked","per_game":{"GB2-01":9.5878133761572,"GB2-05":37.943657728753365,"GB2-06":33.08336169424091,"GB2-07":24.603682233186106,"GB2-08":32.74205921617964},"per_game_all":{"GB2-01":17.528190378300398,"GB2-06":42.53049041283919,"GB2-07":35.46203108296634},"per_game_match_totals_all":{"GB2-01":{"draws":179,"losses":1080,"wins":145},"GB2-02":{"draws":348,"losses":75,"wins":9},"GB2-03":{"draws":267,"losses":468,"wins":157},"GB2-04":{"draws":289,"losses":131,"wins":28},"GB2-05":{"draws":0,"losses":538,"wins":430},"GB2-06":{"draws":54,"losses":790,"wins":524},"GB2-07":{"draws":0,"losses":950,"wins":472},"GB2-08":{"draws":544,"losses":402,"wins":26}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":25,"losses":414,"wins":29},"GB2-05":{"draws":0,"losses":301,"wins":183},"GB2-06":{"draws":12,"losses":310,"wins":134},"GB2-07":{"draws":0,"losses":368,"wins":106},"GB2-08":{"draws":274,"losses":195,"wins":17}},"medium":{"GB2-01":{"draws":66,"losses":390,"wins":12},"GB2-03":{"draws":130,"losses":244,"wins":72},"GB2-05":{"draws":0,"losses":237,"wins":247},"GB2-06":{"draws":12,"losses":255,"wins":189},"GB2-07":{"draws":0,"losses":298,"wins":176},"GB2-08":{"draws":270,"losses":207,"wins":9}},"none":{"GB2-01":{"draws":88,"losses":276,"wins":104},"GB2-02":{"draws":348,"losses":75,"wins":9},"GB2-03":{"draws":137,"losses":224,"wins":85},"GB2-04":{"draws":289,"losses":131,"wins":28},"GB2-06":{"draws":30,"losses":225,"wins":201},"GB2-07":{"draws":0,"losses":284,"wins":190}}},"per_game_raw_elo_all":{"GB2-01":1100.6795857569457,"GB2-06":1341.484449595567,"GB2-07":1264.1715295478762},"per_game_raw_elo_tracks":{"highest":{"GB2-01":985.9596024876771,"GB2-05":1299.0603440284406,"GB2-06":1198.9158217281436,"GB2-07":1118.4836091836594,"GB2-08":1244.6700676909472},"medium":{"GB2-01":1003.2422275830522,"GB2-03":1289.9400934414064,"GB2-05":1468.6894762297427,"GB2-06":1378.9529371335614,"GB2-07":1318.90889195358,"GB2-08":1222.9136224169183},"none":{"GB2-01":1312.836927200108,"GB2-02":1426.772680863115,"GB2-03":1324.6005815158292,"GB2-04":1398.1912461580373,"GB2-06":1446.5845899249957,"GB2-07":1355.122087506389}},"per_game_tracks":{"highest":{"GB2-01":9.5878133761572,"GB2-05":37.943657728753365,"GB2-06":33.08336169424091,"GB2-07":24.603682233186106,"GB2-08":32.74205921617964},"medium":{"GB2-01":10.355356939998487,"GB2-03":33.837050247481926,"GB2-05":51.32088668051307,"GB2-06":45.04194413788909,"GB2-07":39.44444066615452,"GB2-08":30.639506856492588},"none":{"GB2-01":32.6414008187455,"GB2-02":43.64743538888916,"GB2-03":37.68986740117452,"GB2-04":39.71193458741103,"GB2-06":49.466165406387574,"GB2-07":42.337970349558404}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:07:17Z","reasoning":{"highest":17.245071781064652,"medium":26.329898191066217,"none":30.686846744020773},"reasoning_agg":{"highest":{"max":37.943657728753365,"mean":17.245071781064652,"min":0.0},"medium":{"max":51.32088668051307,"mean":26.329898191066217,"min":0.0},"none":{"max":49.466165406387574,"mean":30.686846744020773,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low"},"score_diagnostics":{"reasoning_variance":13.44177496295612}},{"canonical_public_row_identity":"publication-row.v1:overall:inception-mercury-2-5-preview:5306429c9898abc6","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0021869100000000002,"mean":0.0013222775000000001,"median":0.001054655,"min":0.00083106,"recorded_attempt_count":11,"run_count":8,"total":0.010578220000000001},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0025894200000000003,"mean":0.0012652800000000001,"median":0.000871045,"min":0.00078866,"recorded_attempt_count":12,"run_count":8,"total":0.010122240000000001},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0013895600000000002,"mean":0.0009515637499999999,"median":0.001025285,"min":0.00044038,"recorded_attempt_count":14,"run_count":8,"total":0.00761251}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0025894200000000003,"mean":0.0012652800000000001,"median":0.000871045,"min":0.00078866,"recorded_attempt_count":12,"run_count":8,"total":0.010122240000000001},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0013895600000000002,"mean":0.0009515637499999999,"median":0.001025285,"min":0.00044038,"recorded_attempt_count":14,"run_count":8,"total":0.00761251},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0021869100000000002,"mean":0.0013222775000000001,"median":0.001054655,"min":0.00083106,"recorded_attempt_count":11,"run_count":8,"total":0.010578220000000001}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":24,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0025894200000000003,"mean":0.0011797070833333334,"median":0.000945325,"min":0.00044038,"recorded_attempt_count":37,"run_count":24,"total":0.02831297},"codegen_latency_ms":{"attempt_count":37,"max_ms":49328,"mean_ms":21505.916666666668,"min_ms":9355,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":47445,"mean_ms":22491.5,"min_ms":13295,"run_count":8},"medium":{"attempt_count":12,"max_ms":49328,"mean_ms":23044.25,"min_ms":13295,"run_count":8},"none":{"attempt_count":14,"max_ms":24913,"mean_ms":18982.0,"min_ms":9355,"run_count":8}},"codegen_output_tokens":{"attempt_count":37,"output_max":11394,"output_mean":4854.291666666667,"output_min":1030,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":11185,"output_mean":6150.25,"output_min":2902,"run_count":8},"medium":{"attempt_count":12,"output_max":11394,"output_mean":5469.5,"output_min":3022,"run_count":8},"none":{"attempt_count":14,"output_max":4416,"output_mean":2943.125,"output_min":1030,"run_count":8}},"display_name":"Mercury 2.5 Preview","economics":{"all":34.26035286144303,"highest":27.95959880738638,"medium":27.377973226744984,"none":38.75865087635195},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":37,"finish_reasons":["stop"],"indexed_attempts":37,"output_token_observations":37,"provider_post_attempt_observations":37,"provider_post_attempts":37,"reasoning_token_observations":37,"reconciliation_get_attempt_observations":37,"reconciliation_get_attempts":176,"total_output_tokens":116503,"total_reasoning_output_tokens":61584,"total_visible_output_tokens":54919,"visible_token_observations":37},"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":"inception","provider_model":"inception/mercury-2.5-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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","GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-07","GB2-08"],"first_pass_admitted":2,"first_pass_rate":0.25,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-05"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":2,"playable":27.818794432934297,"score":9.272931477644766},"GB2-02":{"attempts":3,"playable":42.5223587533335,"score":42.5223587533335},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":44.82684486659304,"score":14.942281622197681},"GB2-04":{"attempts":3,"playable":41.214831070672936,"score":41.214831070672936},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":28.493741235150793,"score":18.995827490100528},"GB2-06":{"attempts":3,"playable":19.043868760322667,"score":19.043868760322667},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":12.388627786822864,"score":8.259085191215243},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":31.532566745042974,"score":21.02171116336198}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":27.818794432934297,"score":27.818794432934297},"GB2-02":{"attempts":1,"playable":42.134231110877494,"score":42.134231110877494},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":39.37329559005088,"score":39.37329559005088},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":15.912722954782046,"score":15.912722954782046},"GB2-07":{"attempts":1,"playable":13.982037215311566,"score":13.982037215311566},"GB2-08":{"attempts":1,"playable":28.536511540361992,"score":28.536511540361992}},"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":43.06567904542477,"score":43.06567904542477},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.388989744805826,"score":40.388989744805826},"GB2-05":{"attempts":1,"playable":16.7496787648217,"score":16.7496787648217},"GB2-06":{"attempts":1,"playable":18.739651497359514,"score":18.739651497359514},"GB2-07":{"attempts":1,"playable":10.795218358334163,"score":10.795218358334163},"GB2-08":{"attempts":1,"playable":34.528621949723956,"score":34.528621949723956}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":42.36716610369823,"score":42.36716610369823},"GB2-03":{"attempts":1,"playable":44.82684486659304,"score":44.82684486659304},"GB2-04":{"attempts":1,"playable":43.88220787716212,"score":43.88220787716212},"GB2-05":{"attempts":1,"playable":40.23780370547989,"score":40.23780370547989},"GB2-06":{"attempts":1,"playable":22.47923182882644,"score":22.47923182882644},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"inception/mercury-2.5-preview","is_recent_addition":false,"last_measured_at":"2026-10-20T11:13:32Z","match_totals_all":{"draws":2774,"losses":4132,"wins":904},"match_totals_tracks":{"highest":{"draws":1009,"losses":1529,"wins":226},"medium":{"draws":966,"losses":1577,"wins":237},"none":{"draws":799,"losses":1026,"wins":441}},"model_slug":"inception-mercury-2-5-preview","overall":{"max":44.82684486659304,"mean":21.909111941106165,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":56,"overall_ranking_status":"ranked","per_game":{"GB2-01":27.818794432934297,"GB2-02":42.134231110877494,"GB2-04":39.37329559005088,"GB2-06":15.912722954782046,"GB2-07":13.982037215311566,"GB2-08":28.536511540361992},"per_game_all":{"GB2-02":42.5223587533335,"GB2-04":41.214831070672936,"GB2-06":19.043868760322667},"per_game_match_totals_all":{"GB2-01":{"draws":105,"losses":290,"wins":73},"GB2-02":{"draws":1065,"losses":229,"wins":2},"GB2-03":{"draws":103,"losses":210,"wins":133},"GB2-04":{"draws":961,"losses":326,"wins":57},"GB2-05":{"draws":0,"losses":694,"wins":274},"GB2-06":{"draws":11,"losses":1126,"wins":231},"GB2-07":{"draws":0,"losses":846,"wins":102},"GB2-08":{"draws":529,"losses":411,"wins":32}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":105,"losses":290,"wins":73},"GB2-02":{"draws":349,"losses":81,"wins":2},"GB2-04":{"draws":318,"losses":118,"wins":12},"GB2-06":{"draws":3,"losses":389,"wins":64},"GB2-07":{"draws":0,"losses":416,"wins":58},"GB2-08":{"draws":234,"losses":235,"wins":17}},"medium":{"GB2-02":{"draws":361,"losses":71,"wins":0},"GB2-04":{"draws":305,"losses":120,"wins":23},"GB2-05":{"draws":0,"losses":404,"wins":80},"GB2-06":{"draws":5,"losses":376,"wins":75},"GB2-07":{"draws":0,"losses":430,"wins":44},"GB2-08":{"draws":295,"losses":176,"wins":15}},"none":{"GB2-02":{"draws":355,"losses":77,"wins":0},"GB2-03":{"draws":103,"losses":210,"wins":133},"GB2-04":{"draws":338,"losses":88,"wins":22},"GB2-05":{"draws":0,"losses":290,"wins":194},"GB2-06":{"draws":3,"losses":361,"wins":92}}},"per_game_raw_elo_all":{"GB2-02":1418.0623740332555,"GB2-04":1409.9295568478128,"GB2-06":979.581337129357},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1260.8363400017365,"GB2-02":1415.0526605026348,"GB2-04":1395.517117814769,"GB2-06":926.2101322487524,"GB2-07":931.2636621655828,"GB2-08":1200.7312232264708},"medium":{"GB2-02":1422.2736922871886,"GB2-04":1403.521209260476,"GB2-05":961.3030414134053,"GB2-06":975.7102755354753,"GB2-07":856.8201829266351,"GB2-08":1262.9302677557528},"none":{"GB2-02":1416.8607693099427,"GB2-03":1387.1084905270109,"GB2-04":1430.7503434681928,"GB2-05":1329.1724137522365,"GB2-06":1036.8236036038436}},"per_game_tracks":{"highest":{"GB2-01":27.818794432934297,"GB2-02":42.134231110877494,"GB2-04":39.37329559005088,"GB2-06":15.912722954782046,"GB2-07":13.982037215311566,"GB2-08":28.536511540361992},"medium":{"GB2-02":43.06567904542477,"GB2-04":40.388989744805826,"GB2-05":16.7496787648217,"GB2-06":18.739651497359514,"GB2-07":10.795218358334163,"GB2-08":34.528621949723956},"none":{"GB2-02":42.36716610369823,"GB2-03":44.82684486659304,"GB2-04":43.88220787716212,"GB2-05":40.23780370547989,"GB2-06":22.47923182882644}},"provider_color":"#CBD5E1","provider_company":"Inception","provider_key":"inception","provider_text_color":"#0b1120","rank_movement":0,"rank_movement_baseline_at":"2026-10-15T06:51:01Z","reasoning":{"highest":20.969699105539785,"medium":20.53347992005874,"none":24.224156797719967},"reasoning_agg":{"highest":{"max":42.134231110877494,"mean":20.969699105539785,"min":0.0},"medium":{"max":43.06567904542477,"mean":20.53347992005874,"min":0.0},"none":{"max":44.82684486659304,"mean":24.224156797719967,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":3.690676877661229}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-1-flash-lite:f8b6c8a1e8419df3","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"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":0.21994025000000003},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"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},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.00870475,"mean":0.005883593750000001,"median":0.006313125,"min":0.003432,"recorded_attempt_count":13,"run_count":8,"total":0.04706875}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"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":0.08108400000000002},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.00870475,"mean":0.005883593750000001,"median":0.006313125,"min":0.003432,"recorded_attempt_count":13,"run_count":8,"total":0.04706874999999999},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"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":0.21994025000000003}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":24,"cost_basis_counts":{"provider_reported":50},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.0422995,"mean":0.014503875,"median":0.010566625,"min":0.003432,"recorded_attempt_count":50,"run_count":24,"total":0.34809299999999993},"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":16.061453468318728,"highest":28.390116997746397,"medium":26.981604546566217,"none":18.1998150073157},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.5},"baseline":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-04","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":24.42876607318149,"score":16.28584404878766},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":42.94929079597173,"score":14.316430265323909},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":43.71328474314334,"score":29.142189828762227},"GB2-05":{"attempts":3,"playable":11.368246727243125,"score":11.368246727243125},"GB2-06":{"attempts":3,"playable":22.744946642180082,"score":22.744946642180082},"GB2-07":{"attempts":3,"playable":14.071167035532982,"score":14.071167035532982},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":35.52640683060892,"score":23.684271220405947}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.20675917937842,"score":43.20675917937842},"GB2-05":{"attempts":1,"playable":10.890954586047245,"score":10.890954586047245},"GB2-06":{"attempts":1,"playable":20.26341092418769,"score":20.26341092418769},"GB2-07":{"attempts":1,"playable":33.37606265743469,"score":33.37606265743469},"GB2-08":{"attempts":1,"playable":34.213397641683954,"score":34.213397641683954}},"medium":{"GB2-01":{"attempts":1,"playable":34.56492647448691,"score":34.56492647448691},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":44.21981030690826,"score":44.21981030690826},"GB2-05":{"attempts":1,"playable":17.15510757378082,"score":17.15510757378082},"GB2-06":{"attempts":1,"playable":23.175939056515134,"score":23.175939056515134},"GB2-07":{"attempts":1,"playable":5.934427848172306,"score":5.934427848172306},"GB2-08":{"attempts":1,"playable":36.83941601953388,"score":36.83941601953388}},"none":{"GB2-01":{"attempts":1,"playable":14.292605671876068,"score":14.292605671876068},"GB2-02":{"attempts":1,"playable":42.94929079597173,"score":42.94929079597173},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":6.0586780219013106,"score":6.0586780219013106},"GB2-06":{"attempts":1,"playable":24.795489945837428,"score":24.795489945837428},"GB2-07":{"attempts":1,"playable":2.903010600991956,"score":2.903010600991956},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"google/gemini-3.1-flash-lite","is_recent_addition":false,"last_measured_at":"2026-10-20T11:44:10Z","match_totals_all":{"draws":1720,"losses":4879,"wins":879},"match_totals_tracks":{"highest":{"draws":600,"losses":1417,"wins":331},"medium":{"draws":677,"losses":1753,"wins":386},"none":{"draws":443,"losses":1709,"wins":162}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":44.21981030690826,"mean":16.45163697102949,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":57,"overall_ranking_status":"partial","per_game":{"GB2-04":43.20675917937842,"GB2-05":10.890954586047245,"GB2-06":20.26341092418769,"GB2-07":33.37606265743469,"GB2-08":34.213397641683954},"per_game_all":{"GB2-05":11.368246727243125,"GB2-06":22.744946642180082,"GB2-07":14.071167035532982},"per_game_match_totals_all":{"GB2-01":{"draws":314,"losses":559,"wins":63},"GB2-02":{"draws":348,"losses":78,"wins":6},"GB2-04":{"draws":615,"losses":208,"wins":73},"GB2-05":{"draws":0,"losses":1292,"wins":160},"GB2-06":{"draws":10,"losses":1079,"wins":279},"GB2-07":{"draws":0,"losses":1242,"wins":180},"GB2-08":{"draws":433,"losses":421,"wins":118}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":326,"losses":97,"wins":25},"GB2-05":{"draws":0,"losses":433,"wins":51},"GB2-06":{"draws":0,"losses":372,"wins":84},"GB2-07":{"draws":0,"losses":327,"wins":147},"GB2-08":{"draws":274,"losses":188,"wins":24}},"medium":{"GB2-01":{"draws":226,"losses":198,"wins":44},"GB2-04":{"draws":289,"losses":111,"wins":48},"GB2-05":{"draws":0,"losses":402,"wins":82},"GB2-06":{"draws":3,"losses":358,"wins":95},"GB2-07":{"draws":0,"losses":451,"wins":23},"GB2-08":{"draws":159,"losses":233,"wins":94}},"none":{"GB2-01":{"draws":88,"losses":361,"wins":19},"GB2-02":{"draws":348,"losses":78,"wins":6},"GB2-05":{"draws":0,"losses":457,"wins":27},"GB2-06":{"draws":7,"losses":349,"wins":100},"GB2-07":{"draws":0,"losses":464,"wins":10}}},"per_game_raw_elo_all":{"GB2-05":826.3205550355791,"GB2-06":1040.688037353304,"GB2-07":828.5210405487998},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1425.512828990763,"GB2-05":829.9787738905248,"GB2-06":1001.0803401407408,"GB2-07":1241.0493174219387,"GB2-08":1259.7196754588515},"medium":{"GB2-01":1332.6493055961503,"GB2-04":1433.3647011104738,"GB2-05":969.3563630062303,"GB2-06":1047.8420184753654,"GB2-07":702.8563683750998,"GB2-08":1286.3724330913753},"none":{"GB2-01":1078.881575129082,"GB2-02":1421.3726630230817,"GB2-05":679.6265282099823,"GB2-06":1073.141753443806,"GB2-07":541.6574358493607}},"per_game_tracks":{"highest":{"GB2-04":43.20675917937842,"GB2-05":10.890954586047245,"GB2-06":20.26341092418769,"GB2-07":33.37606265743469,"GB2-08":34.213397641683954},"medium":{"GB2-01":34.56492647448691,"GB2-04":44.21981030690826,"GB2-05":17.15510757378082,"GB2-06":23.175939056515134,"GB2-07":5.934427848172306,"GB2-08":36.83941601953388},"none":{"GB2-01":14.292605671876068,"GB2-02":42.94929079597173,"GB2-05":6.0586780219013106,"GB2-06":24.795489945837428,"GB2-07":2.903010600991956}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":17.743823123591497,"medium":20.236203409924663,"none":11.374884379572311},"reasoning_agg":{"highest":{"max":43.20675917937842,"mean":17.743823123591497,"min":0.0},"medium":{"max":44.21981030690826,"mean":20.236203409924663,"min":0.0},"none":{"max":42.94929079597173,"mean":11.374884379572311,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":8.861319030352352}},{"canonical_public_row_identity":"publication-row.v1:overall:upstage-solar-mini4:8ed9f35f2f7d99b2","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.02342595,"mean":0.01633628125,"median":0.016221199999999998,"min":0.011361950000000001,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":18},"recorded_attempt_count":18,"run_count":8,"total":0.13069025},"medium":{"admitted_cell_count":2,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.012110200000000002,"mean":0.0072751125,"median":0.0080226,"min":0.00114085,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":15,"run_count":8,"total":0.0582009},"none":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0023752,"mean":0.0015195812500000002,"median":0.00138595,"min":0.00063975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":16},"recorded_attempt_count":16,"run_count":8,"total":0.012156650000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":2,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.012110200000000002,"mean":0.0072751125,"median":0.0080226,"min":0.00114085,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":15,"run_count":8,"total":0.0582009},"historical-provider-setting-baseline":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0023752,"mean":0.0015195812500000002,"median":0.00138595,"min":0.00063975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":16},"recorded_attempt_count":16,"run_count":8,"total":0.012156650000000001},"historical-provider-setting-intensive":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.02342595,"mean":0.01633628125,"median":0.016221199999999998,"min":0.011361950000000001,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":18},"recorded_attempt_count":18,"run_count":8,"total":0.13069024999999998}},"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":24,"cost_basis_counts":{"provider_reported":49},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":17,"max":0.02342595,"mean":0.008376991666666668,"median":0.0080226,"min":0.00063975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":48},"recorded_attempt_count":49,"run_count":24,"total":0.2010478},"codegen_latency_ms":{"attempt_count":48,"max_ms":1854161,"mean_ms":628655.8260869565,"min_ms":24176,"run_count":23},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":1854161,"mean_ms":1241203.5,"min_ms":669527,"run_count":8},"medium":{"attempt_count":14,"max_ms":912503,"mean_ms":578415.5714285715,"min_ms":208280,"run_count":7},"none":{"attempt_count":16,"max_ms":108436,"mean_ms":60068.375,"min_ms":24176,"run_count":8}},"codegen_output_tokens":{"attempt_count":49,"output_max":112315,"output_mean":38073.333333333336,"output_min":1354,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":112315,"output_mean":77461.75,"output_min":52895,"run_count":8},"medium":{"attempt_count":15,"output_max":54994,"output_mean":32804.625,"output_min":3815,"run_count":8},"none":{"attempt_count":16,"output_max":7089,"output_mean":3953.625,"output_min":1354,"run_count":8}},"display_name":"Solar Mini 4","economics":{"highest":37.16017047128988,"medium":20.00055260582326,"none":40.61460813983791},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":49,"effective_max_output_tokens":[131072],"finish_reason_observations":48,"finish_reasons":["stop"],"indexed_attempts":49,"output_token_observations":49,"provider_post_attempt_observations":49,"provider_post_attempts":51,"reasoning_token_observations":49,"reconciliation_get_attempt_observations":49,"requested_max_output_token_observations":49,"requested_max_output_tokens":[131072],"total_output_tokens":913760,"total_reasoning_output_tokens":808441,"total_visible_output_tokens":105319,"visible_token_observations":49},"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":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"upstage","provider_model":"upstage/solar-mini4","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":2,"evaluated_cells":7,"failed_game_aliases":["GB2-03","GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.14285714285714285,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"infra_failures_excluded":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"infra_excluded_game_aliases":["GB2-02"],"infra_failures_excluded":1,"model_code_failure_rate":0.7142857142857143,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":1,"repaired_rate":0.14285714285714285},"baseline":{"admitted_plugins":1,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-05","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.125,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.875,"model_code_failures":7,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}},"intensive":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-08"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":2,"playable":19.620728220925283,"score":6.540242740308428},"GB2-02":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":40.61460813983791,"score":13.538202713279304},"GB2-05":{"attempts":3,"failed_attempts":2,"playable":46.92603049739365,"score":15.642010165797883},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":25.779397624881273,"score":17.18626508325418},"GB2-07":{"attempts":3,"failed_attempts":2,"playable":33.37606265743469,"score":11.125354219144896},"GB2-08":{"attempts":3,"failed_attempts":3,"score":0.0}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":46.92603049739365,"score":46.92603049739365},"GB2-06":{"attempts":1,"playable":31.17841825904131,"score":31.17841825904131},"GB2-07":{"attempts":1,"playable":33.37606265743469,"score":33.37606265743469},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"medium":{"GB2-01":{"attempts":1,"playable":19.620728220925283,"score":19.620728220925283},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":20.380376990721235,"score":20.380376990721235},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.61460813983791,"score":40.61460813983791},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"upstage/solar-mini4","is_recent_addition":false,"last_measured_at":"2026-10-12T22:38:55Z","match_totals_all":{"draws":406,"losses":1730,"wins":650},"match_totals_tracks":{"highest":{"draws":7,"losses":906,"wins":501},"medium":{"draws":84,"losses":710,"wins":130},"none":{"draws":315,"losses":114,"wins":19}},"model_slug":"upstage-solar-mini4","overall":{"max":46.92603049739365,"mean":8.242111181959077,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold","generation_incomplete"],"overall_official_rank":58,"overall_ranking_status":"partial","per_game":{"GB2-05":46.92603049739365,"GB2-06":31.17841825904131,"GB2-07":33.37606265743469},"per_game_match_totals_all":{"GB2-01":{"draws":79,"losses":341,"wins":48},"GB2-04":{"draws":315,"losses":114,"wins":19},"GB2-05":{"draws":0,"losses":258,"wins":226},"GB2-06":{"draws":12,"losses":690,"wins":210},"GB2-07":{"draws":0,"losses":327,"wins":147}},"per_game_match_totals_tracks":{"highest":{"GB2-05":{"draws":0,"losses":258,"wins":226},"GB2-06":{"draws":7,"losses":321,"wins":128},"GB2-07":{"draws":0,"losses":327,"wins":147}},"medium":{"GB2-01":{"draws":79,"losses":341,"wins":48},"GB2-06":{"draws":5,"losses":369,"wins":82}},"none":{"GB2-04":{"draws":315,"losses":114,"wins":19}}},"per_game_raw_elo_tracks":{"highest":{"GB2-05":1413.9418564331927,"GB2-06":1170.2929442228838,"GB2-07":1241.0493174219387},"medium":{"GB2-01":1160.000743590267,"GB2-06":1002.9981375724441},"none":{"GB2-04":1405.2927587447987}},"per_game_tracks":{"highest":{"GB2-05":46.92603049739365,"GB2-06":31.17841825904131,"GB2-07":33.37606265743469},"medium":{"GB2-01":19.620728220925283,"GB2-06":20.380376990721235},"none":{"GB2-04":40.61460813983791}},"provider_color":"#805CFB","provider_company":"Upstage","provider_key":"upstage","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":13.935063926733706,"medium":5.714443601663788,"none":5.076826017479739},"reasoning_agg":{"highest":{"max":46.92603049739365,"mean":13.935063926733706,"min":0.0},"medium":{"max":20.380376990721235,"mean":5.714443601663788,"min":0.0},"none":{"max":40.61460813983791,"mean":5.076826017479739,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":8.858237909253967}},{"canonical_public_row_identity":"publication-row.v1:overall:ibm-granite-granite-4-2-8b:cad88ef1dc140c69","codegen_cost_by_reasoning":{"highest":{"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.01113168,"mean":0.0083819225,"median":0.007854965,"min":0.00635193,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":18},"recorded_attempt_count":18,"run_count":8,"total":0.06705538},"medium":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.00328117,"mean":0.0022631475,"median":0.0021966650000000004,"min":0.00164236,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":19},"recorded_attempt_count":19,"run_count":8,"total":0.01810518},"none":{"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.00394984,"mean":0.0028174899999999998,"median":0.00280168,"min":0.0021764799999999997,"recorded_attempt_count":19,"run_count":8,"total":0.022539919999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.00328117,"mean":0.0022631475,"median":0.0021966650000000004,"min":0.00164236,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":19},"recorded_attempt_count":19,"run_count":8,"total":0.01810518},"historical-provider-setting-baseline":{"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.00394984,"mean":0.0028174899999999998,"median":0.00280168,"min":0.0021764799999999997,"recorded_attempt_count":19,"run_count":8,"total":0.022539919999999998},"historical-provider-setting-intensive":{"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.01113168,"mean":0.0083819225,"median":0.007854965,"min":0.00635193,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":18},"recorded_attempt_count":18,"run_count":8,"total":0.06705538}},"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":24,"cost_basis_counts":{"provider_reported":56},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":23,"max":0.01113168,"mean":0.00448752,"median":0.002935335,"min":0.00164236,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":37},"recorded_attempt_count":56,"run_count":24,"total":0.10770047999999999},"codegen_latency_ms":{"attempt_count":56,"max_ms":643052,"mean_ms":207186.875,"min_ms":45308,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":643052,"mean_ms":466285.75,"min_ms":257629,"run_count":8},"medium":{"attempt_count":19,"max_ms":129121,"mean_ms":76432.5,"min_ms":45308,"run_count":8},"none":{"attempt_count":19,"max_ms":136274,"mean_ms":78842.375,"min_ms":49515,"run_count":8}},"codegen_output_tokens":{"attempt_count":56,"output_max":39360,"output_mean":13818.666666666666,"output_min":3954,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":39360,"output_mean":29587.25,"output_min":21705,"run_count":8},"medium":{"attempt_count":19,"output_max":7321,"output_mean":5310.0,"output_min":3954,"run_count":8},"none":{"attempt_count":19,"output_max":9484,"output_mean":6558.75,"output_min":4755,"run_count":8}},"display_name":"Granite 4.2 8B","economics":{"medium":38.92166267937459},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":37,"effective_max_output_tokens":[117964],"finish_reason_observations":56,"finish_reasons":["stop"],"indexed_attempts":56,"output_token_observations":56,"provider_post_attempt_observations":56,"provider_post_attempts":56,"reasoning_token_observations":56,"reconciliation_get_attempt_observations":56,"reconciliation_get_attempts":88,"requested_max_output_token_observations":37,"requested_max_output_tokens":[117964],"total_output_tokens":331648,"total_reasoning_output_tokens":194609,"total_visible_output_tokens":137039,"visible_token_observations":56},"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":"ibm","provider_model":"ibm-granite/granite-4.2-8b","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":1,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-05","GB2-06","GB2-07","GB2-08"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.875,"model_code_failures":7,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":0,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":1.0,"model_code_failures":8,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"under_tested","grouped_stable":false,"policy_id":"duellab_official_qualification_v1","ranked":false}},"intensive":{"admitted_plugins":0,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":1.0,"model_code_failures":8,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"under_tested","grouped_stable":false,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-02":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":38.92166267937459,"score":12.97388755979153},"GB2-05":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-06":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-07":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-08":{"attempts":3,"failed_attempts":3,"score":0.0}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":38.92166267937459,"score":38.92166267937459},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"ibm-granite/granite-4.2-8b","is_recent_addition":false,"last_measured_at":"2026-10-14T17:59:01Z","match_totals_all":{"draws":286,"losses":136,"wins":26},"match_totals_tracks":{"medium":{"draws":286,"losses":136,"wins":26}},"model_slug":"ibm-granite-granite-4-2-8b","overall":{"max":38.92166267937459,"mean":1.6217359449739412,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold","fixed_coverage_incomplete","grouped_stability_incomplete"],"overall_official_rank":59,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-04":{"draws":286,"losses":136,"wins":26}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":286,"losses":136,"wins":26}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1391.9414627783788}},"per_game_tracks":{"medium":{"GB2-04":38.92166267937459}},"provider_color":"#0F62FE","provider_company":"IBM","provider_key":"ibm","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":0.0,"medium":4.865207834921824,"none":0.0},"reasoning_agg":{"highest":{"max":0.0,"mean":0.0,"min":0.0},"medium":{"max":38.92166267937459,"mean":4.865207834921824,"min":0.0},"none":{"max":0.0,"mean":0.0,"min":0.0}},"reasoning_labels":{"highest":"Full","medium":"Low","none":"Non-thinking"},"reasoning_settings":{"balanced":"low"},"score_diagnostics":{"reasoning_variance":4.865207834921824}},{"canonical_public_row_identity":"publication-row.v1:overall:unbiased-pareto-26-10-preview:279ed8e1938a92c1","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0380352,"mean":0.030679699999999997,"median":0.0320616,"min":0.0216328,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.24543759999999998}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0380352,"mean":0.030679699999999997,"median":0.0320616,"min":0.0216328,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.24543759999999998}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0380352,"mean":0.030679699999999997,"median":0.0320616,"min":0.0216328,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.24543759999999998},"codegen_latency_ms":{"attempt_count":9,"max_ms":206060,"mean_ms":152052.0,"min_ms":81370,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":9,"max_ms":206060,"mean_ms":152052.0,"min_ms":81370,"run_count":8}},"codegen_output_tokens":{"attempt_count":9,"output_max":9255,"output_mean":7213.75,"output_min":4888,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":9,"output_max":9255,"output_mean":7213.75,"output_min":4888,"run_count":8}},"display_name":"Pareto 26.10 Preview","economics":{"none":89.7648021728229},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":9,"effective_max_output_tokens":[131072],"finish_reason_observations":9,"finish_reasons":["stop"],"indexed_attempts":9,"output_token_observations":9,"provider_post_attempt_observations":9,"provider_post_attempts":9,"reasoning_token_observations":9,"reconciliation_get_attempt_observations":9,"requested_max_output_token_observations":9,"requested_max_output_tokens":[131072],"total_output_tokens":57710,"total_visible_output_tokens":57710,"visible_token_observations":9},"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":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"unbiased","provider_model":"unbiased/pareto-26.10-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":74.3060471198114,"score":74.3060471198114},"GB2-02":{"attempts":1,"playable":91.36032585284258,"score":91.36032585284258},"GB2-03":{"attempts":1,"playable":94.06198382491885,"score":94.06198382491885},"GB2-04":{"attempts":1,"playable":86.00856240981,"score":86.00856240981},"GB2-05":{"attempts":1,"playable":94.83961049619671,"score":94.83961049619671},"GB2-06":{"attempts":1,"playable":87.59042676973955,"score":87.59042676973955},"GB2-07":{"attempts":1,"playable":95.80013112143844,"score":95.80013112143844},"GB2-08":{"attempts":1,"playable":94.15132978782572,"score":94.15132978782572}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":74.3060471198114,"score":74.3060471198114},"GB2-02":{"attempts":1,"playable":91.36032585284258,"score":91.36032585284258},"GB2-03":{"attempts":1,"playable":94.06198382491885,"score":94.06198382491885},"GB2-04":{"attempts":1,"playable":86.00856240981,"score":86.00856240981},"GB2-05":{"attempts":1,"playable":94.83961049619671,"score":94.83961049619671},"GB2-06":{"attempts":1,"playable":87.59042676973955,"score":87.59042676973955},"GB2-07":{"attempts":1,"playable":95.80013112143844,"score":95.80013112143844},"GB2-08":{"attempts":1,"playable":94.15132978782572,"score":94.15132978782572}}},"id":"unbiased/pareto-26.10-preview","is_recent_addition":false,"last_measured_at":"2026-10-13T22:57:19Z","match_totals_all":{"draws":128,"losses":313,"wins":3253},"match_totals_tracks":{"none":{"draws":128,"losses":313,"wins":3253}},"model_slug":"unbiased-pareto-26-10-preview","overall":{"max":95.80013112143844,"mean":89.7648021728229,"min":74.3060471198114},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":12,"losses":117,"wins":339},"GB2-02":{"draws":35,"losses":20,"wins":377},"GB2-03":{"draws":5,"losses":25,"wins":416},"GB2-04":{"draws":39,"losses":46,"wins":363},"GB2-05":{"draws":0,"losses":23,"wins":461},"GB2-06":{"draws":37,"losses":37,"wins":382},"GB2-07":{"draws":0,"losses":17,"wins":457},"GB2-08":{"draws":0,"losses":28,"wins":458}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":12,"losses":117,"wins":339},"GB2-02":{"draws":35,"losses":20,"wins":377},"GB2-03":{"draws":5,"losses":25,"wins":416},"GB2-04":{"draws":39,"losses":46,"wins":363},"GB2-05":{"draws":0,"losses":23,"wins":461},"GB2-06":{"draws":37,"losses":37,"wins":382},"GB2-07":{"draws":0,"losses":17,"wins":457},"GB2-08":{"draws":0,"losses":28,"wins":458}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1736.607542220993,"GB2-02":1967.8461580842056,"GB2-03":2176.374434631331,"GB2-04":1846.6673844386435,"GB2-05":2532.034831562133,"GB2-06":2135.2082607464176,"GB2-07":2492.231169752288,"GB2-08":2298.900366670386}},"per_game_tracks":{"none":{"GB2-01":74.3060471198114,"GB2-02":91.36032585284258,"GB2-03":94.06198382491885,"GB2-04":86.00856240981,"GB2-05":94.83961049619671,"GB2-06":87.59042676973955,"GB2-07":95.80013112143844,"GB2-08":94.15132978782572}},"provider_color":"#FF563F","provider_company":"Unbiased","provider_key":"unbiased","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":89.7648021728229},"reasoning_agg":{"none":{"max":95.80013112143844,"mean":89.7648021728229,"min":74.3060471198114}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Provider default (reasoning controls unavailable)"},"reasoning_settings":{"baseline":"default"}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-pro:ba0e7b91d293d49e","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.158732805,"mean":0.056915889375,"median":0.0447982575,"min":0.02822715,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.45532711499999995},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01198425,"mean":0.00718913625,"median":0.0061211025,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.057513089999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.158732805,"mean":0.056915889375,"median":0.0447982575,"min":0.02822715,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.455327115},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01198425,"mean":0.00718913625,"median":0.0061211025,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.057513089999999996}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.158732805,"mean":0.032052512812499996,"median":0.0201057,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10,"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":19,"run_count":16,"total":0.5128402049999999},"codegen_latency_ms":{"attempt_count":19,"max_ms":3172586,"mean_ms":488857.125,"min_ms":33029,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":9,"max_ms":3172586,"mean_ms":924271.75,"min_ms":388744,"run_count":8},"none":{"attempt_count":10,"max_ms":84396,"mean_ms":53442.5,"min_ms":33029,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":171951,"output_mean":32110.125,"output_min":2214,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":9,"output_max":171951,"output_mean":60792.125,"output_min":28781,"run_count":8},"none":{"attempt_count":10,"output_max":6088,"output_mean":3428.125,"output_min":2214,"run_count":8}},"display_name":"MiMo-V2.6-Pro","economics":{"medium":73.32304610444994,"none":50.87231992857157},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":19,"effective_max_output_tokens":[131072],"finish_reason_observations":19,"finish_reasons":["stop"],"indexed_attempts":19,"output_token_observations":19,"provider_post_attempt_observations":19,"provider_post_attempts":20,"reasoning_token_observations":19,"reconciliation_get_attempt_observations":19,"requested_max_output_token_observations":19,"requested_max_output_tokens":[131072],"total_output_tokens":513762,"total_reasoning_output_tokens":447944,"total_visible_output_tokens":65818,"visible_token_observations":19},"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":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":46.99349317462537,"score":46.99349317462537},"GB2-02":{"attempts":2,"playable":60.8464780241429,"score":60.8464780241429},"GB2-03":{"attempts":2,"playable":65.5304767747214,"score":65.5304767747214},"GB2-04":{"attempts":2,"playable":50.66644478890318,"score":50.66644478890318},"GB2-05":{"attempts":2,"playable":65.21424843154372,"score":65.21424843154372},"GB2-06":{"attempts":2,"playable":56.671738979170726,"score":56.671738979170726},"GB2-07":{"attempts":2,"playable":66.54876752563297,"score":66.54876752563297},"GB2-08":{"attempts":2,"playable":84.30981643334582,"score":84.30981643334582}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":54.19967066428153,"score":54.19967066428153},"GB2-02":{"attempts":1,"playable":80.72412059081351,"score":80.72412059081351},"GB2-03":{"attempts":1,"playable":85.892184919876,"score":85.892184919876},"GB2-04":{"attempts":1,"playable":46.46836392540203,"score":46.46836392540203},"GB2-05":{"attempts":1,"playable":84.96678331289638,"score":84.96678331289638},"GB2-06":{"attempts":1,"playable":57.64941054593974,"score":57.64941054593974},"GB2-07":{"attempts":1,"playable":89.93686685480145,"score":89.93686685480145},"GB2-08":{"attempts":1,"playable":86.74696802158887,"score":86.74696802158887}},"none":{"GB2-01":{"attempts":1,"playable":39.78731568496921,"score":39.78731568496921},"GB2-02":{"attempts":1,"playable":40.96883545747229,"score":40.96883545747229},"GB2-03":{"attempts":1,"playable":45.16876862956678,"score":45.16876862956678},"GB2-04":{"attempts":1,"playable":54.864525652404325,"score":54.864525652404325},"GB2-05":{"attempts":1,"playable":45.46171355019105,"score":45.46171355019105},"GB2-06":{"attempts":1,"playable":55.69406741240171,"score":55.69406741240171},"GB2-07":{"attempts":1,"playable":43.16066819646447,"score":43.16066819646447},"GB2-08":{"attempts":1,"playable":81.87266484510275,"score":81.87266484510275}}},"id":"xiaomi/mimo-v2.6-pro","is_recent_addition":false,"last_measured_at":"2026-10-20T11:17:46Z","match_totals_all":{"draws":1291,"losses":2221,"wins":3876},"match_totals_tracks":{"medium":{"draws":341,"losses":835,"wins":2518},"none":{"draws":950,"losses":1386,"wins":1358}},"model_slug":"xiaomi-mimo-v2-6-pro","overall":{"max":89.93686685480145,"mean":62.09768301651076,"min":39.78731568496921},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":280,"losses":365,"wins":291},"GB2-02":{"draws":407,"losses":143,"wins":314},"GB2-03":{"draws":94,"losses":282,"wins":516},"GB2-04":{"draws":459,"losses":224,"wins":213},"GB2-05":{"draws":0,"losses":339,"wins":629},"GB2-06":{"draws":51,"losses":385,"wins":476},"GB2-07":{"draws":0,"losses":326,"wins":622},"GB2-08":{"draws":0,"losses":157,"wins":815}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":71,"losses":183,"wins":214},"GB2-02":{"draws":76,"losses":48,"wins":308},"GB2-03":{"draws":2,"losses":68,"wins":376},"GB2-04":{"draws":163,"losses":164,"wins":121},"GB2-05":{"draws":0,"losses":74,"wins":410},"GB2-06":{"draws":29,"losses":186,"wins":241},"GB2-07":{"draws":0,"losses":46,"wins":428},"GB2-08":{"draws":0,"losses":66,"wins":420}},"none":{"GB2-01":{"draws":209,"losses":182,"wins":77},"GB2-02":{"draws":331,"losses":95,"wins":6},"GB2-03":{"draws":92,"losses":214,"wins":140},"GB2-04":{"draws":296,"losses":60,"wins":92},"GB2-05":{"draws":0,"losses":265,"wins":219},"GB2-06":{"draws":22,"losses":199,"wins":235},"GB2-07":{"draws":0,"losses":280,"wins":194},"GB2-08":{"draws":0,"losses":91,"wins":395}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1522.845254898622,"GB2-02":1767.113036973324,"GB2-03":1893.6393780479534,"GB2-04":1450.739339012947,"GB2-05":2079.769488086393,"GB2-06":1575.3527913023158,"GB2-07":2181.2404146979516,"GB2-08":2045.1552699434194},"none":{"GB2-01":1384.6380003520933,"GB2-02":1405.9796348756056,"GB2-03":1390.0886468715853,"GB2-04":1516.080712466032,"GB2-05":1395.6362657568977,"GB2-06":1543.9957422795624,"GB2-07":1365.364141131014,"GB2-08":1924.473724341564}},"per_game_tracks":{"medium":{"GB2-01":54.19967066428153,"GB2-02":80.72412059081351,"GB2-03":85.892184919876,"GB2-04":46.46836392540203,"GB2-05":84.96678331289638,"GB2-06":57.64941054593974,"GB2-07":89.93686685480145,"GB2-08":86.74696802158887},"none":{"GB2-01":39.78731568496921,"GB2-02":40.96883545747229,"GB2-03":45.16876862956678,"GB2-04":54.864525652404325,"GB2-05":45.46171355019105,"GB2-06":55.69406741240171,"GB2-07":43.16066819646447,"GB2-08":81.87266484510275}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":73.32304610444994,"none":50.87231992857157},"reasoning_agg":{"medium":{"max":89.93686685480145,"mean":73.32304610444994,"min":46.46836392540203},"none":{"max":81.87266484510275,"mean":50.87231992857157,"min":39.78731568496921}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":22.450726175878373}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-5-preview:d6acf4ab074f64d1","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.183419,"mean":0.183419,"median":0.183419,"min":0.183419,"recorded_attempt_count":1,"run_count":1,"total":0.183419},"medium":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1820682,"mean":0.1820682,"median":0.1820682,"min":0.1820682,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1820682},"none":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1898863,"mean":0.1898863,"median":0.1898863,"min":0.1898863,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1898863}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1820682,"mean":0.1820682,"median":0.1820682,"min":0.1820682,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1820682},"historical-provider-setting-baseline":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1898863,"mean":0.1898863,"median":0.1898863,"min":0.1898863,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1898863},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.183419,"mean":0.183419,"median":0.183419,"min":0.183419,"recorded_attempt_count":1,"run_count":1,"total":0.183419}},"codegen_cost_usd":{"admitted_cell_count":2,"cell_count":3,"cost_basis_counts":{"provider_reported":5},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1898863,"mean":0.1851245,"median":0.183419,"min":0.1820682,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":4},"recorded_attempt_count":5,"run_count":3,"total":0.5553735},"codegen_latency_ms":{"attempt_count":4,"max_ms":724394,"mean_ms":700552.5,"min_ms":676711,"run_count":2},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":2,"max_ms":724394,"mean_ms":724394.0,"min_ms":724394,"run_count":1},"none":{"attempt_count":2,"max_ms":676711,"mean_ms":676711.0,"min_ms":676711,"run_count":1}},"codegen_output_tokens":{"attempt_count":5,"output_max":64000,"output_mean":62025.0,"output_min":59586,"run_count":3},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":1,"output_max":64000,"output_mean":64000.0,"output_min":64000,"run_count":1},"medium":{"attempt_count":2,"output_max":59586,"output_mean":59586.0,"output_min":59586,"run_count":1},"none":{"attempt_count":2,"output_max":62489,"output_mean":62489.0,"output_min":62489,"run_count":1}},"display_name":"Step 5 Preview","economics":{"medium":83.04265097472776,"none":35.3690944480826},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":5,"effective_max_output_tokens":[64000],"finish_reason_observations":4,"finish_reasons":["stop"],"indexed_attempts":5,"output_token_observations":5,"provider_post_attempt_observations":5,"provider_post_attempts":5,"reasoning_token_observations":5,"reconciliation_get_attempt_observations":5,"requested_max_output_token_observations":5,"requested_max_output_tokens":[64000],"total_output_tokens":186075,"total_reasoning_output_tokens":53683,"total_visible_output_tokens":132392,"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":64000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-5-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":1,"evaluated_cells":1,"first_pass_admitted":1,"first_pass_rate":1.0,"game_attempts":{"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}},"baseline":{"admitted_plugins":1,"evaluated_cells":1,"first_pass_admitted":1,"first_pass_rate":1.0,"game_attempts":{"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"headline_games_all":{"GB2-08":{"attempts":2,"playable":59.20587271140518,"score":59.20587271140518}},"headline_games_tracks":{"medium":{"GB2-08":{"attempts":1,"playable":83.04265097472776,"score":83.04265097472776}},"none":{"GB2-08":{"attempts":1,"playable":35.3690944480826,"score":35.3690944480826}}},"id":"stepfun/step-5-preview","is_recent_addition":false,"last_measured_at":"2026-10-13T23:00:32Z","match_totals_all":{"draws":277,"losses":266,"wins":429},"match_totals_tracks":{"medium":{"draws":2,"losses":84,"wins":400},"none":{"draws":275,"losses":182,"wins":29}},"model_slug":"stepfun-step-5-preview","overall":{"max":83.04265097472776,"mean":59.20587271140518,"min":35.3690944480826},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-08":{"draws":277,"losses":266,"wins":429}},"per_game_match_totals_tracks":{"medium":{"GB2-08":{"draws":2,"losses":84,"wins":400}},"none":{"GB2-08":{"draws":275,"losses":182,"wins":29}}},"per_game_raw_elo_tracks":{"medium":{"GB2-08":1951.6725841760901},"none":{"GB2-08":1271.4725775135794}},"per_game_tracks":{"medium":{"GB2-08":83.04265097472776},"none":{"GB2-08":35.3690944480826}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":83.04265097472776,"none":35.3690944480826},"reasoning_agg":{"medium":{"max":83.04265097472776,"mean":83.04265097472776,"min":83.04265097472776},"none":{"max":35.3690944480826,"mean":35.3690944480826,"min":35.3690944480826}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low"},"score_diagnostics":{"reasoning_variance":47.673556526645164}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-flash:1634fd786aeaa347","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02304638,"mean":0.0178225775,"median":0.01816367,"min":0.01029504,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.14258062000000002},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00414456,"mean":0.0029296749999999996,"median":0.00284053,"min":0.00188342,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"recorded_attempt_count":12,"run_count":8,"total":0.0234374}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02304638,"mean":0.0178225775,"median":0.01816367,"min":0.01029504,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.14258062},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00414456,"mean":0.0029296749999999996,"median":0.00284053,"min":0.00188342,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"recorded_attempt_count":12,"run_count":8,"total":0.023437400000000004}},"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02304638,"mean":0.01037612625,"median":0.0072198,"min":0.00188342,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":23},"recorded_attempt_count":23,"run_count":16,"total":0.16601802},"codegen_latency_ms":{"attempt_count":23,"max_ms":1374551,"mean_ms":491530.125,"min_ms":35032,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":11,"max_ms":1374551,"mean_ms":925316.625,"min_ms":428464,"run_count":8},"none":{"attempt_count":12,"max_ms":114099,"mean_ms":57743.625,"min_ms":35032,"run_count":8}},"codegen_output_tokens":{"attempt_count":23,"output_max":78655,"output_mean":31302.375,"output_min":3072,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":11,"output_max":78655,"output_mean":57997.125,"output_min":33074,"run_count":8},"none":{"attempt_count":12,"output_max":6869,"output_mean":4607.625,"output_min":3072,"run_count":8}},"display_name":"MiMo-V2.6-Flash","economics":{"medium":60.29833401817578,"none":46.28256278194392},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":23,"effective_max_output_tokens":[131072],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":23,"output_token_observations":23,"provider_post_attempt_observations":23,"provider_post_attempts":23,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":23,"requested_max_output_token_observations":23,"requested_max_output_tokens":[131072],"total_output_tokens":500838,"total_reasoning_output_tokens":411817,"total_visible_output_tokens":89021,"visible_token_observations":23},"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":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":60.89089977191358,"score":60.89089977191358},"GB2-02":{"attempts":2,"playable":54.43174273774806,"score":54.43174273774806},"GB2-03":{"attempts":2,"playable":52.74536532774458,"score":52.74536532774458},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":58.09410257188268,"score":29.04705128594134},"GB2-05":{"attempts":2,"playable":56.96970949744542,"score":56.96970949744542},"GB2-06":{"attempts":2,"playable":59.98024324736767,"score":59.98024324736767},"GB2-07":{"attempts":2,"playable":62.21068978396515,"score":62.21068978396515},"GB2-08":{"attempts":2,"playable":26.906604157381047,"score":26.906604157381047}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":53.67147815121972,"score":53.67147815121972},"GB2-02":{"attempts":1,"playable":66.9622376805891,"score":66.9622376805891},"GB2-03":{"attempts":1,"playable":64.3307679583894,"score":64.3307679583894},"GB2-04":{"attempts":1,"playable":58.09410257188268,"score":58.09410257188268},"GB2-05":{"attempts":1,"playable":60.52550831322555,"score":60.52550831322555},"GB2-06":{"attempts":1,"playable":67.05772451905908,"score":67.05772451905908},"GB2-07":{"attempts":1,"playable":83.73412154587642,"score":83.73412154587642},"GB2-08":{"attempts":1,"playable":28.01073140516425,"score":28.01073140516425}},"none":{"GB2-01":{"attempts":1,"playable":68.11032139260745,"score":68.11032139260745},"GB2-02":{"attempts":1,"playable":41.90124779490702,"score":41.90124779490702},"GB2-03":{"attempts":1,"playable":41.159962697099765,"score":41.159962697099765},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":53.413910681665286,"score":53.413910681665286},"GB2-06":{"attempts":1,"playable":52.90276197567626,"score":52.90276197567626},"GB2-07":{"attempts":1,"playable":40.687258022053875,"score":40.687258022053875},"GB2-08":{"attempts":1,"playable":25.80247690959784,"score":25.80247690959784}}},"id":"xiaomi/mimo-v2.6-flash","is_recent_addition":false,"last_measured_at":"2026-10-20T11:09:32Z","match_totals_all":{"draws":1399,"losses":2609,"wins":2932},"match_totals_tracks":{"medium":{"draws":545,"losses":1242,"wins":1907},"none":{"draws":854,"losses":1367,"wins":1025}},"model_slug":"xiaomi-mimo-v2-6-flash","overall":{"max":83.73412154587642,"mean":50.397788226188354,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":165,"losses":291,"wins":480},"GB2-02":{"draws":514,"losses":147,"wins":203},"GB2-03":{"draws":166,"losses":368,"wins":358},"GB2-04":{"draws":51,"losses":168,"wins":229},"GB2-05":{"draws":0,"losses":420,"wins":548},"GB2-06":{"draws":46,"losses":355,"wins":511},"GB2-07":{"draws":0,"losses":369,"wins":579},"GB2-08":{"draws":457,"losses":491,"wins":24}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":20,"losses":211,"wins":237},"GB2-02":{"draws":189,"losses":53,"wins":190},"GB2-03":{"draws":29,"losses":159,"wins":258},"GB2-04":{"draws":51,"losses":168,"wins":229},"GB2-05":{"draws":0,"losses":193,"wins":291},"GB2-06":{"draws":15,"losses":147,"wins":294},"GB2-07":{"draws":0,"losses":77,"wins":397},"GB2-08":{"draws":241,"losses":234,"wins":11}},"none":{"GB2-01":{"draws":145,"losses":80,"wins":243},"GB2-02":{"draws":325,"losses":94,"wins":13},"GB2-03":{"draws":137,"losses":209,"wins":100},"GB2-05":{"draws":0,"losses":227,"wins":257},"GB2-06":{"draws":31,"losses":208,"wins":217},"GB2-07":{"draws":0,"losses":292,"wins":182},"GB2-08":{"draws":216,"losses":257,"wins":13}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1517.7531444497333,"GB2-02":1615.755728723777,"GB2-03":1568.620467347929,"GB2-04":1541.9732392294977,"GB2-05":1587.2258943320603,"GB2-06":1733.2886100053177,"GB2-07":1981.5389457535985,"GB2-08":1195.10127641},"none":{"GB2-01":1664.474287474909,"GB2-02":1413.2425051809132,"GB2-03":1355.1332397057465,"GB2-05":1494.922572219597,"GB2-06":1499.9297802588017,"GB2-07":1334.5077088351943,"GB2-08":1170.9965668630737}},"per_game_tracks":{"medium":{"GB2-01":53.67147815121972,"GB2-02":66.9622376805891,"GB2-03":64.3307679583894,"GB2-04":58.09410257188268,"GB2-05":60.52550831322555,"GB2-06":67.05772451905908,"GB2-07":83.73412154587642,"GB2-08":28.01073140516425},"none":{"GB2-01":68.11032139260745,"GB2-02":41.90124779490702,"GB2-03":41.159962697099765,"GB2-05":53.413910681665286,"GB2-06":52.90276197567626,"GB2-07":40.687258022053875,"GB2-08":25.80247690959784}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":60.29833401817578,"none":40.497242434200935},"reasoning_agg":{"medium":{"max":83.73412154587642,"mean":60.29833401817578,"min":28.01073140516425},"none":{"max":68.11032139260745,"mean":40.497242434200935,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":19.801091583974845}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-flash:a78fcb9a5f009aff","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.0376887,"median":0.037827133,"min":0.02582591,"recorded_attempt_count":11,"run_count":8,"total":0.3015096},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.006158996,"mean":0.00343607875,"median":0.002791493,"min":0.0021123,"recorded_attempt_count":11,"run_count":8,"total":0.027488630000000003}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.0376887,"median":0.037827133,"min":0.02582591,"recorded_attempt_count":11,"run_count":8,"total":0.3015096},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.006158996,"mean":0.00343607875,"median":0.002791493,"min":0.0021123,"recorded_attempt_count":11,"run_count":8,"total":0.02748863}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":22},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.020562389374999997,"median":0.015992453,"min":0.0021123,"recorded_attempt_count":22,"run_count":16,"total":0.32899822999999995},"codegen_latency_ms":{"attempt_count":22,"max_ms":1377805,"mean_ms":526774.25,"min_ms":30630,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":11,"max_ms":1377805,"mean_ms":998592.5,"min_ms":680734,"run_count":8},"none":{"attempt_count":11,"max_ms":104368,"mean_ms":54956.0,"min_ms":30630,"run_count":8}},"codegen_output_tokens":{"attempt_count":22,"output_max":125053,"output_mean":40030.0625,"output_min":2070,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":11,"output_max":125053,"output_mean":76276.375,"output_min":52513,"run_count":8},"none":{"attempt_count":11,"output_max":7265,"output_mean":3783.75,"output_min":2070,"run_count":8}},"display_name":"Qwen3.8 Flash","economics":{"medium":61.03030749481585,"none":34.37701796814959},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":22,"finish_reasons":["stop"],"indexed_attempts":22,"output_token_observations":22,"provider_post_attempt_observations":22,"provider_post_attempts":22,"reasoning_token_observations":22,"reconciliation_get_attempt_observations":22,"reconciliation_get_attempts":100,"total_output_tokens":640481,"total_reasoning_output_tokens":544948,"total_visible_output_tokens":95533,"visible_token_observations":22},"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/qwen3.8-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":42.58485645137971,"score":42.58485645137971},"GB2-02":{"attempts":2,"playable":50.5160682821083,"score":50.5160682821083},"GB2-03":{"attempts":2,"playable":55.27579659344035,"score":55.27579659344035},"GB2-04":{"attempts":2,"playable":44.215424131487765,"score":44.215424131487765},"GB2-05":{"attempts":2,"playable":44.36146731885103,"score":44.36146731885103},"GB2-06":{"attempts":2,"playable":67.08018972779843,"score":67.08018972779843},"GB2-07":{"attempts":2,"playable":42.440102299224286,"score":42.440102299224286},"GB2-08":{"attempts":2,"playable":35.15539704757193,"score":35.15539704757193}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":50.71157253248973,"score":50.71157253248973},"GB2-02":{"attempts":1,"playable":57.96645751879183,"score":57.96645751879183},"GB2-03":{"attempts":1,"playable":65.72474832028765,"score":65.72474832028765},"GB2-04":{"attempts":1,"playable":47.70344352130062,"score":47.70344352130062},"GB2-05":{"attempts":1,"playable":71.77056802561738,"score":71.77056802561738},"GB2-06":{"attempts":1,"playable":79.39495877820187,"score":79.39495877820187},"GB2-07":{"attempts":1,"playable":74.77370382568726,"score":74.77370382568726},"GB2-08":{"attempts":1,"playable":40.197007436150464,"score":40.197007436150464}},"none":{"GB2-01":{"attempts":1,"playable":34.458140370269675,"score":34.458140370269675},"GB2-02":{"attempts":1,"playable":43.06567904542477,"score":43.06567904542477},"GB2-03":{"attempts":1,"playable":44.82684486659304,"score":44.82684486659304},"GB2-04":{"attempts":1,"playable":40.7274047416749,"score":40.7274047416749},"GB2-05":{"attempts":1,"playable":16.952366612084667,"score":16.952366612084667},"GB2-06":{"attempts":1,"playable":54.765420677394985,"score":54.765420677394985},"GB2-07":{"attempts":1,"playable":10.106500772761303,"score":10.106500772761303},"GB2-08":{"attempts":1,"playable":30.1137866589934,"score":30.1137866589934}}},"id":"qwen/qwen3.8-flash","is_recent_addition":false,"last_measured_at":"2026-10-20T11:23:11Z","match_totals_all":{"draws":2221,"losses":2861,"wins":2306},"match_totals_tracks":{"medium":{"draws":1096,"losses":933,"wins":1665},"none":{"draws":1125,"losses":1928,"wins":641}},"model_slug":"qwen-qwen3-8-flash","overall":{"max":79.39495877820187,"mean":47.70366273148272,"min":10.106500772761303},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":275,"losses":409,"wins":252},"GB2-02":{"draws":585,"losses":146,"wins":133},"GB2-03":{"draws":225,"losses":316,"wins":351},"GB2-04":{"draws":564,"losses":229,"wins":103},"GB2-05":{"draws":0,"losses":542,"wins":426},"GB2-06":{"draws":56,"losses":281,"wins":575},"GB2-07":{"draws":0,"losses":555,"wins":393},"GB2-08":{"draws":516,"losses":383,"wins":73}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":170,"losses":150,"wins":148},"GB2-02":{"draws":246,"losses":64,"wins":122},"GB2-03":{"draws":106,"losses":114,"wins":226},"GB2-04":{"draws":260,"losses":110,"wins":78},"GB2-05":{"draws":0,"losses":139,"wins":345},"GB2-06":{"draws":47,"losses":71,"wins":338},"GB2-07":{"draws":0,"losses":122,"wins":352},"GB2-08":{"draws":267,"losses":163,"wins":56}},"none":{"GB2-01":{"draws":105,"losses":259,"wins":104},"GB2-02":{"draws":339,"losses":82,"wins":11},"GB2-03":{"draws":119,"losses":202,"wins":125},"GB2-04":{"draws":304,"losses":119,"wins":25},"GB2-05":{"draws":0,"losses":403,"wins":81},"GB2-06":{"draws":9,"losses":210,"wins":237},"GB2-07":{"draws":0,"losses":433,"wins":41},"GB2-08":{"draws":249,"losses":220,"wins":17}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1489.3797806622172,"GB2-02":1538.5430180252633,"GB2-03":1583.4922202444413,"GB2-04":1460.2724808083256,"GB2-05":1758.9932545159652,"GB2-06":1960.0488772473286,"GB2-07":1797.5251297011714,"GB2-08":1320.373397131747},"none":{"GB2-01":1331.5605529298905,"GB2-02":1422.2736922871886,"GB2-03":1387.1084905270109,"GB2-04":1406.177624000989,"GB2-05":965.3417274344575,"GB2-06":1529.2504560252473,"GB2-07":838.712893237883,"GB2-08":1217.4136691648166}},"per_game_tracks":{"medium":{"GB2-01":50.71157253248973,"GB2-02":57.96645751879183,"GB2-03":65.72474832028765,"GB2-04":47.70344352130062,"GB2-05":71.77056802561738,"GB2-06":79.39495877820187,"GB2-07":74.77370382568726,"GB2-08":40.197007436150464},"none":{"GB2-01":34.458140370269675,"GB2-02":43.06567904542477,"GB2-03":44.82684486659304,"GB2-04":40.7274047416749,"GB2-05":16.952366612084667,"GB2-06":54.765420677394985,"GB2-07":10.106500772761303,"GB2-08":30.1137866589934}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":61.03030749481585,"none":34.37701796814959},"reasoning_agg":{"medium":{"max":79.39495877820187,"mean":61.03030749481585,"min":40.197007436150464},"none":{"max":54.765420677394985,"mean":34.37701796814959,"min":10.106500772761303}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":26.653289526666263}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-large-4-0:8588f7e459b09704","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.33846634,"mean":0.191117675,"median":0.19018014,"min":0.07351397,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.5289414},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03127107,"mean":0.02115604125,"median":0.02234344,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.16924833}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03127107,"mean":0.02115604125,"median":0.02234344,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.16924833},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.33846634,"mean":0.191117675,"median":0.19018014,"min":0.07351397,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.5289414}},"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.33846634,"mean":0.10613685812499998,"median":0.05239252,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":23},"recorded_attempt_count":23,"run_count":16,"total":1.69818973},"codegen_latency_ms":{"attempt_count":23,"max_ms":2372746,"mean_ms":755436.1875,"min_ms":27078,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":2372746,"mean_ms":1420193.375,"min_ms":412995,"run_count":8},"none":{"attempt_count":13,"max_ms":165291,"mean_ms":90679.0,"min_ms":27078,"run_count":8}},"codegen_output_tokens":{"attempt_count":23,"output_max":159550,"output_mean":46908.8125,"output_min":3069,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":159550,"output_mean":88125.0,"output_min":32501,"run_count":8},"none":{"attempt_count":13,"output_max":9287,"output_mean":5692.625,"output_min":3069,"run_count":8}},"display_name":"Mistral Large 4","economics":{"highest":57.92224732549012,"none":40.86632727247737},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":23,"effective_max_output_tokens":[262144],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":23,"output_token_observations":23,"provider_post_attempt_observations":23,"provider_post_attempts":25,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":23,"requested_max_output_token_observations":23,"requested_max_output_tokens":[262144],"total_output_tokens":750541,"total_reasoning_output_tokens":655796,"total_visible_output_tokens":94745,"visible_token_observations":23},"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":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-large-4-0","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":["GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":47.07190603449915,"score":47.07190603449915},"GB2-02":{"attempts":2,"playable":54.27916101583694,"score":54.27916101583694},"GB2-03":{"attempts":2,"playable":37.34449090738207,"score":37.34449090738207},"GB2-04":{"attempts":2,"playable":52.15834123756132,"score":52.15834123756132},"GB2-05":{"attempts":2,"playable":56.86150210524681,"score":56.86150210524681},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":80.33207459094119,"score":40.166037295470595},"GB2-07":{"attempts":2,"playable":44.809990476697664,"score":44.809990476697664},"GB2-08":{"attempts":2,"playable":42.029705682936786,"score":42.029705682936786}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":34.351345454290644,"score":34.351345454290644},"GB2-02":{"attempts":1,"playable":65.37626702822097,"score":65.37626702822097},"GB2-03":{"attempts":1,"playable":43.91349499201411,"score":43.91349499201411},"GB2-04":{"attempts":1,"playable":65.73382942060854,"score":65.73382942060854},"GB2-05":{"attempts":1,"playable":50.065055159003954,"score":50.065055159003954},"GB2-06":{"attempts":1,"playable":80.33207459094119,"score":80.33207459094119},"GB2-07":{"attempts":1,"playable":79.74350802911847,"score":79.74350802911847},"GB2-08":{"attempts":1,"playable":43.86240392972311,"score":43.86240392972311}},"none":{"GB2-01":{"attempts":1,"playable":59.79246661470766,"score":59.79246661470766},"GB2-02":{"attempts":1,"playable":43.182055003452916,"score":43.182055003452916},"GB2-03":{"attempts":1,"playable":30.77548682275002,"score":30.77548682275002},"GB2-04":{"attempts":1,"playable":38.58285305451409,"score":38.58285305451409},"GB2-05":{"attempts":1,"playable":63.65794905148966,"score":63.65794905148966},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":9.876472924276849,"score":9.876472924276849},"GB2-08":{"attempts":1,"playable":40.197007436150464,"score":40.197007436150464}}},"id":"mistralai/mistral-large-4-0","is_recent_addition":false,"last_measured_at":"2026-10-15T06:55:22Z","match_totals_all":{"draws":2054,"losses":2527,"wins":2351},"match_totals_tracks":{"highest":{"draws":918,"losses":1141,"wins":1635},"none":{"draws":1136,"losses":1386,"wins":716}},"model_slug":"mistralai-mistral-large-4-0","overall":{"max":80.33207459094119,"mean":46.84014184445391,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-01":34.351345454290644,"GB2-02":65.37626702822097,"GB2-03":43.91349499201411,"GB2-04":65.73382942060854,"GB2-05":50.065055159003954,"GB2-06":80.33207459094119,"GB2-07":79.74350802911847,"GB2-08":43.86240392972311},"per_game_match_totals_all":{"GB2-01":{"draws":120,"losses":444,"wins":372},"GB2-02":{"draws":589,"losses":111,"wins":164},"GB2-03":{"draws":319,"losses":428,"wins":145},"GB2-04":{"draws":477,"losses":201,"wins":218},"GB2-05":{"draws":0,"losses":421,"wins":547},"GB2-06":{"draws":34,"losses":73,"wins":349},"GB2-07":{"draws":0,"losses":531,"wins":417},"GB2-08":{"draws":515,"losses":318,"wins":139}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":22,"losses":301,"wins":145},"GB2-02":{"draws":233,"losses":38,"wins":161},"GB2-03":{"draws":167,"losses":182,"wins":97},"GB2-04":{"draws":206,"losses":56,"wins":186},"GB2-05":{"draws":0,"losses":243,"wins":241},"GB2-06":{"draws":34,"losses":73,"wins":349},"GB2-07":{"draws":0,"losses":97,"wins":377},"GB2-08":{"draws":256,"losses":151,"wins":79}},"none":{"GB2-01":{"draws":98,"losses":143,"wins":227},"GB2-02":{"draws":356,"losses":73,"wins":3},"GB2-03":{"draws":152,"losses":246,"wins":48},"GB2-04":{"draws":271,"losses":145,"wins":32},"GB2-05":{"draws":0,"losses":178,"wins":306},"GB2-07":{"draws":0,"losses":434,"wins":40},"GB2-08":{"draws":259,"losses":167,"wins":60}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1330.470472776861,"GB2-02":1601.3830157885254,"GB2-03":1379.150790344488,"GB2-04":1606.8774497131703,"GB2-05":1453.0316215056675,"GB2-06":1978.479240597495,"GB2-07":1890.56611416368,"GB2-08":1357.8779785529446},"none":{"GB2-01":1577.6589601058608,"GB2-02":1423.174296829968,"GB2-03":1261.457105407046,"GB2-04":1389.251716666378,"GB2-05":1630.715390603076,"GB2-07":832.4646862864635,"GB2-08":1320.373397131747}},"per_game_tracks":{"highest":{"GB2-01":34.351345454290644,"GB2-02":65.37626702822097,"GB2-03":43.91349499201411,"GB2-04":65.73382942060854,"GB2-05":50.065055159003954,"GB2-06":80.33207459094119,"GB2-07":79.74350802911847,"GB2-08":43.86240392972311},"none":{"GB2-01":59.79246661470766,"GB2-02":43.182055003452916,"GB2-03":30.77548682275002,"GB2-04":38.58285305451409,"GB2-05":63.65794905148966,"GB2-07":9.876472924276849,"GB2-08":40.197007436150464}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":57.92224732549012,"none":35.7580363634177},"reasoning_agg":{"highest":{"max":80.33207459094119,"mean":57.92224732549012,"min":34.351345454290644},"none":{"max":63.65794905148966,"mean":35.7580363634177,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":22.164210962072417}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1:8e6f19a50c9cfbcd","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":0.457564}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":0.4575640000000001}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":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":42.14480959285734},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":61.900304527177305,"score":61.900304527177305},"GB2-02":{"attempts":1,"playable":43.06567904542477,"score":43.06567904542477},"GB2-03":{"attempts":1,"playable":38.8500226138914,"score":38.8500226138914},"GB2-04":{"attempts":1,"playable":38.35693984005379,"score":38.35693984005379},"GB2-05":{"attempts":1,"playable":14.119198554741105,"score":14.119198554741105},"GB2-06":{"attempts":1,"playable":50.19774654123482,"score":50.19774654123482},"GB2-07":{"attempts":1,"playable":48.061897239178755,"score":48.061897239178755},"GB2-08":{"attempts":1,"playable":42.60668838115678,"score":42.60668838115678}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":61.900304527177305,"score":61.900304527177305},"GB2-02":{"attempts":1,"playable":43.06567904542477,"score":43.06567904542477},"GB2-03":{"attempts":1,"playable":38.8500226138914,"score":38.8500226138914},"GB2-04":{"attempts":1,"playable":38.35693984005379,"score":38.35693984005379},"GB2-05":{"attempts":1,"playable":14.119198554741105,"score":14.119198554741105},"GB2-06":{"attempts":1,"playable":50.19774654123482,"score":50.19774654123482},"GB2-07":{"attempts":1,"playable":48.061897239178755,"score":48.061897239178755},"GB2-08":{"attempts":1,"playable":42.60668838115678,"score":42.60668838115678}}},"id":"gpt-4.1","is_recent_addition":false,"last_measured_at":"2026-10-20T11:11:08Z","match_totals_all":{"draws":1068,"losses":1663,"wins":963},"match_totals_tracks":{"none":{"draws":1068,"losses":1663,"wins":963}},"model_slug":"gpt-4-1","overall":{"max":61.900304527177305,"mean":42.14480959285734,"min":14.119198554741105},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":32,"losses":166,"wins":270},"GB2-02":{"draws":355,"losses":74,"wins":3},"GB2-03":{"draws":109,"losses":233,"wins":104},"GB2-04":{"draws":287,"losses":138,"wins":23},"GB2-05":{"draws":0,"losses":417,"wins":67},"GB2-06":{"draws":19,"losses":227,"wins":210},"GB2-07":{"draws":0,"losses":256,"wins":218},"GB2-08":{"draws":266,"losses":152,"wins":68}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":32,"losses":166,"wins":270},"GB2-02":{"draws":355,"losses":74,"wins":3},"GB2-03":{"draws":109,"losses":233,"wins":104},"GB2-04":{"draws":287,"losses":138,"wins":23},"GB2-05":{"draws":0,"losses":417,"wins":67},"GB2-06":{"draws":19,"losses":227,"wins":210},"GB2-07":{"draws":0,"losses":256,"wins":218},"GB2-08":{"draws":266,"losses":152,"wins":68}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1598.909794871437,"GB2-02":1422.2736922871886,"GB2-03":1334.8603199555419,"GB2-04":1387.4545700056453,"GB2-05":906.3046500855279,"GB2-06":1457.8701244516071,"GB2-07":1426.2552658238576,"GB2-08":1344.9506438981116}},"per_game_tracks":{"none":{"GB2-01":61.900304527177305,"GB2-02":43.06567904542477,"GB2-03":38.8500226138914,"GB2-04":38.35693984005379,"GB2-05":14.119198554741105,"GB2-06":50.19774654123482,"GB2-07":48.061897239178755,"GB2-08":42.60668838115678}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":42.14480959285734},"reasoning_agg":{"none":{"max":61.900304527177305,"mean":42.14480959285734,"min":14.119198554741105}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"reasoning_settings":{}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k2-7-code:ca5706e1289410bb","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.283003154}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.2830031539999998}},"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"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":47.64892080726681},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":7,"failed_game_aliases":["GB2-06"],"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"infra_failures_excluded":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-03"],"infra_failures_excluded":1,"model_code_failure_rate":0.14285714285714285,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":6,"repaired_rate":0.8571428571428571}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":39.00302434738195,"score":39.00302434738195},"GB2-02":{"attempts":1,"playable":42.600052564014696,"score":42.600052564014696},"GB2-04":{"attempts":1,"playable":38.808734192147654,"score":38.808734192147654},"GB2-05":{"attempts":1,"playable":52.99532212271336,"score":52.99532212271336},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":44.18661709046279,"score":44.18661709046279},"GB2-08":{"attempts":1,"playable":68.29977452688043,"score":68.29977452688043}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":39.00302434738195,"score":39.00302434738195},"GB2-02":{"attempts":1,"playable":42.600052564014696,"score":42.600052564014696},"GB2-04":{"attempts":1,"playable":38.808734192147654,"score":38.808734192147654},"GB2-05":{"attempts":1,"playable":52.99532212271336,"score":52.99532212271336},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":44.18661709046279,"score":44.18661709046279},"GB2-08":{"attempts":1,"playable":68.29977452688043,"score":68.29977452688043}}},"id":"moonshotai/kimi-k2.7-code","is_recent_addition":false,"last_measured_at":"2026-10-20T07:35:00Z","match_totals_all":{"draws":651,"losses":1161,"wins":979},"match_totals_tracks":{"medium":{"draws":651,"losses":1161,"wins":979}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":68.29977452688043,"mean":40.84193212051441,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":7,"losses":286,"wins":174},"GB2-02":{"draws":327,"losses":90,"wins":15},"GB2-04":{"draws":267,"losses":146,"wins":35},"GB2-05":{"draws":0,"losses":229,"wins":255},"GB2-07":{"draws":0,"losses":275,"wins":199},"GB2-08":{"draws":50,"losses":135,"wins":301}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":7,"losses":286,"wins":174},"GB2-02":{"draws":327,"losses":90,"wins":15},"GB2-04":{"draws":267,"losses":146,"wins":35},"GB2-05":{"draws":0,"losses":229,"wins":255},"GB2-07":{"draws":0,"losses":275,"wins":199},"GB2-08":{"draws":50,"losses":135,"wins":301}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1376.962863649612,"GB2-02":1418.666919509663,"GB2-04":1391.0456619731683,"GB2-05":1489.6571707628418,"GB2-07":1378.1171529833719,"GB2-08":1663.3282903028871}},"per_game_tracks":{"medium":{"GB2-01":39.00302434738195,"GB2-02":42.600052564014696,"GB2-04":38.808734192147654,"GB2-05":52.99532212271336,"GB2-07":44.18661709046279,"GB2-08":68.29977452688043}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":40.84193212051441},"reasoning_agg":{"medium":{"max":68.29977452688043,"mean":40.84193212051441,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-mini:2b64bf35e39106cc","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":1.503294825,"median":1.503294825,"min":1.503294825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":3.00658965},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.325659,"mean":0.25189603125,"median":0.25775625,"min":0.169101,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":2.0151682500000003},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.1470525}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.325659,"mean":0.25189603125,"median":0.25775625,"min":0.169101,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":2.01516825},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.1470525},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":1.503294825,"median":1.503294825,"min":1.503294825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":3.00658965}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":17,"cost_basis_counts":{"estimated":2,"local_standard_estimate":22},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":0.2156185632352941,"median":0.169101,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":22},"recorded_attempt_count":2,"run_count":18,"token_priced_attempt_count":22,"total":5.168810400000001},"codegen_latency_ms":{"attempt_count":22,"max_ms":1819696,"mean_ms":244013.16666666666,"min_ms":11548,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":1819696,"mean_ms":1344520.5,"min_ms":869345,"run_count":2},"medium":{"attempt_count":9,"max_ms":308347,"mean_ms":195019.75,"min_ms":115259,"run_count":8},"none":{"attempt_count":10,"max_ms":30363,"mean_ms":17879.75,"min_ms":11548,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":383888,"output_mean":60889.444444444445,"output_min":1571,"run_count":18},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":5,"output_max":383888,"output_mean":319916.0,"output_min":255944,"run_count":2},"medium":{"attempt_count":9,"output_max":69661,"output_mean":54514.75,"output_min":36373,"run_count":8},"none":{"attempt_count":10,"output_max":4247,"output_mean":2507.5,"output_min":1571,"run_count":8}},"display_name":"GPT-5.4 Mini","economics":{"medium":48.655870326703095,"none":30.619804750390234},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":21,"finish_reasons":["incomplete","stop"],"indexed_attempts":24,"output_token_observations":24,"reasoning_token_observations":2,"total_output_tokens":1096010,"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":52.16969369527462,"score":52.16969369527462},"GB2-02":{"attempts":2,"playable":41.84298092226713,"score":41.84298092226713},"GB2-03":{"attempts":2,"playable":45.39647012872943,"score":45.39647012872943},"GB2-04":{"attempts":2,"playable":43.600674173210436,"score":43.600674173210436},"GB2-05":{"attempts":2,"playable":29.009259598778907,"score":29.009259598778907},"GB2-06":{"attempts":2,"playable":39.72651230769548,"score":39.72651230769548},"GB2-07":{"attempts":2,"playable":26.636061696874755,"score":26.636061696874755},"GB2-08":{"attempts":2,"playable":38.721047785542545,"score":38.721047785542545}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":70.84272251456024,"score":70.84272251456024},"GB2-02":{"attempts":1,"playable":41.66821636429997,"score":41.66821636429997},"GB2-03":{"attempts":1,"playable":45.624171627892096,"score":45.624171627892096},"GB2-04":{"attempts":1,"playable":44.21981030690826,"score":44.21981030690826},"GB2-05":{"attempts":1,"playable":46.92603049739365,"score":46.92603049739365},"GB2-06":{"attempts":1,"playable":48.83787747643782,"score":48.83787747643782},"GB2-07":{"attempts":1,"playable":46.63831525158885,"score":46.63831525158885},"GB2-08":{"attempts":1,"playable":44.4898185745439,"score":44.4898185745439}},"none":{"GB2-01":{"attempts":1,"playable":33.496664875989,"score":33.496664875989},"GB2-02":{"attempts":1,"playable":42.01774548023428,"score":42.01774548023428},"GB2-03":{"attempts":1,"playable":45.16876862956678,"score":45.16876862956678},"GB2-04":{"attempts":1,"playable":42.98153803951262,"score":42.98153803951262},"GB2-05":{"attempts":1,"playable":11.092488700164168,"score":11.092488700164168},"GB2-06":{"attempts":1,"playable":30.615147138953137,"score":30.615147138953137},"GB2-07":{"attempts":1,"playable":6.633808142160662,"score":6.633808142160662},"GB2-08":{"attempts":1,"playable":32.952276996541194,"score":32.952276996541194}}},"id":"gpt-5.4-mini","is_recent_addition":false,"last_measured_at":"2026-10-20T11:19:56Z","match_totals_all":{"draws":2387,"losses":3388,"wins":1613},"match_totals_tracks":{"medium":{"draws":999,"losses":1451,"wins":1244},"none":{"draws":1388,"losses":1937,"wins":369}},"model_slug":"gpt-5-4-mini","overall":{"max":70.84272251456024,"mean":39.63783753854666,"min":6.633808142160662},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":175,"losses":368,"wins":393},"GB2-02":{"draws":687,"losses":170,"wins":7},"GB2-03":{"draws":498,"losses":269,"wins":125},"GB2-04":{"draws":553,"losses":240,"wins":103},"GB2-05":{"draws":0,"losses":690,"wins":278},"GB2-06":{"draws":48,"losses":546,"wins":318},"GB2-07":{"draws":0,"losses":711,"wins":237},"GB2-08":{"draws":426,"losses":394,"wins":152}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":29,"losses":125,"wins":314},"GB2-02":{"draws":337,"losses":89,"wins":6},"GB2-03":{"draws":154,"losses":181,"wins":111},"GB2-04":{"draws":291,"losses":110,"wins":47},"GB2-05":{"draws":0,"losses":258,"wins":226},"GB2-06":{"draws":34,"losses":226,"wins":196},"GB2-07":{"draws":0,"losses":263,"wins":211},"GB2-08":{"draws":154,"losses":199,"wins":133}},"none":{"GB2-01":{"draws":146,"losses":243,"wins":79},"GB2-02":{"draws":350,"losses":81,"wins":1},"GB2-03":{"draws":344,"losses":88,"wins":14},"GB2-04":{"draws":262,"losses":130,"wins":56},"GB2-05":{"draws":0,"losses":432,"wins":52},"GB2-06":{"draws":14,"losses":320,"wins":122},"GB2-07":{"draws":0,"losses":448,"wins":26},"GB2-08":{"draws":272,"losses":195,"wins":19}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1695.2412478444937,"GB2-02":1411.430214719613,"GB2-03":1394.0595971564885,"GB2-04":1433.3647011104738,"GB2-05":1413.9418564331927,"GB2-06":1436.9189208292905,"GB2-07":1408.5604382880363,"GB2-08":1364.377520986395},"none":{"GB2-01":1321.7003445158675,"GB2-02":1414.1478441779848,"GB2-03":1390.0886468715853,"GB2-04":1423.7641064794311,"GB2-05":835.124824553973,"GB2-06":1161.8130849889696,"GB2-07":729.9355325807611,"GB2-08":1246.8276685590758}},"per_game_tracks":{"medium":{"GB2-01":70.84272251456024,"GB2-02":41.66821636429997,"GB2-03":45.624171627892096,"GB2-04":44.21981030690826,"GB2-05":46.92603049739365,"GB2-06":48.83787747643782,"GB2-07":46.63831525158885,"GB2-08":44.4898185745439},"none":{"GB2-01":33.496664875989,"GB2-02":42.01774548023428,"GB2-03":45.16876862956678,"GB2-04":42.98153803951262,"GB2-05":11.092488700164168,"GB2-06":30.615147138953137,"GB2-07":6.633808142160662,"GB2-08":32.952276996541194}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":48.655870326703095,"none":30.619804750390234},"reasoning_agg":{"medium":{"max":70.84272251456024,"mean":48.655870326703095,"min":41.66821636429997},"none":{"max":45.16876862956678,"mean":30.619804750390234,"min":6.633808142160662}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":18.03606557631286}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5-pro:023fe3dc3324481d","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","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":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.0317000854,"median":0.0104556789,"min":0.0057139812,"recorded_attempt_count":11,"run_count":8,"total":0.2536006832}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.2996388,"mean":0.13471628689999998,"median":0.1144847257,"min":0.027613287599999998,"recorded_attempt_count":17,"run_count":8,"total":1.0777302951999999},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.0317000854,"median":0.0104556789,"min":0.0057139812,"recorded_attempt_count":11,"run_count":8,"total":0.2536006832}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.2996388,"mean":0.08320818615,"median":0.048126608099999996,"min":0.0057139812,"recorded_attempt_count":28,"run_count":16,"total":1.3313309784},"codegen_latency_ms":{"attempt_count":28,"max_ms":2144825,"mean_ms":691475.625,"min_ms":43161,"run_count":16},"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":11,"max_ms":886851,"mean_ms":223216.625,"min_ms":43161,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":131072,"output_mean":41065.3125,"output_min":2846,"run_count":16},"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":11,"output_max":42691,"output_mean":10871.125,"output_min":2846,"run_count":8}},"display_name":"MiMo-V2.5-Pro","economics":{"medium":46.8502128288467,"none":35.147342073506074},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["error","length","stop"],"indexed_attempts":28,"output_token_observations":28,"total_output_tokens":657045},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":6,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"infra_failures_excluded":1},"GB2-03":{"infra_failures_excluded":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-02","GB2-03"],"infra_failures_excluded":2,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":6,"repaired_rate":1.0},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":53.40233089445066,"score":53.40233089445066},"GB2-02":{"attempts":1,"playable":39.10175389831983,"score":39.10175389831983},"GB2-03":{"attempts":1,"playable":34.54032242491455,"score":34.54032242491455},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":48.3766217169059,"score":24.18831085845295},"GB2-05":{"attempts":2,"playable":22.045869327781602,"score":22.045869327781602},"GB2-06":{"attempts":2,"playable":52.703302351189215,"score":52.703302351189215},"GB2-07":{"attempts":2,"playable":45.50094671985134,"score":45.50094671985134},"GB2-08":{"attempts":2,"playable":28.904537430468388,"score":28.904537430468388}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":70.21243005229606,"score":70.21243005229606},"GB2-04":{"attempts":1,"playable":48.3766217169059,"score":48.3766217169059},"GB2-05":{"attempts":1,"playable":25.109452972119524,"score":25.109452972119524},"GB2-06":{"attempts":1,"playable":67.46607762949442,"score":67.46607762949442},"GB2-07":{"attempts":1,"playable":41.92596319710005,"score":41.92596319710005},"GB2-08":{"attempts":1,"playable":28.01073140516425,"score":28.01073140516425}},"none":{"GB2-01":{"attempts":1,"playable":36.592231736605264,"score":36.592231736605264},"GB2-02":{"attempts":1,"playable":39.10175389831983,"score":39.10175389831983},"GB2-03":{"attempts":1,"playable":34.54032242491455,"score":34.54032242491455},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":18.982285683443685,"score":18.982285683443685},"GB2-06":{"attempts":1,"playable":37.94052707288401,"score":37.94052707288401},"GB2-07":{"attempts":1,"playable":49.07593024260263,"score":49.07593024260263},"GB2-08":{"attempts":1,"playable":29.798343455772525,"score":29.798343455772525}}},"id":"xiaomi/mimo-v2.5-pro","is_recent_addition":false,"last_measured_at":"2026-10-20T11:30:44Z","match_totals_all":{"draws":1395,"losses":2998,"wins":1669},"match_totals_tracks":{"medium":{"draws":551,"losses":1260,"wins":1005},"none":{"draws":844,"losses":1738,"wins":664}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":70.21243005229606,"mean":38.802068571582254,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":176,"losses":356,"wins":404},"GB2-02":{"draws":291,"losses":123,"wins":18},"GB2-03":{"draws":168,"losses":222,"wins":56},"GB2-04":{"draws":224,"losses":125,"wins":99},"GB2-05":{"draws":0,"losses":756,"wins":212},"GB2-06":{"draws":19,"losses":437,"wins":456},"GB2-07":{"draws":0,"losses":537,"wins":411},"GB2-08":{"draws":517,"losses":442,"wins":13}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":57,"losses":114,"wins":297},"GB2-04":{"draws":224,"losses":125,"wins":99},"GB2-05":{"draws":0,"losses":363,"wins":121},"GB2-06":{"draws":13,"losses":146,"wins":297},"GB2-07":{"draws":0,"losses":286,"wins":188},"GB2-08":{"draws":257,"losses":226,"wins":3}},"none":{"GB2-01":{"draws":119,"losses":242,"wins":107},"GB2-02":{"draws":291,"losses":123,"wins":18},"GB2-03":{"draws":168,"losses":222,"wins":56},"GB2-05":{"draws":0,"losses":393,"wins":91},"GB2-06":{"draws":6,"losses":291,"wins":159},"GB2-07":{"draws":0,"losses":251,"wins":223},"GB2-08":{"draws":260,"losses":216,"wins":10}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1688.0143773913283,"GB2-04":1465.47109030541,"GB2-05":1111.409991278871,"GB2-06":1740.4295767711312,"GB2-07":1349.9858874937804,"GB2-08":1195.10127641},"none":{"GB2-01":1353.1012276799195,"GB2-02":1391.3279468860167,"GB2-03":1296.3499563595876,"GB2-05":1004.4914879976818,"GB2-06":1271.7964567548352,"GB2-07":1438.8843736692106,"GB2-08":1214.1000119620403}},"per_game_tracks":{"medium":{"GB2-01":70.21243005229606,"GB2-04":48.3766217169059,"GB2-05":25.109452972119524,"GB2-06":67.46607762949442,"GB2-07":41.92596319710005,"GB2-08":28.01073140516425},"none":{"GB2-01":36.592231736605264,"GB2-02":39.10175389831983,"GB2-03":34.54032242491455,"GB2-05":18.982285683443685,"GB2-06":37.94052707288401,"GB2-07":49.07593024260263,"GB2-08":29.798343455772525}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":46.8502128288467,"none":30.75392431431781},"reasoning_agg":{"medium":{"max":70.21243005229606,"mean":46.8502128288467,"min":25.109452972119524},"none":{"max":49.07593024260263,"mean":30.75392431431781,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":16.09628851452889}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-max:7528e8434c2eda2e","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"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":0.7288237499999999},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"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":0.18239875}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"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},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"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":0.18239875}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"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":0.9112225},"codegen_latency_ms":{"attempt_count":24,"max_ms":500731,"mean_ms":212687.25,"min_ms":38716,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":500731,"mean_ms":358367.875,"min_ms":131800,"run_count":8},"none":{"attempt_count":9,"max_ms":115558,"mean_ms":67006.625,"min_ms":38716,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27099,"output_mean":11144.8125,"output_min":1575,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":27099,"output_mean":19189.625,"output_min":6698,"run_count":8},"none":{"attempt_count":9,"output_max":5506,"output_mean":3100.0,"output_min":1575,"run_count":8}},"display_name":"Qwen3.7 Max","economics":{"medium":45.201460057105955,"none":40.9242817803541},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":42.42926888442078,"score":42.42926888442078},"GB2-02":{"attempts":2,"playable":44.983830452234805,"score":44.983830452234805},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":29.591922824386945,"score":14.795961412193472},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":44.10728525638753,"score":22.053642628193764},"GB2-05":{"attempts":2,"playable":38.04898627406618,"score":38.04898627406618},"GB2-06":{"attempts":2,"playable":37.92508699028608,"score":37.92508699028608},"GB2-07":{"attempts":2,"playable":68.82930211443026,"score":68.82930211443026},"GB2-08":{"attempts":2,"playable":32.37401767528484,"score":32.37401767528484}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":18.536263273309995,"score":18.536263273309995},"GB2-02":{"attempts":1,"playable":43.99634030996448,"score":43.99634030996448},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":44.10728525638753,"score":44.10728525638753},"GB2-05":{"attempts":1,"playable":39.82044082430902,"score":39.82044082430902},"GB2-06":{"attempts":1,"playable":59.70127562105285,"score":59.70127562105285},"GB2-07":{"attempts":1,"playable":76.56064319545096,"score":76.56064319545096},"GB2-08":{"attempts":1,"playable":33.6879719192668,"score":33.6879719192668}},"none":{"GB2-01":{"attempts":1,"playable":66.32227449553156,"score":66.32227449553156},"GB2-02":{"attempts":1,"playable":45.97132059450513,"score":45.97132059450513},"GB2-03":{"attempts":1,"playable":29.591922824386945,"score":29.591922824386945},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":36.277531723823344,"score":36.277531723823344},"GB2-06":{"attempts":1,"playable":16.14889835951932,"score":16.14889835951932},"GB2-07":{"attempts":1,"playable":61.09796103340956,"score":61.09796103340956},"GB2-08":{"attempts":1,"playable":31.060063431302876,"score":31.060063431302876}}},"id":"qwen/qwen3.7-max","is_recent_addition":false,"last_measured_at":"2026-10-20T11:17:46Z","match_totals_all":{"draws":1855,"losses":2841,"wins":1798},"match_totals_tracks":{"medium":{"draws":966,"losses":1329,"wins":953},"none":{"draws":889,"losses":1512,"wins":845}},"model_slug":"qwen-qwen3-7-max","overall":{"max":76.56064319545096,"mean":37.680012053888774,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":209,"losses":442,"wins":285},"GB2-02":{"draws":635,"losses":169,"wins":60},"GB2-03":{"draws":178,"losses":238,"wins":30},"GB2-04":{"draws":242,"losses":135,"wins":71},"GB2-05":{"draws":0,"losses":601,"wins":367},"GB2-06":{"draws":48,"losses":556,"wins":308},"GB2-07":{"draws":0,"losses":304,"wins":644},"GB2-08":{"draws":543,"losses":396,"wins":33}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":69,"losses":351,"wins":48},"GB2-02":{"draws":333,"losses":81,"wins":18},"GB2-04":{"draws":242,"losses":135,"wins":71},"GB2-05":{"draws":0,"losses":292,"wins":192},"GB2-06":{"draws":45,"losses":168,"wins":243},"GB2-07":{"draws":0,"losses":113,"wins":361},"GB2-08":{"draws":277,"losses":189,"wins":20}},"none":{"GB2-01":{"draws":140,"losses":91,"wins":237},"GB2-02":{"draws":302,"losses":88,"wins":42},"GB2-03":{"draws":178,"losses":238,"wins":30},"GB2-05":{"draws":0,"losses":309,"wins":175},"GB2-06":{"draws":3,"losses":388,"wins":65},"GB2-07":{"draws":0,"losses":191,"wins":283},"GB2-08":{"draws":266,"losses":207,"wins":13}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1144.8370361178274,"GB2-02":1429.4675290738298,"GB2-04":1432.493549458165,"GB2-05":1323.7461820710653,"GB2-06":1608.7550117869393,"GB2-07":1829.1095757387468,"GB2-08":1254.3583622903334},"none":{"GB2-01":1645.0525463530444,"GB2-02":1444.6886537377545,"GB2-03":1250.1415433584616,"GB2-05":1276.7017541721077,"GB2-06":930.4956181178545,"GB2-07":1593.3377876875318,"GB2-08":1227.294379997485}},"per_game_tracks":{"medium":{"GB2-01":18.536263273309995,"GB2-02":43.99634030996448,"GB2-04":44.10728525638753,"GB2-05":39.82044082430902,"GB2-06":59.70127562105285,"GB2-07":76.56064319545096,"GB2-08":33.6879719192668},"none":{"GB2-01":66.32227449553156,"GB2-02":45.97132059450513,"GB2-03":29.591922824386945,"GB2-05":36.277531723823344,"GB2-06":16.14889835951932,"GB2-07":61.09796103340956,"GB2-08":31.060063431302876}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":39.55127754996771,"none":35.80874655780984},"reasoning_agg":{"medium":{"max":76.56064319545096,"mean":39.55127754996771,"min":0.0},"none":{"max":66.32227449553156,"mean":35.80874655780984,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":3.7425309921578673}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-build-0-1:996839815f24af4e","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528460000000007}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528460000000007}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528460000000007},"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":34.79447077257987},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":8,"repaired_rate":1.0}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":36.912057446066484,"score":36.912057446066484},"GB2-02":{"attempts":1,"playable":43.99634030996448,"score":43.99634030996448},"GB2-03":{"attempts":1,"playable":29.828902552943205,"score":29.828902552943205},"GB2-04":{"attempts":1,"playable":40.840192917396216,"score":40.840192917396216},"GB2-05":{"attempts":1,"playable":48.60003105671666,"score":48.60003105671666},"GB2-06":{"attempts":1,"playable":31.065872199285177,"score":31.065872199285177},"GB2-07":{"attempts":1,"playable":13.529490271922063,"score":13.529490271922063},"GB2-08":{"attempts":1,"playable":33.58287942634469,"score":33.58287942634469}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":36.912057446066484,"score":36.912057446066484},"GB2-02":{"attempts":1,"playable":43.99634030996448,"score":43.99634030996448},"GB2-03":{"attempts":1,"playable":29.828902552943205,"score":29.828902552943205},"GB2-04":{"attempts":1,"playable":40.840192917396216,"score":40.840192917396216},"GB2-05":{"attempts":1,"playable":48.60003105671666,"score":48.60003105671666},"GB2-06":{"attempts":1,"playable":31.065872199285177,"score":31.065872199285177},"GB2-07":{"attempts":1,"playable":13.529490271922063,"score":13.529490271922063},"GB2-08":{"attempts":1,"playable":33.58287942634469,"score":33.58287942634469}}},"id":"x-ai/grok-build-0.1","is_recent_addition":false,"last_measured_at":"2026-10-20T11:00:58Z","match_totals_all":{"draws":1158,"losses":1886,"wins":650},"match_totals_tracks":{"medium":{"draws":1158,"losses":1886,"wins":650}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":48.60003105671666,"mean":34.79447077257987,"min":13.529490271922063},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":92,"losses":254,"wins":122},"GB2-02":{"draws":351,"losses":72,"wins":9},"GB2-03":{"draws":126,"losses":263,"wins":57},"GB2-04":{"draws":307,"losses":117,"wins":24},"GB2-05":{"draws":0,"losses":250,"wins":234},"GB2-06":{"draws":4,"losses":323,"wins":129},"GB2-07":{"draws":0,"losses":418,"wins":56},"GB2-08":{"draws":278,"losses":189,"wins":19}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":92,"losses":254,"wins":122},"GB2-02":{"draws":351,"losses":72,"wins":9},"GB2-03":{"draws":126,"losses":263,"wins":57},"GB2-04":{"draws":307,"losses":117,"wins":24},"GB2-05":{"draws":0,"losses":250,"wins":234},"GB2-06":{"draws":4,"losses":323,"wins":129},"GB2-07":{"draws":0,"losses":418,"wins":56},"GB2-08":{"draws":278,"losses":189,"wins":19}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1356.2930251861071,"GB2-02":1429.4675290738298,"GB2-03":1252.4228477907795,"GB2-04":1407.0618968922502,"GB2-05":1434.795490953651,"GB2-06":1168.5993572518682,"GB2-07":921.4705777366843,"GB2-08":1253.284415884804}},"per_game_tracks":{"medium":{"GB2-01":36.912057446066484,"GB2-02":43.99634030996448,"GB2-03":29.828902552943205,"GB2-04":40.840192917396216,"GB2-05":48.60003105671666,"GB2-06":31.065872199285177,"GB2-07":13.529490271922063,"GB2-08":33.58287942634469}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":34.79447077257987},"reasoning_agg":{"medium":{"max":48.60003105671666,"mean":34.79447077257987,"min":13.529490271922063}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-1-flash:b57bb69ec0ce5eaa","codegen_cost_by_reasoning":{"medium":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":1,"run_count":1,"total":0.0},"none":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":1,"run_count":1,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":2,"cost_basis_counts":{"provider_reported":3},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":3,"run_count":2,"total":0.0},"codegen_latency_ms":{"attempt_count":2,"max_ms":81836,"mean_ms":81836.0,"min_ms":81836,"run_count":1},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":2,"max_ms":81836,"mean_ms":81836.0,"min_ms":81836,"run_count":1}},"codegen_output_tokens":{"attempt_count":3,"output_max":32768,"output_mean":19502.5,"output_min":6237,"run_count":2},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":1,"output_max":32768,"output_mean":32768.0,"output_min":32768,"run_count":1},"none":{"attempt_count":2,"output_max":6237,"output_mean":6237.0,"output_min":6237,"run_count":1}},"display_name":"Ling 3.1 Flash","economics":{"none":34.528621949723956},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":3,"effective_max_output_tokens":[32768],"finish_reason_observations":2,"finish_reasons":["stop"],"indexed_attempts":3,"output_token_observations":3,"provider_post_attempt_observations":3,"provider_post_attempts":4,"reasoning_token_observations":3,"reconciliation_get_attempt_observations":3,"requested_max_output_token_observations":3,"requested_max_output_tokens":[32768],"total_output_tokens":39005,"total_reasoning_output_tokens":30791,"total_visible_output_tokens":8214,"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":32768,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.1-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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"headline_games_all":{"GB2-08":{"attempts":1,"playable":34.528621949723956,"score":34.528621949723956}},"headline_games_tracks":{"none":{"GB2-08":{"attempts":1,"playable":34.528621949723956,"score":34.528621949723956}}},"id":"inclusionai/ling-3.1-flash","is_recent_addition":false,"last_measured_at":"2026-10-13T22:57:25Z","match_totals_all":{"draws":287,"losses":180,"wins":19},"match_totals_tracks":{"none":{"draws":287,"losses":180,"wins":19}},"model_slug":"inclusionai-ling-3-1-flash","overall":{"max":34.528621949723956,"mean":34.528621949723956,"min":34.528621949723956},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-08":{"draws":287,"losses":180,"wins":19}},"per_game_match_totals_tracks":{"none":{"GB2-08":{"draws":287,"losses":180,"wins":19}}},"per_game_raw_elo_tracks":{"none":{"GB2-08":1262.9302677557528}},"per_game_tracks":{"none":{"GB2-08":34.528621949723956}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#000000","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":34.528621949723956},"reasoning_agg":{"none":{"max":34.528621949723956,"mean":34.528621949723956,"min":34.528621949723956}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning disabled"},"reasoning_settings":{"baseline":"none"}},{"canonical_public_row_identity":"publication-row.v1:overall:poolside-laguna-s-2-1:c6ab2531e1444a25","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0068074,"mean":0.0034371900000000006,"median":0.00326368,"min":0.00211404,"recorded_attempt_count":35,"run_count":14,"total":0.04917796},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"cost_is_complete":false,"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":0.04176385999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0068074,"mean":0.0034371900000000006,"median":0.00326368,"min":0.00211404,"recorded_attempt_count":35,"run_count":14,"total":0.04917796},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0068074,"mean":0.0032179299999999995,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":68,"run_count":28,"total":0.09094181999999998},"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":34.57010830594725,"none":39.902051345780954},"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":"poolside","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":13,"failed_game_aliases":["GB2-01"],"first_pass_admitted":7,"first_pass_rate":0.5833333333333334,"game_attempts":{"GB2-01":{"admitted":1,"model_code_failures":1},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"infra_failures_excluded":1,"performance_rejections":1},"GB2-08":{"admitted":2}},"infra_excluded_game_aliases":["GB2-04","GB2-06","GB2-07"],"infra_failures_excluded":3,"model_code_failure_rate":0.08333333333333333,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-07"],"performance_rejections":1,"repaired_admitted":4,"repaired_rate":0.3333333333333333},"baseline":{"admitted_plugins":12,"evaluated_cells":14,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":7,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"infra_failures_excluded":1,"model_code_failures":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.14285714285714285,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.35714285714285715}},"headline_games_all":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":45.799303323727216,"score":35.506860529132595},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":41.725934610016374,"score":31.571188345608018},"GB2-03":{"attempts":4,"playable":39.093559716314175,"score":39.093559716314175},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":39.03458308399548,"score":19.51729154199774},"GB2-05":{"attempts":4,"playable":38.17256828903673,"score":38.17256828903673},"GB2-06":{"attempts":2,"playable":20.321529022229754,"score":20.321529022229754},"GB2-07":{"attempts":2,"playable":45.56212689447614,"score":45.56212689447614},"GB2-08":{"attempts":4,"playable":33.24130883048869,"score":33.24130883048869}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":41.1697711783785,"score":20.58488558918925},"GB2-02":{"attempts":2,"playable":42.832884162399324,"score":42.832884162399324},"GB2-03":{"attempts":2,"playable":38.37086724491305,"score":38.37086724491305},"GB2-04":{"attempts":1,"playable":39.03458308399548,"score":39.03458308399548},"GB2-05":{"attempts":2,"playable":27.67753175749546,"score":27.67753175749546},"GB2-06":{"attempts":1,"playable":19.795186035547452,"score":19.795186035547452},"GB2-08":{"attempts":2,"playable":33.109934678901524,"score":33.109934678901524}},"none":{"GB2-01":{"attempts":2,"playable":50.428835469075935,"score":50.428835469075935},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.618985057633424,"score":20.309492528816712},"GB2-03":{"attempts":2,"playable":39.81625218771531,"score":39.81625218771531},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":2,"playable":48.667604820578,"score":48.667604820578},"GB2-06":{"attempts":1,"playable":20.847872008912052,"score":20.847872008912052},"GB2-07":{"attempts":2,"playable":45.56212689447614,"score":45.56212689447614},"GB2-08":{"attempts":2,"playable":33.37268298207585,"score":33.37268298207585}}},"id":"poolside/laguna-s-2.1","is_recent_addition":false,"last_measured_at":"2026-10-20T11:31:07Z","match_totals_all":{"draws":3187,"losses":5149,"wins":2336},"match_totals_tracks":{"medium":{"draws":1862,"losses":2448,"wins":758},"none":{"draws":1325,"losses":2701,"wins":1578}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":50.428835469075935,"mean":32.00250936304538,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":225,"losses":640,"wins":539},"GB2-02":{"draws":1030,"losses":252,"wins":14},"GB2-03":{"draws":605,"losses":843,"wins":336},"GB2-04":{"draws":261,"losses":148,"wins":39},"GB2-05":{"draws":0,"losses":1202,"wins":734},"GB2-06":{"draws":17,"losses":735,"wins":160},"GB2-07":{"draws":0,"losses":535,"wins":413},"GB2-08":{"draws":1049,"losses":794,"wins":101}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":78,"losses":241,"wins":149},"GB2-02":{"draws":716,"losses":147,"wins":1},"GB2-03":{"draws":284,"losses":437,"wins":171},"GB2-04":{"draws":261,"losses":148,"wins":39},"GB2-05":{"draws":0,"losses":702,"wins":266},"GB2-06":{"draws":6,"losses":371,"wins":79},"GB2-08":{"draws":517,"losses":402,"wins":53}},"none":{"GB2-01":{"draws":147,"losses":399,"wins":390},"GB2-02":{"draws":314,"losses":105,"wins":13},"GB2-03":{"draws":321,"losses":406,"wins":165},"GB2-05":{"draws":0,"losses":500,"wins":468},"GB2-06":{"draws":11,"losses":364,"wins":81},"GB2-07":{"draws":0,"losses":535,"wins":413},"GB2-08":{"draws":532,"losses":392,"wins":48}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1398.0811514008642,"GB2-02":1420.470975218016,"GB2-03":1330.349255412908,"GB2-04":1392.8364975076547,"GB2-05":1130.1386219090252,"GB2-06":993.363301522623,"GB2-08":1248.4439682183593},"none":{"GB2-01":1487.3325778456765,"GB2-02":1403.2460704779985,"GB2-03":1343.1371105607466,"GB2-05":1449.2211922672661,"GB2-06":1010.625647316549,"GB2-07":1395.0671975317223,"GB2-08":1251.133462981244}},"per_game_tracks":{"medium":{"GB2-01":41.1697711783785,"GB2-02":42.832884162399324,"GB2-03":38.37086724491305,"GB2-04":39.03458308399548,"GB2-05":27.67753175749546,"GB2-06":19.795186035547452,"GB2-08":33.109934678901524},"none":{"GB2-01":50.428835469075935,"GB2-02":40.618985057633424,"GB2-03":39.81625218771531,"GB2-05":48.667604820578,"GB2-06":20.847872008912052,"GB2-07":45.56212689447614,"GB2-08":33.37268298207585}},"provider_color":"#4137FF","provider_company":"Poolside","provider_key":"poolside","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":31.629410364634506,"none":32.37560836145625},"reasoning_agg":{"medium":{"max":42.832884162399324,"mean":31.629410364634506,"min":19.795186035547452},"none":{"max":50.428835469075935,"mean":32.37560836145625,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":0.7461979968217456}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy3-preview:1e3168587010809f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"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":0.031586438999999994},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139174}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139174},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"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}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"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":0.041725612999999995},"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":41.77752809291218,"none":40.34165249071234},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1,"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.2222222222222222,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":71.46150104295342,"score":71.46150104295342},"GB2-02":{"attempts":2,"playable":38.28389052805868,"score":38.28389052805868},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":31.366014843855535,"score":15.683007421927767},"GB2-04":{"attempts":2,"playable":46.016857999251094,"score":46.016857999251094},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":37.20752934170165,"score":22.285150695438634},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":17.092579965670154,"score":8.546289982835077},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":25.90293901333621,"score":12.951469506668104},"GB2-08":{"attempts":2,"playable":37.09575997393385,"score":37.09575997393385}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":64.5331689524617,"score":64.5331689524617},"GB2-02":{"attempts":1,"playable":38.751347590986065,"score":38.751347590986065},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.65709428159629,"score":43.65709428159629},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":59.68951458505206,"score":29.84475729252603},"GB2-06":{"attempts":1,"playable":17.092579965670154,"score":17.092579965670154},"GB2-07":{"attempts":1,"playable":25.90293901333621,"score":25.90293901333621},"GB2-08":{"attempts":1,"playable":42.816052261282756,"score":42.816052261282756}},"none":{"GB2-01":{"attempts":1,"playable":78.38983313344514,"score":78.38983313344514},"GB2-02":{"attempts":1,"playable":37.8164334651313,"score":37.8164334651313},"GB2-03":{"attempts":1,"playable":31.366014843855535,"score":31.366014843855535},"GB2-04":{"attempts":1,"playable":48.3766217169059,"score":48.3766217169059},"GB2-05":{"attempts":1,"playable":14.72554409835124,"score":14.72554409835124},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":31.375467686584948,"score":31.375467686584948}}},"id":"tencent/hy3-preview","is_recent_addition":false,"last_measured_at":"2026-10-20T11:13:49Z","match_totals_all":{"draws":1843,"losses":2691,"wins":1478},"match_totals_tracks":{"highest":{"draws":850,"losses":1501,"wins":897},"none":{"draws":993,"losses":1190,"wins":581}},"model_slug":"tencent-hy3-preview","overall":{"max":78.38983313344514,"mean":31.54049089388333,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-01":64.5331689524617,"GB2-02":38.751347590986065,"GB2-04":43.65709428159629,"GB2-05":59.68951458505206,"GB2-06":17.092579965670154,"GB2-07":25.90293901333621,"GB2-08":42.816052261282756},"per_game_match_totals_all":{"GB2-01":{"draws":148,"losses":199,"wins":589},"GB2-02":{"draws":632,"losses":228,"wins":4},"GB2-03":{"draws":105,"losses":267,"wins":74},"GB2-04":{"draws":600,"losses":195,"wins":101},"GB2-05":{"draws":0,"losses":611,"wins":357},"GB2-06":{"draws":3,"losses":384,"wins":69},"GB2-07":{"draws":0,"losses":362,"wins":112},"GB2-08":{"draws":355,"losses":445,"wins":172}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":73,"losses":133,"wins":262},"GB2-02":{"draws":316,"losses":112,"wins":4},"GB2-04":{"draws":326,"losses":95,"wins":27},"GB2-05":{"draws":0,"losses":197,"wins":287},"GB2-06":{"draws":3,"losses":384,"wins":69},"GB2-07":{"draws":0,"losses":362,"wins":112},"GB2-08":{"draws":132,"losses":218,"wins":136}},"none":{"GB2-01":{"draws":75,"losses":66,"wins":327},"GB2-02":{"draws":316,"losses":116,"wins":0},"GB2-03":{"draws":105,"losses":267,"wins":74},"GB2-04":{"draws":274,"losses":100,"wins":74},"GB2-05":{"draws":0,"losses":414,"wins":70},"GB2-08":{"draws":223,"losses":227,"wins":36}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1626.0916102412423,"GB2-02":1388.5590007897188,"GB2-04":1429.0058715880014,"GB2-05":1575.98720538982,"GB2-06":947.3221316193188,"GB2-07":1137.7935875843402,"GB2-08":1347.0992067746959},"none":{"GB2-01":1789.9913700690706,"GB2-02":1381.1366088241355,"GB2-03":1267.0336991413465,"GB2-04":1465.47109030541,"GB2-05":919.450225631746,"GB2-08":1230.5694970622417}},"per_game_tracks":{"highest":{"GB2-01":64.5331689524617,"GB2-02":38.751347590986065,"GB2-04":43.65709428159629,"GB2-05":59.68951458505206,"GB2-06":17.092579965670154,"GB2-07":25.90293901333621,"GB2-08":42.816052261282756},"none":{"GB2-01":78.38983313344514,"GB2-02":37.8164334651313,"GB2-03":31.366014843855535,"GB2-04":48.3766217169059,"GB2-05":14.72554409835124,"GB2-08":31.375467686584948}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":32.8247424197324,"none":30.256239368034258},"reasoning_agg":{"highest":{"max":64.5331689524617,"mean":32.8247424197324,"min":0.0},"none":{"max":78.38983313344514,"mean":30.256239368034258,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":2.568503051698144}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5:2aacde13c82c4c44","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0597184625,"mean":0.02467013555,"median":0.0239011175,"min":0.0040410944,"recorded_attempt_count":19,"run_count":8,"total":0.1973610844},"medium":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03062629,"mean":0.020124273158333334,"median":0.017895481666666668,"min":0.012095886733333333,"recorded_attempt_count":52,"run_count":24,"total":0.48618750699999996},"none":{"admitted_cell_count":17,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.005169185000000001,"mean":0.002871050658333333,"median":0.0023354879666666667,"min":0.00169122,"recorded_attempt_count":37,"run_count":24,"total":0.06890521579999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0265755425,"mean":0.018416099712499998,"median":0.017703669999999998,"min":0.0109615788,"recorded_attempt_count":32,"run_count":15,"total":0.2720731754},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.038769960000000006,"mean":0.023744302225,"median":0.0230069837,"min":0.0074361952000000005,"recorded_attempt_count":20,"run_count":9,"total":0.2141143316},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.00295601625,"mean":0.0023887339375,"median":0.002303478175,"min":0.0017364400000000001,"recorded_attempt_count":25,"run_count":16,"total":0.038219743},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0097359,"mean":0.0038356840999999994,"median":0.0020557588,"min":0.0014804776,"recorded_attempt_count":12,"run_count":8,"total":0.030685472799999995},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0597184625,"mean":0.02467013555,"median":0.0239011175,"min":0.0040410944,"recorded_attempt_count":19,"run_count":8,"total":0.1973610844}},"codegen_cost_usd":{"admitted_cell_count":37,"cell_count":24,"cost_basis_counts":{"provider_reported":108},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0597184625,"mean":0.015888486455555555,"median":0.014928570933333333,"min":0.00169122,"recorded_attempt_count":108,"run_count":56,"total":0.7524538071999999},"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":35.75217371580358,"highest":37.20795104947764,"medium":31.972402505137875,"none":34.46668831959554},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":15,"evaluated_cells":16,"failed_game_aliases":["GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.0625,"game_attempts":{"GB2-01":{"admitted":2,"infra_failures_excluded":1},"GB2-02":{"admitted":3},"GB2-03":{"infra_failures_excluded":3},"GB2-04":{"admitted":3},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"infra_failures_excluded":2},"GB2-07":{"admitted":2,"infra_failures_excluded":1},"GB2-08":{"admitted":2,"infra_failures_excluded":1,"model_code_failures":1}},"infra_excluded_game_aliases":["GB2-01","GB2-03","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.0625,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":14,"repaired_rate":0.875},"baseline":{"admitted_plugins":17,"evaluated_cells":23,"failed_game_aliases":["GB2-02","GB2-03","GB2-07","GB2-08"],"first_pass_admitted":12,"first_pass_rate":0.5217391304347826,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":1,"model_code_failures":2},"GB2-03":{"admitted":1,"model_code_failures":2},"GB2-04":{"admitted":2,"infra_failures_excluded":1},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":2,"model_code_failures":1},"GB2-08":{"admitted":2,"model_code_failures":1}},"infra_excluded_game_aliases":["GB2-04"],"infra_failures_excluded":1,"model_code_failure_rate":0.2608695652173913,"model_code_failures":6,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.21739130434782608},"intensive":{"admitted_plugins":5,"evaluated_cells":5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"infra_failures_excluded":1},"GB2-04":{"admitted":1},"GB2-05":{"infra_failures_excluded":1},"GB2-06":{"admitted":1},"GB2-07":{"infra_failures_excluded":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-03","GB2-05","GB2-07"],"infra_failures_excluded":3,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":5,"repaired_rate":1.0}},"headline_games_all":{"GB2-01":{"attempts":6,"playable":31.65858030047107,"score":31.65858030047107},"GB2-02":{"attempts":7,"failed_attempts":2,"playable":42.8191736845094,"score":33.637267138390136},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":44.59871902958958,"score":14.86623967652986},"GB2-04":{"attempts":6,"playable":39.667358414104676,"score":39.667358414104676},"GB2-05":{"attempts":5,"playable":26.269026870028952,"score":26.269026870028952},"GB2-06":{"attempts":5,"playable":34.83481033910563,"score":34.83481033910563},"GB2-07":{"attempts":5,"failed_attempts":1,"playable":26.0803504167083,"score":22.531289817806485},"GB2-08":{"attempts":7,"failed_attempts":2,"playable":31.519483043802524,"score":24.405695901982778}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":23.081579140671103,"score":23.081579140671103},"GB2-02":{"attempts":1,"playable":44.2288811072632,"score":44.2288811072632},"GB2-04":{"attempts":1,"playable":39.147495384809844,"score":39.147495384809844},"GB2-06":{"attempts":1,"playable":49.04743475961422,"score":49.04743475961422},"GB2-08":{"attempts":1,"playable":30.534364855029843,"score":30.534364855029843}},"medium":{"GB2-01":{"attempts":2,"playable":29.47800785747411,"score":29.47800785747411},"GB2-02":{"attempts":3,"playable":42.910060488728305,"score":42.910060488728305},"GB2-04":{"attempts":3,"playable":38.39423034358091,"score":38.39423034358091},"GB2-05":{"attempts":2,"playable":24.605570100030903,"score":24.605570100030903},"GB2-06":{"attempts":1,"playable":22.362967339714242,"score":22.362967339714242},"GB2-07":{"attempts":2,"playable":30.86633724000572,"score":30.86633724000572},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":34.90950427893557,"score":23.273002852623716}},"none":{"GB2-01":{"attempts":3,"playable":42.41615390326799,"score":42.41615390326799},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":41.31857945753672,"score":13.772859819178906},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":44.59871902958958,"score":14.86623967652986},"GB2-04":{"attempts":2,"playable":41.46034951392326,"score":41.46034951392326},"GB2-05":{"attempts":3,"playable":27.932483640026998,"score":27.932483640026998},"GB2-06":{"attempts":3,"playable":33.094028917988425,"score":33.094028917988425},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":21.29436359341088,"score":14.196242395607252},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":29.114579997442156,"score":19.409719998294772}}},"id":"xiaomi/mimo-v2.5","is_recent_addition":false,"last_measured_at":"2026-10-20T11:44:13Z","match_totals_all":{"draws":5216,"losses":8879,"wins":3033},"match_totals_tracks":{"highest":{"draws":1113,"losses":917,"wins":260},"medium":{"draws":2270,"losses":3549,"wins":1101},"none":{"draws":1833,"losses":4413,"wins":1672}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":49.04743475961422,"mean":31.123828652391268,"min":13.772859819178906},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_or_non_distinct_settings","untested_or_ineligible_settings","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-01":23.081579140671103,"GB2-02":44.2288811072632,"GB2-04":39.147495384809844,"GB2-06":49.04743475961422,"GB2-08":30.534364855029843},"per_game_all":{"GB2-01":31.11104117432031,"GB2-02":42.79333969078328,"GB2-04":39.78657237032926,"GB2-06":33.55043229978249,"GB2-08":31.519483043802524},"per_game_match_totals_all":{"GB2-01":{"draws":580,"losses":1566,"wins":662},"GB2-02":{"draws":1710,"losses":407,"wins":43},"GB2-03":{"draws":161,"losses":182,"wins":103},"GB2-04":{"draws":1667,"losses":824,"wins":197},"GB2-05":{"draws":0,"losses":1781,"wins":639},"GB2-06":{"draws":56,"losses":1514,"wins":710},"GB2-07":{"draws":0,"losses":1442,"wins":454},"GB2-08":{"draws":1042,"losses":1163,"wins":225}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":199,"losses":265,"wins":4},"GB2-02":{"draws":351,"losses":71,"wins":10},"GB2-04":{"draws":276,"losses":140,"wins":32},"GB2-06":{"draws":20,"losses":232,"wins":204},"GB2-08":{"draws":267,"losses":209,"wins":10}},"medium":{"GB2-01":{"draws":117,"losses":611,"wins":208},"GB2-02":{"draws":1023,"losses":245,"wins":28},"GB2-04":{"draws":834,"losses":427,"wins":83},"GB2-05":{"draws":0,"losses":731,"wins":237},"GB2-06":{"draws":20,"losses":353,"wins":83},"GB2-07":{"draws":0,"losses":677,"wins":271},"GB2-08":{"draws":276,"losses":505,"wins":191}},"none":{"GB2-01":{"draws":264,"losses":690,"wins":450},"GB2-02":{"draws":336,"losses":91,"wins":5},"GB2-03":{"draws":161,"losses":182,"wins":103},"GB2-04":{"draws":557,"losses":257,"wins":82},"GB2-05":{"draws":0,"losses":1050,"wins":402},"GB2-06":{"draws":16,"losses":929,"wins":423},"GB2-07":{"draws":0,"losses":765,"wins":183},"GB2-08":{"draws":499,"losses":449,"wins":24}}},"per_game_raw_elo_all":{"GB2-01":1292.1746685113287,"GB2-02":1420.1432118864452,"GB2-04":1398.7343129353103,"GB2-06":1204.3886929834607,"GB2-08":1229.6522241913365},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1205.1009388242421,"GB2-02":1431.262375744063,"GB2-04":1393.7307774493238,"GB2-06":1440.1401746673462,"GB2-08":1221.8158261460767},"medium":{"GB2-01":1278.3468536632436,"GB2-02":1420.4596799860756,"GB2-04":1390.558531696443,"GB2-05":1101.2186658855944,"GB2-06":1034.9758127901725,"GB2-07":1203.2393394881824,"GB2-08":1260.9721264743666},"none":{"GB2-01":1393.0762130465007,"GB2-02":1408.707579929197,"GB2-03":1385.1206261977213,"GB2-04":1411.9136296601637,"GB2-05":1124.0011482444875,"GB2-06":1138.0500914928634,"GB2-07":1047.1488940254226,"GB2-08":1206.1687199535659}},"per_game_tracks":{"highest":{"GB2-01":23.081579140671103,"GB2-02":44.2288811072632,"GB2-04":39.147495384809844,"GB2-06":49.04743475961422,"GB2-08":30.534364855029843},"medium":{"GB2-01":29.47800785747411,"GB2-02":42.832558507549905,"GB2-04":38.75187221225469,"GB2-05":24.605570100030903,"GB2-06":22.362967339714242,"GB2-07":30.86633724000572,"GB2-08":34.90950427893557},"none":{"GB2-01":40.773536524815725,"GB2-02":41.31857945753672,"GB2-03":44.59871902958958,"GB2-04":41.46034951392326,"GB2-05":27.93248364002699,"GB2-06":29.24089480001902,"GB2-07":21.29436359341088,"GB2-08":29.114579997442156}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":37.20795104947764,"medium":30.27002517459398,"none":25.89350973310218},"reasoning_agg":{"highest":{"max":49.04743475961422,"mean":37.20795104947764,"min":23.081579140671103},"medium":{"max":42.910060488728305,"mean":30.27002517459398,"min":22.362967339714242},"none":{"max":42.41615390326799,"mean":25.89350973310218,"min":13.772859819178906}},"reasoning_labels":{"highest":"High","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":11.314441316375461}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-nano:264b96442a17a515","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.26962149999999996,"mean":0.26962149999999996,"median":0.26962149999999996,"min":0.26962149999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":0.5392429999999999},"medium":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.034210525000000006,"mean":0.024715571875,"median":0.0256067375,"min":0.01676735,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":25},"run_count":16,"token_priced_attempt_count":25,"total":0.3954491500000001},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.01311555,"mean":0.009215359375,"median":0.009537575,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"run_count":16,"token_priced_attempt_count":27,"total":0.14744575000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.034210525000000006,"mean":0.024715571875,"median":0.0256067375,"min":0.01676735,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":25},"run_count":16,"token_priced_attempt_count":25,"total":0.39544914999999997},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.01311555,"mean":0.009215359375,"median":0.009537575,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"run_count":16,"token_priced_attempt_count":27,"total":0.14744575000000001},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.26962149999999996,"mean":0.26962149999999996,"median":0.26962149999999996,"min":0.26962149999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":0.5392429999999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":17,"cost_basis_counts":{"estimated":2,"local_standard_estimate":55},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":8,"max":0.26962149999999996,"mean":0.03182758529411764,"median":0.01676735,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":55},"recorded_attempt_count":2,"run_count":34,"token_priced_attempt_count":55,"total":1.0821378999999998},"codegen_latency_ms":{"attempt_count":55,"max_ms":2131860,"mean_ms":191027.9411764706,"min_ms":20868,"run_count":34},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":2131860,"mean_ms":1627538.0,"min_ms":1123216,"run_count":2},"medium":{"attempt_count":25,"max_ms":1064325,"mean_ms":157709.5,"min_ms":63447,"run_count":16},"none":{"attempt_count":27,"max_ms":101610,"mean_ms":44782.625,"min_ms":20868,"run_count":16}},"codegen_output_tokens":{"attempt_count":55,"output_max":256000,"output_mean":22146.529411764706,"output_min":2711,"run_count":34},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":3,"output_max":256000,"output_mean":192000.0,"output_min":128000,"run_count":2},"medium":{"attempt_count":25,"output_max":25344,"output_mean":17769.9375,"output_min":11435,"run_count":16},"none":{"attempt_count":27,"output_max":10894,"output_mean":5291.4375,"output_min":2711,"run_count":16}},"display_name":"GPT-5.4 Nano","economics":{"medium":43.13223470758749,"none":34.956538080836175},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":54,"finish_reasons":["incomplete","stop"],"indexed_attempts":57,"output_token_observations":57,"reasoning_token_observations":2,"total_output_tokens":752982,"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":["GB2-02","GB2-03","GB2-04"],"first_pass_admitted":5,"first_pass_rate":0.3125,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"model_code_failures":2},"GB2-04":{"admitted":1,"model_code_failures":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.4375},"baseline":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-03","GB2-04","GB2-07"],"first_pass_admitted":5,"first_pass_rate":0.3125,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":1,"model_code_failures":1},"GB2-04":{"model_code_failures":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":1,"model_code_failures":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.4375}},"headline_games_all":{"GB2-01":{"attempts":4,"playable":31.195517380205118,"score":31.195517380205118},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":40.41478837145293,"score":30.405871750114677},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":34.77447488899868,"score":8.69361872224967},"GB2-04":{"attempts":4,"failed_attempts":3,"playable":51.960667648675205,"score":12.990166912168801},"GB2-05":{"attempts":4,"playable":29.528297207811967,"score":29.528297207811967},"GB2-06":{"attempts":4,"playable":50.38578490978209,"score":50.38578490978209},"GB2-07":{"attempts":4,"failed_attempts":1,"playable":28.042420214553132,"score":22.76485004393445},"GB2-08":{"attempts":4,"playable":50.37632540684065,"score":50.37632540684065}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"playable":15.763921073475887,"score":15.763921073475887},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.035666485353,"score":20.0178332426765},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":51.960667648675205,"score":25.980333824337603},"GB2-05":{"attempts":2,"playable":50.68309553652033,"score":50.68309553652033},"GB2-06":{"attempts":2,"playable":59.125793785261365,"score":59.125793785261365},"GB2-07":{"attempts":2,"playable":34.97455974663154,"score":34.97455974663154},"GB2-08":{"attempts":2,"playable":49.38193867719515,"score":49.38193867719515}},"none":{"GB2-01":{"attempts":2,"playable":46.62711368693435,"score":46.62711368693435},"GB2-02":{"attempts":2,"playable":40.79391025755285,"score":40.79391025755285},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":34.77447488899868,"score":17.38723744449934},"GB2-04":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-05":{"attempts":2,"playable":8.373498879103607,"score":8.373498879103607},"GB2-06":{"attempts":2,"playable":41.64577603430282,"score":41.64577603430282},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":21.11028068247472,"score":10.55514034123736},"GB2-08":{"attempts":2,"playable":51.37071213648615,"score":51.37071213648615}}},"id":"gpt-5.4-nano","is_recent_addition":false,"last_measured_at":"2026-10-20T11:38:48Z","match_totals_all":{"draws":2203,"losses":5816,"wins":3169},"match_totals_tracks":{"medium":{"draws":925,"losses":2816,"wins":1875},"none":{"draws":1278,"losses":3000,"wins":1294}},"model_slug":"gpt-5-4-nano","overall":{"max":59.125793785261365,"mean":29.54255404163843,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":349,"losses":1130,"wins":393},"GB2-02":{"draws":992,"losses":291,"wins":13},"GB2-03":{"draws":134,"losses":238,"wins":74},"GB2-04":{"draws":214,"losses":114,"wins":120},"GB2-05":{"draws":0,"losses":1371,"wins":565},"GB2-06":{"draws":44,"losses":910,"wins":870},"GB2-07":{"draws":0,"losses":1014,"wins":408},"GB2-08":{"draws":470,"losses":748,"wins":726}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":146,"losses":723,"wins":67},"GB2-02":{"draws":331,"losses":99,"wins":2},"GB2-04":{"draws":214,"losses":114,"wins":120},"GB2-05":{"draws":0,"losses":480,"wins":488},"GB2-06":{"draws":41,"losses":366,"wins":505},"GB2-07":{"draws":0,"losses":630,"wins":318},"GB2-08":{"draws":193,"losses":404,"wins":375}},"none":{"GB2-01":{"draws":203,"losses":407,"wins":326},"GB2-02":{"draws":661,"losses":192,"wins":11},"GB2-03":{"draws":134,"losses":238,"wins":74},"GB2-05":{"draws":0,"losses":891,"wins":77},"GB2-06":{"draws":3,"losses":544,"wins":365},"GB2-07":{"draws":0,"losses":384,"wins":90},"GB2-08":{"draws":277,"losses":344,"wins":351}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1061.0338729192576,"GB2-02":1398.6767889214864,"GB2-04":1493.2679605546205,"GB2-05":1503.678153653781,"GB2-06":1600.4976682325932,"GB2-07":1204.3972349547203,"GB2-08":1468.3528327787708},"none":{"GB2-01":1450.2783279117016,"GB2-02":1404.612852676802,"GB2-03":1298.4747594834803,"GB2-05":759.523035794987,"GB2-06":1332.81278849756,"GB2-07":1063.6275861306992,"GB2-08":1479.6240334388126}},"per_game_tracks":{"medium":{"GB2-01":15.763921073475887,"GB2-02":40.035666485353,"GB2-04":51.960667648675205,"GB2-05":50.68309553652033,"GB2-06":59.125793785261365,"GB2-07":34.97455974663154,"GB2-08":49.38193867719515},"none":{"GB2-01":46.62711368693435,"GB2-02":40.79391025755285,"GB2-03":34.77447488899868,"GB2-05":8.373498879103607,"GB2-06":41.64577603430282,"GB2-07":21.11028068247472,"GB2-08":51.37071213648615}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":31.990934485762295,"none":27.094173597514565},"reasoning_agg":{"medium":{"max":59.125793785261365,"mean":31.990934485762295,"min":0.0},"none":{"max":51.37071213648615,"mean":27.094173597514565,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":4.89676088824773}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemma-4-31b-it:b01aa117506268d3","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0061656,"mean":0.00384247375,"median":0.003310595,"min":0.00192299,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.030739789999999996},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00371018,"mean":0.00186558375,"median":0.00131646,"min":0.0011068,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.014924670000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0061656,"mean":0.00384247375,"median":0.003310595,"min":0.00192299,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.030739789999999996},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00371018,"mean":0.00186558375,"median":0.00131646,"min":0.0011068,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.01492467}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0061656,"mean":0.0028540287500000002,"median":0.00232709,"min":0.0011068,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":25},"recorded_attempt_count":25,"run_count":16,"total":0.04566446},"codegen_latency_ms":{"attempt_count":25,"max_ms":425398,"mean_ms":137358.0,"min_ms":22859,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":14,"max_ms":425398,"mean_ms":207893.5,"min_ms":65353,"run_count":8},"none":{"attempt_count":11,"max_ms":256957,"mean_ms":66822.5,"min_ms":22859,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":12120,"output_mean":4888.4375,"output_min":1108,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":14,"output_max":12120,"output_mean":7438.375,"output_min":3314,"run_count":8},"none":{"attempt_count":11,"output_max":4877,"output_mean":2338.5,"output_min":1108,"run_count":8}},"display_name":"Gemma 4 31B","economics":{"medium":38.2878374931067,"none":27.375875585406913},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[16384],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":26,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[16384],"total_output_tokens":78215,"total_reasoning_output_tokens":27437,"total_visible_output_tokens":50778,"visible_token_observations":25},"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":16384,"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":21.24474991443506,"score":10.62237495721753},"GB2-02":{"attempts":2,"playable":41.95855733573111,"score":41.95855733573111},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":44.59871902958958,"score":22.29935951479479},"GB2-04":{"attempts":2,"playable":44.950154289897796,"score":44.950154289897796},"GB2-05":{"attempts":2,"playable":44.370180780821926,"score":44.370180780821926},"GB2-06":{"attempts":2,"playable":22.60478208658894,"score":22.60478208658894},"GB2-07":{"attempts":2,"playable":14.627986476822546,"score":14.627986476822546},"GB2-08":{"attempts":2,"playable":33.8455812867729,"score":33.8455812867729}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":21.24474991443506,"score":21.24474991443506},"GB2-02":{"attempts":1,"playable":43.41476993886233,"score":43.41476993886233},"GB2-03":{"attempts":1,"playable":44.59871902958958,"score":44.59871902958958},"GB2-04":{"attempts":1,"playable":43.431944654393554,"score":43.431944654393554},"GB2-05":{"attempts":1,"playable":72.59843546851896,"score":72.59843546851896},"GB2-06":{"attempts":1,"playable":28.234851241888947,"score":28.234851241888947},"GB2-07":{"attempts":1,"playable":18.46075459531093,"score":18.46075459531093},"GB2-08":{"attempts":1,"playable":34.318475101854226,"score":34.318475101854226}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":40.50234473259989,"score":40.50234473259989},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":46.46836392540203,"score":46.46836392540203},"GB2-05":{"attempts":1,"playable":16.14192609312489,"score":16.14192609312489},"GB2-06":{"attempts":1,"playable":16.974712931288934,"score":16.974712931288934},"GB2-07":{"attempts":1,"playable":10.795218358334163,"score":10.795218358334163},"GB2-08":{"attempts":1,"playable":33.37268747169157,"score":33.37268747169157}}},"id":"google/gemma-4-31b-it","is_recent_addition":false,"last_measured_at":"2026-10-14T17:59:40Z","match_totals_all":{"draws":2053,"losses":3371,"wins":1050},"match_totals_tracks":{"medium":{"draws":1163,"losses":1756,"wins":775},"none":{"draws":890,"losses":1615,"wins":275}},"model_slug":"google-gemma-4-31b-it","overall":{"max":72.59843546851896,"mean":29.409872091080942,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":118,"losses":314,"wins":36},"GB2-02":{"draws":677,"losses":174,"wins":13},"GB2-03":{"draws":101,"losses":212,"wins":133},"GB2-04":{"draws":571,"losses":219,"wins":106},"GB2-05":{"draws":0,"losses":542,"wins":426},"GB2-06":{"draws":37,"losses":705,"wins":170},"GB2-07":{"draws":0,"losses":826,"wins":122},"GB2-08":{"draws":549,"losses":379,"wins":44}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":118,"losses":314,"wins":36},"GB2-02":{"draws":344,"losses":78,"wins":10},"GB2-03":{"draws":101,"losses":212,"wins":133},"GB2-04":{"draws":292,"losses":113,"wins":43},"GB2-05":{"draws":0,"losses":135,"wins":349},"GB2-06":{"draws":35,"losses":320,"wins":101},"GB2-07":{"draws":0,"losses":396,"wins":78},"GB2-08":{"draws":273,"losses":188,"wins":25}},"none":{"GB2-02":{"draws":333,"losses":96,"wins":3},"GB2-04":{"draws":279,"losses":106,"wins":63},"GB2-05":{"draws":0,"losses":407,"wins":77},"GB2-06":{"draws":2,"losses":385,"wins":69},"GB2-07":{"draws":0,"losses":430,"wins":44},"GB2-08":{"draws":276,"losses":191,"wins":19}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1181.7303606758644,"GB2-02":1424.9742744403968,"GB2-03":1385.1206261977213,"GB2-04":1427.2600586451053,"GB2-05":1773.943197320714,"GB2-06":1125.8367374746967,"GB2-07":1018.357527237269,"GB2-08":1260.7903594715249},"none":{"GB2-02":1402.3335795544785,"GB2-04":1450.739339012947,"GB2-05":949.0366706285803,"GB2-06":945.2449819089081,"GB2-07":856.8201829266351,"GB2-08":1251.1347177854918}},"per_game_tracks":{"medium":{"GB2-01":21.24474991443506,"GB2-02":43.41476993886233,"GB2-03":44.59871902958958,"GB2-04":43.431944654393554,"GB2-05":72.59843546851896,"GB2-06":28.234851241888947,"GB2-07":18.46075459531093,"GB2-08":34.318475101854226},"none":{"GB2-02":40.50234473259989,"GB2-04":46.46836392540203,"GB2-05":16.14192609312489,"GB2-06":16.974712931288934,"GB2-07":10.795218358334163,"GB2-08":33.37268747169157}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":38.2878374931067,"none":20.531906689055184},"reasoning_agg":{"medium":{"max":72.59843546851896,"mean":38.2878374931067,"min":18.46075459531093},"none":{"max":46.46836392540203,"mean":20.531906689055184,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":17.755930804051516}},{"canonical_public_row_identity":"publication-row.v1:overall:meituan-longcat-2-0:6b5ca8216d334a6a","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":70},"cost_is_complete":false,"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},"cost_is_complete":false,"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_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":70},"cost_is_complete":false,"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},"historical-provider-setting-baseline":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"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":0.214047204}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":16,"cost_basis_counts":{"provider_reported":108},"cost_is_complete":false,"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":36.11850851980561,"none":35.21292073683939},"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":"meituan","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"model_code_failures":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":1,"model_code_failures":1},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"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,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":1,"model_code_failures":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":6,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":4,"failed_attempts":2,"playable":42.76343318004244,"score":21.38171659002122},"GB2-02":{"attempts":4,"failed_attempts":2,"playable":42.07504696027475,"score":21.037523480137374},"GB2-03":{"attempts":4,"failed_attempts":1,"playable":37.42612283524179,"score":27.424441327876877},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":41.80724054938011,"score":30.386791262845577},"GB2-05":{"attempts":4,"playable":22.553036250365935,"score":22.553036250365935},"GB2-06":{"attempts":4,"playable":31.066207676286997,"score":31.066207676286997},"GB2-07":{"attempts":4,"playable":35.910754009424515,"score":35.910754009424515},"GB2-08":{"attempts":4,"playable":35.04633789568187,"score":35.04633789568187}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.53110886291607,"score":21.765554431458035},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":40.006726029459664,"score":20.003363014729832},"GB2-04":{"attempts":2,"playable":37.932683952622085,"score":37.932683952622085},"GB2-05":{"attempts":2,"playable":33.306049208512256,"score":33.306049208512256},"GB2-06":{"attempts":2,"playable":24.840430344609935,"score":24.840430344609935},"GB2-07":{"attempts":2,"playable":37.22819140605892,"score":37.22819140605892},"GB2-08":{"attempts":2,"playable":35.98436983446029,"score":35.98436983446029}},"none":{"GB2-01":{"attempts":2,"playable":42.76343318004244,"score":42.76343318004244},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.618985057633424,"score":20.309492528816712},"GB2-03":{"attempts":2,"playable":34.84551964102392,"score":34.84551964102392},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":45.68179714613813,"score":22.840898573069065},"GB2-05":{"attempts":2,"playable":11.800023292219617,"score":11.800023292219617},"GB2-06":{"attempts":2,"playable":37.29198500796406,"score":37.29198500796406},"GB2-07":{"attempts":2,"playable":34.59331661279011,"score":34.59331661279011},"GB2-08":{"attempts":2,"playable":34.10830595690346,"score":34.10830595690346}}},"id":"meituan/longcat-2.0","is_recent_addition":false,"last_measured_at":"2026-10-20T11:23:24Z","match_totals_all":{"draws":2978,"losses":6611,"wins":2492},"match_totals_tracks":{"medium":{"draws":1320,"losses":3033,"wins":1220},"none":{"draws":1658,"losses":3578,"wins":1272}},"model_slug":"meituan-longcat-2-0","overall":{"max":42.76343318004244,"mean":28.100851061580045,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":226,"losses":432,"wins":278},"GB2-02":{"draws":699,"losses":162,"wins":3},"GB2-03":{"draws":405,"losses":689,"wins":244},"GB2-04":{"draws":750,"losses":440,"wins":153},"GB2-05":{"draws":0,"losses":1505,"wins":431},"GB2-06":{"draws":79,"losses":1257,"wins":488},"GB2-07":{"draws":0,"losses":1252,"wins":644},"GB2-08":{"draws":819,"losses":874,"wins":251}},"per_game_match_totals_tracks":{"medium":{"GB2-02":{"draws":361,"losses":69,"wins":2},"GB2-03":{"draws":139,"losses":213,"wins":94},"GB2-04":{"draws":490,"losses":321,"wins":84},"GB2-05":{"draws":0,"losses":648,"wins":320},"GB2-06":{"draws":31,"losses":689,"wins":192},"GB2-07":{"draws":0,"losses":610,"wins":338},"GB2-08":{"draws":299,"losses":483,"wins":190}},"none":{"GB2-01":{"draws":226,"losses":432,"wins":278},"GB2-02":{"draws":338,"losses":93,"wins":1},"GB2-03":{"draws":266,"losses":476,"wins":150},"GB2-04":{"draws":260,"losses":119,"wins":69},"GB2-05":{"draws":0,"losses":857,"wins":111},"GB2-06":{"draws":48,"losses":568,"wins":296},"GB2-07":{"draws":0,"losses":642,"wins":306},"GB2-08":{"draws":520,"losses":391,"wins":61}}},"per_game_raw_elo_tracks":{"medium":{"GB2-02":1425.873668759836,"GB2-03":1345.0333373971737,"GB2-04":1383.9512829410455,"GB2-05":1205.1356692316285,"GB2-06":1073.35258775994,"GB2-07":1257.2012641066096,"GB2-08":1271.4796816779256},"none":{"GB2-01":1413.4638447918471,"GB2-02":1403.2460704779985,"GB2-03":1297.5995324856044,"GB2-04":1444.6667701273284,"GB2-05":849.1980528185619,"GB2-06":1262.3626203825088,"GB2-07":1255.0451301527178,"GB2-08":1258.6461396391842}},"per_game_tracks":{"medium":{"GB2-02":43.53110886291607,"GB2-03":40.006726029459664,"GB2-04":37.932683952622085,"GB2-05":33.306049208512256,"GB2-06":24.840430344609935,"GB2-07":37.22819140605892,"GB2-08":35.98436983446029},"none":{"GB2-01":42.76343318004244,"GB2-02":40.618985057633424,"GB2-03":34.84551964102392,"GB2-04":45.68179714613813,"GB2-05":11.800023292219617,"GB2-06":37.29198500796406,"GB2-07":34.59331661279011,"GB2-08":34.10830595690346}},"provider_color":"#29E154","provider_company":"Meituan","provider_key":"meituan","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":26.38258027405642,"none":29.819121849103674},"reasoning_agg":{"medium":{"max":37.932683952622085,"mean":26.38258027405642,"min":0.0},"none":{"max":42.76343318004244,"mean":29.819121849103674,"min":11.800023292219617}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":3.4365415750472543}},{"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3:eb4b745f99eebdb9","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"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},"cost_is_complete":false,"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_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"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":0.5845103399999999},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.09803328,"mean":0.0253809975,"median":0.00943521,"min":0.00639384,"recorded_attempt_count":13,"run_count":8,"total":0.20304798}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":false,"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":27.64917758013414,"none":40.615068721389235},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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"],"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":39.17198319784611,"score":39.17198319784611},"GB2-02":{"attempts":2,"playable":40.03557353489443,"score":40.03557353489443},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":40.12220594818917,"score":20.061102974094585},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":40.61460813983791,"score":20.307304069918956},"GB2-05":{"attempts":2,"playable":15.520722786780352,"score":15.520722786780352},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":16.974712931288934,"score":8.487356465644467},"GB2-07":{"attempts":2,"playable":32.92727534446691,"score":32.92727534446691},"GB2-08":{"attempts":2,"playable":42.106009320991376,"score":42.106009320991376}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":19.07867722646969,"score":19.07867722646969},"GB2-02":{"attempts":1,"playable":39.56880233718898,"score":39.56880233718898},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.61460813983791,"score":40.61460813983791},"GB2-05":{"attempts":1,"playable":2.2274128604154,"score":2.2274128604154},"GB2-06":{"attempts":1,"playable":16.974712931288934,"score":16.974712931288934},"GB2-07":{"attempts":1,"playable":42.33797034955842,"score":42.33797034955842},"GB2-08":{"attempts":1,"playable":32.74205921617964,"score":32.74205921617964}},"none":{"GB2-01":{"attempts":1,"playable":59.265289169222534,"score":59.265289169222534},"GB2-02":{"attempts":1,"playable":40.50234473259989,"score":40.50234473259989},"GB2-03":{"attempts":1,"playable":40.12220594818917,"score":40.12220594818917},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":28.814032713145306,"score":28.814032713145306},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":23.516580339375412,"score":23.516580339375412},"GB2-08":{"attempts":1,"playable":51.469959425803104,"score":51.469959425803104}}},"id":"minimax/minimax-m3","is_recent_addition":false,"last_measured_at":"2026-10-20T11:22:55Z","match_totals_all":{"draws":1423,"losses":3387,"wins":1228},"match_totals_tracks":{"medium":{"draws":898,"losses":1950,"wins":400},"none":{"draws":525,"losses":1437,"wins":828}},"model_slug":"minimax-minimax-m3","overall":{"max":59.265289169222534,"mean":27.32716596182965,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":97,"losses":529,"wins":310},"GB2-02":{"draws":662,"losses":198,"wins":4},"GB2-03":{"draws":96,"losses":234,"wins":116},"GB2-04":{"draws":287,"losses":128,"wins":33},"GB2-05":{"draws":0,"losses":821,"wins":147},"GB2-06":{"draws":4,"losses":384,"wins":68},"GB2-07":{"draws":0,"losses":657,"wins":291},"GB2-08":{"draws":277,"losses":436,"wins":259}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":22,"losses":372,"wins":74},"GB2-02":{"draws":329,"losses":102,"wins":1},"GB2-04":{"draws":287,"losses":128,"wins":33},"GB2-05":{"draws":0,"losses":476,"wins":8},"GB2-06":{"draws":4,"losses":384,"wins":68},"GB2-07":{"draws":0,"losses":284,"wins":190},"GB2-08":{"draws":256,"losses":204,"wins":26}},"none":{"GB2-01":{"draws":75,"losses":157,"wins":236},"GB2-02":{"draws":333,"losses":96,"wins":3},"GB2-03":{"draws":96,"losses":234,"wins":116},"GB2-05":{"draws":0,"losses":345,"wins":139},"GB2-07":{"draws":0,"losses":373,"wins":101},"GB2-08":{"draws":21,"losses":232,"wins":233}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1152.492089863343,"GB2-02":1395.0085032498407,"GB2-04":1405.2927587447987,"GB2-05":460.60974181203574,"GB2-06":945.2449819089081,"GB2-07":1355.1220875063893,"GB2-08":1244.6700676909472},"none":{"GB2-01":1572.4040693995616,"GB2-02":1402.3335795544785,"GB2-03":1346.0463996855215,"GB2-05":1169.767546378081,"GB2-07":1101.9077473679981,"GB2-08":1439.432439430848}},"per_game_tracks":{"medium":{"GB2-01":19.07867722646969,"GB2-02":39.56880233718898,"GB2-04":40.61460813983791,"GB2-05":2.2274128604154,"GB2-06":16.974712931288934,"GB2-07":42.33797034955842,"GB2-08":32.74205921617964},"none":{"GB2-01":59.265289169222534,"GB2-02":40.50234473259989,"GB2-03":40.12220594818917,"GB2-05":28.814032713145306,"GB2-07":23.516580339375412,"GB2-08":51.469959425803104}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":24.193030382617373,"none":30.461301541041923},"reasoning_agg":{"medium":{"max":42.33797034955842,"mean":24.193030382617373,"min":0.0},"none":{"max":59.265289169222534,"mean":30.461301541041923,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":6.26827115842455}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-medium-3-5:58ee641433c53262","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.27741402547937455,"mean":0.17469283299791016,"median":0.15577176465417142,"min":0.1042008119864669,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":13},"run_count":8,"token_priced_attempt_count":13,"total":1.397542663983281},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":12},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.11538050836051075,"mean":0.06762316700208985,"median":0.06087263456058671,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"run_count":8,"token_priced_attempt_count":12,"total":0.5409853360167187}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":12},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.11538050836051075,"mean":0.06762316700208985,"median":0.06087263456058671,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"run_count":8,"token_priced_attempt_count":12,"total":0.5409853360167187},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.27741402547937455,"mean":0.17469283299791016,"median":0.15577176465417142,"min":0.1042008119864669,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":13},"run_count":8,"token_priced_attempt_count":13,"total":1.397542663983281}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.27741402547937455,"mean":0.12115799999999999,"median":0.10979066017348882,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":16,"token_priced_attempt_count":25,"total":1.938528},"codegen_output_tokens":{"attempt_count":25,"output_max":39199,"output_mean":13770.375,"output_min":1490,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":13,"output_max":39199,"output_mean":24874.75,"output_min":14259,"run_count":8},"none":{"attempt_count":12,"output_max":5186,"output_mean":2666.0,"output_min":1490,"run_count":8}},"display_name":"Mistral Medium 3.5","economics":{"highest":33.476691427432854,"none":26.54639848375849},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[209715],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":34,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[209715],"total_output_tokens":220326,"total_visible_output_tokens":220326,"visible_token_observations":25},"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":209715,"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":["GB2-07"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-01"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.5}},"headline_games_all":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":12.654316775568889,"score":6.327158387784444},"GB2-02":{"attempts":2,"playable":42.831323612012696,"score":42.831323612012696},"GB2-03":{"attempts":2,"playable":36.17159087356351,"score":36.17159087356351},"GB2-04":{"attempts":2,"playable":36.771861500412506,"score":36.771861500412506},"GB2-05":{"attempts":2,"playable":25.318177845512203,"score":25.318177845512203},"GB2-06":{"attempts":2,"playable":22.390636683854993,"score":22.390636683854993},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":12.848993580715117,"score":6.4244967903575585},"GB2-08":{"attempts":2,"playable":33.845568995671826,"score":33.845568995671826}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":44.6938117665531,"score":44.6938117665531},"GB2-03":{"attempts":1,"playable":38.15434275171209,"score":38.15434275171209},"GB2-04":{"attempts":1,"playable":39.82479781827604,"score":39.82479781827604},"GB2-05":{"attempts":1,"playable":37.52692450104805,"score":37.52692450104805},"GB2-06":{"attempts":1,"playable":26.864419686210294,"score":26.864419686210294},"GB2-07":{"attempts":1,"playable":12.848993580715117,"score":12.848993580715117},"GB2-08":{"attempts":1,"playable":34.423549887515314,"score":34.423549887515314}},"none":{"GB2-01":{"attempts":1,"playable":12.654316775568889,"score":12.654316775568889},"GB2-02":{"attempts":1,"playable":40.96883545747229,"score":40.96883545747229},"GB2-03":{"attempts":1,"playable":34.188838995414926,"score":34.188838995414926},"GB2-04":{"attempts":1,"playable":33.71892518254897,"score":33.71892518254897},"GB2-05":{"attempts":1,"playable":13.109431189976354,"score":13.109431189976354},"GB2-06":{"attempts":1,"playable":17.916853681499695,"score":17.916853681499695},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":33.26758810382834,"score":33.26758810382834}}},"id":"mistralai/mistral-medium-3-5","is_recent_addition":false,"last_measured_at":"2026-10-20T11:45:25Z","match_totals_all":{"draws":2001,"losses":3617,"wins":828},"match_totals_tracks":{"highest":{"draws":1041,"losses":1681,"wins":504},"none":{"draws":960,"losses":1936,"wins":324}},"model_slug":"mistralai-mistral-medium-3-5","overall":{"max":44.6938117665531,"mean":26.260101836146212,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-02":44.6938117665531,"GB2-03":38.15434275171209,"GB2-04":39.82479781827604,"GB2-05":37.52692450104805,"GB2-06":26.864419686210294,"GB2-07":12.848993580715117,"GB2-08":34.423549887515314},"per_game_match_totals_all":{"GB2-01":{"draws":45,"losses":390,"wins":33},"GB2-02":{"draws":680,"losses":165,"wins":19},"GB2-03":{"draws":230,"losses":483,"wins":179},"GB2-04":{"draws":508,"losses":323,"wins":65},"GB2-05":{"draws":0,"losses":725,"wins":243},"GB2-06":{"draws":17,"losses":717,"wins":178},"GB2-07":{"draws":0,"losses":421,"wins":53},"GB2-08":{"draws":521,"losses":393,"wins":58}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":339,"losses":75,"wins":18},"GB2-03":{"draws":125,"losses":228,"wins":93},"GB2-04":{"draws":294,"losses":128,"wins":26},"GB2-05":{"draws":0,"losses":303,"wins":181},"GB2-06":{"draws":15,"losses":336,"wins":105},"GB2-07":{"draws":0,"losses":421,"wins":53},"GB2-08":{"draws":268,"losses":190,"wins":28}},"none":{"GB2-01":{"draws":45,"losses":390,"wins":33},"GB2-02":{"draws":341,"losses":90,"wins":1},"GB2-03":{"draws":105,"losses":255,"wins":86},"GB2-04":{"draws":214,"losses":195,"wins":39},"GB2-05":{"draws":0,"losses":422,"wins":62},"GB2-06":{"draws":2,"losses":381,"wins":73},"GB2-08":{"draws":253,"losses":203,"wins":30}}},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1434.8483176997659,"GB2-03":1328.7157866151467,"GB2-04":1399.0812310313784,"GB2-05":1293.5097844510447,"GB2-06":1104.9706638116238,"GB2-07":906.3093753017763,"GB2-08":1261.8605519911894},"none":{"GB2-01":1049.614063447393,"GB2-02":1405.9796348756056,"GB2-03":1293.1518102653158,"GB2-04":1349.7445924671506,"GB2-05":883.6761494839096,"GB2-06":961.6703647203755,"GB2-08":1250.0589353645134}},"per_game_tracks":{"highest":{"GB2-02":44.6938117665531,"GB2-03":38.15434275171209,"GB2-04":39.82479781827604,"GB2-05":37.52692450104805,"GB2-06":26.864419686210294,"GB2-07":12.848993580715117,"GB2-08":34.423549887515314},"none":{"GB2-01":12.654316775568889,"GB2-02":40.96883545747229,"GB2-03":34.188838995414926,"GB2-04":33.71892518254897,"GB2-05":13.109431189976354,"GB2-06":17.916853681499695,"GB2-08":33.26758810382834}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":29.292104999003747,"none":23.22809867328868},"reasoning_agg":{"highest":{"max":44.6938117665531,"mean":29.292104999003747,"min":0.0},"none":{"max":40.96883545747229,"mean":23.22809867328868,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":6.0640063257150665}},{"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-pro:ffc7b0980fa12b22","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.215758025,"mean":0.16162675,"median":0.1594081875,"min":0.098579625,"recorded_attempt_count":36,"run_count":16,"total":2.5860279999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.13491350000000002,"mean":0.10247140625000001,"median":0.113468875,"min":0.061553000000000004,"recorded_attempt_count":17,"run_count":8,"total":0.8197712500000001},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":false,"evidence_basis":"Provider-reported","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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"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":18.788454924032525,"none":35.95197732477861},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":6,"failed_game_aliases":["GB2-04"],"game_attempts":{"GB2-01":{"infra_failures_excluded":1},"GB2-02":{"infra_failures_excluded":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02"],"infra_failures_excluded":2,"model_code_failure_rate":0.16666666666666666,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":5,"repaired_rate":0.8333333333333334},"baseline":{"admitted_plugins":7,"evaluated_cells":7,"game_attempts":{"GB2-01":{"infra_failures_excluded":2},"GB2-02":{"admitted":1,"infra_failures_excluded":1},"GB2-03":{"admitted":1,"infra_failures_excluded":1},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"admitted":1,"infra_failures_excluded":1},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":1,"infra_failures_excluded":1},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":9,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":7,"repaired_rate":1.0}},"headline_games_all":{"GB2-02":{"attempts":1,"playable":36.52976427820548,"score":36.52976427820548},"GB2-03":{"attempts":2,"playable":32.77781492370461,"score":32.77781492370461},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":42.41833034922002,"score":21.20916517461001},"GB2-05":{"attempts":2,"playable":20.981256594543375,"score":20.981256594543375},"GB2-06":{"attempts":2,"playable":12.476725037464998,"score":12.476725037464998},"GB2-07":{"attempts":2,"playable":44.48929774871753,"score":44.48929774871753},"GB2-08":{"attempts":2,"playable":22.603916328663153,"score":22.603916328663153}},"headline_games_tracks":{"medium":{"GB2-03":{"attempts":1,"playable":31.48401986384779,"score":31.48401986384779},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":11.495635837765146,"score":11.495635837765146},"GB2-06":{"attempts":1,"playable":15.085375035215057,"score":15.085375035215057},"GB2-07":{"attempts":1,"playable":23.516580339375412,"score":23.516580339375412},"GB2-08":{"attempts":1,"playable":12.360663543959202,"score":12.360663543959202}},"none":{"GB2-02":{"attempts":1,"playable":36.52976427820548,"score":36.52976427820548},"GB2-03":{"attempts":1,"playable":34.07160998356144,"score":34.07160998356144},"GB2-04":{"attempts":1,"playable":42.41833034922002,"score":42.41833034922002},"GB2-05":{"attempts":1,"playable":30.466877351321603,"score":30.466877351321603},"GB2-06":{"attempts":1,"playable":9.868075039714938,"score":9.868075039714938},"GB2-07":{"attempts":1,"playable":65.46201515805966,"score":65.46201515805966},"GB2-08":{"attempts":1,"playable":32.84716911336711,"score":32.84716911336711}}},"id":"nex-agi/nex-n2-pro","is_recent_addition":false,"last_measured_at":"2026-10-20T11:13:38Z","match_totals_all":{"draws":1331,"losses":3384,"wins":857},"match_totals_tracks":{"medium":{"draws":224,"losses":1833,"wins":289},"none":{"draws":1107,"losses":1551,"wins":568}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":65.46201515805966,"mean":25.804511547402857,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-02":{"draws":295,"losses":132,"wins":5},"GB2-03":{"draws":358,"losses":448,"wins":86},"GB2-04":{"draws":331,"losses":98,"wins":19},"GB2-05":{"draws":0,"losses":767,"wins":201},"GB2-06":{"draws":34,"losses":793,"wins":85},"GB2-07":{"draws":0,"losses":542,"wins":406},"GB2-08":{"draws":313,"losses":604,"wins":55}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":150,"losses":244,"wins":52},"GB2-05":{"draws":0,"losses":430,"wins":54},"GB2-06":{"draws":28,"losses":380,"wins":48},"GB2-07":{"draws":0,"losses":373,"wins":101},"GB2-08":{"draws":46,"losses":406,"wins":34}},"none":{"GB2-02":{"draws":295,"losses":132,"wins":5},"GB2-03":{"draws":208,"losses":204,"wins":34},"GB2-04":{"draws":331,"losses":98,"wins":19},"GB2-05":{"draws":0,"losses":337,"wins":147},"GB2-06":{"draws":6,"losses":413,"wins":37},"GB2-07":{"draws":0,"losses":169,"wins":305},"GB2-08":{"draws":267,"losses":198,"wins":21}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1268.1429111063744,"GB2-05":845.2424328020625,"GB2-06":910.9358737697077,"GB2-07":1101.9077473679981,"GB2-08":989.860320949793},"none":{"GB2-02":1370.8291649618752,"GB2-03":1292.0827706581179,"GB2-04":1419.385264517577,"GB2-05":1194.5609056639905,"GB2-06":800.7333978171953,"GB2-07":1653.5224396960512,"GB2-08":1245.7492209433503}},"per_game_tracks":{"medium":{"GB2-03":31.48401986384779,"GB2-05":11.495635837765146,"GB2-06":15.085375035215057,"GB2-07":23.516580339375412,"GB2-08":12.360663543959202},"none":{"GB2-02":36.52976427820548,"GB2-03":34.07160998356144,"GB2-04":42.41833034922002,"GB2-05":30.466877351321603,"GB2-06":9.868075039714938,"GB2-07":65.46201515805966,"GB2-08":32.84716911336711}},"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":15.657045770027105,"none":35.95197732477861},"reasoning_agg":{"medium":{"max":31.48401986384779,"mean":15.657045770027105,"min":0.0},"none":{"max":65.46201515805966,"mean":35.95197732477861,"min":9.868075039714938}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":20.294931554751507}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-plus:c142af8439c129ad","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500895999999994},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"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_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500895999999994},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":false,"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":44.32324762286482,"none":25.5464411477134},"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"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,"game_attempts":{"GB2-01":{"admitted":1,"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.3333333333333333,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":34.6332843350833,"score":29.809399101868983},"GB2-02":{"attempts":2,"playable":41.257798229505156,"score":41.257798229505156},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.90607078115067,"score":21.953035390575334},"GB2-05":{"attempts":2,"playable":37.85537765664469,"score":37.85537765664469},"GB2-06":{"attempts":2,"playable":40.953126911111575,"score":40.953126911111575},"GB2-07":{"attempts":2,"playable":16.53285923213105,"score":16.53285923213105},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":32.84716911336711,"score":16.423584556683554}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":49.97102773730933,"score":49.97102773730933},"GB2-02":{"attempts":1,"playable":43.64743538888916,"score":43.64743538888916},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":44.416109237384404,"score":44.416109237384404},"GB2-06":{"attempts":1,"playable":70.02034667617035,"score":70.02034667617035},"GB2-07":{"attempts":1,"playable":25.03739758406858,"score":25.03739758406858},"GB2-08":{"attempts":1,"playable":32.84716911336711,"score":32.84716911336711}},"none":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":19.295540932857275,"score":9.647770466428637},"GB2-02":{"attempts":1,"playable":38.86816107012116,"score":38.86816107012116},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.90607078115067,"score":43.90607078115067},"GB2-05":{"attempts":1,"playable":31.294646075904986,"score":31.294646075904986},"GB2-06":{"attempts":1,"playable":11.885907146052801,"score":11.885907146052801},"GB2-07":{"attempts":1,"playable":8.028320880193517,"score":8.028320880193517},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"qwen/qwen3.7-plus","is_recent_addition":false,"last_measured_at":"2026-10-20T11:23:51Z","match_totals_all":{"draws":1478,"losses":2946,"wins":1137},"match_totals_tracks":{"medium":{"draws":748,"losses":1221,"wins":831},"none":{"draws":730,"losses":1725,"wins":306}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":70.02034667617035,"mean":25.598147634815042,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":177,"losses":532,"wins":227},"GB2-02":{"draws":681,"losses":178,"wins":5},"GB2-04":{"draws":304,"losses":104,"wins":39},"GB2-05":{"draws":0,"losses":603,"wins":365},"GB2-06":{"draws":23,"losses":536,"wins":353},"GB2-07":{"draws":0,"losses":808,"wins":140},"GB2-08":{"draws":293,"losses":185,"wins":8}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":77,"losses":200,"wins":191},"GB2-02":{"draws":358,"losses":70,"wins":4},"GB2-05":{"draws":0,"losses":270,"wins":214},"GB2-06":{"draws":20,"losses":130,"wins":306},"GB2-07":{"draws":0,"losses":366,"wins":108},"GB2-08":{"draws":293,"losses":185,"wins":8}},"none":{"GB2-01":{"draws":100,"losses":332,"wins":36},"GB2-02":{"draws":323,"losses":108,"wins":1},"GB2-04":{"draws":304,"losses":104,"wins":39},"GB2-05":{"draws":0,"losses":333,"wins":151},"GB2-06":{"draws":3,"losses":406,"wins":47},"GB2-07":{"draws":0,"losses":442,"wins":32}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1482.3112478622959,"GB2-02":1426.772680863115,"GB2-05":1382.5030143173904,"GB2-06":1785.6326831080053,"GB2-07":1124.9873084407418,"GB2-08":1245.7492209433503},"none":{"GB2-01":1155.512626260828,"GB2-02":1389.4828201748783,"GB2-04":1430.9352050792938,"GB2-05":1206.71784211342,"GB2-06":846.9393967796677,"GB2-07":777.8720328202725}},"per_game_tracks":{"medium":{"GB2-01":49.97102773730933,"GB2-02":43.64743538888916,"GB2-05":44.416109237384404,"GB2-06":70.02034667617035,"GB2-07":25.03739758406858,"GB2-08":32.84716911336711},"none":{"GB2-01":19.295540932857275,"GB2-02":38.86816107012116,"GB2-04":43.90607078115067,"GB2-05":31.294646075904986,"GB2-06":11.885907146052801,"GB2-07":8.028320880193517}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":33.24243571714862,"none":17.95385955248147},"reasoning_agg":{"medium":{"max":70.02034667617035,"mean":33.24243571714862,"min":0.0},"none":{"max":43.90607078115067,"mean":17.95385955248147,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":15.288576164667145}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-0-flash:34309b55f784132e","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.00217964,"mean":0.000272455,"median":0.0,"min":0.0,"recorded_attempt_count":53,"run_count":17,"total":0.00653892},"none":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":43},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0010891599999999998,"mean":0.00013614499999999998,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":43,"run_count":17,"total":0.0032674799999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00653892,"mean":0.00653892,"median":0.00653892,"min":0.00653892,"recorded_attempt_count":1,"run_count":1,"total":0.00653892},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":52,"run_count":16,"total":0.0},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":3},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0032674799999999997,"mean":0.0032674799999999997,"median":0.0032674799999999997,"min":0.0032674799999999997,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":3,"run_count":1,"total":0.0032674799999999997},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":10,"cell_count":8,"cost_basis_counts":{"provider_reported":40},"cost_is_complete":false,"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":17,"cell_count":16,"cost_basis_counts":{"provider_reported":96},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.00217964,"mean":0.00020429999999999998,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":96,"run_count":34,"total":0.0098064},"codegen_latency_ms":{"attempt_count":96,"max_ms":410978,"mean_ms":155707.0,"min_ms":18717,"run_count":33},"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":43,"max_ms":90441,"mean_ms":48570.82352941176,"min_ms":18717,"run_count":17}},"codegen_output_tokens":{"attempt_count":96,"output_max":92074,"output_mean":32817.64705882353,"output_min":2036,"run_count":34},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":53,"output_max":92074,"output_mean":58883.76470588235,"output_min":20000,"run_count":17},"none":{"attempt_count":43,"output_max":17378,"output_mean":6751.529411764706,"output_min":2036,"run_count":17}},"display_name":"Ling 3.0 Flash","economics":{"medium":30.16423506011546,"none":31.57159249022332},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":4,"effective_max_output_tokens":[32768],"finish_reason_observations":96,"finish_reasons":["length","stop","unknown"],"indexed_attempts":98,"output_token_observations":97,"provider_post_attempt_observations":4,"provider_post_attempts":5,"reasoning_token_observations":69,"reconciliation_get_attempt_observations":4,"requested_max_output_token_observations":4,"requested_max_output_tokens":[32768],"total_output_tokens":1115800,"total_reasoning_output_tokens":656294,"total_visible_output_tokens":120852,"visible_token_observations":59},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.0-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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":6,"first_pass_admitted":1,"first_pass_rate":0.16666666666666666,"game_attempts":{"GB2-01":{"admitted":1,"infra_failures_excluded":1},"GB2-02":{"admitted":1,"infra_failures_excluded":1},"GB2-03":{"infra_failures_excluded":2},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"infra_failures_excluded":2},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":2},"GB2-08":{"infra_failures_excluded":2}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-08"],"infra_failures_excluded":10,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":5,"repaired_rate":0.8333333333333334},"baseline":{"admitted_plugins":11,"evaluated_cells":17,"failed_game_aliases":["GB2-02","GB2-04","GB2-05","GB2-07"],"first_pass_admitted":7,"first_pass_rate":0.4117647058823529,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":1,"model_code_failures":1},"GB2-05":{"model_code_failures":2},"GB2-06":{"admitted":2},"GB2-07":{"model_code_failures":2},"GB2-08":{"admitted":3}},"model_code_failure_rate":0.35294117647058826,"model_code_failures":6,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.23529411764705882}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":27.322330271614366,"score":27.322330271614366},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":38.808720882557694,"score":28.712297710688826},"GB2-03":{"attempts":2,"playable":28.507951939049818,"score":28.507951939049818},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":42.41674930875594,"score":31.277416653128796},"GB2-05":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-06":{"attempts":3,"playable":14.306502616537148,"score":14.306502616537148},"GB2-07":{"attempts":4,"failed_attempts":2,"playable":35.36858495177522,"score":17.68429247588761},"GB2-08":{"attempts":3,"playable":30.814472038046045,"score":30.814472038046045}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":18.97022361180084,"score":18.97022361180084},"GB2-02":{"attempts":1,"playable":37.23174907763992,"score":37.23174907763992},"GB2-04":{"attempts":1,"playable":40.27616799500331,"score":40.27616799500331},"GB2-06":{"attempts":1,"playable":18.97444966435799,"score":18.97444966435799},"GB2-07":{"attempts":2,"playable":35.36858495177522,"score":35.36858495177522}},"none":{"GB2-01":{"attempts":2,"playable":35.67443693142789,"score":35.67443693142789},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.38569268747547,"score":20.192846343737735},"GB2-03":{"attempts":2,"playable":28.507951939049818,"score":28.507951939049818},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":44.557330622508566,"score":22.278665311254283},"GB2-05":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-06":{"attempts":2,"playable":9.638555568716304,"score":9.638555568716304},"GB2-07":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-08":{"attempts":3,"playable":30.814472038046045,"score":30.814472038046045}}},"id":"inclusionai/ling-3.0-flash","is_recent_addition":false,"last_measured_at":"2026-10-20T11:33:02Z","match_totals_all":{"draws":2624,"losses":4283,"wins":923},"match_totals_tracks":{"medium":{"draws":741,"losses":1575,"wins":436},"none":{"draws":1883,"losses":2708,"wins":487}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":40.27616799500331,"mean":24.276300538322232,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":298,"losses":846,"wins":260},"GB2-02":{"draws":643,"losses":218,"wins":3},"GB2-03":{"draws":280,"losses":523,"wins":89},"GB2-04":{"draws":636,"losses":209,"wins":51},"GB2-06":{"draws":10,"losses":1207,"wins":151},"GB2-07":{"draws":0,"losses":635,"wins":313},"GB2-08":{"draws":757,"losses":645,"wins":56}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":117,"losses":325,"wins":26},"GB2-02":{"draws":309,"losses":122,"wins":1},"GB2-04":{"draws":312,"losses":117,"wins":19},"GB2-06":{"draws":3,"losses":376,"wins":77},"GB2-07":{"draws":0,"losses":635,"wins":313}},"none":{"GB2-01":{"draws":181,"losses":521,"wins":234},"GB2-02":{"draws":334,"losses":96,"wins":2},"GB2-03":{"draws":280,"losses":523,"wins":89},"GB2-04":{"draws":324,"losses":92,"wins":32},"GB2-06":{"draws":7,"losses":831,"wins":74},"GB2-08":{"draws":757,"losses":645,"wins":56}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1150.9730763870386,"GB2-02":1376.466880023731,"GB2-04":1402.6345039696923,"GB2-06":979.6699695452589,"GB2-07":1266.7522562094887},"none":{"GB2-01":1342.4212055687503,"GB2-02":1401.4204177465176,"GB2-03":1238.475164443902,"GB2-04":1435.976462197025,"GB2-06":667.4969414397901,"GB2-08":1223.0303418785224}},"per_game_tracks":{"medium":{"GB2-01":18.97022361180084,"GB2-02":37.23174907763992,"GB2-04":40.27616799500331,"GB2-06":18.97444966435799,"GB2-07":35.36858495177522},"none":{"GB2-01":35.67443693142789,"GB2-02":40.38569268747547,"GB2-03":28.507951939049818,"GB2-04":44.557330622508566,"GB2-06":9.638555568716304,"GB2-08":30.665587192161873}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#000000","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.16423506011546,"none":18.38836601652901},"reasoning_agg":{"medium":{"max":40.27616799500331,"mean":30.16423506011546,"min":18.97022361180084},"none":{"max":35.67443693142789,"mean":18.38836601652901,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":11.77586904358645}},{"canonical_public_row_identity":"publication-row.v1:overall:cohere-north-mini-code:305083fd896b3511","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"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":3,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":15,"run_count":8,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"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},"historical-provider-setting-baseline":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":15,"run_count":8,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":9,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":30,"run_count":16,"total":0.0},"codegen_latency_ms":{"attempt_count":30,"max_ms":905283,"mean_ms":265606.6875,"min_ms":7507,"run_count":16},"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":15,"max_ms":59126,"mean_ms":22095.0,"min_ms":7507,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":52275,"output_mean":16877.75,"output_min":1148,"run_count":16},"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":15,"output_max":7281,"output_mean":3649.625,"output_min":1148,"run_count":8}},"display_name":"North Mini Code","economics":{"medium":30.838922125340147,"none":18.142133723818105},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":15,"effective_max_output_tokens":[64000],"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":15,"provider_post_attempts":15,"reasoning_token_observations":15,"reconciliation_get_attempt_observations":15,"requested_max_output_token_observations":15,"requested_max_output_tokens":[64000],"total_output_tokens":270044,"total_visible_output_tokens":29197,"visible_token_observations":15},"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":"cohere","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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","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,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-06"],"first_pass_admitted":2,"first_pass_rate":0.25,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-02":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":21.697831096709788,"score":10.848915548354894},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":41.51674379958626,"score":20.75837189979313},"GB2-05":{"attempts":2,"playable":33.04433386804871,"score":33.04433386804871},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":18.26966871882775,"score":9.134834359413874},"GB2-07":{"attempts":2,"playable":15.882483294200469,"score":15.882483294200469},"GB2-08":{"attempts":2,"playable":30.061027991936538,"score":30.061027991936538}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":21.697831096709788,"score":21.697831096709788},"GB2-04":{"attempts":1,"playable":41.51674379958626,"score":41.51674379958626},"GB2-05":{"attempts":1,"playable":46.08921798534714,"score":46.08921798534714},"GB2-06":{"attempts":1,"playable":18.26966871882775,"score":18.26966871882775},"GB2-07":{"attempts":1,"playable":29.554496272342774,"score":29.554496272342774},"GB2-08":{"attempts":1,"playable":27.905574879227196,"score":27.905574879227196}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":19.999449750750276,"score":19.999449750750276},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":2.210470316058165,"score":2.210470316058165},"GB2-08":{"attempts":1,"playable":32.21648110464588,"score":32.21648110464588}}},"id":"cohere/north-mini-code","is_recent_addition":false,"last_measured_at":"2026-08-05T05:19:01Z","match_totals_all":{"draws":919,"losses":2700,"wins":619},"match_totals_tracks":{"medium":{"draws":636,"losses":1652,"wins":506},"none":{"draws":283,"losses":1048,"wins":113}},"model_slug":"cohere-north-mini-code","overall":{"max":46.08921798534714,"mean":14.96624587021845,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","unknown_capability_evidence","missing_generation_quality","below_generation_quality_threshold"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-03":{"draws":106,"losses":307,"wins":33},"GB2-04":{"draws":277,"losses":129,"wins":42},"GB2-05":{"draws":0,"losses":650,"wins":318},"GB2-06":{"draws":5,"losses":378,"wins":73},"GB2-07":{"draws":0,"losses":812,"wins":136},"GB2-08":{"draws":531,"losses":424,"wins":17}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":106,"losses":307,"wins":33},"GB2-04":{"draws":277,"losses":129,"wins":42},"GB2-05":{"draws":0,"losses":262,"wins":222},"GB2-06":{"draws":5,"losses":378,"wins":73},"GB2-07":{"draws":0,"losses":345,"wins":129},"GB2-08":{"draws":248,"losses":231,"wins":7}},"none":{"GB2-05":{"draws":0,"losses":388,"wins":96},"GB2-07":{"draws":0,"losses":467,"wins":7},"GB2-08":{"draws":283,"losses":193,"wins":10}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1167.9242529578655,"GB2-04":1412.3556741604834,"GB2-05":1403.4911574637956,"GB2-06":967.7231116383729,"GB2-07":1189.6517914904878,"GB2-08":1193.9707003494245},"none":{"GB2-05":1023.3129604788802,"GB2-07":484.68294534188783,"GB2-08":1239.263156904563}},"per_game_tracks":{"medium":{"GB2-03":21.697831096709788,"GB2-04":41.51674379958626,"GB2-05":46.08921798534714,"GB2-06":18.26966871882775,"GB2-07":29.554496272342774,"GB2-08":27.905574879227196},"none":{"GB2-05":19.999449750750276,"GB2-07":2.210470316058165,"GB2-08":32.21648110464588}},"provider_color":"#FF7759","provider_company":"Cohere","provider_key":"cohere","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":23.12919159400511,"none":6.80330014643179},"reasoning_agg":{"medium":{"max":46.08921798534714,"mean":23.12919159400511,"min":0.0},"none":{"max":32.21648110464588,"mean":6.80330014643179,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":16.32589144757332}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1-nano:b9eef861e1de91ea","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":5,"max":0.0034966000000000003,"mean":0.002188375,"median":0.0022738000000000003,"min":0.0011728,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"run_count":8,"token_priced_attempt_count":13,"total":0.017507}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":5,"max":0.0034966000000000003,"mean":0.002188375,"median":0.0022738000000000003,"min":0.0011728,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"run_count":8,"token_priced_attempt_count":13,"total":0.017507}},"codegen_cost_usd":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":5,"max":0.0034966000000000003,"mean":0.002188375,"median":0.0022738000000000003,"min":0.0011728,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"run_count":8,"token_priced_attempt_count":13,"total":0.017507},"codegen_latency_ms":{"attempt_count":13,"max_ms":44784,"mean_ms":22388.5,"min_ms":11128,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":13,"max_ms":44784,"mean_ms":22388.5,"min_ms":11128,"run_count":8}},"codegen_output_tokens":{"attempt_count":13,"output_max":4341,"output_mean":2556.0,"output_min":1068,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":13,"output_max":4341,"output_mean":2556.0,"output_min":1068,"run_count":8}},"display_name":"GPT-4.1 Nano","economics":{"none":31.4921900583806},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":13,"effective_max_output_tokens":[32768],"finish_reason_observations":13,"finish_reasons":["stop"],"indexed_attempts":13,"output_token_observations":13,"provider_post_attempt_observations":13,"provider_post_attempts":13,"reasoning_token_observations":13,"reconciliation_get_attempt_observations":13,"requested_max_output_token_observations":13,"requested_max_output_tokens":[32768],"total_output_tokens":20448,"total_visible_output_tokens":20448,"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":"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":32768,"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":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"headline_games_all":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":41.66821636429997,"score":41.66821636429997},"GB2-03":{"attempts":1,"playable":34.89150012934213,"score":34.89150012934213},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":17.916853681499695,"score":17.916853681499695},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":41.66821636429997,"score":41.66821636429997},"GB2-03":{"attempts":1,"playable":34.89150012934213,"score":34.89150012934213},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":17.916853681499695,"score":17.916853681499695},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"gpt-4.1-nano","is_recent_addition":false,"last_measured_at":"2026-10-12T23:41:16Z","match_totals_all":{"draws":620,"losses":634,"wins":80},"match_totals_tracks":{"none":{"draws":620,"losses":634,"wins":80}},"model_slug":"gpt-4-1-nano","overall":{"max":41.66821636429997,"mean":11.809571271892725,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","below_generation_quality_threshold"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-02":{"draws":343,"losses":86,"wins":3},"GB2-03":{"draws":271,"losses":169,"wins":6},"GB2-06":{"draws":6,"losses":379,"wins":71}},"per_game_match_totals_tracks":{"none":{"GB2-02":{"draws":343,"losses":86,"wins":3},"GB2-03":{"draws":271,"losses":169,"wins":6},"GB2-06":{"draws":6,"losses":379,"wins":71}}},"per_game_raw_elo_tracks":{"none":{"GB2-02":1411.430214719613,"GB2-03":1299.5350268823825,"GB2-06":961.6703647203755}},"per_game_tracks":{"none":{"GB2-02":41.66821636429997,"GB2-03":34.89150012934213,"GB2-06":17.916853681499695}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":11.809571271892727},"reasoning_agg":{"none":{"max":41.66821636429997,"mean":11.809571271892727,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning field omitted"},"reasoning_settings":{"baseline":"none"}}],"public_release_id":"gb2-20261020-7c5039941207","rating_method":{"bootstrap_iterations":0,"first_player_advantage":true,"method":"bradley_terry_newton","reference_field":{"manifest_sha256":"f02ffdc046ccbb060241b53df78dedf7e60ba7d8e68807f11921754cf4f0345a","population_revision":"62c0f9ac87b4c843aacf3d3e0c418e498bb133c2c43cf3ae7fd93c0d1fef2ed0","rule":"model_balanced_common_field_v1","source":"frozen_manifest","version":"v1"}},"results_cut_id":"gb2-20261020-7c5039941207","schema_version":2,"snapshot_id":"20261020_123659","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-10-20 12:36 UTC","versus_totals_all":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":27,"wins":27},"claude-fable-5":{"draws":20,"losses":95,"wins":17},"claude-fable-5-1":{"draws":5,"losses":140,"wins":3},"claude-haiku-5-5":{"draws":27,"losses":74,"wins":25},"claude-opus-4-5":{"draws":73,"losses":90,"wins":51},"claude-opus-4-8":{"draws":30,"losses":70,"wins":20},"claude-opus-5":{"draws":27,"losses":179,"wins":20},"claude-opus-5-5":{"draws":6,"losses":131,"wins":7},"claude-sonnet-5":{"draws":41,"losses":68,"wins":23},"claude-sonnet-5-5":{"draws":28,"losses":79,"wins":25},"cohere/north-mini-code":{"draws":13,"losses":14,"wins":23},"deepseek/deepseek-v4-flash":{"draws":65,"losses":62,"wins":69},"deepseek/deepseek-v4-pro":{"draws":30,"losses":60,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":54,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":60,"wins":32},"fireworks/ember-1":{"draws":40,"losses":68,"wins":24},"gemini-3.1-pro-preview":{"draws":36,"losses":58,"wins":38},"google/gemini-3.1-flash-lite":{"draws":29,"losses":19,"wins":40},"google/gemini-3.5-flash":{"draws":37,"losses":82,"wins":47},"google/gemini-3.5-flash-lite":{"draws":80,"losses":73,"wins":81},"google/gemini-3.6-flash":{"draws":67,"losses":136,"wins":51},"google/gemini-3.8-flash":{"draws":32,"losses":79,"wins":21},"google/gemma-4-31b-it":{"draws":27,"losses":24,"wins":25},"gpt-4.1":{"draws":16,"losses":17,"wins":11},"gpt-4.1-nano":{"draws":8,"losses":4,"wins":4},"gpt-5":{"draws":37,"losses":43,"wins":36},"gpt-5.4":{"draws":31,"losses":70,"wins":27},"gpt-5.4-mini":{"draws":35,"losses":25,"wins":28},"gpt-5.4-nano":{"draws":30,"losses":48,"wins":54},"gpt-5.5":{"draws":47,"losses":54,"wins":21},"gpt-5.6-luna":{"draws":43,"losses":42,"wins":47},"gpt-5.6-sol":{"draws":23,"losses":95,"wins":14},"gpt-5.6-terra":{"draws":37,"losses":65,"wins":24},"gpt-6-astra":{"draws":6,"losses":118,"wins":8},"gpt-6-luna":{"draws":39,"losses":54,"wins":39},"gpt-6-sol":{"draws":15,"losses":102,"wins":15},"gpt-6.1-sol":{"draws":10,"losses":114,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":36,"losses":24,"wins":32},"inclusionai/ling-3.0-flash":{"draws":39,"losses":16,"wins":39},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":43,"losses":41,"wins":60},"meta/muse-glimmer-30b":{"draws":46,"losses":33,"wins":37},"meta/muse-spark-1.2":{"draws":33,"losses":62,"wins":31},"meta/muse-spark-1.3":{"draws":29,"losses":81,"wins":22},"meta/muse-wonder":{"draws":30,"losses":86,"wins":16},"minimax/minimax-m3":{"draws":20,"losses":15,"wins":35},"mistralai/mistral-large-4-0":{"draws":25,"losses":33,"wins":24},"mistralai/mistral-medium-3-5":{"draws":34,"losses":18,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":15,"wins":8},"moonshotai/kimi-k3":{"draws":36,"losses":60,"wins":30},"nex-agi/nex-n2-pro":{"draws":19,"losses":11,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":47,"losses":35,"wins":34},"o3":{"draws":42,"losses":87,"wins":55},"openai/gpt-oss-120b":{"draws":40,"losses":32,"wins":42},"poolside/laguna-s-2.1":{"draws":51,"losses":39,"wins":38},"qwen/qwen3.7-max":{"draws":26,"losses":27,"wins":23},"qwen/qwen3.7-plus":{"draws":22,"losses":20,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":66,"wins":25},"qwen/qwen3.8-27b":{"draws":23,"losses":48,"wins":23},"qwen/qwen3.8-flash":{"draws":30,"losses":39,"wins":19},"qwen/qwen3.8-max":{"draws":47,"losses":52,"wins":33},"qwen/qwen3.8-max-0902":{"draws":37,"losses":74,"wins":21},"stealth/ox-alpha":{"draws":102,"losses":251,"wins":87},"stealth/space-bunny-alpha":{"draws":35,"losses":38,"wins":31},"stepfun/step-3.7-flash":{"draws":25,"losses":33,"wins":36},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":23,"losses":23,"wins":26},"tencent/hy4-preview":{"draws":41,"losses":72,"wins":15},"thinkingmachines/inkling":{"draws":61,"losses":46,"wins":71},"thinkingmachines/inkling-small":{"draws":50,"losses":30,"wins":52},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":2},"upstage/solar-mini4":{"draws":5,"losses":15,"wins":14},"x-ai/grok-4.5":{"draws":30,"losses":84,"wins":18},"x-ai/grok-4.6":{"draws":35,"losses":82,"wins":15},"x-ai/grok-4.7":{"draws":6,"losses":91,"wins":17},"x-ai/grok-build-0.1":{"draws":16,"losses":10,"wins":18},"xiaomi/mimo-v2.5":{"draws":72,"losses":52,"wins":80},"xiaomi/mimo-v2.5-pro":{"draws":25,"losses":24,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":49,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":57,"wins":18},"z-ai/glm-5.2":{"draws":96,"losses":96,"wins":72},"z-ai/glm-5.3":{"draws":25,"losses":84,"wins":17},"z-ai/glm-5.3-flash":{"draws":31,"losses":75,"wins":26},"z-ai/glm-5.3-flashx":{"draws":24,"losses":83,"wins":25}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":17,"wins":95},"claude-fable-5":{"draws":12,"losses":42,"wins":42},"claude-fable-5-1":{"draws":13,"losses":129,"wins":20},"claude-haiku-5-5":{"draws":24,"losses":42,"wins":72},"claude-opus-4-5":{"draws":38,"losses":35,"wins":161},"claude-opus-4-8":{"draws":25,"losses":35,"wins":72},"claude-opus-5":{"draws":38,"losses":144,"wins":64},"claude-opus-5-5":{"draws":12,"losses":123,"wins":21},"claude-sonnet-5":{"draws":26,"losses":25,"wins":93},"claude-sonnet-5-5":{"draws":25,"losses":57,"wins":62},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":44},"deepseek/deepseek-v4-flash":{"draws":38,"losses":14,"wins":164},"deepseek/deepseek-v4-pro":{"draws":25,"losses":28,"wins":79},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":27,"wins":86},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":36,"wins":73},"fireworks/ember-1":{"draws":29,"losses":22,"wins":93},"gemini-3.1-pro-preview":{"draws":28,"losses":29,"wins":87},"google/gemini-3.1-flash-lite":{"draws":11,"losses":3,"wins":82},"google/gemini-3.5-flash":{"draws":33,"losses":33,"wins":114},"google/gemini-3.5-flash-lite":{"draws":47,"losses":27,"wins":178},"google/gemini-3.6-flash":{"draws":48,"losses":80,"wins":148},"google/gemini-3.8-flash":{"draws":24,"losses":52,"wins":68},"google/gemma-4-31b-it":{"draws":18,"losses":8,"wins":58},"gpt-4.1":{"draws":8,"losses":12,"wins":28},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":26,"losses":21,"wins":79},"gpt-5.4":{"draws":33,"losses":42,"wins":63},"gpt-5.4-mini":{"draws":22,"losses":11,"wins":63},"gpt-5.4-nano":{"draws":19,"losses":13,"wins":112},"gpt-5.5":{"draws":30,"losses":38,"wins":64},"gpt-5.6-luna":{"draws":33,"losses":18,"wins":93},"gpt-5.6-sol":{"draws":17,"losses":59,"wins":68},"gpt-5.6-terra":{"draws":38,"losses":20,"wins":80},"gpt-6-astra":{"draws":12,"losses":106,"wins":26},"gpt-6-luna":{"draws":31,"losses":28,"wins":85},"gpt-6-sol":{"draws":19,"losses":82,"wins":43},"gpt-6.1-sol":{"draws":11,"losses":101,"wins":32},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":25,"losses":5,"wins":72},"inclusionai/ling-3.0-flash":{"draws":18,"losses":4,"wins":80},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":23,"losses":20,"wins":113},"meta/muse-glimmer-30b":{"draws":27,"losses":7,"wins":92},"meta/muse-spark-1.2":{"draws":22,"losses":31,"wins":85},"meta/muse-spark-1.3":{"draws":26,"losses":41,"wins":77},"meta/muse-wonder":{"draws":25,"losses":57,"wins":62},"minimax/minimax-m3":{"draws":19,"losses":6,"wins":53},"mistralai/mistral-large-4-0":{"draws":18,"losses":23,"wins":49},"mistralai/mistral-medium-3-5":{"draws":19,"losses":6,"wins":59},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":21},"moonshotai/kimi-k3":{"draws":26,"losses":26,"wins":86},"nex-agi/nex-n2-pro":{"draws":15,"losses":1,"wins":56},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":10,"wins":89},"o3":{"draws":20,"losses":29,"wins":149},"openai/gpt-oss-120b":{"draws":30,"losses":11,"wins":85},"poolside/laguna-s-2.1":{"draws":27,"losses":21,"wins":90},"qwen/qwen3.7-max":{"draws":15,"losses":13,"wins":56},"qwen/qwen3.7-plus":{"draws":13,"losses":8,"wins":51},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":34,"wins":74},"qwen/qwen3.8-27b":{"draws":20,"losses":16,"wins":66},"qwen/qwen3.8-flash":{"draws":24,"losses":18,"wins":54},"qwen/qwen3.8-max":{"draws":26,"losses":37,"wins":81},"qwen/qwen3.8-max-0902":{"draws":29,"losses":34,"wins":81},"stealth/ox-alpha":{"draws":86,"losses":112,"wins":276},"stealth/space-bunny-alpha":{"draws":31,"losses":15,"wins":68},"stepfun/step-3.7-flash":{"draws":15,"losses":7,"wins":80},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":22,"losses":11,"wins":45},"tencent/hy4-preview":{"draws":25,"losses":32,"wins":81},"thinkingmachines/inkling":{"draws":40,"losses":11,"wins":141},"thinkingmachines/inkling-small":{"draws":29,"losses":14,"wins":101},"unbiased/pareto-26.10-preview":{"draws":5,"losses":33,"wins":10},"upstage/solar-mini4":{"draws":4,"losses":4,"wins":28},"x-ai/grok-4.5":{"draws":21,"losses":49,"wins":74},"x-ai/grok-4.6":{"draws":33,"losses":50,"wins":61},"x-ai/grok-4.7":{"draws":7,"losses":76,"wins":43},"x-ai/grok-build-0.1":{"draws":11,"losses":6,"wins":31},"xiaomi/mimo-v2.5":{"draws":43,"losses":5,"wins":174},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":4,"wins":65},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":22,"wins":50},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":41,"wins":47},"z-ai/glm-5.2":{"draws":61,"losses":42,"wins":185},"z-ai/glm-5.3":{"draws":22,"losses":64,"wins":52},"z-ai/glm-5.3-flash":{"draws":25,"losses":45,"wins":74},"z-ai/glm-5.3-flashx":{"draws":29,"losses":42,"wins":73}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":3,"wins":140},"claude-fable-5":{"draws":13,"losses":20,"wins":129},"claude-fable-5-1":{"draws":12,"losses":60,"wins":60},"claude-haiku-5-5":{"draws":8,"losses":8,"wins":138},"claude-opus-4-5":{"draws":14,"losses":8,"wins":240},"claude-opus-4-8":{"draws":8,"losses":11,"wins":127},"claude-opus-5":{"draws":28,"losses":80,"wins":170},"claude-opus-5-5":{"draws":16,"losses":95,"wins":63},"claude-sonnet-5":{"draws":9,"losses":4,"wins":149},"claude-sonnet-5-5":{"draws":10,"losses":34,"wins":118},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":61},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":231},"deepseek/deepseek-v4-pro":{"draws":9,"losses":3,"wins":138},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":3,"wins":144},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":12,"wins":133},"fireworks/ember-1":{"draws":4,"losses":8,"wins":150},"gemini-3.1-pro-preview":{"draws":6,"losses":6,"wins":150},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":101},"google/gemini-3.5-flash":{"draws":11,"losses":8,"wins":183},"google/gemini-3.5-flash-lite":{"draws":21,"losses":2,"wins":261},"google/gemini-3.6-flash":{"draws":25,"losses":17,"wins":270},"google/gemini-3.8-flash":{"draws":8,"losses":13,"wins":141},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":89},"gpt-4.1":{"draws":3,"losses":2,"wins":49},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":20},"gpt-5":{"draws":7,"losses":1,"wins":134},"gpt-5.4":{"draws":10,"losses":16,"wins":130},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":104},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":153},"gpt-5.5":{"draws":5,"losses":18,"wins":127},"gpt-5.6-luna":{"draws":7,"losses":5,"wins":150},"gpt-5.6-sol":{"draws":12,"losses":20,"wins":130},"gpt-5.6-terra":{"draws":12,"losses":3,"wins":141},"gpt-6-astra":{"draws":13,"losses":91,"wins":58},"gpt-6-luna":{"draws":10,"losses":6,"wins":146},"gpt-6-sol":{"draws":15,"losses":37,"wins":110},"gpt-6.1-sol":{"draws":13,"losses":77,"wins":72},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":105},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":107},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":5,"losses":5,"wins":165},"meta/muse-glimmer-30b":{"draws":9,"losses":1,"wins":133},"meta/muse-spark-1.2":{"draws":8,"losses":7,"wins":141},"meta/muse-spark-1.3":{"draws":11,"losses":15,"wins":136},"meta/muse-wonder":{"draws":13,"losses":31,"wins":118},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":83},"mistralai/mistral-large-4-0":{"draws":4,"losses":6,"wins":92},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":88},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":36},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":137},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":78},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":0,"wins":129},"o3":{"draws":5,"losses":9,"wins":204},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":137},"poolside/laguna-s-2.1":{"draws":5,"losses":2,"wins":145},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":88},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":72},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":6,"wins":143},"qwen/qwen3.8-27b":{"draws":6,"losses":1,"wins":107},"qwen/qwen3.8-flash":{"draws":6,"losses":5,"wins":97},"qwen/qwen3.8-max":{"draws":8,"losses":3,"wins":151},"qwen/qwen3.8-max-0902":{"draws":5,"losses":15,"wins":142},"stealth/ox-alpha":{"draws":32,"losses":26,"wins":492},"stealth/space-bunny-alpha":{"draws":6,"losses":3,"wins":121},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":111},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":74},"tencent/hy4-preview":{"draws":9,"losses":12,"wins":135},"thinkingmachines/inkling":{"draws":9,"losses":0,"wins":209},"thinkingmachines/inkling-small":{"draws":7,"losses":0,"wins":155},"unbiased/pareto-26.10-preview":{"draws":3,"losses":29,"wins":22},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":37},"x-ai/grok-4.5":{"draws":10,"losses":11,"wins":141},"x-ai/grok-4.6":{"draws":9,"losses":21,"wins":132},"x-ai/grok-4.7":{"draws":6,"losses":39,"wins":95},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":53},"xiaomi/mimo-v2.5":{"draws":12,"losses":5,"wins":227},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":84},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":10,"wins":85},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":10,"wins":84},"z-ai/glm-5.2":{"draws":20,"losses":8,"wins":296},"z-ai/glm-5.3":{"draws":11,"losses":22,"wins":123},"z-ai/glm-5.3-flash":{"draws":8,"losses":16,"wins":138},"z-ai/glm-5.3-flashx":{"draws":15,"losses":13,"wins":134}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":25,"wins":74},"claude-fable-5":{"draws":24,"losses":72,"wins":42},"claude-fable-5-1":{"draws":8,"losses":138,"wins":8},"claude-haiku-5-5":{"draws":16,"losses":36,"wins":36},"claude-opus-4-5":{"draws":64,"losses":57,"wins":105},"claude-opus-4-8":{"draws":28,"losses":57,"wins":45},"claude-opus-5":{"draws":35,"losses":160,"wins":39},"claude-opus-5-5":{"draws":16,"losses":126,"wins":8},"claude-sonnet-5":{"draws":35,"losses":40,"wins":63},"claude-sonnet-5-5":{"draws":25,"losses":70,"wins":43},"cohere/north-mini-code":{"draws":10,"losses":9,"wins":33},"deepseek/deepseek-v4-flash":{"draws":57,"losses":30,"wins":121},"deepseek/deepseek-v4-pro":{"draws":35,"losses":41,"wins":50},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":29,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":39,"wins":56},"fireworks/ember-1":{"draws":36,"losses":38,"wins":64},"gemini-3.1-pro-preview":{"draws":32,"losses":46,"wins":60},"google/gemini-3.1-flash-lite":{"draws":22,"losses":8,"wins":66},"google/gemini-3.5-flash":{"draws":39,"losses":58,"wins":77},"google/gemini-3.5-flash-lite":{"draws":53,"losses":40,"wins":149},"google/gemini-3.6-flash":{"draws":65,"losses":99,"wins":100},"google/gemini-3.8-flash":{"draws":33,"losses":62,"wins":43},"google/gemma-4-31b-it":{"draws":23,"losses":9,"wins":50},"gpt-4.1":{"draws":15,"losses":8,"wins":23},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":9},"gpt-5":{"draws":31,"losses":27,"wins":62},"gpt-5.4":{"draws":31,"losses":50,"wins":51},"gpt-5.4-mini":{"draws":27,"losses":12,"wins":53},"gpt-5.4-nano":{"draws":27,"losses":39,"wins":76},"gpt-5.5":{"draws":46,"losses":35,"wins":45},"gpt-5.6-luna":{"draws":40,"losses":24,"wins":74},"gpt-5.6-sol":{"draws":21,"losses":76,"wins":41},"gpt-5.6-terra":{"draws":39,"losses":37,"wins":56},"gpt-6-astra":{"draws":10,"losses":121,"wins":7},"gpt-6-luna":{"draws":36,"losses":39,"wins":63},"gpt-6-sol":{"draws":27,"losses":84,"wins":27},"gpt-6.1-sol":{"draws":15,"losses":113,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":4,"wins":68},"inclusionai/ling-3.0-flash":{"draws":32,"losses":5,"wins":61},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":33,"losses":21,"wins":96},"meta/muse-glimmer-30b":{"draws":37,"losses":15,"wins":68},"meta/muse-spark-1.2":{"draws":26,"losses":41,"wins":65},"meta/muse-spark-1.3":{"draws":26,"losses":51,"wins":61},"meta/muse-wonder":{"draws":30,"losses":79,"wins":29},"minimax/minimax-m3":{"draws":8,"losses":15,"wins":53},"mistralai/mistral-large-4-0":{"draws":30,"losses":28,"wins":28},"mistralai/mistral-medium-3-5":{"draws":22,"losses":4,"wins":54},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":15,"wins":15},"moonshotai/kimi-k3":{"draws":34,"losses":40,"wins":58},"nex-agi/nex-n2-pro":{"draws":15,"losses":10,"wins":43},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":26,"wins":66},"o3":{"draws":32,"losses":61,"wins":101},"openai/gpt-oss-120b":{"draws":30,"losses":12,"wins":78},"poolside/laguna-s-2.1":{"draws":34,"losses":35,"wins":61},"qwen/qwen3.7-max":{"draws":27,"losses":20,"wins":35},"qwen/qwen3.7-plus":{"draws":14,"losses":8,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":47,"wins":55},"qwen/qwen3.8-27b":{"draws":22,"losses":29,"wins":47},"qwen/qwen3.8-flash":{"draws":28,"losses":19,"wins":45},"qwen/qwen3.8-max":{"draws":34,"losses":37,"wins":67},"qwen/qwen3.8-max-0902":{"draws":40,"losses":48,"wins":50},"stealth/ox-alpha":{"draws":96,"losses":165,"wins":173},"stealth/space-bunny-alpha":{"draws":33,"losses":23,"wins":54},"stepfun/step-3.7-flash":{"draws":15,"losses":16,"wins":67},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":4},"tencent/hy3-preview":{"draws":25,"losses":20,"wins":31},"tencent/hy4-preview":{"draws":30,"losses":54,"wins":48},"thinkingmachines/inkling":{"draws":49,"losses":23,"wins":110},"thinkingmachines/inkling-small":{"draws":33,"losses":13,"wins":92},"unbiased/pareto-26.10-preview":{"draws":2,"losses":35,"wins":9},"upstage/solar-mini4":{"draws":5,"losses":4,"wins":27},"x-ai/grok-4.5":{"draws":30,"losses":60,"wins":48},"x-ai/grok-4.6":{"draws":36,"losses":60,"wins":42},"x-ai/grok-4.7":{"draws":12,"losses":90,"wins":20},"x-ai/grok-build-0.1":{"draws":13,"losses":4,"wins":29},"xiaomi/mimo-v2.5":{"draws":56,"losses":31,"wins":133},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":18,"wins":41},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":27,"wins":38},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":43,"wins":32},"z-ai/glm-5.2":{"draws":64,"losses":64,"wins":148},"z-ai/glm-5.3":{"draws":24,"losses":76,"wins":32},"z-ai/glm-5.3-flash":{"draws":27,"losses":57,"wins":54},"z-ai/glm-5.3-flashx":{"draws":27,"losses":51,"wins":60}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":30,"wins":62},"claude-fable-5":{"draws":23,"losses":96,"wins":25},"claude-fable-5-1":{"draws":12,"losses":145,"wins":5},"claude-haiku-5-5":{"draws":40,"losses":55,"wins":43},"claude-opus-4-5":{"draws":63,"losses":52,"wins":71},"claude-opus-4-8":{"draws":37,"losses":57,"wins":38},"claude-opus-5":{"draws":41,"losses":181,"wins":24},"claude-opus-5-5":{"draws":12,"losses":136,"wins":8},"claude-sonnet-5":{"draws":50,"losses":42,"wins":52},"claude-sonnet-5-5":{"draws":30,"losses":75,"wins":39},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":42},"deepseek/deepseek-v4-flash":{"draws":62,"losses":42,"wins":112},"deepseek/deepseek-v4-pro":{"draws":34,"losses":48,"wins":50},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":46,"wins":50},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":62,"wins":44},"fireworks/ember-1":{"draws":50,"losses":55,"wins":39},"gemini-3.1-pro-preview":{"draws":36,"losses":45,"wins":63},"google/gemini-3.1-flash-lite":{"draws":22,"losses":5,"wins":69},"google/gemini-3.5-flash":{"draws":49,"losses":69,"wins":62},"google/gemini-3.5-flash-lite":{"draws":83,"losses":53,"wins":116},"google/gemini-3.6-flash":{"draws":78,"losses":120,"wins":78},"google/gemini-3.8-flash":{"draws":43,"losses":73,"wins":28},"google/gemma-4-31b-it":{"draws":28,"losses":10,"wins":46},"gpt-4.1":{"draws":20,"losses":12,"wins":16},"gpt-4.1-nano":{"draws":12,"losses":0,"wins":6},"gpt-5":{"draws":38,"losses":39,"wins":49},"gpt-5.4":{"draws":40,"losses":66,"wins":32},"gpt-5.4-mini":{"draws":39,"losses":20,"wins":37},"gpt-5.4-nano":{"draws":42,"losses":34,"wins":68},"gpt-5.5":{"draws":56,"losses":52,"wins":24},"gpt-5.6-luna":{"draws":53,"losses":32,"wins":59},"gpt-5.6-sol":{"draws":22,"losses":93,"wins":29},"gpt-5.6-terra":{"draws":54,"losses":39,"wins":45},"gpt-6-astra":{"draws":9,"losses":124,"wins":11},"gpt-6-luna":{"draws":45,"losses":47,"wins":52},"gpt-6-sol":{"draws":24,"losses":103,"wins":17},"gpt-6.1-sol":{"draws":11,"losses":121,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":43,"losses":6,"wins":53},"inclusionai/ling-3.0-flash":{"draws":37,"losses":10,"wins":55},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":42,"losses":21,"wins":93},"meta/muse-glimmer-30b":{"draws":43,"losses":18,"wins":65},"meta/muse-spark-1.2":{"draws":34,"losses":65,"wins":39},"meta/muse-spark-1.3":{"draws":28,"losses":80,"wins":36},"meta/muse-wonder":{"draws":27,"losses":87,"wins":30},"minimax/minimax-m3":{"draws":21,"losses":9,"wins":48},"mistralai/mistral-large-4-0":{"draws":30,"losses":27,"wins":33},"mistralai/mistral-medium-3-5":{"draws":26,"losses":8,"wins":50},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":8,"wins":20},"moonshotai/kimi-k3":{"draws":48,"losses":48,"wins":42},"nex-agi/nex-n2-pro":{"draws":18,"losses":9,"wins":45},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":17,"wins":64},"o3":{"draws":31,"losses":53,"wins":114},"openai/gpt-oss-120b":{"draws":40,"losses":22,"wins":64},"poolside/laguna-s-2.1":{"draws":48,"losses":22,"wins":68},"qwen/qwen3.7-max":{"draws":24,"losses":20,"wins":40},"qwen/qwen3.7-plus":{"draws":22,"losses":15,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":53,"losses":56,"wins":35},"qwen/qwen3.8-27b":{"draws":31,"losses":36,"wins":35},"qwen/qwen3.8-flash":{"draws":35,"losses":29,"wins":32},"qwen/qwen3.8-max":{"draws":41,"losses":61,"wins":42},"qwen/qwen3.8-max-0902":{"draws":36,"losses":58,"wins":50},"stealth/ox-alpha":{"draws":134,"losses":198,"wins":142},"stealth/space-bunny-alpha":{"draws":36,"losses":27,"wins":51},"stepfun/step-3.7-flash":{"draws":15,"losses":21,"wins":66},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":27,"losses":18,"wins":33},"tencent/hy4-preview":{"draws":34,"losses":61,"wins":43},"thinkingmachines/inkling":{"draws":58,"losses":33,"wins":101},"thinkingmachines/inkling-small":{"draws":49,"losses":18,"wins":77},"unbiased/pareto-26.10-preview":{"draws":1,"losses":46,"wins":1},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":26},"x-ai/grok-4.5":{"draws":43,"losses":59,"wins":42},"x-ai/grok-4.6":{"draws":36,"losses":76,"wins":32},"x-ai/grok-4.7":{"draws":12,"losses":90,"wins":24},"x-ai/grok-build-0.1":{"draws":17,"losses":5,"wins":26},"xiaomi/mimo-v2.5":{"draws":73,"losses":30,"wins":119},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":26,"wins":33},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":43,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":51,"wins":21},"z-ai/glm-5.2":{"draws":90,"losses":79,"wins":119},"z-ai/glm-5.3":{"draws":33,"losses":81,"wins":24},"z-ai/glm-5.3-flash":{"draws":33,"losses":73,"wins":38},"z-ai/glm-5.3-flashx":{"draws":37,"losses":74,"wins":33}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":20,"wins":70},"claude-fable-5":{"draws":25,"losses":72,"wins":35},"claude-fable-5-1":{"draws":8,"losses":127,"wins":11},"claude-haiku-5-5":{"draws":28,"losses":45,"wins":57},"claude-opus-4-5":{"draws":64,"losses":54,"wins":100},"claude-opus-4-8":{"draws":14,"losses":35,"wins":35},"claude-opus-5":{"draws":35,"losses":152,"wins":35},"claude-opus-5-5":{"draws":13,"losses":114,"wins":17},"claude-sonnet-5":{"draws":36,"losses":38,"wins":58},"claude-sonnet-5-5":{"draws":28,"losses":62,"wins":42},"cohere/north-mini-code":{"draws":9,"losses":3,"wins":38},"deepseek/deepseek-v4-flash":{"draws":48,"losses":27,"wins":125},"deepseek/deepseek-v4-pro":{"draws":28,"losses":36,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":38,"wins":54},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":53,"wins":47},"fireworks/ember-1":{"draws":44,"losses":37,"wins":51},"gemini-3.1-pro-preview":{"draws":35,"losses":35,"wins":62},"google/gemini-3.1-flash-lite":{"draws":20,"losses":5,"wins":71},"google/gemini-3.5-flash":{"draws":37,"losses":49,"wins":82},"google/gemini-3.5-flash-lite":{"draws":63,"losses":22,"wins":147},"google/gemini-3.6-flash":{"draws":57,"losses":101,"wins":94},"google/gemini-3.8-flash":{"draws":28,"losses":60,"wins":44},"google/gemma-4-31b-it":{"draws":23,"losses":10,"wins":47},"gpt-4.1":{"draws":14,"losses":5,"wins":25},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":7},"gpt-5":{"draws":30,"losses":30,"wins":54},"gpt-5.4":{"draws":29,"losses":54,"wins":43},"gpt-5.4-mini":{"draws":23,"losses":21,"wins":44},"gpt-5.4-nano":{"draws":25,"losses":31,"wins":84},"gpt-5.5":{"draws":38,"losses":47,"wins":35},"gpt-5.6-luna":{"draws":42,"losses":28,"wins":62},"gpt-5.6-sol":{"draws":17,"losses":72,"wins":43},"gpt-5.6-terra":{"draws":32,"losses":35,"wins":59},"gpt-6-astra":{"draws":8,"losses":113,"wins":11},"gpt-6-luna":{"draws":35,"losses":36,"wins":61},"gpt-6-sol":{"draws":20,"losses":79,"wins":33},"gpt-6.1-sol":{"draws":7,"losses":110,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":32,"losses":10,"wins":56},"inclusionai/ling-3.0-flash":{"draws":29,"losses":0,"wins":65},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":33,"losses":21,"wins":90},"meta/muse-glimmer-30b":{"draws":32,"losses":16,"wins":66},"meta/muse-spark-1.2":{"draws":29,"losses":44,"wins":53},"meta/muse-spark-1.3":{"draws":27,"losses":54,"wins":51},"meta/muse-wonder":{"draws":26,"losses":62,"wins":44},"minimax/minimax-m3":{"draws":16,"losses":10,"wins":48},"mistralai/mistral-large-4-0":{"draws":18,"losses":33,"wins":31},"mistralai/mistral-medium-3-5":{"draws":25,"losses":6,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":7,"wins":19},"moonshotai/kimi-k3":{"draws":32,"losses":43,"wins":51},"nex-agi/nex-n2-pro":{"draws":16,"losses":4,"wins":44},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":18,"wins":77},"o3":{"draws":27,"losses":55,"wins":108},"openai/gpt-oss-120b":{"draws":36,"losses":10,"wins":68},"poolside/laguna-s-2.1":{"draws":37,"losses":16,"wins":69},"qwen/qwen3.7-max":{"draws":24,"losses":21,"wins":35},"qwen/qwen3.7-plus":{"draws":16,"losses":13,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":50,"wins":44},"qwen/qwen3.8-27b":{"draws":20,"losses":31,"wins":43},"qwen/qwen3.8-flash":{"draws":31,"losses":16,"wins":41},"qwen/qwen3.8-max":{"draws":26,"losses":45,"wins":61},"qwen/qwen3.8-max-0902":{"draws":33,"losses":48,"wins":51},"stealth/ox-alpha":{"draws":85,"losses":156,"wins":153},"stealth/space-bunny-alpha":{"draws":30,"losses":24,"wins":52},"stepfun/step-3.7-flash":{"draws":16,"losses":17,"wins":61},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":6},"tencent/hy3-preview":{"draws":20,"losses":16,"wins":38},"tencent/hy4-preview":{"draws":31,"losses":50,"wins":45},"thinkingmachines/inkling":{"draws":43,"losses":21,"wins":108},"thinkingmachines/inkling-small":{"draws":40,"losses":12,"wins":80},"unbiased/pareto-26.10-preview":{"draws":2,"losses":41,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":3,"wins":27},"x-ai/grok-4.5":{"draws":35,"losses":51,"wins":46},"x-ai/grok-4.6":{"draws":32,"losses":58,"wins":42},"x-ai/grok-4.7":{"draws":16,"losses":72,"wins":30},"x-ai/grok-build-0.1":{"draws":10,"losses":6,"wins":28},"xiaomi/mimo-v2.5":{"draws":63,"losses":24,"wins":131},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":15,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":38,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":42,"wins":35},"z-ai/glm-5.2":{"draws":74,"losses":57,"wins":133},"z-ai/glm-5.3":{"draws":21,"losses":73,"wins":32},"z-ai/glm-5.3-flash":{"draws":19,"losses":60,"wins":53},"z-ai/glm-5.3-flashx":{"draws":25,"losses":48,"wins":59}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":20,"wins":179},"claude-fable-5":{"draws":38,"losses":64,"wins":144},"claude-fable-5-1":{"draws":28,"losses":170,"wins":80},"claude-haiku-5-5":{"draws":35,"losses":39,"wins":160},"claude-opus-4-5":{"draws":71,"losses":40,"wins":287},"claude-opus-4-8":{"draws":35,"losses":35,"wins":152},"claude-opus-5":{"draws":52,"losses":166,"wins":166},"claude-opus-5-5":{"draws":25,"losses":167,"wins":78},"claude-sonnet-5":{"draws":33,"losses":34,"wins":179},"claude-sonnet-5-5":{"draws":25,"losses":82,"wins":139},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":80},"deepseek/deepseek-v4-flash":{"draws":38,"losses":21,"wins":303},"deepseek/deepseek-v4-pro":{"draws":26,"losses":31,"wins":175},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":26,"wins":174},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":37,"wins":171},"fireworks/ember-1":{"draws":27,"losses":44,"wins":175},"gemini-3.1-pro-preview":{"draws":24,"losses":37,"wins":185},"google/gemini-3.1-flash-lite":{"draws":16,"losses":8,"wins":126},"google/gemini-3.5-flash":{"draws":37,"losses":30,"wins":237},"google/gemini-3.5-flash-lite":{"draws":54,"losses":30,"wins":340},"google/gemini-3.6-flash":{"draws":66,"losses":82,"wins":320},"google/gemini-3.8-flash":{"draws":28,"losses":54,"wins":164},"google/gemma-4-31b-it":{"draws":21,"losses":10,"wins":109},"gpt-4.1":{"draws":9,"losses":5,"wins":68},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":18},"gpt-5":{"draws":23,"losses":18,"wins":179},"gpt-5.4":{"draws":29,"losses":36,"wins":169},"gpt-5.4-mini":{"draws":31,"losses":12,"wins":121},"gpt-5.4-nano":{"draws":21,"losses":17,"wins":198},"gpt-5.5":{"draws":32,"losses":45,"wins":155},"gpt-5.6-luna":{"draws":26,"losses":25,"wins":195},"gpt-5.6-sol":{"draws":30,"losses":59,"wins":157},"gpt-5.6-terra":{"draws":26,"losses":21,"wins":187},"gpt-6-astra":{"draws":23,"losses":166,"wins":57},"gpt-6-luna":{"draws":47,"losses":22,"wins":177},"gpt-6-sol":{"draws":33,"losses":93,"wins":120},"gpt-6.1-sol":{"draws":32,"losses":138,"wins":76},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":2,"wins":6},"inception/mercury-2.5-preview":{"draws":31,"losses":6,"wins":129},"inclusionai/ling-3.0-flash":{"draws":26,"losses":8,"wins":132},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":12},"meituan/longcat-2.0":{"draws":28,"losses":20,"wins":208},"meta/muse-glimmer-30b":{"draws":15,"losses":23,"wins":192},"meta/muse-spark-1.2":{"draws":31,"losses":34,"wins":179},"meta/muse-spark-1.3":{"draws":33,"losses":50,"wins":163},"meta/muse-wonder":{"draws":29,"losses":76,"wins":141},"minimax/minimax-m3":{"draws":15,"losses":7,"wins":116},"mistralai/mistral-large-4-0":{"draws":24,"losses":19,"wins":119},"mistralai/mistral-medium-3-5":{"draws":22,"losses":12,"wins":110},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":58},"moonshotai/kimi-k3":{"draws":38,"losses":39,"wins":167},"nex-agi/nex-n2-pro":{"draws":3,"losses":6,"wins":107},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":6,"wins":180},"o3":{"draws":26,"losses":20,"wins":266},"openai/gpt-oss-120b":{"draws":32,"losses":11,"wins":177},"poolside/laguna-s-2.1":{"draws":24,"losses":14,"wins":210},"qwen/qwen3.7-max":{"draws":17,"losses":12,"wins":111},"qwen/qwen3.7-plus":{"draws":16,"losses":8,"wins":92},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":41,"wins":176},"qwen/qwen3.8-27b":{"draws":28,"losses":13,"wins":125},"qwen/qwen3.8-flash":{"draws":23,"losses":14,"wins":127},"qwen/qwen3.8-max":{"draws":36,"losses":30,"wins":180},"qwen/qwen3.8-max-0902":{"draws":35,"losses":42,"wins":169},"stealth/ox-alpha":{"draws":130,"losses":123,"wins":579},"stealth/space-bunny-alpha":{"draws":31,"losses":14,"wins":151},"stepfun/step-3.7-flash":{"draws":14,"losses":7,"wins":141},"stepfun/step-5-preview":{"draws":0,"losses":7,"wins":17},"tencent/hy3-preview":{"draws":25,"losses":11,"wins":106},"tencent/hy4-preview":{"draws":24,"losses":35,"wins":175},"thinkingmachines/inkling":{"draws":48,"losses":29,"wins":261},"thinkingmachines/inkling-small":{"draws":38,"losses":12,"wins":196},"unbiased/pareto-26.10-preview":{"draws":3,"losses":50,"wins":29},"upstage/solar-mini4":{"draws":7,"losses":1,"wins":40},"x-ai/grok-4.5":{"draws":35,"losses":42,"wins":169},"x-ai/grok-4.6":{"draws":37,"losses":51,"wins":157},"x-ai/grok-4.7":{"draws":22,"losses":98,"wins":100},"x-ai/grok-build-0.1":{"draws":13,"losses":4,"wins":65},"xiaomi/mimo-v2.5":{"draws":57,"losses":26,"wins":295},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":5,"wins":110},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":17,"wins":119},"xiaomi/mimo-v2.6-pro":{"draws":26,"losses":39,"wins":99},"z-ai/glm-5.2":{"draws":76,"losses":33,"wins":383},"z-ai/glm-5.3":{"draws":32,"losses":63,"wins":139},"z-ai/glm-5.3-flash":{"draws":35,"losses":47,"wins":164},"z-ai/glm-5.3-flashx":{"draws":36,"losses":44,"wins":166}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":131},"claude-fable-5":{"draws":12,"losses":21,"wins":123},"claude-fable-5-1":{"draws":16,"losses":63,"wins":95},"claude-haiku-5-5":{"draws":16,"losses":8,"wins":126},"claude-opus-4-5":{"draws":20,"losses":15,"wins":219},"claude-opus-4-8":{"draws":13,"losses":17,"wins":114},"claude-opus-5":{"draws":25,"losses":78,"wins":167},"claude-opus-5-5":{"draws":8,"losses":58,"wins":58},"claude-sonnet-5":{"draws":11,"losses":11,"wins":134},"claude-sonnet-5-5":{"draws":16,"losses":29,"wins":111},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":60},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":217},"deepseek/deepseek-v4-pro":{"draws":11,"losses":5,"wins":128},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":4,"wins":134},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":132},"fireworks/ember-1":{"draws":8,"losses":11,"wins":137},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":138},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":98},"google/gemini-3.5-flash":{"draws":12,"losses":9,"wins":175},"google/gemini-3.5-flash-lite":{"draws":17,"losses":2,"wins":253},"google/gemini-3.6-flash":{"draws":24,"losses":20,"wins":252},"google/gemini-3.8-flash":{"draws":16,"losses":20,"wins":120},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":87},"gpt-4.1":{"draws":5,"losses":1,"wins":46},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":9,"losses":5,"wins":124},"gpt-5.4":{"draws":11,"losses":11,"wins":128},"gpt-5.4-mini":{"draws":5,"losses":2,"wins":97},"gpt-5.4-nano":{"draws":7,"losses":2,"wins":151},"gpt-5.5":{"draws":15,"losses":15,"wins":114},"gpt-5.6-luna":{"draws":17,"losses":5,"wins":134},"gpt-5.6-sol":{"draws":12,"losses":22,"wins":122},"gpt-5.6-terra":{"draws":9,"losses":3,"wins":138},"gpt-6-astra":{"draws":17,"losses":74,"wins":65},"gpt-6-luna":{"draws":16,"losses":1,"wins":139},"gpt-6-sol":{"draws":14,"losses":39,"wins":103},"gpt-6.1-sol":{"draws":18,"losses":63,"wins":75},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":102},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":107},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":154},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":131},"meta/muse-spark-1.2":{"draws":12,"losses":10,"wins":128},"meta/muse-spark-1.3":{"draws":8,"losses":14,"wins":134},"meta/muse-wonder":{"draws":9,"losses":31,"wins":116},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":83},"mistralai/mistral-large-4-0":{"draws":14,"losses":5,"wins":79},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":85},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":36},"moonshotai/kimi-k3":{"draws":5,"losses":13,"wins":132},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":74},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":137},"o3":{"draws":11,"losses":3,"wins":204},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":130},"poolside/laguna-s-2.1":{"draws":10,"losses":0,"wins":144},"qwen/qwen3.7-max":{"draws":6,"losses":0,"wins":86},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":71},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":18,"wins":127},"qwen/qwen3.8-27b":{"draws":5,"losses":3,"wins":98},"qwen/qwen3.8-flash":{"draws":9,"losses":3,"wins":92},"qwen/qwen3.8-max":{"draws":13,"losses":12,"wins":131},"qwen/qwen3.8-max-0902":{"draws":16,"losses":12,"wins":128},"stealth/ox-alpha":{"draws":49,"losses":30,"wins":427},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":116},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":106},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":16},"tencent/hy3-preview":{"draws":8,"losses":0,"wins":78},"tencent/hy4-preview":{"draws":12,"losses":13,"wins":125},"thinkingmachines/inkling":{"draws":18,"losses":0,"wins":186},"thinkingmachines/inkling-small":{"draws":10,"losses":0,"wins":146},"unbiased/pareto-26.10-preview":{"draws":1,"losses":25,"wins":26},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":34},"x-ai/grok-4.5":{"draws":17,"losses":16,"wins":123},"x-ai/grok-4.6":{"draws":18,"losses":15,"wins":123},"x-ai/grok-4.7":{"draws":11,"losses":31,"wins":96},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":51},"xiaomi/mimo-v2.5":{"draws":11,"losses":4,"wins":227},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":82},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":2,"wins":87},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":14,"wins":80},"z-ai/glm-5.2":{"draws":18,"losses":11,"wins":283},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":116},"z-ai/glm-5.3-flash":{"draws":13,"losses":10,"wins":133},"z-ai/glm-5.3-flashx":{"draws":15,"losses":10,"wins":131}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":23,"wins":68},"claude-fable-5":{"draws":26,"losses":93,"wins":25},"claude-fable-5-1":{"draws":9,"losses":149,"wins":4},"claude-haiku-5-5":{"draws":35,"losses":63,"wins":40},"claude-opus-4-5":{"draws":77,"losses":81,"wins":76},"claude-opus-4-8":{"draws":36,"losses":58,"wins":38},"claude-opus-5":{"draws":33,"losses":179,"wins":34},"claude-opus-5-5":{"draws":11,"losses":134,"wins":11},"claude-sonnet-5":{"draws":28,"losses":34,"wins":34},"claude-sonnet-5-5":{"draws":25,"losses":83,"wins":36},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":37},"deepseek/deepseek-v4-flash":{"draws":63,"losses":40,"wins":113},"deepseek/deepseek-v4-pro":{"draws":40,"losses":46,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":42,"losses":48,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":44,"losses":53,"wins":47},"fireworks/ember-1":{"draws":44,"losses":60,"wins":40},"gemini-3.1-pro-preview":{"draws":43,"losses":50,"wins":51},"google/gemini-3.1-flash-lite":{"draws":29,"losses":7,"wins":60},"google/gemini-3.5-flash":{"draws":49,"losses":74,"wins":57},"google/gemini-3.5-flash-lite":{"draws":73,"losses":52,"wins":127},"google/gemini-3.6-flash":{"draws":64,"losses":123,"wins":89},"google/gemini-3.8-flash":{"draws":34,"losses":76,"wins":34},"google/gemma-4-31b-it":{"draws":27,"losses":12,"wins":45},"gpt-4.1":{"draws":17,"losses":14,"wins":17},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":39,"losses":35,"wins":52},"gpt-5.4":{"draws":37,"losses":70,"wins":31},"gpt-5.4-mini":{"draws":38,"losses":28,"wins":30},"gpt-5.4-nano":{"draws":34,"losses":39,"wins":71},"gpt-5.5":{"draws":51,"losses":57,"wins":24},"gpt-5.6-luna":{"draws":45,"losses":38,"wins":61},"gpt-5.6-sol":{"draws":20,"losses":105,"wins":19},"gpt-5.6-terra":{"draws":53,"losses":44,"wins":41},"gpt-6-astra":{"draws":6,"losses":130,"wins":8},"gpt-6-luna":{"draws":38,"losses":56,"wins":50},"gpt-6-sol":{"draws":24,"losses":101,"wins":19},"gpt-6.1-sol":{"draws":6,"losses":129,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":38,"losses":10,"wins":54},"inclusionai/ling-3.0-flash":{"draws":36,"losses":8,"wins":58},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":47,"losses":27,"wins":82},"meta/muse-glimmer-30b":{"draws":43,"losses":19,"wins":64},"meta/muse-spark-1.2":{"draws":40,"losses":62,"wins":36},"meta/muse-spark-1.3":{"draws":38,"losses":72,"wins":34},"meta/muse-wonder":{"draws":31,"losses":85,"wins":28},"minimax/minimax-m3":{"draws":21,"losses":15,"wins":42},"mistralai/mistral-large-4-0":{"draws":27,"losses":24,"wins":39},"mistralai/mistral-medium-3-5":{"draws":32,"losses":10,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":17,"wins":9},"moonshotai/kimi-k3":{"draws":41,"losses":59,"wins":38},"nex-agi/nex-n2-pro":{"draws":24,"losses":10,"wins":38},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":29,"wins":52},"o3":{"draws":29,"losses":82,"wins":87},"openai/gpt-oss-120b":{"draws":38,"losses":17,"wins":71},"poolside/laguna-s-2.1":{"draws":43,"losses":26,"wins":69},"qwen/qwen3.7-max":{"draws":27,"losses":17,"wins":40},"qwen/qwen3.7-plus":{"draws":20,"losses":17,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":62,"wins":37},"qwen/qwen3.8-27b":{"draws":26,"losses":38,"wins":38},"qwen/qwen3.8-flash":{"draws":32,"losses":31,"wins":33},"qwen/qwen3.8-max":{"draws":46,"losses":54,"wins":44},"qwen/qwen3.8-max-0902":{"draws":42,"losses":66,"wins":36},"stealth/ox-alpha":{"draws":109,"losses":232,"wins":133},"stealth/space-bunny-alpha":{"draws":30,"losses":37,"wins":47},"stepfun/step-3.7-flash":{"draws":24,"losses":28,"wins":50},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":25,"losses":22,"wins":31},"tencent/hy4-preview":{"draws":40,"losses":64,"wins":34},"thinkingmachines/inkling":{"draws":62,"losses":28,"wins":102},"thinkingmachines/inkling-small":{"draws":47,"losses":24,"wins":73},"unbiased/pareto-26.10-preview":{"draws":0,"losses":48,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":8,"wins":22},"x-ai/grok-4.5":{"draws":39,"losses":71,"wins":34},"x-ai/grok-4.6":{"draws":39,"losses":73,"wins":32},"x-ai/grok-4.7":{"draws":12,"losses":90,"wins":24},"x-ai/grok-build-0.1":{"draws":19,"losses":3,"wins":26},"xiaomi/mimo-v2.5":{"draws":80,"losses":39,"wins":103},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":21,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":50,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":57,"wins":24},"z-ai/glm-5.2":{"draws":79,"losses":88,"wins":121},"z-ai/glm-5.3":{"draws":28,"losses":91,"wins":19},"z-ai/glm-5.3-flash":{"draws":26,"losses":77,"wins":41},"z-ai/glm-5.3-flashx":{"draws":39,"losses":72,"wins":33}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":25,"wins":79},"claude-fable-5":{"draws":25,"losses":62,"wins":57},"claude-fable-5-1":{"draws":10,"losses":118,"wins":34},"claude-haiku-5-5":{"draws":25,"losses":43,"wins":70},"claude-opus-4-5":{"draws":48,"losses":57,"wins":129},"claude-opus-4-8":{"draws":28,"losses":42,"wins":62},"claude-opus-5":{"draws":25,"losses":139,"wins":82},"claude-opus-5-5":{"draws":16,"losses":111,"wins":29},"claude-sonnet-5":{"draws":25,"losses":36,"wins":83},"claude-sonnet-5-5":{"draws":10,"losses":43,"wins":43},"cohere/north-mini-code":{"draws":6,"losses":8,"wins":40},"deepseek/deepseek-v4-flash":{"draws":46,"losses":31,"wins":139},"deepseek/deepseek-v4-pro":{"draws":32,"losses":33,"wins":67},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":33,"wins":77},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":40,"wins":72},"fireworks/ember-1":{"draws":30,"losses":42,"wins":72},"gemini-3.1-pro-preview":{"draws":22,"losses":39,"wins":83},"google/gemini-3.1-flash-lite":{"draws":15,"losses":12,"wins":69},"google/gemini-3.5-flash":{"draws":29,"losses":47,"wins":104},"google/gemini-3.5-flash-lite":{"draws":49,"losses":40,"wins":163},"google/gemini-3.6-flash":{"draws":54,"losses":96,"wins":126},"google/gemini-3.8-flash":{"draws":20,"losses":56,"wins":68},"google/gemma-4-31b-it":{"draws":14,"losses":16,"wins":54},"gpt-4.1":{"draws":10,"losses":8,"wins":30},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":9},"gpt-5":{"draws":27,"losses":26,"wins":73},"gpt-5.4":{"draws":37,"losses":42,"wins":59},"gpt-5.4-mini":{"draws":18,"losses":18,"wins":60},"gpt-5.4-nano":{"draws":21,"losses":18,"wins":105},"gpt-5.5":{"draws":29,"losses":42,"wins":61},"gpt-5.6-luna":{"draws":33,"losses":28,"wins":83},"gpt-5.6-sol":{"draws":15,"losses":70,"wins":59},"gpt-5.6-terra":{"draws":34,"losses":30,"wins":74},"gpt-6-astra":{"draws":13,"losses":105,"wins":26},"gpt-6-luna":{"draws":32,"losses":44,"wins":68},"gpt-6-sol":{"draws":15,"losses":81,"wins":48},"gpt-6.1-sol":{"draws":5,"losses":103,"wins":36},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":25,"losses":12,"wins":65},"inclusionai/ling-3.0-flash":{"draws":26,"losses":7,"wins":69},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":21,"losses":31,"wins":104},"meta/muse-glimmer-30b":{"draws":21,"losses":21,"wins":84},"meta/muse-spark-1.2":{"draws":27,"losses":41,"wins":70},"meta/muse-spark-1.3":{"draws":22,"losses":54,"wins":68},"meta/muse-wonder":{"draws":21,"losses":54,"wins":69},"minimax/minimax-m3":{"draws":13,"losses":13,"wins":52},"mistralai/mistral-large-4-0":{"draws":23,"losses":24,"wins":43},"mistralai/mistral-medium-3-5":{"draws":19,"losses":8,"wins":57},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":21},"moonshotai/kimi-k3":{"draws":28,"losses":47,"wins":63},"nex-agi/nex-n2-pro":{"draws":15,"losses":10,"wins":47},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":22,"wins":82},"o3":{"draws":17,"losses":45,"wins":136},"openai/gpt-oss-120b":{"draws":26,"losses":18,"wins":82},"poolside/laguna-s-2.1":{"draws":25,"losses":26,"wins":87},"qwen/qwen3.7-max":{"draws":18,"losses":22,"wins":44},"qwen/qwen3.7-plus":{"draws":17,"losses":12,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":49,"wins":63},"qwen/qwen3.8-27b":{"draws":17,"losses":25,"wins":60},"qwen/qwen3.8-flash":{"draws":17,"losses":30,"wins":49},"qwen/qwen3.8-max":{"draws":23,"losses":41,"wins":80},"qwen/qwen3.8-max-0902":{"draws":26,"losses":51,"wins":67},"stealth/ox-alpha":{"draws":85,"losses":164,"wins":225},"stealth/space-bunny-alpha":{"draws":22,"losses":24,"wins":68},"stepfun/step-3.7-flash":{"draws":11,"losses":26,"wins":65},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":19,"losses":10,"wins":49},"tencent/hy4-preview":{"draws":24,"losses":47,"wins":67},"thinkingmachines/inkling":{"draws":41,"losses":41,"wins":110},"thinkingmachines/inkling-small":{"draws":32,"losses":21,"wins":91},"unbiased/pareto-26.10-preview":{"draws":2,"losses":37,"wins":9},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":26},"x-ai/grok-4.5":{"draws":31,"losses":50,"wins":63},"x-ai/grok-4.6":{"draws":24,"losses":59,"wins":61},"x-ai/grok-4.7":{"draws":15,"losses":64,"wins":47},"x-ai/grok-build-0.1":{"draws":9,"losses":6,"wins":33},"xiaomi/mimo-v2.5":{"draws":49,"losses":27,"wins":146},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":13,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":34,"wins":46},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":37,"wins":46},"z-ai/glm-5.2":{"draws":55,"losses":66,"wins":167},"z-ai/glm-5.3":{"draws":24,"losses":62,"wins":52},"z-ai/glm-5.3-flash":{"draws":20,"losses":55,"wins":69},"z-ai/glm-5.3-flashx":{"draws":25,"losses":54,"wins":65}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":23,"wins":14},"claude-fable-5":{"draws":8,"losses":44,"wins":2},"claude-fable-5-1":{"draws":0,"losses":61,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":33,"wins":9},"claude-opus-4-5":{"draws":11,"losses":70,"wins":7},"claude-opus-4-8":{"draws":9,"losses":38,"wins":3},"claude-opus-5":{"draws":6,"losses":80,"wins":4},"claude-opus-5-5":{"draws":2,"losses":60,"wins":0},"claude-sonnet-5":{"draws":9,"losses":37,"wins":8},"claude-sonnet-5-5":{"draws":6,"losses":40,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":25,"losses":34,"wins":21},"deepseek/deepseek-v4-pro":{"draws":11,"losses":29,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":32,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":32,"wins":7},"fireworks/ember-1":{"draws":11,"losses":34,"wins":9},"gemini-3.1-pro-preview":{"draws":12,"losses":28,"wins":14},"google/gemini-3.1-flash-lite":{"draws":11,"losses":15,"wins":16},"google/gemini-3.5-flash":{"draws":18,"losses":43,"wins":9},"google/gemini-3.5-flash-lite":{"draws":34,"losses":34,"wins":30},"google/gemini-3.6-flash":{"draws":22,"losses":73,"wins":9},"google/gemini-3.8-flash":{"draws":10,"losses":38,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":18,"wins":6},"gpt-4.1":{"draws":6,"losses":9,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":11,"losses":33,"wins":6},"gpt-5.4":{"draws":11,"losses":35,"wins":8},"gpt-5.4-mini":{"draws":11,"losses":17,"wins":8},"gpt-5.4-nano":{"draws":11,"losses":36,"wins":9},"gpt-5.5":{"draws":15,"losses":33,"wins":4},"gpt-5.6-luna":{"draws":18,"losses":27,"wins":9},"gpt-5.6-sol":{"draws":3,"losses":46,"wins":5},"gpt-5.6-terra":{"draws":12,"losses":32,"wins":6},"gpt-6-astra":{"draws":2,"losses":52,"wins":0},"gpt-6-luna":{"draws":14,"losses":32,"wins":8},"gpt-6-sol":{"draws":6,"losses":47,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":52,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":13,"wins":13},"inclusionai/ling-3.0-flash":{"draws":16,"losses":12,"wins":6},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":37,"wins":13},"meta/muse-glimmer-30b":{"draws":22,"losses":17,"wins":11},"meta/muse-spark-1.2":{"draws":3,"losses":40,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":47,"wins":2},"meta/muse-wonder":{"draws":3,"losses":47,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":16,"wins":9},"mistralai/mistral-large-4-0":{"draws":9,"losses":20,"wins":5},"mistralai/mistral-medium-3-5":{"draws":11,"losses":11,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":9,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":33,"wins":8},"nex-agi/nex-n2-pro":{"draws":10,"losses":14,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":16,"wins":11},"o3":{"draws":17,"losses":58,"wins":13},"openai/gpt-oss-120b":{"draws":17,"losses":18,"wins":15},"poolside/laguna-s-2.1":{"draws":21,"losses":18,"wins":15},"qwen/qwen3.7-max":{"draws":11,"losses":17,"wins":4},"qwen/qwen3.7-plus":{"draws":6,"losses":12,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":43,"wins":3},"qwen/qwen3.8-27b":{"draws":5,"losses":25,"wins":4},"qwen/qwen3.8-flash":{"draws":11,"losses":18,"wins":7},"qwen/qwen3.8-max":{"draws":10,"losses":40,"wins":4},"qwen/qwen3.8-max-0902":{"draws":10,"losses":39,"wins":5},"stealth/ox-alpha":{"draws":30,"losses":127,"wins":21},"stealth/space-bunny-alpha":{"draws":11,"losses":28,"wins":7},"stepfun/step-3.7-flash":{"draws":10,"losses":25,"wins":5},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":13,"wins":6},"tencent/hy4-preview":{"draws":15,"losses":36,"wins":3},"thinkingmachines/inkling":{"draws":18,"losses":33,"wins":21},"thinkingmachines/inkling-small":{"draws":19,"losses":22,"wins":13},"unbiased/pareto-26.10-preview":{"draws":0,"losses":18,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":8,"losses":43,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":41,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":45,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":9,"wins":3},"xiaomi/mimo-v2.5":{"draws":25,"losses":31,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":15,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":22,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":31,"wins":5},"z-ai/glm-5.2":{"draws":36,"losses":58,"wins":14},"z-ai/glm-5.3":{"draws":8,"losses":44,"wins":2},"z-ai/glm-5.3-flash":{"draws":10,"losses":36,"wins":8},"z-ai/glm-5.3-flashx":{"draws":11,"losses":39,"wins":4}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":65,"losses":69,"wins":62},"claude-fable-5":{"draws":38,"losses":164,"wins":14},"claude-fable-5-1":{"draws":8,"losses":231,"wins":1},"claude-haiku-5-5":{"draws":57,"losses":121,"wins":30},"claude-opus-4-5":{"draws":106,"losses":182,"wins":64},"claude-opus-4-8":{"draws":48,"losses":125,"wins":27},"claude-opus-5":{"draws":38,"losses":303,"wins":21},"claude-opus-5-5":{"draws":13,"losses":217,"wins":6},"claude-sonnet-5":{"draws":63,"losses":113,"wins":40},"claude-sonnet-5-5":{"draws":46,"losses":139,"wins":31},"cohere/north-mini-code":{"draws":25,"losses":21,"wins":34},"deepseek/deepseek-v4-flash":{"draws":86,"losses":87,"wins":87},"deepseek/deepseek-v4-pro":{"draws":55,"losses":100,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":61,"losses":89,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":75,"losses":116,"wins":25},"fireworks/ember-1":{"draws":70,"losses":109,"wins":37},"gemini-3.1-pro-preview":{"draws":69,"losses":95,"wins":52},"google/gemini-3.1-flash-lite":{"draws":46,"losses":26,"wins":74},"google/gemini-3.5-flash":{"draws":69,"losses":143,"wins":58},"google/gemini-3.5-flash-lite":{"draws":121,"losses":133,"wins":120},"google/gemini-3.6-flash":{"draws":100,"losses":256,"wins":56},"google/gemini-3.8-flash":{"draws":44,"losses":148,"wins":24},"google/gemma-4-31b-it":{"draws":58,"losses":22,"wins":46},"gpt-4.1":{"draws":24,"losses":32,"wins":16},"gpt-4.1-nano":{"draws":17,"losses":3,"wins":8},"gpt-5":{"draws":62,"losses":88,"wins":40},"gpt-5.4":{"draws":57,"losses":121,"wins":28},"gpt-5.4-mini":{"draws":58,"losses":50,"wins":36},"gpt-5.4-nano":{"draws":56,"losses":89,"wins":81},"gpt-5.5":{"draws":73,"losses":102,"wins":21},"gpt-5.6-luna":{"draws":83,"losses":83,"wins":50},"gpt-5.6-sol":{"draws":29,"losses":166,"wins":21},"gpt-5.6-terra":{"draws":69,"losses":107,"wins":32},"gpt-6-astra":{"draws":11,"losses":200,"wins":5},"gpt-6-luna":{"draws":66,"losses":105,"wins":45},"gpt-6-sol":{"draws":32,"losses":168,"wins":16},"gpt-6.1-sol":{"draws":14,"losses":197,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":66,"losses":25,"wins":61},"inclusionai/ling-3.0-flash":{"draws":67,"losses":38,"wins":53},"inclusionai/ling-3.1-flash":{"draws":8,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":68,"losses":76,"wins":90},"meta/muse-glimmer-30b":{"draws":88,"losses":43,"wins":55},"meta/muse-spark-1.2":{"draws":52,"losses":120,"wins":34},"meta/muse-spark-1.3":{"draws":41,"losses":151,"wins":24},"meta/muse-wonder":{"draws":37,"losses":148,"wins":31},"minimax/minimax-m3":{"draws":38,"losses":41,"wins":41},"mistralai/mistral-large-4-0":{"draws":45,"losses":69,"wins":20},"mistralai/mistral-medium-3-5":{"draws":55,"losses":28,"wins":41},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":30,"wins":11},"moonshotai/kimi-k3":{"draws":61,"losses":103,"wins":42},"nex-agi/nex-n2-pro":{"draws":27,"losses":29,"wins":52},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":76,"losses":52,"wins":66},"o3":{"draws":51,"losses":178,"wins":77},"openai/gpt-oss-120b":{"draws":74,"losses":62,"wins":54},"poolside/laguna-s-2.1":{"draws":83,"losses":69,"wins":58},"qwen/qwen3.7-max":{"draws":56,"losses":48,"wins":26},"qwen/qwen3.7-plus":{"draws":35,"losses":35,"wins":42},"qwen/qwen3.8-2.4t-a95b":{"draws":71,"losses":113,"wins":32},"qwen/qwen3.8-27b":{"draws":39,"losses":80,"wins":35},"qwen/qwen3.8-flash":{"draws":51,"losses":64,"wins":29},"qwen/qwen3.8-max":{"draws":70,"losses":110,"wins":36},"qwen/qwen3.8-max-0902":{"draws":64,"losses":123,"wins":29},"stealth/ox-alpha":{"draws":175,"losses":398,"wins":123},"stealth/space-bunny-alpha":{"draws":60,"losses":70,"wins":38},"stepfun/step-3.7-flash":{"draws":41,"losses":57,"wins":60},"stepfun/step-5-preview":{"draws":6,"losses":10,"wins":4},"tencent/hy3-preview":{"draws":35,"losses":42,"wins":39},"tencent/hy4-preview":{"draws":56,"losses":116,"wins":34},"thinkingmachines/inkling":{"draws":94,"losses":98,"wins":92},"thinkingmachines/inkling-small":{"draws":93,"losses":47,"wins":76},"unbiased/pareto-26.10-preview":{"draws":0,"losses":71,"wins":1},"upstage/solar-mini4":{"draws":10,"losses":16,"wins":28},"x-ai/grok-4.5":{"draws":40,"losses":142,"wins":34},"x-ai/grok-4.6":{"draws":58,"losses":137,"wins":21},"x-ai/grok-4.7":{"draws":20,"losses":157,"wins":15},"x-ai/grok-build-0.1":{"draws":27,"losses":18,"wins":27},"xiaomi/mimo-v2.5":{"draws":121,"losses":104,"wins":109},"xiaomi/mimo-v2.5-pro":{"draws":38,"losses":44,"wins":38},"xiaomi/mimo-v2.6-flash":{"draws":33,"losses":79,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":95,"wins":24},"z-ai/glm-5.2":{"draws":156,"losses":177,"wins":99},"z-ai/glm-5.3":{"draws":46,"losses":148,"wins":12},"z-ai/glm-5.3-flash":{"draws":58,"losses":119,"wins":39},"z-ai/glm-5.3-flashx":{"draws":58,"losses":126,"wins":32}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":32,"wins":60},"claude-fable-5":{"draws":25,"losses":79,"wins":28},"claude-fable-5-1":{"draws":9,"losses":138,"wins":3},"claude-haiku-5-5":{"draws":35,"losses":50,"wins":41},"claude-opus-4-5":{"draws":59,"losses":79,"wins":76},"claude-opus-4-8":{"draws":28,"losses":56,"wins":36},"claude-opus-5":{"draws":26,"losses":175,"wins":31},"claude-opus-5-5":{"draws":11,"losses":128,"wins":5},"claude-sonnet-5":{"draws":40,"losses":46,"wins":46},"claude-sonnet-5-5":{"draws":32,"losses":67,"wins":33},"cohere/north-mini-code":{"draws":11,"losses":12,"wins":29},"deepseek/deepseek-v4-flash":{"draws":55,"losses":41,"wins":100},"deepseek/deepseek-v4-pro":{"draws":20,"losses":30,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":45,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":55,"wins":42},"fireworks/ember-1":{"draws":39,"losses":53,"wins":40},"gemini-3.1-pro-preview":{"draws":33,"losses":46,"wins":53},"google/gemini-3.1-flash-lite":{"draws":25,"losses":7,"wins":56},"google/gemini-3.5-flash":{"draws":41,"losses":70,"wins":55},"google/gemini-3.5-flash-lite":{"draws":63,"losses":62,"wins":107},"google/gemini-3.6-flash":{"draws":65,"losses":105,"wins":84},"google/gemini-3.8-flash":{"draws":27,"losses":72,"wins":33},"google/gemma-4-31b-it":{"draws":28,"losses":14,"wins":34},"gpt-4.1":{"draws":13,"losses":9,"wins":22},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":4},"gpt-5":{"draws":32,"losses":33,"wins":53},"gpt-5.4":{"draws":29,"losses":61,"wins":38},"gpt-5.4-mini":{"draws":32,"losses":23,"wins":33},"gpt-5.4-nano":{"draws":18,"losses":45,"wins":67},"gpt-5.5":{"draws":36,"losses":60,"wins":28},"gpt-5.6-luna":{"draws":43,"losses":37,"wins":52},"gpt-5.6-sol":{"draws":16,"losses":87,"wins":29},"gpt-5.6-terra":{"draws":40,"losses":42,"wins":44},"gpt-6-astra":{"draws":12,"losses":112,"wins":8},"gpt-6-luna":{"draws":34,"losses":56,"wins":42},"gpt-6-sol":{"draws":12,"losses":98,"wins":22},"gpt-6.1-sol":{"draws":8,"losses":116,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":37,"losses":8,"wins":45},"inclusionai/ling-3.0-flash":{"draws":34,"losses":14,"wins":44},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":33,"losses":26,"wins":85},"meta/muse-glimmer-30b":{"draws":37,"losses":27,"wins":56},"meta/muse-spark-1.2":{"draws":24,"losses":59,"wins":45},"meta/muse-spark-1.3":{"draws":20,"losses":76,"wins":36},"meta/muse-wonder":{"draws":23,"losses":79,"wins":30},"minimax/minimax-m3":{"draws":13,"losses":11,"wins":48},"mistralai/mistral-large-4-0":{"draws":26,"losses":32,"wins":26},"mistralai/mistral-medium-3-5":{"draws":20,"losses":9,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":12,"wins":14},"moonshotai/kimi-k3":{"draws":28,"losses":56,"wins":44},"nex-agi/nex-n2-pro":{"draws":17,"losses":12,"wins":37},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":19,"wins":55},"o3":{"draws":24,"losses":69,"wins":91},"openai/gpt-oss-120b":{"draws":35,"losses":26,"wins":55},"poolside/laguna-s-2.1":{"draws":36,"losses":43,"wins":49},"qwen/qwen3.7-max":{"draws":25,"losses":15,"wins":36},"qwen/qwen3.7-plus":{"draws":16,"losses":13,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":60,"wins":36},"qwen/qwen3.8-27b":{"draws":26,"losses":35,"wins":31},"qwen/qwen3.8-flash":{"draws":22,"losses":36,"wins":30},"qwen/qwen3.8-max":{"draws":37,"losses":59,"wins":36},"qwen/qwen3.8-max-0902":{"draws":34,"losses":64,"wins":34},"stealth/ox-alpha":{"draws":107,"losses":203,"wins":132},"stealth/space-bunny-alpha":{"draws":31,"losses":28,"wins":47},"stepfun/step-3.7-flash":{"draws":19,"losses":21,"wins":54},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":24,"losses":18,"wins":30},"tencent/hy4-preview":{"draws":32,"losses":60,"wins":36},"thinkingmachines/inkling":{"draws":56,"losses":31,"wins":93},"thinkingmachines/inkling-small":{"draws":47,"losses":17,"wins":68},"unbiased/pareto-26.10-preview":{"draws":0,"losses":43,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":22},"x-ai/grok-4.5":{"draws":34,"losses":59,"wins":39},"x-ai/grok-4.6":{"draws":33,"losses":73,"wins":26},"x-ai/grok-4.7":{"draws":10,"losses":85,"wins":21},"x-ai/grok-build-0.1":{"draws":18,"losses":9,"wins":17},"xiaomi/mimo-v2.5":{"draws":72,"losses":33,"wins":97},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":22,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":36,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":47,"wins":25},"z-ai/glm-5.2":{"draws":90,"losses":75,"wins":99},"z-ai/glm-5.3":{"draws":23,"losses":78,"wins":25},"z-ai/glm-5.3-flash":{"draws":24,"losses":72,"wins":36},"z-ai/glm-5.3-flashx":{"draws":32,"losses":60,"wins":40}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":34,"wins":54},"claude-fable-5":{"draws":19,"losses":86,"wins":27},"claude-fable-5-1":{"draws":3,"losses":144,"wins":3},"claude-haiku-5-5":{"draws":34,"losses":63,"wins":29},"claude-opus-4-5":{"draws":61,"losses":77,"wins":76},"claude-opus-4-8":{"draws":28,"losses":54,"wins":38},"claude-opus-5":{"draws":22,"losses":174,"wins":26},"claude-opus-5-5":{"draws":6,"losses":134,"wins":4},"claude-sonnet-5":{"draws":42,"losses":42,"wins":48},"claude-sonnet-5-5":{"draws":22,"losses":77,"wins":33},"cohere/north-mini-code":{"draws":12,"losses":6,"wins":32},"deepseek/deepseek-v4-flash":{"draws":61,"losses":48,"wins":89},"deepseek/deepseek-v4-pro":{"draws":36,"losses":41,"wins":45},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":34,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":63,"wins":32},"fireworks/ember-1":{"draws":34,"losses":56,"wins":42},"gemini-3.1-pro-preview":{"draws":35,"losses":43,"wins":54},"google/gemini-3.1-flash-lite":{"draws":23,"losses":12,"wins":53},"google/gemini-3.5-flash":{"draws":43,"losses":72,"wins":51},"google/gemini-3.5-flash-lite":{"draws":73,"losses":48,"wins":111},"google/gemini-3.6-flash":{"draws":60,"losses":117,"wins":77},"google/gemini-3.8-flash":{"draws":33,"losses":64,"wins":35},"google/gemma-4-31b-it":{"draws":31,"losses":7,"wins":38},"gpt-4.1":{"draws":15,"losses":9,"wins":20},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":8},"gpt-5":{"draws":29,"losses":42,"wins":45},"gpt-5.4":{"draws":27,"losses":64,"wins":37},"gpt-5.4-mini":{"draws":32,"losses":18,"wins":38},"gpt-5.4-nano":{"draws":26,"losses":41,"wins":63},"gpt-5.5":{"draws":35,"losses":51,"wins":36},"gpt-5.6-luna":{"draws":43,"losses":38,"wins":51},"gpt-5.6-sol":{"draws":18,"losses":87,"wins":27},"gpt-5.6-terra":{"draws":39,"losses":49,"wins":40},"gpt-6-astra":{"draws":8,"losses":123,"wins":1},"gpt-6-luna":{"draws":36,"losses":50,"wins":46},"gpt-6-sol":{"draws":13,"losses":99,"wins":20},"gpt-6.1-sol":{"draws":8,"losses":121,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":34,"losses":11,"wins":47},"inclusionai/ling-3.0-flash":{"draws":38,"losses":16,"wins":44},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":45,"losses":30,"wins":69},"meta/muse-glimmer-30b":{"draws":40,"losses":18,"wins":58},"meta/muse-spark-1.2":{"draws":30,"losses":58,"wins":38},"meta/muse-spark-1.3":{"draws":27,"losses":66,"wins":39},"meta/muse-wonder":{"draws":27,"losses":78,"wins":27},"minimax/minimax-m3":{"draws":17,"losses":13,"wins":40},"mistralai/mistral-large-4-0":{"draws":30,"losses":24,"wins":28},"mistralai/mistral-medium-3-5":{"draws":23,"losses":12,"wins":41},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":11,"wins":14},"moonshotai/kimi-k3":{"draws":38,"losses":39,"wins":49},"nex-agi/nex-n2-pro":{"draws":14,"losses":10,"wins":42},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":44,"losses":15,"wins":55},"o3":{"draws":31,"losses":54,"wins":99},"openai/gpt-oss-120b":{"draws":36,"losses":27,"wins":51},"poolside/laguna-s-2.1":{"draws":39,"losses":32,"wins":53},"qwen/qwen3.7-max":{"draws":27,"losses":17,"wins":32},"qwen/qwen3.7-plus":{"draws":17,"losses":20,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":56,"wins":43},"qwen/qwen3.8-27b":{"draws":26,"losses":37,"wins":31},"qwen/qwen3.8-flash":{"draws":27,"losses":30,"wins":31},"qwen/qwen3.8-max":{"draws":41,"losses":52,"wins":39},"qwen/qwen3.8-max-0902":{"draws":39,"losses":54,"wins":39},"stealth/ox-alpha":{"draws":109,"losses":180,"wins":151},"stealth/space-bunny-alpha":{"draws":31,"losses":27,"wins":46},"stepfun/step-3.7-flash":{"draws":24,"losses":20,"wins":52},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":26,"losses":19,"wins":25},"tencent/hy4-preview":{"draws":29,"losses":56,"wins":43},"thinkingmachines/inkling":{"draws":58,"losses":43,"wins":75},"thinkingmachines/inkling-small":{"draws":42,"losses":24,"wins":66},"unbiased/pareto-26.10-preview":{"draws":1,"losses":41,"wins":2},"upstage/solar-mini4":{"draws":5,"losses":3,"wins":26},"x-ai/grok-4.5":{"draws":29,"losses":60,"wins":43},"x-ai/grok-4.6":{"draws":42,"losses":62,"wins":28},"x-ai/grok-4.7":{"draws":9,"losses":83,"wins":22},"x-ai/grok-build-0.1":{"draws":19,"losses":4,"wins":21},"xiaomi/mimo-v2.5":{"draws":71,"losses":35,"wins":96},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":20,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":31,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":48,"wins":27},"z-ai/glm-5.2":{"draws":89,"losses":82,"wins":93},"z-ai/glm-5.3":{"draws":25,"losses":77,"wins":24},"z-ai/glm-5.3-flash":{"draws":22,"losses":71,"wins":39},"z-ai/glm-5.3-flashx":{"draws":30,"losses":63,"wins":39}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":32,"wins":60},"claude-fable-5":{"draws":35,"losses":73,"wins":36},"claude-fable-5-1":{"draws":17,"losses":133,"wins":12},"claude-haiku-5-5":{"draws":43,"losses":56,"wins":39},"claude-opus-4-5":{"draws":62,"losses":68,"wins":104},"claude-opus-4-8":{"draws":32,"losses":47,"wins":53},"claude-opus-5":{"draws":38,"losses":171,"wins":37},"claude-opus-5-5":{"draws":9,"losses":132,"wins":15},"claude-sonnet-5":{"draws":44,"losses":47,"wins":53},"claude-sonnet-5-5":{"draws":32,"losses":72,"wins":40},"cohere/north-mini-code":{"draws":15,"losses":7,"wins":32},"deepseek/deepseek-v4-flash":{"draws":75,"losses":25,"wins":116},"deepseek/deepseek-v4-pro":{"draws":35,"losses":42,"wins":55},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":32,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":37,"wins":37},"fireworks/ember-1":{"draws":46,"losses":53,"wins":45},"gemini-3.1-pro-preview":{"draws":41,"losses":51,"wins":52},"google/gemini-3.1-flash-lite":{"draws":35,"losses":9,"wins":52},"google/gemini-3.5-flash":{"draws":52,"losses":54,"wins":74},"google/gemini-3.5-flash-lite":{"draws":83,"losses":49,"wins":120},"google/gemini-3.6-flash":{"draws":76,"losses":110,"wins":90},"google/gemini-3.8-flash":{"draws":37,"losses":61,"wins":46},"google/gemma-4-31b-it":{"draws":34,"losses":12,"wins":38},"gpt-4.1":{"draws":13,"losses":11,"wins":24},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":9},"gpt-5":{"draws":43,"losses":28,"wins":55},"gpt-5.4":{"draws":42,"losses":53,"wins":43},"gpt-5.4-mini":{"draws":37,"losses":20,"wins":39},"gpt-5.4-nano":{"draws":37,"losses":35,"wins":72},"gpt-5.5":{"draws":45,"losses":42,"wins":45},"gpt-5.6-luna":{"draws":54,"losses":26,"wins":64},"gpt-5.6-sol":{"draws":26,"losses":75,"wins":43},"gpt-5.6-terra":{"draws":55,"losses":34,"wins":49},"gpt-6-astra":{"draws":16,"losses":122,"wins":6},"gpt-6-luna":{"draws":44,"losses":40,"wins":60},"gpt-6-sol":{"draws":26,"losses":86,"wins":32},"gpt-6.1-sol":{"draws":14,"losses":115,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":45,"losses":9,"wins":48},"inclusionai/ling-3.0-flash":{"draws":44,"losses":9,"wins":49},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":37,"losses":34,"wins":85},"meta/muse-glimmer-30b":{"draws":52,"losses":14,"wins":60},"meta/muse-spark-1.2":{"draws":35,"losses":50,"wins":53},"meta/muse-spark-1.3":{"draws":30,"losses":61,"wins":53},"meta/muse-wonder":{"draws":37,"losses":71,"wins":36},"minimax/minimax-m3":{"draws":19,"losses":17,"wins":42},"mistralai/mistral-large-4-0":{"draws":33,"losses":26,"wins":31},"mistralai/mistral-medium-3-5":{"draws":30,"losses":9,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":11,"wins":15},"moonshotai/kimi-k3":{"draws":40,"losses":41,"wins":57},"nex-agi/nex-n2-pro":{"draws":16,"losses":6,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":22,"wins":58},"o3":{"draws":45,"losses":62,"wins":91},"openai/gpt-oss-120b":{"draws":40,"losses":24,"wins":62},"poolside/laguna-s-2.1":{"draws":59,"losses":22,"wins":57},"qwen/qwen3.7-max":{"draws":30,"losses":19,"wins":35},"qwen/qwen3.7-plus":{"draws":25,"losses":7,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":50,"wins":57},"qwen/qwen3.8-27b":{"draws":24,"losses":29,"wins":49},"qwen/qwen3.8-flash":{"draws":36,"losses":19,"wins":41},"qwen/qwen3.8-max":{"draws":41,"losses":48,"wins":55},"qwen/qwen3.8-max-0902":{"draws":49,"losses":44,"wins":51},"stealth/ox-alpha":{"draws":110,"losses":181,"wins":182},"stealth/space-bunny-alpha":{"draws":36,"losses":25,"wins":53},"stepfun/step-3.7-flash":{"draws":26,"losses":16,"wins":60},"stepfun/step-5-preview":{"draws":4,"losses":7,"wins":1},"tencent/hy3-preview":{"draws":26,"losses":15,"wins":37},"tencent/hy4-preview":{"draws":41,"losses":56,"wins":41},"thinkingmachines/inkling":{"draws":63,"losses":30,"wins":99},"thinkingmachines/inkling-small":{"draws":46,"losses":25,"wins":73},"unbiased/pareto-26.10-preview":{"draws":2,"losses":43,"wins":3},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":26},"x-ai/grok-4.5":{"draws":31,"losses":65,"wins":48},"x-ai/grok-4.6":{"draws":40,"losses":61,"wins":43},"x-ai/grok-4.7":{"draws":11,"losses":83,"wins":32},"x-ai/grok-build-0.1":{"draws":16,"losses":5,"wins":27},"xiaomi/mimo-v2.5":{"draws":76,"losses":28,"wins":118},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":20,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":32,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":23,"losses":43,"wins":30},"z-ai/glm-5.2":{"draws":103,"losses":63,"wins":122},"z-ai/glm-5.3":{"draws":28,"losses":83,"wins":27},"z-ai/glm-5.3-flash":{"draws":32,"losses":59,"wins":53},"z-ai/glm-5.3-flashx":{"draws":40,"losses":61,"wins":43}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":24,"wins":68},"claude-fable-5":{"draws":29,"losses":93,"wins":22},"claude-fable-5-1":{"draws":4,"losses":150,"wins":8},"claude-haiku-5-5":{"draws":36,"losses":64,"wins":38},"claude-opus-4-5":{"draws":81,"losses":63,"wins":90},"claude-opus-4-8":{"draws":44,"losses":51,"wins":37},"claude-opus-5":{"draws":27,"losses":175,"wins":44},"claude-opus-5-5":{"draws":8,"losses":137,"wins":11},"claude-sonnet-5":{"draws":44,"losses":40,"wins":60},"claude-sonnet-5-5":{"draws":30,"losses":72,"wins":42},"cohere/north-mini-code":{"draws":11,"losses":9,"wins":34},"deepseek/deepseek-v4-flash":{"draws":70,"losses":37,"wins":109},"deepseek/deepseek-v4-pro":{"draws":39,"losses":40,"wins":53},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":42,"wins":56},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":45,"wins":53},"fireworks/ember-1":{"draws":28,"losses":34,"wins":34},"gemini-3.1-pro-preview":{"draws":40,"losses":40,"wins":64},"google/gemini-3.1-flash-lite":{"draws":24,"losses":4,"wins":68},"google/gemini-3.5-flash":{"draws":51,"losses":61,"wins":68},"google/gemini-3.5-flash-lite":{"draws":95,"losses":44,"wins":113},"google/gemini-3.6-flash":{"draws":79,"losses":96,"wins":101},"google/gemini-3.8-flash":{"draws":35,"losses":61,"wins":48},"google/gemma-4-31b-it":{"draws":31,"losses":12,"wins":41},"gpt-4.1":{"draws":14,"losses":15,"wins":19},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":8},"gpt-5":{"draws":36,"losses":30,"wins":60},"gpt-5.4":{"draws":40,"losses":60,"wins":38},"gpt-5.4-mini":{"draws":36,"losses":15,"wins":45},"gpt-5.4-nano":{"draws":35,"losses":31,"wins":78},"gpt-5.5":{"draws":42,"losses":49,"wins":41},"gpt-5.6-luna":{"draws":50,"losses":40,"wins":54},"gpt-5.6-sol":{"draws":23,"losses":83,"wins":38},"gpt-5.6-terra":{"draws":44,"losses":36,"wins":58},"gpt-6-astra":{"draws":10,"losses":128,"wins":6},"gpt-6-luna":{"draws":39,"losses":41,"wins":64},"gpt-6-sol":{"draws":21,"losses":100,"wins":23},"gpt-6.1-sol":{"draws":9,"losses":118,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":44,"losses":6,"wins":52},"inclusionai/ling-3.0-flash":{"draws":44,"losses":4,"wins":54},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":48,"losses":20,"wins":88},"meta/muse-glimmer-30b":{"draws":44,"losses":15,"wins":67},"meta/muse-spark-1.2":{"draws":37,"losses":48,"wins":53},"meta/muse-spark-1.3":{"draws":39,"losses":63,"wins":42},"meta/muse-wonder":{"draws":38,"losses":76,"wins":30},"minimax/minimax-m3":{"draws":19,"losses":5,"wins":54},"mistralai/mistral-large-4-0":{"draws":26,"losses":33,"wins":31},"mistralai/mistral-medium-3-5":{"draws":27,"losses":6,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":11,"wins":14},"moonshotai/kimi-k3":{"draws":45,"losses":37,"wins":56},"nex-agi/nex-n2-pro":{"draws":19,"losses":9,"wins":44},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":18,"wins":59},"o3":{"draws":40,"losses":48,"wins":110},"openai/gpt-oss-120b":{"draws":48,"losses":14,"wins":64},"poolside/laguna-s-2.1":{"draws":52,"losses":22,"wins":64},"qwen/qwen3.7-max":{"draws":26,"losses":19,"wins":39},"qwen/qwen3.7-plus":{"draws":23,"losses":11,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":50,"losses":47,"wins":47},"qwen/qwen3.8-27b":{"draws":29,"losses":38,"wins":35},"qwen/qwen3.8-flash":{"draws":34,"losses":29,"wins":33},"qwen/qwen3.8-max":{"draws":44,"losses":42,"wins":58},"qwen/qwen3.8-max-0902":{"draws":44,"losses":58,"wins":42},"stealth/ox-alpha":{"draws":124,"losses":179,"wins":171},"stealth/space-bunny-alpha":{"draws":36,"losses":23,"wins":55},"stepfun/step-3.7-flash":{"draws":23,"losses":18,"wins":61},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":5},"tencent/hy3-preview":{"draws":30,"losses":12,"wins":36},"tencent/hy4-preview":{"draws":42,"losses":54,"wins":42},"thinkingmachines/inkling":{"draws":60,"losses":25,"wins":107},"thinkingmachines/inkling-small":{"draws":50,"losses":17,"wins":77},"unbiased/pareto-26.10-preview":{"draws":1,"losses":46,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":8,"wins":23},"x-ai/grok-4.5":{"draws":33,"losses":71,"wins":40},"x-ai/grok-4.6":{"draws":40,"losses":61,"wins":43},"x-ai/grok-4.7":{"draws":11,"losses":88,"wins":27},"x-ai/grok-build-0.1":{"draws":18,"losses":6,"wins":24},"xiaomi/mimo-v2.5":{"draws":83,"losses":27,"wins":112},"xiaomi/mimo-v2.5-pro":{"draws":25,"losses":18,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":36,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":45,"wins":30},"z-ai/glm-5.2":{"draws":94,"losses":66,"wins":128},"z-ai/glm-5.3":{"draws":26,"losses":85,"wins":27},"z-ai/glm-5.3-flash":{"draws":31,"losses":67,"wins":46},"z-ai/glm-5.3-flashx":{"draws":35,"losses":59,"wins":50}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":38,"wins":58},"claude-fable-5":{"draws":28,"losses":87,"wins":29},"claude-fable-5-1":{"draws":6,"losses":150,"wins":6},"claude-haiku-5-5":{"draws":32,"losses":60,"wins":46},"claude-opus-4-5":{"draws":61,"losses":98,"wins":75},"claude-opus-4-8":{"draws":35,"losses":62,"wins":35},"claude-opus-5":{"draws":24,"losses":185,"wins":37},"claude-opus-5-5":{"draws":8,"losses":138,"wins":10},"claude-sonnet-5":{"draws":43,"losses":51,"wins":50},"claude-sonnet-5-5":{"draws":22,"losses":83,"wins":39},"cohere/north-mini-code":{"draws":12,"losses":14,"wins":28},"deepseek/deepseek-v4-flash":{"draws":69,"losses":52,"wins":95},"deepseek/deepseek-v4-pro":{"draws":33,"losses":53,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":54,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":52,"wins":51},"fireworks/ember-1":{"draws":40,"losses":64,"wins":40},"gemini-3.1-pro-preview":{"draws":26,"losses":35,"wins":35},"google/gemini-3.1-flash-lite":{"draws":22,"losses":21,"wins":53},"google/gemini-3.5-flash":{"draws":42,"losses":79,"wins":59},"google/gemini-3.5-flash-lite":{"draws":81,"losses":65,"wins":106},"google/gemini-3.6-flash":{"draws":63,"losses":123,"wins":90},"google/gemini-3.8-flash":{"draws":28,"losses":82,"wins":34},"google/gemma-4-31b-it":{"draws":30,"losses":15,"wins":39},"gpt-4.1":{"draws":15,"losses":15,"wins":18},"gpt-4.1-nano":{"draws":11,"losses":3,"wins":4},"gpt-5":{"draws":40,"losses":35,"wins":51},"gpt-5.4":{"draws":30,"losses":66,"wins":42},"gpt-5.4-mini":{"draws":38,"losses":25,"wins":33},"gpt-5.4-nano":{"draws":36,"losses":40,"wins":68},"gpt-5.5":{"draws":38,"losses":62,"wins":32},"gpt-5.6-luna":{"draws":42,"losses":47,"wins":55},"gpt-5.6-sol":{"draws":18,"losses":95,"wins":31},"gpt-5.6-terra":{"draws":47,"losses":44,"wins":47},"gpt-6-astra":{"draws":10,"losses":130,"wins":4},"gpt-6-luna":{"draws":36,"losses":46,"wins":62},"gpt-6-sol":{"draws":18,"losses":100,"wins":26},"gpt-6.1-sol":{"draws":8,"losses":126,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":40,"losses":22,"wins":40},"inclusionai/ling-3.0-flash":{"draws":39,"losses":10,"wins":53},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":37,"losses":44,"wins":75},"meta/muse-glimmer-30b":{"draws":49,"losses":15,"wins":62},"meta/muse-spark-1.2":{"draws":33,"losses":57,"wins":48},"meta/muse-spark-1.3":{"draws":26,"losses":79,"wins":39},"meta/muse-wonder":{"draws":26,"losses":94,"wins":24},"minimax/minimax-m3":{"draws":19,"losses":22,"wins":37},"mistralai/mistral-large-4-0":{"draws":21,"losses":35,"wins":34},"mistralai/mistral-medium-3-5":{"draws":32,"losses":10,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":11,"wins":17},"moonshotai/kimi-k3":{"draws":36,"losses":62,"wins":40},"nex-agi/nex-n2-pro":{"draws":21,"losses":11,"wins":40},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":28,"wins":50},"o3":{"draws":33,"losses":90,"wins":75},"openai/gpt-oss-120b":{"draws":42,"losses":29,"wins":55},"poolside/laguna-s-2.1":{"draws":47,"losses":32,"wins":59},"qwen/qwen3.7-max":{"draws":26,"losses":29,"wins":29},"qwen/qwen3.7-plus":{"draws":23,"losses":14,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":62,"wins":46},"qwen/qwen3.8-27b":{"draws":23,"losses":47,"wins":32},"qwen/qwen3.8-flash":{"draws":36,"losses":30,"wins":30},"qwen/qwen3.8-max":{"draws":43,"losses":55,"wins":46},"qwen/qwen3.8-max-0902":{"draws":39,"losses":68,"wins":37},"stealth/ox-alpha":{"draws":106,"losses":223,"wins":145},"stealth/space-bunny-alpha":{"draws":36,"losses":34,"wins":44},"stepfun/step-3.7-flash":{"draws":25,"losses":32,"wins":45},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":22,"losses":22,"wins":34},"tencent/hy4-preview":{"draws":33,"losses":65,"wins":40},"thinkingmachines/inkling":{"draws":57,"losses":48,"wins":87},"thinkingmachines/inkling-small":{"draws":45,"losses":29,"wins":70},"unbiased/pareto-26.10-preview":{"draws":1,"losses":46,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":13,"wins":18},"x-ai/grok-4.5":{"draws":31,"losses":73,"wins":40},"x-ai/grok-4.6":{"draws":40,"losses":76,"wins":28},"x-ai/grok-4.7":{"draws":14,"losses":89,"wins":23},"x-ai/grok-build-0.1":{"draws":17,"losses":12,"wins":19},"xiaomi/mimo-v2.5":{"draws":73,"losses":49,"wins":100},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":24,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":42,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":56,"wins":24},"z-ai/glm-5.2":{"draws":85,"losses":94,"wins":109},"z-ai/glm-5.3":{"draws":25,"losses":82,"wins":31},"z-ai/glm-5.3-flash":{"draws":36,"losses":66,"wins":42},"z-ai/glm-5.3-flashx":{"draws":35,"losses":74,"wins":35}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":40,"wins":19},"claude-fable-5":{"draws":11,"losses":82,"wins":3},"claude-fable-5-1":{"draws":5,"losses":101,"wins":0},"claude-haiku-5-5":{"draws":22,"losses":66,"wins":8},"claude-opus-4-5":{"draws":38,"losses":115,"wins":7},"claude-opus-4-8":{"draws":20,"losses":71,"wins":5},"claude-opus-5":{"draws":16,"losses":126,"wins":8},"claude-opus-5-5":{"draws":6,"losses":98,"wins":0},"claude-sonnet-5":{"draws":29,"losses":60,"wins":7},"claude-sonnet-5-5":{"draws":15,"losses":69,"wins":12},"cohere/north-mini-code":{"draws":11,"losses":16,"wins":15},"deepseek/deepseek-v4-flash":{"draws":46,"losses":74,"wins":26},"deepseek/deepseek-v4-pro":{"draws":25,"losses":56,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":53,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":52,"wins":9},"fireworks/ember-1":{"draws":24,"losses":68,"wins":4},"gemini-3.1-pro-preview":{"draws":22,"losses":53,"wins":21},"google/gemini-3.1-flash-lite":{"draws":4,"losses":22,"wins":22},"google/gemini-3.5-flash":{"draws":32,"losses":81,"wins":13},"google/gemini-3.5-flash-lite":{"draws":49,"losses":91,"wins":34},"google/gemini-3.6-flash":{"draws":41,"losses":131,"wins":14},"google/gemini-3.8-flash":{"draws":25,"losses":69,"wins":2},"google/gemma-4-31b-it":{"draws":19,"losses":26,"wins":15},"gpt-4.1":{"draws":11,"losses":17,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":5},"gpt-5":{"draws":25,"losses":56,"wins":3},"gpt-5.4":{"draws":19,"losses":67,"wins":8},"gpt-5.4-mini":{"draws":21,"losses":37,"wins":6},"gpt-5.4-nano":{"draws":24,"losses":62,"wins":22},"gpt-5.5":{"draws":25,"losses":57,"wins":6},"gpt-5.6-luna":{"draws":26,"losses":50,"wins":20},"gpt-5.6-sol":{"draws":8,"losses":83,"wins":5},"gpt-5.6-terra":{"draws":28,"losses":55,"wins":7},"gpt-6-astra":{"draws":2,"losses":94,"wins":0},"gpt-6-luna":{"draws":26,"losses":59,"wins":11},"gpt-6-sol":{"draws":13,"losses":82,"wins":1},"gpt-6.1-sol":{"draws":4,"losses":92,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":27,"losses":28,"wins":17},"inclusionai/ling-3.0-flash":{"draws":25,"losses":22,"wins":19},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":60,"wins":27},"meta/muse-glimmer-30b":{"draws":33,"losses":30,"wins":19},"meta/muse-spark-1.2":{"draws":21,"losses":60,"wins":9},"meta/muse-spark-1.3":{"draws":16,"losses":75,"wins":5},"meta/muse-wonder":{"draws":9,"losses":84,"wins":3},"minimax/minimax-m3":{"draws":13,"losses":25,"wins":16},"mistralai/mistral-large-4-0":{"draws":17,"losses":39,"wins":2},"mistralai/mistral-medium-3-5":{"draws":14,"losses":24,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":20,"wins":2},"moonshotai/kimi-k3":{"draws":23,"losses":56,"wins":11},"nex-agi/nex-n2-pro":{"draws":10,"losses":26,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":42,"wins":22},"o3":{"draws":23,"losses":123,"wins":12},"openai/gpt-oss-120b":{"draws":24,"losses":40,"wins":18},"poolside/laguna-s-2.1":{"draws":25,"losses":45,"wins":16},"qwen/qwen3.7-max":{"draws":19,"losses":34,"wins":7},"qwen/qwen3.7-plus":{"draws":13,"losses":30,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":68,"wins":3},"qwen/qwen3.8-27b":{"draws":14,"losses":45,"wins":11},"qwen/qwen3.8-flash":{"draws":21,"losses":33,"wins":10},"qwen/qwen3.8-max":{"draws":29,"losses":66,"wins":1},"qwen/qwen3.8-max-0902":{"draws":28,"losses":66,"wins":2},"stealth/ox-alpha":{"draws":52,"losses":191,"wins":29},"stealth/space-bunny-alpha":{"draws":21,"losses":47,"wins":12},"stepfun/step-3.7-flash":{"draws":15,"losses":49,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":17,"losses":24,"wins":11},"tencent/hy4-preview":{"draws":23,"losses":68,"wins":3},"thinkingmachines/inkling":{"draws":34,"losses":58,"wins":34},"thinkingmachines/inkling-small":{"draws":34,"losses":33,"wins":29},"unbiased/pareto-26.10-preview":{"draws":1,"losses":31,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":19,"wins":7},"x-ai/grok-4.5":{"draws":19,"losses":74,"wins":3},"x-ai/grok-4.6":{"draws":18,"losses":72,"wins":6},"x-ai/grok-4.7":{"draws":6,"losses":79,"wins":1},"x-ai/grok-build-0.1":{"draws":10,"losses":18,"wins":4},"xiaomi/mimo-v2.5":{"draws":56,"losses":70,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":45,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":44,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":50,"wins":5},"z-ai/glm-5.2":{"draws":42,"losses":126,"wins":24},"z-ai/glm-5.3":{"draws":15,"losses":76,"wins":1},"z-ai/glm-5.3-flash":{"draws":21,"losses":63,"wins":12},"z-ai/glm-5.3-flashx":{"draws":25,"losses":64,"wins":7}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":37,"losses":47,"wins":82},"claude-fable-5":{"draws":33,"losses":114,"wins":33},"claude-fable-5-1":{"draws":11,"losses":183,"wins":8},"claude-haiku-5-5":{"draws":39,"losses":77,"wins":58},"claude-opus-4-5":{"draws":86,"losses":98,"wins":110},"claude-opus-4-8":{"draws":37,"losses":82,"wins":49},"claude-opus-5":{"draws":37,"losses":237,"wins":30},"claude-opus-5-5":{"draws":12,"losses":175,"wins":9},"claude-sonnet-5":{"draws":49,"losses":57,"wins":74},"claude-sonnet-5-5":{"draws":29,"losses":104,"wins":47},"cohere/north-mini-code":{"draws":18,"losses":9,"wins":43},"deepseek/deepseek-v4-flash":{"draws":69,"losses":58,"wins":143},"deepseek/deepseek-v4-pro":{"draws":41,"losses":55,"wins":70},"deepseek/deepseek-v4-pro-0813":{"draws":43,"losses":51,"wins":72},"deepseek/deepseek-v4.1-flash":{"draws":52,"losses":74,"wins":54},"fireworks/ember-1":{"draws":51,"losses":68,"wins":61},"gemini-3.1-pro-preview":{"draws":42,"losses":59,"wins":79},"google/gemini-3.1-flash-lite":{"draws":32,"losses":13,"wins":81},"google/gemini-3.5-flash":{"draws":36,"losses":66,"wins":66},"google/gemini-3.5-flash-lite":{"draws":79,"losses":81,"wins":158},"google/gemini-3.6-flash":{"draws":79,"losses":137,"wins":130},"google/gemini-3.8-flash":{"draws":38,"losses":98,"wins":44},"google/gemma-4-31b-it":{"draws":31,"losses":22,"wins":53},"gpt-4.1":{"draws":14,"losses":17,"wins":29},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":11},"gpt-5":{"draws":40,"losses":50,"wins":68},"gpt-5.4":{"draws":29,"losses":96,"wins":49},"gpt-5.4-mini":{"draws":41,"losses":29,"wins":50},"gpt-5.4-nano":{"draws":34,"losses":48,"wins":102},"gpt-5.5":{"draws":50,"losses":68,"wins":48},"gpt-5.6-luna":{"draws":50,"losses":49,"wins":81},"gpt-5.6-sol":{"draws":19,"losses":120,"wins":41},"gpt-5.6-terra":{"draws":57,"losses":63,"wins":52},"gpt-6-astra":{"draws":11,"losses":162,"wins":7},"gpt-6-luna":{"draws":50,"losses":60,"wins":70},"gpt-6-sol":{"draws":28,"losses":126,"wins":26},"gpt-6.1-sol":{"draws":11,"losses":151,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":47,"losses":16,"wins":65},"inclusionai/ling-3.0-flash":{"draws":39,"losses":12,"wins":77},"inclusionai/ling-3.1-flash":{"draws":5,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":39,"losses":36,"wins":123},"meta/muse-glimmer-30b":{"draws":52,"losses":25,"wins":81},"meta/muse-spark-1.2":{"draws":35,"losses":79,"wins":58},"meta/muse-spark-1.3":{"draws":33,"losses":99,"wins":48},"meta/muse-wonder":{"draws":30,"losses":121,"wins":29},"minimax/minimax-m3":{"draws":23,"losses":23,"wins":52},"mistralai/mistral-large-4-0":{"draws":38,"losses":39,"wins":35},"mistralai/mistral-medium-3-5":{"draws":31,"losses":15,"wins":58},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":16,"wins":19},"moonshotai/kimi-k3":{"draws":53,"losses":60,"wins":59},"nex-agi/nex-n2-pro":{"draws":24,"losses":17,"wins":49},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":33,"wins":79},"o3":{"draws":42,"losses":84,"wins":132},"openai/gpt-oss-120b":{"draws":45,"losses":34,"wins":77},"poolside/laguna-s-2.1":{"draws":43,"losses":34,"wins":93},"qwen/qwen3.7-max":{"draws":32,"losses":33,"wins":41},"qwen/qwen3.7-plus":{"draws":22,"losses":19,"wins":51},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":76,"wins":56},"qwen/qwen3.8-27b":{"draws":22,"losses":49,"wins":57},"qwen/qwen3.8-flash":{"draws":37,"losses":35,"wins":48},"qwen/qwen3.8-max":{"draws":57,"losses":61,"wins":62},"qwen/qwen3.8-max-0902":{"draws":49,"losses":84,"wins":47},"stealth/ox-alpha":{"draws":115,"losses":259,"wins":202},"stealth/space-bunny-alpha":{"draws":43,"losses":33,"wins":68},"stepfun/step-3.7-flash":{"draws":24,"losses":26,"wins":80},"stepfun/step-5-preview":{"draws":6,"losses":10,"wins":0},"tencent/hy3-preview":{"draws":28,"losses":29,"wins":41},"tencent/hy4-preview":{"draws":39,"losses":89,"wins":46},"thinkingmachines/inkling":{"draws":57,"losses":48,"wins":135},"thinkingmachines/inkling-small":{"draws":53,"losses":30,"wins":97},"unbiased/pareto-26.10-preview":{"draws":0,"losses":55,"wins":5},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":29},"x-ai/grok-4.5":{"draws":31,"losses":86,"wins":63},"x-ai/grok-4.6":{"draws":48,"losses":97,"wins":35},"x-ai/grok-4.7":{"draws":15,"losses":119,"wins":24},"x-ai/grok-build-0.1":{"draws":19,"losses":10,"wins":31},"xiaomi/mimo-v2.5":{"draws":83,"losses":51,"wins":150},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":30,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":52,"wins":40},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":62,"wins":37},"z-ai/glm-5.2":{"draws":100,"losses":109,"wins":151},"z-ai/glm-5.3":{"draws":30,"losses":106,"wins":36},"z-ai/glm-5.3-flash":{"draws":28,"losses":92,"wins":60},"z-ai/glm-5.3-flashx":{"draws":47,"losses":89,"wins":44}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":80,"losses":81,"wins":73},"claude-fable-5":{"draws":47,"losses":178,"wins":27},"claude-fable-5-1":{"draws":21,"losses":261,"wins":2},"claude-haiku-5-5":{"draws":53,"losses":149,"wins":40},"claude-opus-4-5":{"draws":132,"losses":183,"wins":95},"claude-opus-4-8":{"draws":63,"losses":147,"wins":22},"claude-opus-5":{"draws":54,"losses":340,"wins":30},"claude-opus-5-5":{"draws":17,"losses":253,"wins":2},"claude-sonnet-5":{"draws":73,"losses":127,"wins":52},"claude-sonnet-5-5":{"draws":49,"losses":163,"wins":40},"cohere/north-mini-code":{"draws":34,"losses":30,"wins":34},"deepseek/deepseek-v4-flash":{"draws":121,"losses":120,"wins":133},"deepseek/deepseek-v4-pro":{"draws":63,"losses":107,"wins":62},"deepseek/deepseek-v4-pro-0813":{"draws":73,"losses":111,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":83,"losses":120,"wins":49},"fireworks/ember-1":{"draws":95,"losses":113,"wins":44},"gemini-3.1-pro-preview":{"draws":81,"losses":106,"wins":65},"google/gemini-3.1-flash-lite":{"draws":49,"losses":34,"wins":91},"google/gemini-3.5-flash":{"draws":79,"losses":158,"wins":81},"google/gemini-3.5-flash-lite":{"draws":118,"losses":123,"wins":123},"google/gemini-3.6-flash":{"draws":140,"losses":254,"wins":92},"google/gemini-3.8-flash":{"draws":50,"losses":184,"wins":18},"google/gemma-4-31b-it":{"draws":55,"losses":35,"wins":58},"gpt-4.1":{"draws":30,"losses":26,"wins":28},"gpt-4.1-nano":{"draws":18,"losses":3,"wins":9},"gpt-5":{"draws":73,"losses":92,"wins":55},"gpt-5.4":{"draws":58,"losses":149,"wins":37},"gpt-5.4-mini":{"draws":60,"losses":58,"wins":50},"gpt-5.4-nano":{"draws":54,"losses":93,"wins":105},"gpt-5.5":{"draws":91,"losses":109,"wins":32},"gpt-5.6-luna":{"draws":83,"losses":96,"wins":73},"gpt-5.6-sol":{"draws":36,"losses":194,"wins":22},"gpt-5.6-terra":{"draws":77,"losses":114,"wins":49},"gpt-6-astra":{"draws":14,"losses":237,"wins":1},"gpt-6-luna":{"draws":81,"losses":114,"wins":57},"gpt-6-sol":{"draws":39,"losses":191,"wins":22},"gpt-6.1-sol":{"draws":16,"losses":235,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":76,"losses":33,"wins":71},"inclusionai/ling-3.0-flash":{"draws":67,"losses":31,"wins":78},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":78,"losses":81,"wins":119},"meta/muse-glimmer-30b":{"draws":91,"losses":51,"wins":78},"meta/muse-spark-1.2":{"draws":60,"losses":133,"wins":47},"meta/muse-spark-1.3":{"draws":52,"losses":164,"wins":36},"meta/muse-wonder":{"draws":43,"losses":182,"wins":27},"minimax/minimax-m3":{"draws":38,"losses":46,"wins":50},"mistralai/mistral-large-4-0":{"draws":52,"losses":75,"wins":29},"mistralai/mistral-medium-3-5":{"draws":54,"losses":31,"wins":63},"moonshotai/kimi-k2.7-code":{"draws":15,"losses":33,"wins":14},"moonshotai/kimi-k3":{"draws":79,"losses":117,"wins":44},"nex-agi/nex-n2-pro":{"draws":36,"losses":34,"wins":58},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":88,"losses":66,"wins":66},"o3":{"draws":64,"losses":198,"wins":94},"openai/gpt-oss-120b":{"draws":70,"losses":74,"wins":74},"poolside/laguna-s-2.1":{"draws":81,"losses":95,"wins":62},"qwen/qwen3.7-max":{"draws":41,"losses":63,"wins":42},"qwen/qwen3.7-plus":{"draws":37,"losses":40,"wins":49},"qwen/qwen3.8-2.4t-a95b":{"draws":82,"losses":127,"wins":43},"qwen/qwen3.8-27b":{"draws":37,"losses":100,"wins":43},"qwen/qwen3.8-flash":{"draws":58,"losses":80,"wins":30},"qwen/qwen3.8-max":{"draws":84,"losses":121,"wins":47},"qwen/qwen3.8-max-0902":{"draws":76,"losses":140,"wins":36},"stealth/ox-alpha":{"draws":180,"losses":483,"wins":163},"stealth/space-bunny-alpha":{"draws":58,"losses":84,"wins":60},"stepfun/step-3.7-flash":{"draws":51,"losses":60,"wins":69},"stepfun/step-5-preview":{"draws":10,"losses":10,"wins":0},"tencent/hy3-preview":{"draws":48,"losses":58,"wins":30},"tencent/hy4-preview":{"draws":62,"losses":133,"wins":49},"thinkingmachines/inkling":{"draws":94,"losses":113,"wins":131},"thinkingmachines/inkling-small":{"draws":88,"losses":72,"wins":92},"unbiased/pareto-26.10-preview":{"draws":2,"losses":81,"wins":1},"upstage/solar-mini4":{"draws":20,"losses":25,"wins":23},"x-ai/grok-4.5":{"draws":64,"losses":145,"wins":43},"x-ai/grok-4.6":{"draws":62,"losses":159,"wins":31},"x-ai/grok-4.7":{"draws":20,"losses":170,"wins":28},"x-ai/grok-build-0.1":{"draws":34,"losses":24,"wins":26},"xiaomi/mimo-v2.5":{"draws":125,"losses":126,"wins":141},"xiaomi/mimo-v2.5-pro":{"draws":41,"losses":49,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":27,"losses":105,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":118,"wins":29},"z-ai/glm-5.2":{"draws":173,"losses":197,"wins":134},"z-ai/glm-5.3":{"draws":41,"losses":184,"wins":17},"z-ai/glm-5.3-flash":{"draws":56,"losses":149,"wins":47},"z-ai/glm-5.3-flashx":{"draws":65,"losses":139,"wins":48}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":67,"losses":51,"wins":136},"claude-fable-5":{"draws":48,"losses":148,"wins":80},"claude-fable-5-1":{"draws":25,"losses":270,"wins":17},"claude-haiku-5-5":{"draws":65,"losses":100,"wins":99},"claude-opus-4-5":{"draws":132,"losses":118,"wins":198},"claude-opus-4-8":{"draws":57,"losses":94,"wins":101},"claude-opus-5":{"draws":66,"losses":320,"wins":82},"claude-opus-5-5":{"draws":24,"losses":252,"wins":20},"claude-sonnet-5":{"draws":64,"losses":89,"wins":123},"claude-sonnet-5-5":{"draws":54,"losses":126,"wins":96},"cohere/north-mini-code":{"draws":22,"losses":9,"wins":73},"deepseek/deepseek-v4-flash":{"draws":100,"losses":56,"wins":256},"deepseek/deepseek-v4-pro":{"draws":65,"losses":84,"wins":105},"deepseek/deepseek-v4-pro-0813":{"draws":60,"losses":77,"wins":117},"deepseek/deepseek-v4.1-flash":{"draws":76,"losses":90,"wins":110},"fireworks/ember-1":{"draws":79,"losses":101,"wins":96},"gemini-3.1-pro-preview":{"draws":63,"losses":90,"wins":123},"google/gemini-3.1-flash-lite":{"draws":41,"losses":14,"wins":131},"google/gemini-3.5-flash":{"draws":79,"losses":130,"wins":137},"google/gemini-3.5-flash-lite":{"draws":140,"losses":92,"wins":254},"google/gemini-3.6-flash":{"draws":90,"losses":175,"wins":175},"google/gemini-3.8-flash":{"draws":64,"losses":133,"wins":79},"google/gemma-4-31b-it":{"draws":51,"losses":20,"wins":89},"gpt-4.1":{"draws":25,"losses":21,"wins":46},"gpt-4.1-nano":{"draws":14,"losses":2,"wins":18},"gpt-5":{"draws":53,"losses":74,"wins":115},"gpt-5.4":{"draws":59,"losses":117,"wins":90},"gpt-5.4-mini":{"draws":55,"losses":30,"wins":99},"gpt-5.4-nano":{"draws":50,"losses":58,"wins":166},"gpt-5.5":{"draws":74,"losses":93,"wins":87},"gpt-5.6-luna":{"draws":79,"losses":60,"wins":137},"gpt-5.6-sol":{"draws":41,"losses":161,"wins":74},"gpt-5.6-terra":{"draws":82,"losses":69,"wins":113},"gpt-6-astra":{"draws":20,"losses":239,"wins":17},"gpt-6-luna":{"draws":81,"losses":67,"wins":128},"gpt-6-sol":{"draws":35,"losses":182,"wins":59},"gpt-6.1-sol":{"draws":18,"losses":230,"wins":28},"ibm-granite/granite-4.2-8b":{"draws":11,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":69,"losses":12,"wins":113},"inclusionai/ling-3.0-flash":{"draws":68,"losses":18,"wins":108},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":69,"losses":44,"wins":187},"meta/muse-glimmer-30b":{"draws":76,"losses":34,"wins":132},"meta/muse-spark-1.2":{"draws":54,"losses":107,"wins":103},"meta/muse-spark-1.3":{"draws":50,"losses":133,"wins":93},"meta/muse-wonder":{"draws":50,"losses":155,"wins":71},"minimax/minimax-m3":{"draws":30,"losses":25,"wins":93},"mistralai/mistral-large-4-0":{"draws":41,"losses":59,"wins":72},"mistralai/mistral-medium-3-5":{"draws":57,"losses":14,"wins":89},"moonshotai/kimi-k2.7-code":{"draws":19,"losses":16,"wins":33},"moonshotai/kimi-k3":{"draws":71,"losses":90,"wins":103},"nex-agi/nex-n2-pro":{"draws":25,"losses":17,"wins":96},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":76,"losses":34,"wins":128},"o3":{"draws":56,"losses":124,"wins":204},"openai/gpt-oss-120b":{"draws":72,"losses":32,"wins":136},"poolside/laguna-s-2.1":{"draws":79,"losses":48,"wins":135},"qwen/qwen3.7-max":{"draws":47,"losses":38,"wins":75},"qwen/qwen3.7-plus":{"draws":39,"losses":22,"wins":77},"qwen/qwen3.8-2.4t-a95b":{"draws":73,"losses":96,"wins":107},"qwen/qwen3.8-27b":{"draws":44,"losses":64,"wins":90},"qwen/qwen3.8-flash":{"draws":60,"losses":47,"wins":77},"qwen/qwen3.8-max":{"draws":72,"losses":89,"wins":115},"qwen/qwen3.8-max-0902":{"draws":76,"losses":105,"wins":95},"stealth/ox-alpha":{"draws":195,"losses":360,"wins":361},"stealth/space-bunny-alpha":{"draws":57,"losses":45,"wins":118},"stepfun/step-3.7-flash":{"draws":37,"losses":32,"wins":129},"stepfun/step-5-preview":{"draws":6,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":47,"losses":31,"wins":70},"tencent/hy4-preview":{"draws":59,"losses":105,"wins":102},"thinkingmachines/inkling":{"draws":103,"losses":56,"wins":213},"thinkingmachines/inkling-small":{"draws":82,"losses":44,"wins":150},"unbiased/pareto-26.10-preview":{"draws":5,"losses":78,"wins":9},"upstage/solar-mini4":{"draws":14,"losses":9,"wins":49},"x-ai/grok-4.5":{"draws":60,"losses":116,"wins":100},"x-ai/grok-4.6":{"draws":71,"losses":123,"wins":82},"x-ai/grok-4.7":{"draws":14,"losses":173,"wins":53},"x-ai/grok-build-0.1":{"draws":30,"losses":5,"wins":57},"xiaomi/mimo-v2.5":{"draws":130,"losses":49,"wins":245},"xiaomi/mimo-v2.5-pro":{"draws":33,"losses":29,"wins":88},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":73,"wins":74},"xiaomi/mimo-v2.6-pro":{"draws":38,"losses":86,"wins":60},"z-ai/glm-5.2":{"draws":153,"losses":152,"wins":247},"z-ai/glm-5.3":{"draws":52,"losses":153,"wins":59},"z-ai/glm-5.3-flash":{"draws":42,"losses":141,"wins":93},"z-ai/glm-5.3-flashx":{"draws":67,"losses":113,"wins":96}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":21,"wins":79},"claude-fable-5":{"draws":24,"losses":68,"wins":52},"claude-fable-5-1":{"draws":8,"losses":141,"wins":13},"claude-haiku-5-5":{"draws":33,"losses":43,"wins":62},"claude-opus-4-5":{"draws":72,"losses":43,"wins":119},"claude-opus-4-8":{"draws":28,"losses":44,"wins":60},"claude-opus-5":{"draws":28,"losses":164,"wins":54},"claude-opus-5-5":{"draws":16,"losses":120,"wins":20},"claude-sonnet-5":{"draws":34,"losses":34,"wins":76},"claude-sonnet-5-5":{"draws":20,"losses":68,"wins":56},"cohere/north-mini-code":{"draws":10,"losses":6,"wins":38},"deepseek/deepseek-v4-flash":{"draws":44,"losses":24,"wins":148},"deepseek/deepseek-v4-pro":{"draws":27,"losses":33,"wins":72},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":35,"wins":64},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":46,"wins":61},"fireworks/ember-1":{"draws":35,"losses":48,"wins":61},"gemini-3.1-pro-preview":{"draws":28,"losses":34,"wins":82},"google/gemini-3.1-flash-lite":{"draws":25,"losses":2,"wins":69},"google/gemini-3.5-flash":{"draws":38,"losses":44,"wins":98},"google/gemini-3.5-flash-lite":{"draws":50,"losses":18,"wins":184},"google/gemini-3.6-flash":{"draws":64,"losses":79,"wins":133},"google/gemini-3.8-flash":{"draws":22,"losses":37,"wins":37},"google/gemma-4-31b-it":{"draws":23,"losses":9,"wins":52},"gpt-4.1":{"draws":16,"losses":6,"wins":26},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":30,"losses":28,"wins":68},"gpt-5.4":{"draws":30,"losses":51,"wins":57},"gpt-5.4-mini":{"draws":25,"losses":13,"wins":58},"gpt-5.4-nano":{"draws":31,"losses":24,"wins":89},"gpt-5.5":{"draws":47,"losses":42,"wins":43},"gpt-5.6-luna":{"draws":32,"losses":25,"wins":87},"gpt-5.6-sol":{"draws":19,"losses":72,"wins":53},"gpt-5.6-terra":{"draws":42,"losses":35,"wins":61},"gpt-6-astra":{"draws":15,"losses":120,"wins":9},"gpt-6-luna":{"draws":42,"losses":33,"wins":69},"gpt-6-sol":{"draws":22,"losses":89,"wins":33},"gpt-6.1-sol":{"draws":20,"losses":107,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":32,"losses":4,"wins":66},"inclusionai/ling-3.0-flash":{"draws":32,"losses":1,"wins":69},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":33,"losses":15,"wins":108},"meta/muse-glimmer-30b":{"draws":34,"losses":14,"wins":78},"meta/muse-spark-1.2":{"draws":25,"losses":54,"wins":59},"meta/muse-spark-1.3":{"draws":34,"losses":51,"wins":59},"meta/muse-wonder":{"draws":36,"losses":68,"wins":40},"minimax/minimax-m3":{"draws":17,"losses":6,"wins":55},"mistralai/mistral-large-4-0":{"draws":28,"losses":26,"wins":36},"mistralai/mistral-medium-3-5":{"draws":20,"losses":5,"wins":59},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":15,"wins":13},"moonshotai/kimi-k3":{"draws":36,"losses":33,"wins":69},"nex-agi/nex-n2-pro":{"draws":14,"losses":7,"wins":51},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":8,"wins":77},"o3":{"draws":28,"losses":44,"wins":126},"openai/gpt-oss-120b":{"draws":28,"losses":8,"wins":90},"poolside/laguna-s-2.1":{"draws":31,"losses":14,"wins":93},"qwen/qwen3.7-max":{"draws":27,"losses":20,"wins":37},"qwen/qwen3.7-plus":{"draws":19,"losses":7,"wins":46},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":41,"wins":67},"qwen/qwen3.8-27b":{"draws":17,"losses":22,"wins":63},"qwen/qwen3.8-flash":{"draws":25,"losses":26,"wins":45},"qwen/qwen3.8-max":{"draws":38,"losses":46,"wins":60},"qwen/qwen3.8-max-0902":{"draws":39,"losses":46,"wins":59},"stealth/ox-alpha":{"draws":103,"losses":148,"wins":223},"stealth/space-bunny-alpha":{"draws":31,"losses":17,"wins":66},"stepfun/step-3.7-flash":{"draws":20,"losses":9,"wins":73},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":5},"tencent/hy3-preview":{"draws":31,"losses":8,"wins":39},"tencent/hy4-preview":{"draws":33,"losses":53,"wins":52},"thinkingmachines/inkling":{"draws":50,"losses":19,"wins":123},"thinkingmachines/inkling-small":{"draws":43,"losses":17,"wins":84},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":6},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":29},"x-ai/grok-4.5":{"draws":25,"losses":67,"wins":52},"x-ai/grok-4.6":{"draws":42,"losses":53,"wins":49},"x-ai/grok-4.7":{"draws":14,"losses":85,"wins":27},"x-ai/grok-build-0.1":{"draws":13,"losses":3,"wins":32},"xiaomi/mimo-v2.5":{"draws":63,"losses":19,"wins":140},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":12,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":28,"wins":40},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":49,"wins":27},"z-ai/glm-5.2":{"draws":78,"losses":57,"wins":153},"z-ai/glm-5.3":{"draws":30,"losses":71,"wins":37},"z-ai/glm-5.3-flash":{"draws":24,"losses":55,"wins":65},"z-ai/glm-5.3-flashx":{"draws":30,"losses":52,"wins":62}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":25,"wins":24},"claude-fable-5":{"draws":18,"losses":58,"wins":8},"claude-fable-5-1":{"draws":4,"losses":89,"wins":1},"claude-haiku-5-5":{"draws":23,"losses":50,"wins":9},"claude-opus-4-5":{"draws":46,"losses":77,"wins":15},"claude-opus-4-8":{"draws":23,"losses":47,"wins":10},"claude-opus-5":{"draws":21,"losses":109,"wins":10},"claude-opus-5-5":{"draws":5,"losses":87,"wins":0},"claude-sonnet-5":{"draws":27,"losses":45,"wins":12},"claude-sonnet-5-5":{"draws":14,"losses":54,"wins":16},"cohere/north-mini-code":{"draws":10,"losses":6,"wins":18},"deepseek/deepseek-v4-flash":{"draws":58,"losses":46,"wins":22},"deepseek/deepseek-v4-pro":{"draws":28,"losses":34,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":38,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":38,"wins":12},"fireworks/ember-1":{"draws":31,"losses":41,"wins":12},"gemini-3.1-pro-preview":{"draws":30,"losses":39,"wins":15},"google/gemini-3.1-flash-lite":{"draws":19,"losses":15,"wins":26},"google/gemini-3.5-flash":{"draws":31,"losses":53,"wins":22},"google/gemini-3.5-flash-lite":{"draws":55,"losses":58,"wins":35},"google/gemini-3.6-flash":{"draws":51,"losses":89,"wins":20},"google/gemini-3.8-flash":{"draws":23,"losses":52,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":7,"wins":7},"gpt-4.1":{"draws":11,"losses":11,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":5},"gpt-5":{"draws":31,"losses":32,"wins":9},"gpt-5.4":{"draws":28,"losses":43,"wins":9},"gpt-5.4-mini":{"draws":22,"losses":24,"wins":10},"gpt-5.4-nano":{"draws":26,"losses":43,"wins":17},"gpt-5.5":{"draws":30,"losses":40,"wins":6},"gpt-5.6-luna":{"draws":34,"losses":30,"wins":20},"gpt-5.6-sol":{"draws":11,"losses":67,"wins":6},"gpt-5.6-terra":{"draws":32,"losses":39,"wins":9},"gpt-6-astra":{"draws":4,"losses":80,"wins":0},"gpt-6-luna":{"draws":28,"losses":38,"wins":18},"gpt-6-sol":{"draws":9,"losses":73,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":80,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":16,"wins":18},"inclusionai/ling-3.0-flash":{"draws":32,"losses":13,"wins":13},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":35,"wins":26},"meta/muse-glimmer-30b":{"draws":38,"losses":17,"wins":17},"meta/muse-spark-1.2":{"draws":23,"losses":40,"wins":17},"meta/muse-spark-1.3":{"draws":23,"losses":53,"wins":8},"meta/muse-wonder":{"draws":17,"losses":60,"wins":7},"minimax/minimax-m3":{"draws":19,"losses":16,"wins":11},"mistralai/mistral-large-4-0":{"draws":19,"losses":24,"wins":9},"mistralai/mistral-medium-3-5":{"draws":22,"losses":7,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":11,"wins":4},"moonshotai/kimi-k3":{"draws":29,"losses":38,"wins":13},"nex-agi/nex-n2-pro":{"draws":17,"losses":11,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":18,"wins":18},"o3":{"draws":26,"losses":71,"wins":21},"openai/gpt-oss-120b":{"draws":31,"losses":33,"wins":10},"poolside/laguna-s-2.1":{"draws":33,"losses":25,"wins":20},"qwen/qwen3.7-max":{"draws":17,"losses":20,"wins":13},"qwen/qwen3.7-plus":{"draws":16,"losses":15,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":45,"wins":10},"qwen/qwen3.8-27b":{"draws":19,"losses":29,"wins":10},"qwen/qwen3.8-flash":{"draws":27,"losses":23,"wins":6},"qwen/qwen3.8-max":{"draws":33,"losses":43,"wins":8},"qwen/qwen3.8-max-0902":{"draws":29,"losses":46,"wins":9},"stealth/ox-alpha":{"draws":60,"losses":160,"wins":40},"stealth/space-bunny-alpha":{"draws":26,"losses":26,"wins":16},"stepfun/step-3.7-flash":{"draws":18,"losses":27,"wins":13},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":21,"losses":16,"wins":9},"tencent/hy4-preview":{"draws":26,"losses":43,"wins":11},"thinkingmachines/inkling":{"draws":40,"losses":36,"wins":32},"thinkingmachines/inkling-small":{"draws":35,"losses":25,"wins":24},"unbiased/pareto-26.10-preview":{"draws":1,"losses":27,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":5},"x-ai/grok-4.5":{"draws":19,"losses":55,"wins":10},"x-ai/grok-4.6":{"draws":24,"losses":54,"wins":6},"x-ai/grok-4.7":{"draws":8,"losses":62,"wins":4},"x-ai/grok-build-0.1":{"draws":11,"losses":9,"wins":8},"xiaomi/mimo-v2.5":{"draws":61,"losses":41,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":22,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":32,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":41,"wins":4},"z-ai/glm-5.2":{"draws":69,"losses":70,"wins":29},"z-ai/glm-5.3":{"draws":22,"losses":53,"wins":7},"z-ai/glm-5.3-flash":{"draws":25,"losses":45,"wins":14},"z-ai/glm-5.3-flashx":{"draws":28,"losses":45,"wins":11}},"gpt-4.1":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":11,"wins":17},"claude-fable-5":{"draws":8,"losses":28,"wins":12},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":23,"wins":8},"claude-opus-4-5":{"draws":32,"losses":29,"wins":17},"claude-opus-4-8":{"draws":14,"losses":25,"wins":5},"claude-opus-5":{"draws":9,"losses":68,"wins":5},"claude-opus-5-5":{"draws":5,"losses":46,"wins":1},"claude-sonnet-5":{"draws":17,"losses":17,"wins":14},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":24,"losses":16,"wins":32},"deepseek/deepseek-v4-pro":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":20,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":24,"wins":11},"fireworks/ember-1":{"draws":14,"losses":19,"wins":15},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":14,"losses":29,"wins":17},"google/gemini-3.5-flash-lite":{"draws":30,"losses":28,"wins":26},"google/gemini-3.6-flash":{"draws":25,"losses":46,"wins":21},"google/gemini-3.8-flash":{"draws":16,"losses":26,"wins":6},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":14,"wins":15},"gpt-5.4":{"draws":13,"losses":24,"wins":9},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":11,"losses":17,"wins":20},"gpt-5.5":{"draws":11,"losses":24,"wins":9},"gpt-5.6-luna":{"draws":17,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":8,"losses":33,"wins":7},"gpt-5.6-terra":{"draws":19,"losses":12,"wins":15},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":10,"losses":19,"wins":19},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":8,"wins":11},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":20},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":18,"losses":10,"wins":24},"meta/muse-glimmer-30b":{"draws":19,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":17,"losses":21,"wins":8},"meta/muse-spark-1.3":{"draws":18,"losses":26,"wins":4},"meta/muse-wonder":{"draws":7,"losses":35,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":13},"mistralai/mistral-large-4-0":{"draws":12,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":13,"losses":21,"wins":12},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":7,"wins":17},"o3":{"draws":13,"losses":26,"wins":27},"openai/gpt-oss-120b":{"draws":13,"losses":9,"wins":20},"poolside/laguna-s-2.1":{"draws":16,"losses":12,"wins":18},"qwen/qwen3.7-max":{"draws":13,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":16,"wins":5},"qwen/qwen3.8-max":{"draws":19,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":23,"wins":7},"stealth/ox-alpha":{"draws":43,"losses":79,"wins":36},"stealth/space-bunny-alpha":{"draws":15,"losses":13,"wins":10},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":19},"stepfun/step-5-preview":{"draws":3,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":13,"losses":24,"wins":9},"thinkingmachines/inkling":{"draws":17,"losses":20,"wins":27},"thinkingmachines/inkling-small":{"draws":17,"losses":13,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":29,"wins":8},"x-ai/grok-4.6":{"draws":19,"losses":23,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":29,"losses":17,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":17,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":35,"losses":38,"wins":23},"z-ai/glm-5.3":{"draws":7,"losses":31,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":28,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":30,"wins":7}},"gpt-4.1-nano":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":4},"claude-fable-5":{"draws":6,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":9,"wins":0},"claude-opus-4-5":{"draws":17,"losses":11,"wins":0},"claude-opus-4-8":{"draws":7,"losses":7,"wins":0},"claude-opus-5":{"draws":8,"losses":18,"wins":0},"claude-opus-5-5":{"draws":2,"losses":16,"wins":0},"claude-sonnet-5":{"draws":9,"losses":9,"wins":0},"claude-sonnet-5-5":{"draws":8,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":3},"deepseek/deepseek-v4-pro":{"draws":10,"losses":4,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":8,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":9,"wins":1},"fireworks/ember-1":{"draws":9,"losses":8,"wins":1},"gemini-3.1-pro-preview":{"draws":11,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":5,"wins":1},"google/gemini-3.5-flash":{"draws":8,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":18,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":14,"losses":18,"wins":2},"google/gemini-3.8-flash":{"draws":6,"losses":12,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":1},"gpt-4.1":{"draws":3,"losses":3,"wins":0},"gpt-5":{"draws":10,"losses":4,"wins":0},"gpt-5.4":{"draws":10,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":1},"gpt-5.5":{"draws":9,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":0},"gpt-6-astra":{"draws":2,"losses":16,"wins":0},"gpt-6-luna":{"draws":9,"losses":7,"wins":2},"gpt-6-sol":{"draws":2,"losses":16,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":17,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":2},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":1},"meta/muse-spark-1.2":{"draws":9,"losses":5,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":0},"meta/muse-wonder":{"draws":9,"losses":9,"wins":0},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":1},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":2},"o3":{"draws":6,"losses":10,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":13,"losses":2,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":11,"wins":1},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"wins":1},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":0},"qwen/qwen3.8-max":{"draws":10,"losses":7,"wins":1},"qwen/qwen3.8-max-0902":{"draws":7,"losses":10,"wins":1},"stealth/ox-alpha":{"draws":33,"losses":34,"wins":5},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":5,"losses":11,"wins":0},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":1},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":9,"losses":9,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":6,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":21,"losses":15,"wins":0},"z-ai/glm-5.3":{"draws":7,"losses":11,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":9,"wins":2},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":0}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":37,"losses":36,"wins":43},"claude-fable-5":{"draws":26,"losses":79,"wins":21},"claude-fable-5-1":{"draws":7,"losses":134,"wins":1},"claude-haiku-5-5":{"draws":31,"losses":62,"wins":27},"claude-opus-4-5":{"draws":64,"losses":74,"wins":66},"claude-opus-4-8":{"draws":30,"losses":54,"wins":30},"claude-opus-5":{"draws":23,"losses":179,"wins":18},"claude-opus-5-5":{"draws":9,"losses":124,"wins":5},"claude-sonnet-5":{"draws":39,"losses":52,"wins":35},"claude-sonnet-5-5":{"draws":27,"losses":73,"wins":26},"cohere/north-mini-code":{"draws":11,"losses":6,"wins":33},"deepseek/deepseek-v4-flash":{"draws":62,"losses":40,"wins":88},"deepseek/deepseek-v4-pro":{"draws":32,"losses":53,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":45,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":55,"wins":28},"fireworks/ember-1":{"draws":36,"losses":60,"wins":30},"gemini-3.1-pro-preview":{"draws":40,"losses":51,"wins":35},"google/gemini-3.1-flash-lite":{"draws":25,"losses":3,"wins":56},"google/gemini-3.5-flash":{"draws":40,"losses":68,"wins":50},"google/gemini-3.5-flash-lite":{"draws":73,"losses":55,"wins":92},"google/gemini-3.6-flash":{"draws":53,"losses":115,"wins":74},"google/gemini-3.8-flash":{"draws":30,"losses":68,"wins":28},"google/gemma-4-31b-it":{"draws":31,"losses":9,"wins":32},"gpt-4.1":{"draws":13,"losses":15,"wins":14},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":4},"gpt-5":{"draws":20,"losses":26,"wins":26},"gpt-5.4":{"draws":24,"losses":69,"wins":29},"gpt-5.4-mini":{"draws":29,"losses":27,"wins":28},"gpt-5.4-nano":{"draws":23,"losses":41,"wins":64},"gpt-5.5":{"draws":45,"losses":48,"wins":25},"gpt-5.6-luna":{"draws":40,"losses":35,"wins":51},"gpt-5.6-sol":{"draws":20,"losses":89,"wins":17},"gpt-5.6-terra":{"draws":33,"losses":51,"wins":36},"gpt-6-astra":{"draws":9,"losses":115,"wins":2},"gpt-6-luna":{"draws":39,"losses":45,"wins":42},"gpt-6-sol":{"draws":15,"losses":95,"wins":16},"gpt-6.1-sol":{"draws":6,"losses":115,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":35,"losses":8,"wins":41},"inclusionai/ling-3.0-flash":{"draws":34,"losses":20,"wins":34},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":42,"losses":31,"wins":65},"meta/muse-glimmer-30b":{"draws":44,"losses":23,"wins":47},"meta/muse-spark-1.2":{"draws":26,"losses":64,"wins":32},"meta/muse-spark-1.3":{"draws":29,"losses":71,"wins":26},"meta/muse-wonder":{"draws":23,"losses":80,"wins":23},"minimax/minimax-m3":{"draws":19,"losses":17,"wins":34},"mistralai/mistral-large-4-0":{"draws":30,"losses":34,"wins":16},"mistralai/mistral-medium-3-5":{"draws":24,"losses":15,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":15,"wins":11},"moonshotai/kimi-k3":{"draws":34,"losses":48,"wins":40},"nex-agi/nex-n2-pro":{"draws":17,"losses":15,"wins":32},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":20,"wins":47},"o3":{"draws":32,"losses":64,"wins":84},"openai/gpt-oss-120b":{"draws":35,"losses":21,"wins":56},"poolside/laguna-s-2.1":{"draws":49,"losses":33,"wins":44},"qwen/qwen3.7-max":{"draws":31,"losses":15,"wins":28},"qwen/qwen3.7-plus":{"draws":18,"losses":9,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":54,"wins":33},"qwen/qwen3.8-27b":{"draws":18,"losses":40,"wins":30},"qwen/qwen3.8-flash":{"draws":25,"losses":30,"wins":29},"qwen/qwen3.8-max":{"draws":41,"losses":56,"wins":29},"qwen/qwen3.8-max-0902":{"draws":38,"losses":58,"wins":30},"stealth/ox-alpha":{"draws":102,"losses":198,"wins":124},"stealth/space-bunny-alpha":{"draws":26,"losses":35,"wins":39},"stepfun/step-3.7-flash":{"draws":27,"losses":18,"wins":47},"stepfun/step-5-preview":{"draws":5,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":20,"losses":27,"wins":21},"tencent/hy4-preview":{"draws":37,"losses":50,"wins":35},"thinkingmachines/inkling":{"draws":40,"losses":39,"wins":93},"thinkingmachines/inkling-small":{"draws":52,"losses":19,"wins":55},"unbiased/pareto-26.10-preview":{"draws":1,"losses":40,"wins":1},"upstage/solar-mini4":{"draws":4,"losses":3,"wins":23},"x-ai/grok-4.5":{"draws":25,"losses":67,"wins":34},"x-ai/grok-4.6":{"draws":40,"losses":68,"wins":18},"x-ai/grok-4.7":{"draws":10,"losses":84,"wins":18},"x-ai/grok-build-0.1":{"draws":15,"losses":9,"wins":18},"xiaomi/mimo-v2.5":{"draws":63,"losses":37,"wins":90},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":20,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":33,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":51,"wins":22},"z-ai/glm-5.2":{"draws":86,"losses":74,"wins":92},"z-ai/glm-5.3":{"draws":19,"losses":79,"wins":22},"z-ai/glm-5.3-flash":{"draws":26,"losses":71,"wins":29},"z-ai/glm-5.3-flashx":{"draws":38,"losses":56,"wins":32}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":27,"wins":70},"claude-fable-5":{"draws":33,"losses":63,"wins":42},"claude-fable-5-1":{"draws":10,"losses":130,"wins":16},"claude-haiku-5-5":{"draws":31,"losses":51,"wins":50},"claude-opus-4-5":{"draws":66,"losses":49,"wins":109},"claude-opus-4-8":{"draws":29,"losses":43,"wins":54},"claude-opus-5":{"draws":29,"losses":169,"wins":36},"claude-opus-5-5":{"draws":11,"losses":128,"wins":11},"claude-sonnet-5":{"draws":37,"losses":31,"wins":70},"claude-sonnet-5-5":{"draws":37,"losses":59,"wins":42},"cohere/north-mini-code":{"draws":11,"losses":8,"wins":35},"deepseek/deepseek-v4-flash":{"draws":57,"losses":28,"wins":121},"deepseek/deepseek-v4-pro":{"draws":29,"losses":38,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":37,"wins":64},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":43,"wins":53},"fireworks/ember-1":{"draws":40,"losses":38,"wins":60},"gemini-3.1-pro-preview":{"draws":30,"losses":42,"wins":66},"google/gemini-3.1-flash-lite":{"draws":19,"losses":8,"wins":67},"google/gemini-3.5-flash":{"draws":29,"losses":49,"wins":96},"google/gemini-3.5-flash-lite":{"draws":58,"losses":37,"wins":149},"google/gemini-3.6-flash":{"draws":59,"losses":90,"wins":117},"google/gemini-3.8-flash":{"draws":30,"losses":57,"wins":51},"google/gemma-4-31b-it":{"draws":28,"losses":9,"wins":43},"gpt-4.1":{"draws":13,"losses":9,"wins":24},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":6},"gpt-5":{"draws":24,"losses":29,"wins":69},"gpt-5.4":{"draws":20,"losses":34,"wins":34},"gpt-5.4-mini":{"draws":30,"losses":6,"wins":56},"gpt-5.4-nano":{"draws":20,"losses":32,"wins":86},"gpt-5.5":{"draws":41,"losses":42,"wins":45},"gpt-5.6-luna":{"draws":46,"losses":21,"wins":71},"gpt-5.6-sol":{"draws":23,"losses":69,"wins":46},"gpt-5.6-terra":{"draws":37,"losses":35,"wins":60},"gpt-6-astra":{"draws":6,"losses":116,"wins":16},"gpt-6-luna":{"draws":43,"losses":34,"wins":61},"gpt-6-sol":{"draws":15,"losses":101,"wins":22},"gpt-6.1-sol":{"draws":9,"losses":109,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":42,"losses":2,"wins":52},"inclusionai/ling-3.0-flash":{"draws":27,"losses":14,"wins":57},"inclusionai/ling-3.1-flash":{"draws":5,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":37,"losses":20,"wins":95},"meta/muse-glimmer-30b":{"draws":31,"losses":17,"wins":74},"meta/muse-spark-1.2":{"draws":27,"losses":47,"wins":58},"meta/muse-spark-1.3":{"draws":30,"losses":53,"wins":55},"meta/muse-wonder":{"draws":29,"losses":66,"wins":43},"minimax/minimax-m3":{"draws":15,"losses":16,"wins":43},"mistralai/mistral-large-4-0":{"draws":30,"losses":16,"wins":40},"mistralai/mistral-medium-3-5":{"draws":23,"losses":12,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":20},"moonshotai/kimi-k3":{"draws":27,"losses":37,"wins":68},"nex-agi/nex-n2-pro":{"draws":18,"losses":15,"wins":37},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":8,"wins":70},"o3":{"draws":22,"losses":46,"wins":128},"openai/gpt-oss-120b":{"draws":33,"losses":20,"wins":67},"poolside/laguna-s-2.1":{"draws":35,"losses":16,"wins":81},"qwen/qwen3.7-max":{"draws":18,"losses":19,"wins":43},"qwen/qwen3.7-plus":{"draws":12,"losses":7,"wins":49},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":53,"wins":56},"qwen/qwen3.8-27b":{"draws":22,"losses":20,"wins":56},"qwen/qwen3.8-flash":{"draws":21,"losses":28,"wins":43},"qwen/qwen3.8-max":{"draws":38,"losses":49,"wins":51},"qwen/qwen3.8-max-0902":{"draws":31,"losses":45,"wins":62},"stealth/ox-alpha":{"draws":124,"losses":155,"wins":179},"stealth/space-bunny-alpha":{"draws":33,"losses":16,"wins":61},"stepfun/step-3.7-flash":{"draws":20,"losses":16,"wins":64},"stepfun/step-5-preview":{"draws":5,"losses":6,"wins":1},"tencent/hy3-preview":{"draws":28,"losses":13,"wins":33},"tencent/hy4-preview":{"draws":31,"losses":45,"wins":58},"thinkingmachines/inkling":{"draws":49,"losses":29,"wins":108},"thinkingmachines/inkling-small":{"draws":43,"losses":15,"wins":80},"unbiased/pareto-26.10-preview":{"draws":2,"losses":38,"wins":6},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":29},"x-ai/grok-4.5":{"draws":33,"losses":46,"wins":59},"x-ai/grok-4.6":{"draws":40,"losses":51,"wins":47},"x-ai/grok-4.7":{"draws":13,"losses":79,"wins":28},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":28},"xiaomi/mimo-v2.5":{"draws":57,"losses":21,"wins":134},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":13,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":23,"losses":27,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":38,"wins":37},"z-ai/glm-5.2":{"draws":81,"losses":59,"wins":136},"z-ai/glm-5.3":{"draws":25,"losses":69,"wins":38},"z-ai/glm-5.3-flash":{"draws":21,"losses":55,"wins":62},"z-ai/glm-5.3-flashx":{"draws":34,"losses":54,"wins":50}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":28,"wins":25},"claude-fable-5":{"draws":22,"losses":63,"wins":11},"claude-fable-5-1":{"draws":4,"losses":104,"wins":0},"claude-haiku-5-5":{"draws":27,"losses":53,"wins":12},"claude-opus-4-5":{"draws":57,"losses":64,"wins":35},"claude-opus-4-8":{"draws":23,"losses":44,"wins":21},"claude-opus-5":{"draws":31,"losses":121,"wins":12},"claude-opus-5-5":{"draws":5,"losses":97,"wins":2},"claude-sonnet-5":{"draws":38,"losses":30,"wins":28},"claude-sonnet-5-5":{"draws":18,"losses":60,"wins":18},"cohere/north-mini-code":{"draws":11,"losses":8,"wins":17},"deepseek/deepseek-v4-flash":{"draws":58,"losses":36,"wins":50},"deepseek/deepseek-v4-pro":{"draws":32,"losses":33,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":38,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":39,"wins":20},"fireworks/ember-1":{"draws":36,"losses":45,"wins":15},"gemini-3.1-pro-preview":{"draws":38,"losses":33,"wins":25},"google/gemini-3.1-flash-lite":{"draws":21,"losses":6,"wins":37},"google/gemini-3.5-flash":{"draws":41,"losses":50,"wins":29},"google/gemini-3.5-flash-lite":{"draws":60,"losses":50,"wins":58},"google/gemini-3.6-flash":{"draws":55,"losses":99,"wins":30},"google/gemini-3.8-flash":{"draws":25,"losses":58,"wins":13},"google/gemma-4-31b-it":{"draws":22,"losses":10,"wins":24},"gpt-4.1":{"draws":12,"losses":7,"wins":13},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":3},"gpt-5":{"draws":29,"losses":28,"wins":27},"gpt-5.4":{"draws":30,"losses":56,"wins":6},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":9},"gpt-5.4-nano":{"draws":26,"losses":41,"wins":29},"gpt-5.5":{"draws":40,"losses":33,"wins":15},"gpt-5.6-luna":{"draws":38,"losses":31,"wins":27},"gpt-5.6-sol":{"draws":21,"losses":63,"wins":12},"gpt-5.6-terra":{"draws":39,"losses":32,"wins":21},"gpt-6-astra":{"draws":6,"losses":90,"wins":0},"gpt-6-luna":{"draws":43,"losses":40,"wins":13},"gpt-6-sol":{"draws":13,"losses":72,"wins":11},"gpt-6.1-sol":{"draws":5,"losses":87,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":31,"losses":14,"wins":23},"inclusionai/ling-3.0-flash":{"draws":31,"losses":12,"wins":25},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":42,"losses":26,"wins":36},"meta/muse-glimmer-30b":{"draws":43,"losses":11,"wins":30},"meta/muse-spark-1.2":{"draws":27,"losses":45,"wins":20},"meta/muse-spark-1.3":{"draws":19,"losses":66,"wins":11},"meta/muse-wonder":{"draws":24,"losses":62,"wins":10},"minimax/minimax-m3":{"draws":18,"losses":17,"wins":17},"mistralai/mistral-large-4-0":{"draws":28,"losses":20,"wins":12},"mistralai/mistral-medium-3-5":{"draws":24,"losses":8,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":32,"losses":38,"wins":22},"nex-agi/nex-n2-pro":{"draws":19,"losses":12,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":21,"wins":24},"o3":{"draws":29,"losses":69,"wins":34},"openai/gpt-oss-120b":{"draws":32,"losses":21,"wins":31},"poolside/laguna-s-2.1":{"draws":39,"losses":22,"wins":31},"qwen/qwen3.7-max":{"draws":19,"losses":22,"wins":15},"qwen/qwen3.7-plus":{"draws":16,"losses":18,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":49,"wins":13},"qwen/qwen3.8-27b":{"draws":17,"losses":32,"wins":19},"qwen/qwen3.8-flash":{"draws":25,"losses":25,"wins":14},"qwen/qwen3.8-max":{"draws":41,"losses":37,"wins":18},"qwen/qwen3.8-max-0902":{"draws":38,"losses":44,"wins":14},"stealth/ox-alpha":{"draws":94,"losses":162,"wins":60},"stealth/space-bunny-alpha":{"draws":28,"losses":33,"wins":15},"stepfun/step-3.7-flash":{"draws":24,"losses":22,"wins":22},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":21,"losses":17,"wins":14},"tencent/hy4-preview":{"draws":34,"losses":47,"wins":11},"thinkingmachines/inkling":{"draws":48,"losses":37,"wins":43},"thinkingmachines/inkling-small":{"draws":44,"losses":22,"wins":30},"unbiased/pareto-26.10-preview":{"draws":1,"losses":31,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":8,"wins":11},"x-ai/grok-4.5":{"draws":30,"losses":52,"wins":14},"x-ai/grok-4.6":{"draws":32,"losses":50,"wins":14},"x-ai/grok-4.7":{"draws":14,"losses":66,"wins":4},"x-ai/grok-build-0.1":{"draws":12,"losses":7,"wins":13},"xiaomi/mimo-v2.5":{"draws":57,"losses":40,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":17,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":32,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":40,"wins":9},"z-ai/glm-5.2":{"draws":87,"losses":70,"wins":35},"z-ai/glm-5.3":{"draws":21,"losses":62,"wins":9},"z-ai/glm-5.3-flash":{"draws":28,"losses":51,"wins":17},"z-ai/glm-5.3-flashx":{"draws":27,"losses":56,"wins":13}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":54,"wins":48},"claude-fable-5":{"draws":19,"losses":112,"wins":13},"claude-fable-5-1":{"draws":1,"losses":153,"wins":0},"claude-haiku-5-5":{"draws":27,"losses":76,"wins":39},"claude-opus-4-5":{"draws":64,"losses":110,"wins":64},"claude-opus-4-8":{"draws":25,"losses":84,"wins":31},"claude-opus-5":{"draws":21,"losses":198,"wins":17},"claude-opus-5-5":{"draws":7,"losses":151,"wins":2},"claude-sonnet-5":{"draws":34,"losses":71,"wins":39},"claude-sonnet-5-5":{"draws":21,"losses":105,"wins":18},"cohere/north-mini-code":{"draws":11,"losses":9,"wins":36},"deepseek/deepseek-v4-flash":{"draws":56,"losses":81,"wins":89},"deepseek/deepseek-v4-pro":{"draws":18,"losses":67,"wins":45},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":63,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":72,"wins":35},"fireworks/ember-1":{"draws":35,"losses":78,"wins":31},"gemini-3.1-pro-preview":{"draws":36,"losses":68,"wins":40},"google/gemini-3.1-flash-lite":{"draws":24,"losses":22,"wins":62},"google/gemini-3.5-flash":{"draws":34,"losses":102,"wins":48},"google/gemini-3.5-flash-lite":{"draws":54,"losses":105,"wins":93},"google/gemini-3.6-flash":{"draws":50,"losses":166,"wins":58},"google/gemini-3.8-flash":{"draws":31,"losses":89,"wins":24},"google/gemma-4-31b-it":{"draws":26,"losses":17,"wins":43},"gpt-4.1":{"draws":11,"losses":20,"wins":17},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":7},"gpt-5":{"draws":23,"losses":64,"wins":41},"gpt-5.4":{"draws":20,"losses":86,"wins":32},"gpt-5.4-mini":{"draws":26,"losses":29,"wins":41},"gpt-5.4-nano":{"draws":20,"losses":50,"wins":50},"gpt-5.5":{"draws":33,"losses":64,"wins":33},"gpt-5.6-luna":{"draws":35,"losses":60,"wins":49},"gpt-5.6-sol":{"draws":15,"losses":115,"wins":14},"gpt-5.6-terra":{"draws":27,"losses":73,"wins":36},"gpt-6-astra":{"draws":2,"losses":140,"wins":2},"gpt-6-luna":{"draws":30,"losses":72,"wins":42},"gpt-6-sol":{"draws":20,"losses":112,"wins":12},"gpt-6.1-sol":{"draws":7,"losses":132,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":32,"losses":14,"wins":56},"inclusionai/ling-3.0-flash":{"draws":30,"losses":26,"wins":48},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":28,"losses":49,"wins":83},"meta/muse-glimmer-30b":{"draws":31,"losses":42,"wins":49},"meta/muse-spark-1.2":{"draws":22,"losses":70,"wins":44},"meta/muse-spark-1.3":{"draws":27,"losses":90,"wins":27},"meta/muse-wonder":{"draws":12,"losses":110,"wins":22},"minimax/minimax-m3":{"draws":18,"losses":27,"wins":39},"mistralai/mistral-large-4-0":{"draws":16,"losses":48,"wins":24},"mistralai/mistral-medium-3-5":{"draws":19,"losses":16,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":16,"wins":14},"moonshotai/kimi-k3":{"draws":35,"losses":69,"wins":32},"nex-agi/nex-n2-pro":{"draws":16,"losses":22,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":46,"wins":58},"o3":{"draws":22,"losses":104,"wins":100},"openai/gpt-oss-120b":{"draws":35,"losses":47,"wins":44},"poolside/laguna-s-2.1":{"draws":40,"losses":54,"wins":50},"qwen/qwen3.7-max":{"draws":27,"losses":36,"wins":29},"qwen/qwen3.7-plus":{"draws":18,"losses":31,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":79,"wins":29},"qwen/qwen3.8-27b":{"draws":22,"losses":48,"wins":34},"qwen/qwen3.8-flash":{"draws":27,"losses":43,"wins":26},"qwen/qwen3.8-max":{"draws":33,"losses":74,"wins":37},"qwen/qwen3.8-max-0902":{"draws":38,"losses":71,"wins":35},"stealth/ox-alpha":{"draws":83,"losses":225,"wins":116},"stealth/space-bunny-alpha":{"draws":26,"losses":47,"wins":39},"stepfun/step-3.7-flash":{"draws":20,"losses":33,"wins":57},"stepfun/step-5-preview":{"draws":3,"losses":9,"wins":4},"tencent/hy3-preview":{"draws":20,"losses":37,"wins":23},"tencent/hy4-preview":{"draws":23,"losses":86,"wins":29},"thinkingmachines/inkling":{"draws":42,"losses":69,"wins":77},"thinkingmachines/inkling-small":{"draws":49,"losses":39,"wins":56},"unbiased/pareto-26.10-preview":{"draws":1,"losses":47,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":15,"wins":22},"x-ai/grok-4.5":{"draws":30,"losses":84,"wins":30},"x-ai/grok-4.6":{"draws":23,"losses":97,"wins":24},"x-ai/grok-4.7":{"draws":17,"losses":104,"wins":11},"x-ai/grok-build-0.1":{"draws":11,"losses":14,"wins":23},"xiaomi/mimo-v2.5":{"draws":55,"losses":74,"wins":107},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":38,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":50,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":66,"wins":17},"z-ai/glm-5.2":{"draws":71,"losses":120,"wins":97},"z-ai/glm-5.3":{"draws":20,"losses":96,"wins":20},"z-ai/glm-5.3-flash":{"draws":25,"losses":81,"wins":38},"z-ai/glm-5.3-flashx":{"draws":30,"losses":81,"wins":33}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":47,"losses":21,"wins":54},"claude-fable-5":{"draws":30,"losses":64,"wins":38},"claude-fable-5-1":{"draws":5,"losses":127,"wins":18},"claude-haiku-5-5":{"draws":46,"losses":45,"wins":35},"claude-opus-4-5":{"draws":88,"losses":47,"wins":79},"claude-opus-4-8":{"draws":38,"losses":35,"wins":47},"claude-opus-5":{"draws":32,"losses":155,"wins":45},"claude-opus-5-5":{"draws":15,"losses":114,"wins":15},"claude-sonnet-5":{"draws":51,"losses":24,"wins":57},"claude-sonnet-5-5":{"draws":29,"losses":61,"wins":42},"cohere/north-mini-code":{"draws":15,"losses":4,"wins":33},"deepseek/deepseek-v4-flash":{"draws":73,"losses":21,"wins":102},"deepseek/deepseek-v4-pro":{"draws":36,"losses":28,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":36,"wins":51},"deepseek/deepseek-v4.1-flash":{"draws":45,"losses":45,"wins":42},"fireworks/ember-1":{"draws":42,"losses":41,"wins":49},"gemini-3.1-pro-preview":{"draws":38,"losses":32,"wins":62},"google/gemini-3.1-flash-lite":{"draws":25,"losses":6,"wins":57},"google/gemini-3.5-flash":{"draws":50,"losses":48,"wins":68},"google/gemini-3.5-flash-lite":{"draws":91,"losses":32,"wins":109},"google/gemini-3.6-flash":{"draws":74,"losses":87,"wins":93},"google/gemini-3.8-flash":{"draws":47,"losses":43,"wins":42},"google/gemma-4-31b-it":{"draws":30,"losses":6,"wins":40},"gpt-4.1":{"draws":11,"losses":9,"wins":24},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":4},"gpt-5":{"draws":45,"losses":25,"wins":48},"gpt-5.4":{"draws":41,"losses":45,"wins":42},"gpt-5.4-mini":{"draws":40,"losses":15,"wins":33},"gpt-5.4-nano":{"draws":33,"losses":33,"wins":64},"gpt-5.5":{"draws":36,"losses":22,"wins":22},"gpt-5.6-luna":{"draws":49,"losses":24,"wins":59},"gpt-5.6-sol":{"draws":27,"losses":59,"wins":46},"gpt-5.6-terra":{"draws":48,"losses":29,"wins":49},"gpt-6-astra":{"draws":4,"losses":118,"wins":10},"gpt-6-luna":{"draws":52,"losses":27,"wins":53},"gpt-6-sol":{"draws":20,"losses":83,"wins":29},"gpt-6.1-sol":{"draws":8,"losses":103,"wins":21},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":2,"wins":1},"inception/mercury-2.5-preview":{"draws":40,"losses":8,"wins":42},"inclusionai/ling-3.0-flash":{"draws":41,"losses":7,"wins":44},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":50,"losses":22,"wins":72},"meta/muse-glimmer-30b":{"draws":48,"losses":16,"wins":56},"meta/muse-spark-1.2":{"draws":27,"losses":43,"wins":58},"meta/muse-spark-1.3":{"draws":31,"losses":53,"wins":48},"meta/muse-wonder":{"draws":37,"losses":59,"wins":36},"minimax/minimax-m3":{"draws":24,"losses":11,"wins":37},"mistralai/mistral-large-4-0":{"draws":29,"losses":22,"wins":33},"mistralai/mistral-medium-3-5":{"draws":26,"losses":8,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":10,"wins":11},"moonshotai/kimi-k3":{"draws":37,"losses":47,"wins":44},"nex-agi/nex-n2-pro":{"draws":18,"losses":5,"wins":43},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":52,"losses":8,"wins":54},"o3":{"draws":40,"losses":44,"wins":100},"openai/gpt-oss-120b":{"draws":44,"losses":16,"wins":56},"poolside/laguna-s-2.1":{"draws":52,"losses":21,"wins":55},"qwen/qwen3.7-max":{"draws":27,"losses":14,"wins":35},"qwen/qwen3.7-plus":{"draws":26,"losses":6,"wins":32},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":45,"wins":47},"qwen/qwen3.8-27b":{"draws":28,"losses":26,"wins":38},"qwen/qwen3.8-flash":{"draws":34,"losses":18,"wins":36},"qwen/qwen3.8-max":{"draws":44,"losses":40,"wins":48},"qwen/qwen3.8-max-0902":{"draws":47,"losses":43,"wins":42},"stealth/ox-alpha":{"draws":123,"losses":163,"wins":156},"stealth/space-bunny-alpha":{"draws":41,"losses":19,"wins":46},"stepfun/step-3.7-flash":{"draws":27,"losses":13,"wins":54},"stepfun/step-5-preview":{"draws":6,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":33,"losses":9,"wins":30},"tencent/hy4-preview":{"draws":44,"losses":44,"wins":40},"thinkingmachines/inkling":{"draws":55,"losses":27,"wins":98},"thinkingmachines/inkling-small":{"draws":50,"losses":18,"wins":64},"unbiased/pareto-26.10-preview":{"draws":1,"losses":39,"wins":4},"upstage/solar-mini4":{"draws":5,"losses":7,"wins":20},"x-ai/grok-4.5":{"draws":35,"losses":51,"wins":46},"x-ai/grok-4.6":{"draws":41,"losses":55,"wins":36},"x-ai/grok-4.7":{"draws":11,"losses":69,"wins":36},"x-ai/grok-build-0.1":{"draws":23,"losses":7,"wins":14},"xiaomi/mimo-v2.5":{"draws":85,"losses":20,"wins":97},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":12,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":26,"losses":23,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":37,"wins":31},"z-ai/glm-5.2":{"draws":101,"losses":48,"wins":115},"z-ai/glm-5.3":{"draws":31,"losses":72,"wins":23},"z-ai/glm-5.3-flash":{"draws":26,"losses":58,"wins":48},"z-ai/glm-5.3-flashx":{"draws":42,"losses":46,"wins":44}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":43,"losses":47,"wins":42},"claude-fable-5":{"draws":33,"losses":93,"wins":18},"claude-fable-5-1":{"draws":7,"losses":150,"wins":5},"claude-haiku-5-5":{"draws":40,"losses":74,"wins":24},"claude-opus-4-5":{"draws":84,"losses":91,"wins":59},"claude-opus-4-8":{"draws":42,"losses":62,"wins":28},"claude-opus-5":{"draws":26,"losses":195,"wins":25},"claude-opus-5-5":{"draws":17,"losses":134,"wins":5},"claude-sonnet-5":{"draws":45,"losses":61,"wins":38},"claude-sonnet-5-5":{"draws":33,"losses":83,"wins":28},"cohere/north-mini-code":{"draws":18,"losses":9,"wins":27},"deepseek/deepseek-v4-flash":{"draws":83,"losses":50,"wins":83},"deepseek/deepseek-v4-pro":{"draws":43,"losses":52,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":43,"losses":51,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":54,"losses":64,"wins":26},"fireworks/ember-1":{"draws":50,"losses":54,"wins":40},"gemini-3.1-pro-preview":{"draws":42,"losses":55,"wins":47},"google/gemini-3.1-flash-lite":{"draws":26,"losses":20,"wins":50},"google/gemini-3.5-flash":{"draws":50,"losses":81,"wins":49},"google/gemini-3.5-flash-lite":{"draws":83,"losses":73,"wins":96},"google/gemini-3.6-flash":{"draws":79,"losses":137,"wins":60},"google/gemini-3.8-flash":{"draws":32,"losses":87,"wins":25},"google/gemma-4-31b-it":{"draws":34,"losses":20,"wins":30},"gpt-4.1":{"draws":17,"losses":16,"wins":15},"gpt-4.1-nano":{"draws":11,"losses":1,"wins":6},"gpt-5":{"draws":40,"losses":51,"wins":35},"gpt-5.4":{"draws":46,"losses":71,"wins":21},"gpt-5.4-mini":{"draws":38,"losses":27,"wins":31},"gpt-5.4-nano":{"draws":35,"losses":49,"wins":60},"gpt-5.5":{"draws":49,"losses":59,"wins":24},"gpt-5.6-luna":{"draws":40,"losses":28,"wins":28},"gpt-5.6-sol":{"draws":21,"losses":99,"wins":24},"gpt-5.6-terra":{"draws":45,"losses":49,"wins":44},"gpt-6-astra":{"draws":15,"losses":127,"wins":2},"gpt-6-luna":{"draws":48,"losses":58,"wins":38},"gpt-6-sol":{"draws":24,"losses":106,"wins":14},"gpt-6.1-sol":{"draws":10,"losses":125,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":51,"losses":16,"wins":35},"inclusionai/ling-3.0-flash":{"draws":48,"losses":19,"wins":35},"inclusionai/ling-3.1-flash":{"draws":3,"losses":3,"wins":0},"meituan/longcat-2.0":{"draws":48,"losses":46,"wins":62},"meta/muse-glimmer-30b":{"draws":52,"losses":32,"wins":42},"meta/muse-spark-1.2":{"draws":36,"losses":66,"wins":36},"meta/muse-spark-1.3":{"draws":36,"losses":79,"wins":29},"meta/muse-wonder":{"draws":28,"losses":91,"wins":25},"minimax/minimax-m3":{"draws":25,"losses":21,"wins":32},"mistralai/mistral-large-4-0":{"draws":32,"losses":43,"wins":15},"mistralai/mistral-medium-3-5":{"draws":34,"losses":12,"wins":38},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":15,"wins":9},"moonshotai/kimi-k3":{"draws":46,"losses":61,"wins":31},"nex-agi/nex-n2-pro":{"draws":21,"losses":11,"wins":40},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":51,"losses":33,"wins":42},"o3":{"draws":40,"losses":88,"wins":70},"openai/gpt-oss-120b":{"draws":57,"losses":27,"wins":42},"poolside/laguna-s-2.1":{"draws":51,"losses":41,"wins":46},"qwen/qwen3.7-max":{"draws":31,"losses":32,"wins":21},"qwen/qwen3.7-plus":{"draws":26,"losses":18,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":51,"losses":66,"wins":27},"qwen/qwen3.8-27b":{"draws":32,"losses":45,"wins":25},"qwen/qwen3.8-flash":{"draws":31,"losses":37,"wins":28},"qwen/qwen3.8-max":{"draws":48,"losses":65,"wins":31},"qwen/qwen3.8-max-0902":{"draws":51,"losses":61,"wins":32},"stealth/ox-alpha":{"draws":146,"losses":228,"wins":100},"stealth/space-bunny-alpha":{"draws":43,"losses":40,"wins":31},"stepfun/step-3.7-flash":{"draws":30,"losses":31,"wins":41},"stepfun/step-5-preview":{"draws":4,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":29,"losses":28,"wins":21},"tencent/hy4-preview":{"draws":43,"losses":69,"wins":26},"thinkingmachines/inkling":{"draws":63,"losses":44,"wins":85},"thinkingmachines/inkling-small":{"draws":58,"losses":37,"wins":49},"unbiased/pareto-26.10-preview":{"draws":3,"losses":42,"wins":3},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":17},"x-ai/grok-4.5":{"draws":37,"losses":71,"wins":36},"x-ai/grok-4.6":{"draws":37,"losses":84,"wins":23},"x-ai/grok-4.7":{"draws":13,"losses":96,"wins":17},"x-ai/grok-build-0.1":{"draws":19,"losses":11,"wins":18},"xiaomi/mimo-v2.5":{"draws":91,"losses":47,"wins":84},"xiaomi/mimo-v2.5-pro":{"draws":28,"losses":28,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":43,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":62,"wins":17},"z-ai/glm-5.2":{"draws":109,"losses":110,"wins":69},"z-ai/glm-5.3":{"draws":28,"losses":95,"wins":15},"z-ai/glm-5.3-flash":{"draws":39,"losses":77,"wins":28},"z-ai/glm-5.3-flashx":{"draws":42,"losses":73,"wins":29}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":14,"wins":95},"claude-fable-5":{"draws":17,"losses":68,"wins":59},"claude-fable-5-1":{"draws":12,"losses":130,"wins":20},"claude-haiku-5-5":{"draws":21,"losses":41,"wins":76},"claude-opus-4-5":{"draws":44,"losses":44,"wins":146},"claude-opus-4-8":{"draws":17,"losses":43,"wins":72},"claude-opus-5":{"draws":30,"losses":157,"wins":59},"claude-opus-5-5":{"draws":12,"losses":122,"wins":22},"claude-sonnet-5":{"draws":20,"losses":19,"wins":105},"claude-sonnet-5-5":{"draws":15,"losses":59,"wins":70},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":46},"deepseek/deepseek-v4-flash":{"draws":29,"losses":21,"wins":166},"deepseek/deepseek-v4-pro":{"draws":16,"losses":29,"wins":87},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":27,"wins":87},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":43,"wins":75},"fireworks/ember-1":{"draws":23,"losses":38,"wins":83},"gemini-3.1-pro-preview":{"draws":18,"losses":31,"wins":95},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":83},"google/gemini-3.5-flash":{"draws":19,"losses":41,"wins":120},"google/gemini-3.5-flash-lite":{"draws":36,"losses":22,"wins":194},"google/gemini-3.6-flash":{"draws":41,"losses":74,"wins":161},"google/gemini-3.8-flash":{"draws":19,"losses":53,"wins":72},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":67},"gpt-4.1":{"draws":8,"losses":7,"wins":33},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":14},"gpt-5":{"draws":20,"losses":17,"wins":89},"gpt-5.4":{"draws":23,"losses":46,"wins":69},"gpt-5.4-mini":{"draws":21,"losses":12,"wins":63},"gpt-5.4-nano":{"draws":15,"losses":14,"wins":115},"gpt-5.5":{"draws":27,"losses":46,"wins":59},"gpt-5.6-luna":{"draws":21,"losses":24,"wins":99},"gpt-5.6-sol":{"draws":12,"losses":42,"wins":42},"gpt-5.6-terra":{"draws":32,"losses":24,"wins":82},"gpt-6-astra":{"draws":15,"losses":118,"wins":11},"gpt-6-luna":{"draws":30,"losses":22,"wins":92},"gpt-6-sol":{"draws":13,"losses":84,"wins":47},"gpt-6.1-sol":{"draws":13,"losses":110,"wins":21},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":19,"losses":0,"wins":83},"inclusionai/ling-3.0-flash":{"draws":12,"losses":4,"wins":86},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":22,"losses":13,"wins":121},"meta/muse-glimmer-30b":{"draws":19,"losses":8,"wins":99},"meta/muse-spark-1.2":{"draws":18,"losses":34,"wins":86},"meta/muse-spark-1.3":{"draws":21,"losses":48,"wins":75},"meta/muse-wonder":{"draws":22,"losses":65,"wins":57},"minimax/minimax-m3":{"draws":13,"losses":4,"wins":61},"mistralai/mistral-large-4-0":{"draws":19,"losses":20,"wins":51},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":66},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":7,"wins":23},"moonshotai/kimi-k3":{"draws":22,"losses":31,"wins":85},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":59},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":11,"wins":99},"o3":{"draws":14,"losses":31,"wins":153},"openai/gpt-oss-120b":{"draws":15,"losses":7,"wins":104},"poolside/laguna-s-2.1":{"draws":19,"losses":8,"wins":111},"qwen/qwen3.7-max":{"draws":11,"losses":14,"wins":59},"qwen/qwen3.7-plus":{"draws":15,"losses":7,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":36,"wins":85},"qwen/qwen3.8-27b":{"draws":17,"losses":18,"wins":67},"qwen/qwen3.8-flash":{"draws":19,"losses":19,"wins":58},"qwen/qwen3.8-max":{"draws":26,"losses":30,"wins":88},"qwen/qwen3.8-max-0902":{"draws":23,"losses":34,"wins":87},"stealth/ox-alpha":{"draws":74,"losses":114,"wins":286},"stealth/space-bunny-alpha":{"draws":20,"losses":14,"wins":80},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":84},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":14,"losses":9,"wins":55},"tencent/hy4-preview":{"draws":20,"losses":45,"wins":73},"thinkingmachines/inkling":{"draws":28,"losses":17,"wins":147},"thinkingmachines/inkling-small":{"draws":22,"losses":13,"wins":109},"unbiased/pareto-26.10-preview":{"draws":3,"losses":43,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":32},"x-ai/grok-4.5":{"draws":19,"losses":43,"wins":82},"x-ai/grok-4.6":{"draws":28,"losses":55,"wins":61},"x-ai/grok-4.7":{"draws":16,"losses":66,"wins":44},"x-ai/grok-build-0.1":{"draws":10,"losses":4,"wins":34},"xiaomi/mimo-v2.5":{"draws":37,"losses":13,"wins":172},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":14,"wins":54},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":19,"wins":62},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":35,"wins":44},"z-ai/glm-5.2":{"draws":37,"losses":45,"wins":206},"z-ai/glm-5.3":{"draws":23,"losses":55,"wins":60},"z-ai/glm-5.3-flash":{"draws":25,"losses":47,"wins":72},"z-ai/glm-5.3-flashx":{"draws":23,"losses":40,"wins":81}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":37,"losses":24,"wins":65},"claude-fable-5":{"draws":38,"losses":80,"wins":20},"claude-fable-5-1":{"draws":12,"losses":141,"wins":3},"claude-haiku-5-5":{"draws":39,"losses":56,"wins":37},"claude-opus-4-5":{"draws":80,"losses":77,"wins":67},"claude-opus-4-8":{"draws":32,"losses":59,"wins":35},"claude-opus-5":{"draws":26,"losses":187,"wins":21},"claude-opus-5-5":{"draws":9,"losses":138,"wins":3},"claude-sonnet-5":{"draws":53,"losses":41,"wins":44},"claude-sonnet-5-5":{"draws":34,"losses":74,"wins":30},"cohere/north-mini-code":{"draws":12,"losses":6,"wins":32},"deepseek/deepseek-v4-flash":{"draws":69,"losses":32,"wins":107},"deepseek/deepseek-v4-pro":{"draws":40,"losses":44,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":40,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":55,"losses":49,"wins":34},"fireworks/ember-1":{"draws":44,"losses":58,"wins":36},"gemini-3.1-pro-preview":{"draws":47,"losses":47,"wins":44},"google/gemini-3.1-flash-lite":{"draws":28,"losses":7,"wins":55},"google/gemini-3.5-flash":{"draws":57,"losses":52,"wins":63},"google/gemini-3.5-flash-lite":{"draws":77,"losses":49,"wins":114},"google/gemini-3.6-flash":{"draws":82,"losses":113,"wins":69},"google/gemini-3.8-flash":{"draws":42,"losses":61,"wins":35},"google/gemma-4-31b-it":{"draws":32,"losses":9,"wins":39},"gpt-4.1":{"draws":19,"losses":15,"wins":12},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":8},"gpt-5":{"draws":33,"losses":36,"wins":51},"gpt-5.4":{"draws":37,"losses":60,"wins":35},"gpt-5.4-mini":{"draws":39,"losses":21,"wins":32},"gpt-5.4-nano":{"draws":27,"losses":36,"wins":73},"gpt-5.5":{"draws":48,"losses":49,"wins":29},"gpt-5.6-luna":{"draws":45,"losses":44,"wins":49},"gpt-5.6-sol":{"draws":32,"losses":82,"wins":24},"gpt-5.6-terra":{"draws":32,"losses":28,"wins":28},"gpt-6-astra":{"draws":12,"losses":122,"wins":4},"gpt-6-luna":{"draws":40,"losses":57,"wins":41},"gpt-6-sol":{"draws":24,"losses":98,"wins":16},"gpt-6.1-sol":{"draws":9,"losses":122,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":42,"losses":7,"wins":49},"inclusionai/ling-3.0-flash":{"draws":35,"losses":7,"wins":60},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":45,"losses":32,"wins":71},"meta/muse-glimmer-30b":{"draws":47,"losses":16,"wins":57},"meta/muse-spark-1.2":{"draws":42,"losses":52,"wins":38},"meta/muse-spark-1.3":{"draws":33,"losses":65,"wins":40},"meta/muse-wonder":{"draws":31,"losses":77,"wins":30},"minimax/minimax-m3":{"draws":19,"losses":13,"wins":42},"mistralai/mistral-large-4-0":{"draws":41,"losses":26,"wins":19},"mistralai/mistral-medium-3-5":{"draws":26,"losses":8,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":11,"wins":13},"moonshotai/kimi-k3":{"draws":38,"losses":51,"wins":43},"nex-agi/nex-n2-pro":{"draws":19,"losses":8,"wins":41},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":19,"wins":55},"o3":{"draws":39,"losses":67,"wins":80},"openai/gpt-oss-120b":{"draws":42,"losses":12,"wins":66},"poolside/laguna-s-2.1":{"draws":52,"losses":16,"wins":62},"qwen/qwen3.7-max":{"draws":24,"losses":16,"wins":40},"qwen/qwen3.7-plus":{"draws":27,"losses":11,"wins":30},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":61,"wins":29},"qwen/qwen3.8-27b":{"draws":36,"losses":29,"wins":33},"qwen/qwen3.8-flash":{"draws":30,"losses":29,"wins":33},"qwen/qwen3.8-max":{"draws":58,"losses":44,"wins":36},"qwen/qwen3.8-max-0902":{"draws":48,"losses":53,"wins":37},"stealth/ox-alpha":{"draws":135,"losses":195,"wins":126},"stealth/space-bunny-alpha":{"draws":37,"losses":32,"wins":39},"stepfun/step-3.7-flash":{"draws":28,"losses":20,"wins":50},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":31,"losses":15,"wins":28},"tencent/hy4-preview":{"draws":37,"losses":59,"wins":36},"thinkingmachines/inkling":{"draws":55,"losses":36,"wins":91},"thinkingmachines/inkling-small":{"draws":46,"losses":22,"wins":70},"unbiased/pareto-26.10-preview":{"draws":3,"losses":39,"wins":4},"upstage/solar-mini4":{"draws":5,"losses":4,"wins":25},"x-ai/grok-4.5":{"draws":39,"losses":69,"wins":30},"x-ai/grok-4.6":{"draws":46,"losses":71,"wins":21},"x-ai/grok-4.7":{"draws":13,"losses":86,"wins":21},"x-ai/grok-build-0.1":{"draws":17,"losses":5,"wins":24},"xiaomi/mimo-v2.5":{"draws":80,"losses":15,"wins":117},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":12,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":32,"wins":34},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":44,"wins":24},"z-ai/glm-5.2":{"draws":117,"losses":63,"wins":96},"z-ai/glm-5.3":{"draws":36,"losses":75,"wins":21},"z-ai/glm-5.3-flash":{"draws":34,"losses":63,"wins":41},"z-ai/glm-5.3-flashx":{"draws":38,"losses":63,"wins":37}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":8,"wins":118},"claude-fable-5":{"draws":12,"losses":26,"wins":106},"claude-fable-5-1":{"draws":13,"losses":58,"wins":91},"claude-haiku-5-5":{"draws":10,"losses":7,"wins":121},"claude-opus-4-5":{"draws":15,"losses":15,"wins":204},"claude-opus-4-8":{"draws":8,"losses":11,"wins":113},"claude-opus-5":{"draws":23,"losses":57,"wins":166},"claude-opus-5-5":{"draws":17,"losses":65,"wins":74},"claude-sonnet-5":{"draws":6,"losses":8,"wins":130},"claude-sonnet-5-5":{"draws":13,"losses":26,"wins":105},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":52},"deepseek/deepseek-v4-flash":{"draws":11,"losses":5,"wins":200},"deepseek/deepseek-v4-pro":{"draws":12,"losses":8,"wins":112},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":1,"wins":123},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":6,"wins":122},"fireworks/ember-1":{"draws":10,"losses":6,"wins":128},"gemini-3.1-pro-preview":{"draws":10,"losses":4,"wins":130},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":94},"google/gemini-3.5-flash":{"draws":11,"losses":7,"wins":162},"google/gemini-3.5-flash-lite":{"draws":14,"losses":1,"wins":237},"google/gemini-3.6-flash":{"draws":20,"losses":17,"wins":239},"google/gemini-3.8-flash":{"draws":15,"losses":9,"wins":120},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":80},"gpt-4.1":{"draws":3,"losses":0,"wins":45},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":9,"losses":2,"wins":115},"gpt-5.4":{"draws":6,"losses":16,"wins":116},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":90},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":140},"gpt-5.5":{"draws":4,"losses":10,"wins":118},"gpt-5.6-luna":{"draws":15,"losses":2,"wins":127},"gpt-5.6-sol":{"draws":15,"losses":11,"wins":118},"gpt-5.6-terra":{"draws":12,"losses":4,"wins":122},"gpt-6-astra":{"draws":10,"losses":43,"wins":43},"gpt-6-luna":{"draws":15,"losses":9,"wins":120},"gpt-6-sol":{"draws":15,"losses":26,"wins":103},"gpt-6.1-sol":{"draws":18,"losses":49,"wins":77},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":95},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":96},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":146},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":120},"meta/muse-spark-1.2":{"draws":7,"losses":4,"wins":127},"meta/muse-spark-1.3":{"draws":14,"losses":13,"wins":117},"meta/muse-wonder":{"draws":14,"losses":16,"wins":114},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":75},"mistralai/mistral-large-4-0":{"draws":9,"losses":5,"wins":76},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":78},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":33},"moonshotai/kimi-k3":{"draws":9,"losses":10,"wins":119},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":68},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":1,"wins":116},"o3":{"draws":7,"losses":2,"wins":189},"openai/gpt-oss-120b":{"draws":12,"losses":0,"wins":114},"poolside/laguna-s-2.1":{"draws":7,"losses":0,"wins":131},"qwen/qwen3.7-max":{"draws":6,"losses":1,"wins":77},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":69},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":6,"wins":133},"qwen/qwen3.8-27b":{"draws":4,"losses":1,"wins":97},"qwen/qwen3.8-flash":{"draws":13,"losses":3,"wins":80},"qwen/qwen3.8-max":{"draws":13,"losses":2,"wins":129},"qwen/qwen3.8-max-0902":{"draws":9,"losses":6,"wins":129},"stealth/ox-alpha":{"draws":35,"losses":20,"wins":419},"stealth/space-bunny-alpha":{"draws":6,"losses":0,"wins":108},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":96},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":11,"losses":0,"wins":67},"tencent/hy4-preview":{"draws":9,"losses":5,"wins":124},"thinkingmachines/inkling":{"draws":11,"losses":3,"wins":178},"thinkingmachines/inkling-small":{"draws":9,"losses":0,"wins":135},"unbiased/pareto-26.10-preview":{"draws":6,"losses":20,"wins":22},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":34},"x-ai/grok-4.5":{"draws":9,"losses":14,"wins":121},"x-ai/grok-4.6":{"draws":11,"losses":14,"wins":119},"x-ai/grok-4.7":{"draws":12,"losses":22,"wins":92},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":45},"xiaomi/mimo-v2.5":{"draws":13,"losses":2,"wins":207},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":74},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":6,"wins":81},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":7,"wins":80},"z-ai/glm-5.2":{"draws":19,"losses":11,"wins":258},"z-ai/glm-5.3":{"draws":18,"losses":11,"wins":109},"z-ai/glm-5.3-flash":{"draws":13,"losses":8,"wins":123},"z-ai/glm-5.3-flashx":{"draws":14,"losses":9,"wins":121}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":39,"losses":39,"wins":54},"claude-fable-5":{"draws":31,"losses":85,"wins":28},"claude-fable-5-1":{"draws":10,"losses":146,"wins":6},"claude-haiku-5-5":{"draws":36,"losses":63,"wins":39},"claude-opus-4-5":{"draws":79,"losses":80,"wins":75},"claude-opus-4-8":{"draws":35,"losses":61,"wins":36},"claude-opus-5":{"draws":47,"losses":177,"wins":22},"claude-opus-5-5":{"draws":16,"losses":139,"wins":1},"claude-sonnet-5":{"draws":38,"losses":50,"wins":56},"claude-sonnet-5-5":{"draws":32,"losses":68,"wins":44},"cohere/north-mini-code":{"draws":14,"losses":8,"wins":32},"deepseek/deepseek-v4-flash":{"draws":66,"losses":45,"wins":105},"deepseek/deepseek-v4-pro":{"draws":34,"losses":42,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":46,"wins":50},"deepseek/deepseek-v4.1-flash":{"draws":44,"losses":60,"wins":40},"fireworks/ember-1":{"draws":39,"losses":64,"wins":41},"gemini-3.1-pro-preview":{"draws":36,"losses":62,"wins":46},"google/gemini-3.1-flash-lite":{"draws":26,"losses":11,"wins":59},"google/gemini-3.5-flash":{"draws":50,"losses":70,"wins":60},"google/gemini-3.5-flash-lite":{"draws":81,"losses":57,"wins":114},"google/gemini-3.6-flash":{"draws":81,"losses":128,"wins":67},"google/gemini-3.8-flash":{"draws":42,"losses":69,"wins":33},"google/gemma-4-31b-it":{"draws":28,"losses":18,"wins":38},"gpt-4.1":{"draws":10,"losses":19,"wins":19},"gpt-4.1-nano":{"draws":9,"losses":2,"wins":7},"gpt-5":{"draws":39,"losses":42,"wins":45},"gpt-5.4":{"draws":43,"losses":61,"wins":34},"gpt-5.4-mini":{"draws":43,"losses":13,"wins":40},"gpt-5.4-nano":{"draws":30,"losses":42,"wins":72},"gpt-5.5":{"draws":52,"losses":53,"wins":27},"gpt-5.6-luna":{"draws":48,"losses":38,"wins":58},"gpt-5.6-sol":{"draws":30,"losses":92,"wins":22},"gpt-5.6-terra":{"draws":40,"losses":41,"wins":57},"gpt-6-astra":{"draws":15,"losses":120,"wins":9},"gpt-6-luna":{"draws":24,"losses":36,"wins":36},"gpt-6-sol":{"draws":24,"losses":101,"wins":19},"gpt-6.1-sol":{"draws":13,"losses":125,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":41,"losses":9,"wins":52},"inclusionai/ling-3.0-flash":{"draws":35,"losses":13,"wins":54},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":39,"losses":33,"wins":84},"meta/muse-glimmer-30b":{"draws":45,"losses":18,"wins":63},"meta/muse-spark-1.2":{"draws":40,"losses":60,"wins":38},"meta/muse-spark-1.3":{"draws":25,"losses":83,"wins":36},"meta/muse-wonder":{"draws":34,"losses":77,"wins":33},"minimax/minimax-m3":{"draws":22,"losses":14,"wins":42},"mistralai/mistral-large-4-0":{"draws":27,"losses":31,"wins":32},"mistralai/mistral-medium-3-5":{"draws":30,"losses":7,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":10,"wins":14},"moonshotai/kimi-k3":{"draws":45,"losses":51,"wins":42},"nex-agi/nex-n2-pro":{"draws":15,"losses":11,"wins":46},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":25,"wins":59},"o3":{"draws":34,"losses":64,"wins":100},"openai/gpt-oss-120b":{"draws":41,"losses":27,"wins":58},"poolside/laguna-s-2.1":{"draws":45,"losses":34,"wins":59},"qwen/qwen3.7-max":{"draws":22,"losses":27,"wins":35},"qwen/qwen3.7-plus":{"draws":25,"losses":12,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":59,"wins":48},"qwen/qwen3.8-27b":{"draws":26,"losses":35,"wins":41},"qwen/qwen3.8-flash":{"draws":28,"losses":33,"wins":35},"qwen/qwen3.8-max":{"draws":37,"losses":57,"wins":50},"qwen/qwen3.8-max-0902":{"draws":41,"losses":56,"wins":47},"stealth/ox-alpha":{"draws":112,"losses":208,"wins":154},"stealth/space-bunny-alpha":{"draws":41,"losses":23,"wins":50},"stepfun/step-3.7-flash":{"draws":22,"losses":23,"wins":57},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":26,"losses":20,"wins":32},"tencent/hy4-preview":{"draws":39,"losses":64,"wins":35},"thinkingmachines/inkling":{"draws":56,"losses":40,"wins":96},"thinkingmachines/inkling-small":{"draws":40,"losses":32,"wins":72},"unbiased/pareto-26.10-preview":{"draws":2,"losses":45,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":10,"wins":25},"x-ai/grok-4.5":{"draws":34,"losses":66,"wins":44},"x-ai/grok-4.6":{"draws":39,"losses":81,"wins":24},"x-ai/grok-4.7":{"draws":10,"losses":96,"wins":20},"x-ai/grok-build-0.1":{"draws":20,"losses":4,"wins":24},"xiaomi/mimo-v2.5":{"draws":79,"losses":30,"wins":113},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":18,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":35,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":50,"wins":27},"z-ai/glm-5.2":{"draws":102,"losses":73,"wins":113},"z-ai/glm-5.3":{"draws":26,"losses":85,"wins":27},"z-ai/glm-5.3-flash":{"draws":38,"losses":71,"wins":35},"z-ai/glm-5.3-flashx":{"draws":30,"losses":72,"wins":42}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":15,"wins":102},"claude-fable-5":{"draws":19,"losses":43,"wins":82},"claude-fable-5-1":{"draws":15,"losses":110,"wins":37},"claude-haiku-5-5":{"draws":27,"losses":27,"wins":84},"claude-opus-4-5":{"draws":36,"losses":27,"wins":171},"claude-opus-4-8":{"draws":20,"losses":33,"wins":79},"claude-opus-5":{"draws":33,"losses":120,"wins":93},"claude-opus-5-5":{"draws":14,"losses":103,"wins":39},"claude-sonnet-5":{"draws":24,"losses":19,"wins":101},"claude-sonnet-5-5":{"draws":15,"losses":48,"wins":81},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":47},"deepseek/deepseek-v4-flash":{"draws":32,"losses":16,"wins":168},"deepseek/deepseek-v4-pro":{"draws":12,"losses":22,"wins":98},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":20,"wins":99},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":32,"wins":86},"fireworks/ember-1":{"draws":21,"losses":23,"wins":100},"gemini-3.1-pro-preview":{"draws":18,"losses":26,"wins":100},"google/gemini-3.1-flash-lite":{"draws":13,"losses":1,"wins":82},"google/gemini-3.5-flash":{"draws":28,"losses":26,"wins":126},"google/gemini-3.5-flash-lite":{"draws":39,"losses":22,"wins":191},"google/gemini-3.6-flash":{"draws":35,"losses":59,"wins":182},"google/gemini-3.8-flash":{"draws":22,"losses":33,"wins":89},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":73},"gpt-4.1":{"draws":7,"losses":7,"wins":34},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":15,"losses":16,"wins":95},"gpt-5.4":{"draws":15,"losses":22,"wins":101},"gpt-5.4-mini":{"draws":13,"losses":11,"wins":72},"gpt-5.4-nano":{"draws":20,"losses":12,"wins":112},"gpt-5.5":{"draws":20,"losses":29,"wins":83},"gpt-5.6-luna":{"draws":24,"losses":14,"wins":106},"gpt-5.6-sol":{"draws":13,"losses":47,"wins":84},"gpt-5.6-terra":{"draws":24,"losses":16,"wins":98},"gpt-6-astra":{"draws":15,"losses":103,"wins":26},"gpt-6-luna":{"draws":24,"losses":19,"wins":101},"gpt-6-sol":{"draws":14,"losses":41,"wins":41},"gpt-6.1-sol":{"draws":17,"losses":91,"wins":36},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":16,"losses":4,"wins":82},"inclusionai/ling-3.0-flash":{"draws":15,"losses":8,"wins":79},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":11,"losses":13,"wins":132},"meta/muse-glimmer-30b":{"draws":19,"losses":10,"wins":97},"meta/muse-spark-1.2":{"draws":18,"losses":24,"wins":96},"meta/muse-spark-1.3":{"draws":24,"losses":21,"wins":99},"meta/muse-wonder":{"draws":18,"losses":45,"wins":81},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":62},"mistralai/mistral-large-4-0":{"draws":15,"losses":14,"wins":61},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":73},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":2,"wins":27},"moonshotai/kimi-k3":{"draws":15,"losses":26,"wins":97},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":61},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":106},"o3":{"draws":10,"losses":17,"wins":171},"openai/gpt-oss-120b":{"draws":19,"losses":6,"wins":101},"poolside/laguna-s-2.1":{"draws":22,"losses":11,"wins":105},"qwen/qwen3.7-max":{"draws":16,"losses":10,"wins":58},"qwen/qwen3.7-plus":{"draws":10,"losses":7,"wins":55},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":32,"wins":93},"qwen/qwen3.8-27b":{"draws":17,"losses":14,"wins":71},"qwen/qwen3.8-flash":{"draws":9,"losses":18,"wins":69},"qwen/qwen3.8-max":{"draws":17,"losses":28,"wins":99},"qwen/qwen3.8-max-0902":{"draws":16,"losses":28,"wins":100},"stealth/ox-alpha":{"draws":61,"losses":73,"wins":340},"stealth/space-bunny-alpha":{"draws":16,"losses":11,"wins":87},"stepfun/step-3.7-flash":{"draws":13,"losses":4,"wins":85},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":8},"tencent/hy3-preview":{"draws":15,"losses":5,"wins":58},"tencent/hy4-preview":{"draws":19,"losses":26,"wins":93},"thinkingmachines/inkling":{"draws":25,"losses":13,"wins":154},"thinkingmachines/inkling-small":{"draws":18,"losses":8,"wins":118},"unbiased/pareto-26.10-preview":{"draws":5,"losses":34,"wins":9},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":32},"x-ai/grok-4.5":{"draws":20,"losses":32,"wins":92},"x-ai/grok-4.6":{"draws":21,"losses":31,"wins":92},"x-ai/grok-4.7":{"draws":13,"losses":60,"wins":53},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":38},"xiaomi/mimo-v2.5":{"draws":35,"losses":17,"wins":170},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":64},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":18,"wins":62},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":24,"wins":54},"z-ai/glm-5.2":{"draws":43,"losses":34,"wins":211},"z-ai/glm-5.3":{"draws":21,"losses":47,"wins":70},"z-ai/glm-5.3-flash":{"draws":19,"losses":35,"wins":90},"z-ai/glm-5.3-flashx":{"draws":20,"losses":37,"wins":87}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":8,"wins":114},"claude-fable-5":{"draws":11,"losses":32,"wins":101},"claude-fable-5-1":{"draws":13,"losses":72,"wins":77},"claude-haiku-5-5":{"draws":15,"losses":10,"wins":113},"claude-opus-4-5":{"draws":20,"losses":16,"wins":198},"claude-opus-4-8":{"draws":7,"losses":15,"wins":110},"claude-opus-5":{"draws":32,"losses":76,"wins":138},"claude-opus-5-5":{"draws":18,"losses":75,"wins":63},"claude-sonnet-5":{"draws":6,"losses":9,"wins":129},"claude-sonnet-5-5":{"draws":5,"losses":36,"wins":103},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":52},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":197},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":116},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":3,"wins":121},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":15,"wins":115},"fireworks/ember-1":{"draws":9,"losses":17,"wins":118},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":126},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":92},"google/gemini-3.5-flash":{"draws":11,"losses":18,"wins":151},"google/gemini-3.5-flash-lite":{"draws":16,"losses":1,"wins":235},"google/gemini-3.6-flash":{"draws":18,"losses":28,"wins":230},"google/gemini-3.8-flash":{"draws":20,"losses":17,"wins":107},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":80},"gpt-4.1":{"draws":4,"losses":1,"wins":43},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":17},"gpt-5":{"draws":6,"losses":5,"wins":115},"gpt-5.4":{"draws":9,"losses":20,"wins":109},"gpt-5.4-mini":{"draws":5,"losses":4,"wins":87},"gpt-5.4-nano":{"draws":7,"losses":5,"wins":132},"gpt-5.5":{"draws":8,"losses":21,"wins":103},"gpt-5.6-luna":{"draws":10,"losses":9,"wins":125},"gpt-5.6-sol":{"draws":13,"losses":21,"wins":110},"gpt-5.6-terra":{"draws":9,"losses":7,"wins":122},"gpt-6-astra":{"draws":18,"losses":77,"wins":49},"gpt-6-luna":{"draws":13,"losses":6,"wins":125},"gpt-6-sol":{"draws":17,"losses":36,"wins":91},"gpt-6.1-sol":{"draws":6,"losses":45,"wins":45},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":93},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":98},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":6,"losses":10,"wins":140},"meta/muse-glimmer-30b":{"draws":8,"losses":1,"wins":117},"meta/muse-spark-1.2":{"draws":9,"losses":18,"wins":111},"meta/muse-spark-1.3":{"draws":14,"losses":14,"wins":116},"meta/muse-wonder":{"draws":19,"losses":29,"wins":96},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":70},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":70},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":81},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":31},"moonshotai/kimi-k3":{"draws":10,"losses":14,"wins":114},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":68},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":112},"o3":{"draws":3,"losses":9,"wins":186},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":118},"poolside/laguna-s-2.1":{"draws":9,"losses":1,"wins":128},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":75},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":66},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":20,"wins":113},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":91},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":82},"qwen/qwen3.8-max":{"draws":11,"losses":9,"wins":124},"qwen/qwen3.8-max-0902":{"draws":12,"losses":11,"wins":121},"stealth/ox-alpha":{"draws":44,"losses":30,"wins":400},"stealth/space-bunny-alpha":{"draws":9,"losses":5,"wins":100},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":99},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":68},"tencent/hy4-preview":{"draws":7,"losses":13,"wins":118},"thinkingmachines/inkling":{"draws":13,"losses":6,"wins":173},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":138},"unbiased/pareto-26.10-preview":{"draws":2,"losses":28,"wins":18},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":35},"x-ai/grok-4.5":{"draws":10,"losses":16,"wins":118},"x-ai/grok-4.6":{"draws":16,"losses":14,"wins":114},"x-ai/grok-4.7":{"draws":6,"losses":41,"wins":79},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":48},"xiaomi/mimo-v2.5":{"draws":19,"losses":8,"wins":195},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":1,"wins":70},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":7,"wins":79},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":20,"wins":62},"z-ai/glm-5.2":{"draws":30,"losses":10,"wins":248},"z-ai/glm-5.3":{"draws":21,"losses":25,"wins":92},"z-ai/glm-5.3-flash":{"draws":13,"losses":16,"wins":115},"z-ai/glm-5.3-flashx":{"draws":19,"losses":18,"wins":107}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":4,"losses":2,"wins":0},"claude-fable-5-1":{"draws":3,"losses":4,"wins":1},"claude-haiku-5-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-5":{"draws":9,"losses":1,"wins":0},"claude-opus-4-8":{"draws":6,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":6,"wins":2},"claude-opus-5-5":{"draws":1,"losses":5,"wins":0},"claude-sonnet-5":{"draws":3,"losses":3,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":3,"wins":0},"google/gemini-3.6-flash":{"draws":11,"losses":1,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":0},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":1},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":1,"losses":5,"wins":0},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":4,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":1,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":0,"wins":1},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":1,"wins":2},"meta/muse-wonder":{"draws":4,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":0},"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":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":0},"o3":{"draws":4,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":1},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.8-max-0902":{"draws":1,"losses":4,"wins":1},"stealth/ox-alpha":{"draws":9,"losses":8,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":1,"wins":0},"x-ai/grok-4.6":{"draws":5,"losses":1,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":12,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":0},"z-ai/glm-5.3":{"draws":3,"losses":3,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":2,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":2,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":32,"wins":24},"claude-fable-5":{"draws":25,"losses":72,"wins":5},"claude-fable-5-1":{"draws":9,"losses":105,"wins":0},"claude-haiku-5-5":{"draws":28,"losses":68,"wins":4},"claude-opus-4-5":{"draws":72,"losses":88,"wins":8},"claude-opus-4-8":{"draws":32,"losses":56,"wins":10},"claude-opus-5":{"draws":31,"losses":129,"wins":6},"claude-opus-5-5":{"draws":8,"losses":102,"wins":0},"claude-sonnet-5":{"draws":38,"losses":54,"wins":10},"claude-sonnet-5-5":{"draws":25,"losses":65,"wins":12},"cohere/north-mini-code":{"draws":12,"losses":13,"wins":13},"deepseek/deepseek-v4-flash":{"draws":66,"losses":61,"wins":25},"deepseek/deepseek-v4-pro":{"draws":37,"losses":45,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":47,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":45,"losses":48,"wins":9},"fireworks/ember-1":{"draws":44,"losses":52,"wins":6},"gemini-3.1-pro-preview":{"draws":40,"losses":40,"wins":22},"google/gemini-3.1-flash-lite":{"draws":27,"losses":17,"wins":28},"google/gemini-3.5-flash":{"draws":47,"losses":65,"wins":16},"google/gemini-3.5-flash-lite":{"draws":76,"losses":71,"wins":33},"google/gemini-3.6-flash":{"draws":69,"losses":113,"wins":12},"google/gemini-3.8-flash":{"draws":32,"losses":66,"wins":4},"google/gemma-4-31b-it":{"draws":30,"losses":18,"wins":16},"gpt-4.1":{"draws":15,"losses":11,"wins":8},"gpt-4.1-nano":{"draws":6,"losses":5,"wins":3},"gpt-5":{"draws":35,"losses":41,"wins":8},"gpt-5.4":{"draws":42,"losses":52,"wins":2},"gpt-5.4-mini":{"draws":31,"losses":23,"wins":14},"gpt-5.4-nano":{"draws":32,"losses":56,"wins":14},"gpt-5.5":{"draws":40,"losses":42,"wins":8},"gpt-5.6-luna":{"draws":51,"losses":35,"wins":16},"gpt-5.6-sol":{"draws":19,"losses":83,"wins":0},"gpt-5.6-terra":{"draws":42,"losses":49,"wins":7},"gpt-6-astra":{"draws":7,"losses":95,"wins":0},"gpt-6-luna":{"draws":41,"losses":52,"wins":9},"gpt-6-sol":{"draws":16,"losses":82,"wins":4},"gpt-6.1-sol":{"draws":9,"losses":93,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":10,"wins":10},"inclusionai/ling-3.0-flash":{"draws":35,"losses":19,"wins":18},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":44,"losses":42,"wins":26},"meta/muse-glimmer-30b":{"draws":44,"losses":23,"wins":17},"meta/muse-spark-1.2":{"draws":34,"losses":51,"wins":11},"meta/muse-spark-1.3":{"draws":29,"losses":65,"wins":8},"meta/muse-wonder":{"draws":28,"losses":70,"wins":4},"minimax/minimax-m3":{"draws":26,"losses":19,"wins":9},"mistralai/mistral-large-4-0":{"draws":26,"losses":27,"wins":9},"mistralai/mistral-medium-3-5":{"draws":29,"losses":16,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":14,"wins":2},"moonshotai/kimi-k3":{"draws":44,"losses":44,"wins":8},"nex-agi/nex-n2-pro":{"draws":21,"losses":15,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":44,"losses":26,"wins":22},"o3":{"draws":33,"losses":87,"wins":16},"openai/gpt-oss-120b":{"draws":38,"losses":29,"wins":21},"poolside/laguna-s-2.1":{"draws":40,"losses":28,"wins":22},"qwen/qwen3.7-max":{"draws":25,"losses":23,"wins":12},"qwen/qwen3.7-plus":{"draws":22,"losses":22,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":56,"wins":6},"qwen/qwen3.8-27b":{"draws":22,"losses":43,"wins":7},"qwen/qwen3.8-flash":{"draws":31,"losses":31,"wins":6},"qwen/qwen3.8-max":{"draws":43,"losses":51,"wins":8},"qwen/qwen3.8-max-0902":{"draws":44,"losses":48,"wins":10},"stealth/ox-alpha":{"draws":102,"losses":175,"wins":33},"stealth/space-bunny-alpha":{"draws":37,"losses":35,"wins":10},"stepfun/step-3.7-flash":{"draws":22,"losses":38,"wins":8},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":28,"losses":16,"wins":12},"tencent/hy4-preview":{"draws":39,"losses":50,"wins":7},"thinkingmachines/inkling":{"draws":52,"losses":44,"wins":32},"thinkingmachines/inkling-small":{"draws":49,"losses":31,"wins":22},"unbiased/pareto-26.10-preview":{"draws":1,"losses":33,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":11},"x-ai/grok-4.5":{"draws":34,"losses":64,"wins":4},"x-ai/grok-4.6":{"draws":31,"losses":64,"wins":7},"x-ai/grok-4.7":{"draws":13,"losses":72,"wins":3},"x-ai/grok-build-0.1":{"draws":18,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":79,"losses":66,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":25,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":41,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":48,"wins":1},"z-ai/glm-5.2":{"draws":87,"losses":98,"wins":19},"z-ai/glm-5.3":{"draws":28,"losses":69,"wins":3},"z-ai/glm-5.3-flash":{"draws":26,"losses":65,"wins":11},"z-ai/glm-5.3-flashx":{"draws":29,"losses":68,"wins":5}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":39,"losses":39,"wins":16},"claude-fable-5":{"draws":18,"losses":80,"wins":4},"claude-fable-5-1":{"draws":7,"losses":107,"wins":0},"claude-haiku-5-5":{"draws":32,"losses":61,"wins":5},"claude-opus-4-5":{"draws":59,"losses":88,"wins":19},"claude-opus-4-8":{"draws":29,"losses":65,"wins":0},"claude-opus-5":{"draws":26,"losses":132,"wins":8},"claude-opus-5-5":{"draws":7,"losses":107,"wins":0},"claude-sonnet-5":{"draws":36,"losses":58,"wins":8},"claude-sonnet-5-5":{"draws":26,"losses":69,"wins":7},"cohere/north-mini-code":{"draws":16,"losses":6,"wins":12},"deepseek/deepseek-v4-flash":{"draws":67,"losses":53,"wins":38},"deepseek/deepseek-v4-pro":{"draws":34,"losses":44,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":44,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":44,"losses":49,"wins":9},"fireworks/ember-1":{"draws":44,"losses":54,"wins":4},"gemini-3.1-pro-preview":{"draws":39,"losses":53,"wins":10},"google/gemini-3.1-flash-lite":{"draws":25,"losses":19,"wins":22},"google/gemini-3.5-flash":{"draws":39,"losses":77,"wins":12},"google/gemini-3.5-flash-lite":{"draws":67,"losses":78,"wins":31},"google/gemini-3.6-flash":{"draws":68,"losses":108,"wins":18},"google/gemini-3.8-flash":{"draws":32,"losses":69,"wins":1},"google/gemma-4-31b-it":{"draws":32,"losses":13,"wins":13},"gpt-4.1":{"draws":13,"losses":20,"wins":1},"gpt-4.1-nano":{"draws":6,"losses":6,"wins":2},"gpt-5":{"draws":34,"losses":34,"wins":20},"gpt-5.4":{"draws":27,"losses":57,"wins":14},"gpt-5.4-mini":{"draws":31,"losses":25,"wins":12},"gpt-5.4-nano":{"draws":30,"losses":48,"wins":26},"gpt-5.5":{"draws":41,"losses":44,"wins":7},"gpt-5.6-luna":{"draws":48,"losses":35,"wins":19},"gpt-5.6-sol":{"draws":12,"losses":86,"wins":4},"gpt-5.6-terra":{"draws":35,"losses":60,"wins":7},"gpt-6-astra":{"draws":5,"losses":96,"wins":1},"gpt-6-luna":{"draws":35,"losses":54,"wins":13},"gpt-6-sol":{"draws":15,"losses":79,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":98,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":35,"losses":18,"wins":19},"inclusionai/ling-3.0-flash":{"draws":22,"losses":15,"wins":15},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":50,"losses":38,"wins":20},"meta/muse-glimmer-30b":{"draws":50,"losses":22,"wins":14},"meta/muse-spark-1.2":{"draws":27,"losses":58,"wins":11},"meta/muse-spark-1.3":{"draws":16,"losses":76,"wins":10},"meta/muse-wonder":{"draws":18,"losses":79,"wins":5},"minimax/minimax-m3":{"draws":21,"losses":23,"wins":10},"mistralai/mistral-large-4-0":{"draws":28,"losses":25,"wins":9},"mistralai/mistral-medium-3-5":{"draws":25,"losses":18,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":5},"moonshotai/kimi-k3":{"draws":31,"losses":53,"wins":12},"nex-agi/nex-n2-pro":{"draws":20,"losses":11,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":26,"wins":21},"o3":{"draws":33,"losses":90,"wins":17},"openai/gpt-oss-120b":{"draws":38,"losses":40,"wins":8},"poolside/laguna-s-2.1":{"draws":45,"losses":36,"wins":13},"qwen/qwen3.7-max":{"draws":29,"losses":24,"wins":7},"qwen/qwen3.7-plus":{"draws":20,"losses":16,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":57,"wins":4},"qwen/qwen3.8-27b":{"draws":15,"losses":46,"wins":13},"qwen/qwen3.8-flash":{"draws":27,"losses":36,"wins":5},"qwen/qwen3.8-max":{"draws":41,"losses":47,"wins":14},"qwen/qwen3.8-max-0902":{"draws":39,"losses":54,"wins":9},"stealth/ox-alpha":{"draws":94,"losses":208,"wins":26},"stealth/space-bunny-alpha":{"draws":34,"losses":31,"wins":11},"stepfun/step-3.7-flash":{"draws":30,"losses":30,"wins":16},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":25,"wins":7},"tencent/hy4-preview":{"draws":37,"losses":56,"wins":5},"thinkingmachines/inkling":{"draws":51,"losses":52,"wins":27},"thinkingmachines/inkling-small":{"draws":50,"losses":33,"wins":19},"unbiased/pareto-26.10-preview":{"draws":2,"losses":32,"wins":0},"upstage/solar-mini4":{"draws":10,"losses":11,"wins":5},"x-ai/grok-4.5":{"draws":24,"losses":72,"wins":6},"x-ai/grok-4.6":{"draws":35,"losses":62,"wins":5},"x-ai/grok-4.7":{"draws":9,"losses":74,"wins":5},"x-ai/grok-build-0.1":{"draws":13,"losses":18,"wins":3},"xiaomi/mimo-v2.5":{"draws":71,"losses":55,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":27,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":41,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":49,"wins":5},"z-ai/glm-5.2":{"draws":101,"losses":78,"wins":25},"z-ai/glm-5.3":{"draws":22,"losses":71,"wins":3},"z-ai/glm-5.3-flash":{"draws":34,"losses":56,"wins":12},"z-ai/glm-5.3-flashx":{"draws":34,"losses":60,"wins":8}},"inclusionai/ling-3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":0},"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-5":{"draws":3,"losses":7,"wins":0},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":4,"losses":2,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":0,"wins":1},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":5,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":6,"losses":0,"wins":0},"gpt-5.4":{"draws":5,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":1},"gpt-5.5":{"draws":3,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":0,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":3,"losses":2,"wins":1},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":0,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":5,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":3,"wins":0},"meta/muse-wonder":{"draws":0,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":0},"o3":{"draws":8,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":0},"qwen/qwen3.8-max-0902":{"draws":6,"losses":0,"wins":0},"stealth/ox-alpha":{"draws":6,"losses":9,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":4,"wins":1},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":3,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":2,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":0,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":43,"losses":60,"wins":41},"claude-fable-5":{"draws":23,"losses":113,"wins":20},"claude-fable-5-1":{"draws":5,"losses":165,"wins":5},"claude-haiku-5-5":{"draws":33,"losses":96,"wins":21},"claude-opus-4-5":{"draws":67,"losses":151,"wins":36},"claude-opus-4-8":{"draws":33,"losses":90,"wins":21},"claude-opus-5":{"draws":28,"losses":208,"wins":20},"claude-opus-5-5":{"draws":11,"losses":154,"wins":7},"claude-sonnet-5":{"draws":47,"losses":82,"wins":27},"claude-sonnet-5-5":{"draws":21,"losses":104,"wins":31},"cohere/north-mini-code":{"draws":18,"losses":13,"wins":37},"deepseek/deepseek-v4-flash":{"draws":68,"losses":90,"wins":76},"deepseek/deepseek-v4-pro":{"draws":33,"losses":85,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":45,"losses":69,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":85,"wins":34},"fireworks/ember-1":{"draws":48,"losses":88,"wins":20},"gemini-3.1-pro-preview":{"draws":37,"losses":75,"wins":44},"google/gemini-3.1-flash-lite":{"draws":25,"losses":27,"wins":60},"google/gemini-3.5-flash":{"draws":39,"losses":123,"wins":36},"google/gemini-3.5-flash-lite":{"draws":78,"losses":119,"wins":81},"google/gemini-3.6-flash":{"draws":69,"losses":187,"wins":44},"google/gemini-3.8-flash":{"draws":33,"losses":108,"wins":15},"google/gemma-4-31b-it":{"draws":33,"losses":26,"wins":35},"gpt-4.1":{"draws":18,"losses":24,"wins":10},"gpt-4.1-nano":{"draws":10,"losses":2,"wins":6},"gpt-5":{"draws":42,"losses":65,"wins":31},"gpt-5.4":{"draws":37,"losses":95,"wins":20},"gpt-5.4-mini":{"draws":42,"losses":36,"wins":26},"gpt-5.4-nano":{"draws":28,"losses":83,"wins":49},"gpt-5.5":{"draws":50,"losses":72,"wins":22},"gpt-5.6-luna":{"draws":48,"losses":62,"wins":46},"gpt-5.6-sol":{"draws":22,"losses":121,"wins":13},"gpt-5.6-terra":{"draws":45,"losses":71,"wins":32},"gpt-6-astra":{"draws":8,"losses":146,"wins":2},"gpt-6-luna":{"draws":39,"losses":84,"wins":33},"gpt-6-sol":{"draws":11,"losses":132,"wins":13},"gpt-6.1-sol":{"draws":6,"losses":140,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":44,"losses":26,"wins":42},"inclusionai/ling-3.0-flash":{"draws":50,"losses":20,"wins":38},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":44,"losses":42,"wins":42},"meta/muse-glimmer-30b":{"draws":53,"losses":44,"wins":39},"meta/muse-spark-1.2":{"draws":29,"losses":93,"wins":26},"meta/muse-spark-1.3":{"draws":32,"losses":103,"wins":21},"meta/muse-wonder":{"draws":31,"losses":105,"wins":20},"minimax/minimax-m3":{"draws":19,"losses":30,"wins":35},"mistralai/mistral-large-4-0":{"draws":34,"losses":46,"wins":16},"mistralai/mistral-medium-3-5":{"draws":36,"losses":22,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":24,"wins":7},"moonshotai/kimi-k3":{"draws":47,"losses":76,"wins":25},"nex-agi/nex-n2-pro":{"draws":20,"losses":26,"wins":40},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":53,"losses":43,"wins":42},"o3":{"draws":38,"losses":136,"wins":58},"openai/gpt-oss-120b":{"draws":44,"losses":38,"wins":56},"poolside/laguna-s-2.1":{"draws":54,"losses":53,"wins":43},"qwen/qwen3.7-max":{"draws":30,"losses":44,"wins":18},"qwen/qwen3.7-plus":{"draws":17,"losses":28,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":43,"losses":91,"wins":22},"qwen/qwen3.8-27b":{"draws":23,"losses":67,"wins":18},"qwen/qwen3.8-flash":{"draws":35,"losses":47,"wins":22},"qwen/qwen3.8-max":{"draws":49,"losses":79,"wins":28},"qwen/qwen3.8-max-0902":{"draws":32,"losses":101,"wins":23},"stealth/ox-alpha":{"draws":120,"losses":317,"wins":73},"stealth/space-bunny-alpha":{"draws":40,"losses":57,"wins":29},"stepfun/step-3.7-flash":{"draws":28,"losses":48,"wins":38},"stepfun/step-5-preview":{"draws":7,"losses":8,"wins":1},"tencent/hy3-preview":{"draws":25,"losses":32,"wins":25},"tencent/hy4-preview":{"draws":40,"losses":91,"wins":21},"thinkingmachines/inkling":{"draws":55,"losses":77,"wins":74},"thinkingmachines/inkling-small":{"draws":54,"losses":47,"wins":55},"unbiased/pareto-26.10-preview":{"draws":1,"losses":49,"wins":2},"upstage/solar-mini4":{"draws":9,"losses":16,"wins":17},"x-ai/grok-4.5":{"draws":31,"losses":101,"wins":24},"x-ai/grok-4.6":{"draws":42,"losses":94,"wins":20},"x-ai/grok-4.7":{"draws":8,"losses":120,"wins":8},"x-ai/grok-build-0.1":{"draws":19,"losses":17,"wins":16},"xiaomi/mimo-v2.5":{"draws":81,"losses":78,"wins":79},"xiaomi/mimo-v2.5-pro":{"draws":27,"losses":40,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":54,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":75,"wins":10},"z-ai/glm-5.2":{"draws":93,"losses":146,"wins":73},"z-ai/glm-5.3":{"draws":28,"losses":113,"wins":11},"z-ai/glm-5.3-flash":{"draws":33,"losses":94,"wins":29},"z-ai/glm-5.3-flashx":{"draws":36,"losses":101,"wins":19}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":46,"losses":37,"wins":33},"claude-fable-5":{"draws":27,"losses":92,"wins":7},"claude-fable-5-1":{"draws":9,"losses":133,"wins":1},"claude-haiku-5-5":{"draws":37,"losses":68,"wins":15},"claude-opus-4-5":{"draws":74,"losses":101,"wins":29},"claude-opus-4-8":{"draws":32,"losses":66,"wins":16},"claude-opus-5":{"draws":15,"losses":192,"wins":23},"claude-opus-5-5":{"draws":7,"losses":131,"wins":0},"claude-sonnet-5":{"draws":43,"losses":64,"wins":19},"claude-sonnet-5-5":{"draws":21,"losses":84,"wins":21},"cohere/north-mini-code":{"draws":22,"losses":11,"wins":17},"deepseek/deepseek-v4-flash":{"draws":88,"losses":55,"wins":43},"deepseek/deepseek-v4-pro":{"draws":37,"losses":56,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":40,"losses":58,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":52,"losses":60,"wins":14},"fireworks/ember-1":{"draws":44,"losses":67,"wins":15},"gemini-3.1-pro-preview":{"draws":49,"losses":62,"wins":15},"google/gemini-3.1-flash-lite":{"draws":33,"losses":19,"wins":30},"google/gemini-3.5-flash":{"draws":52,"losses":81,"wins":25},"google/gemini-3.5-flash-lite":{"draws":91,"losses":78,"wins":51},"google/gemini-3.6-flash":{"draws":76,"losses":132,"wins":34},"google/gemini-3.8-flash":{"draws":34,"losses":78,"wins":14},"google/gemma-4-31b-it":{"draws":38,"losses":17,"wins":17},"gpt-4.1":{"draws":19,"losses":13,"wins":10},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":2},"gpt-5":{"draws":44,"losses":47,"wins":23},"gpt-5.4":{"draws":31,"losses":74,"wins":17},"gpt-5.4-mini":{"draws":43,"losses":30,"wins":11},"gpt-5.4-nano":{"draws":31,"losses":49,"wins":42},"gpt-5.5":{"draws":48,"losses":56,"wins":16},"gpt-5.6-luna":{"draws":52,"losses":42,"wins":32},"gpt-5.6-sol":{"draws":19,"losses":99,"wins":8},"gpt-5.6-terra":{"draws":47,"losses":57,"wins":16},"gpt-6-astra":{"draws":6,"losses":120,"wins":0},"gpt-6-luna":{"draws":45,"losses":63,"wins":18},"gpt-6-sol":{"draws":19,"losses":97,"wins":10},"gpt-6.1-sol":{"draws":8,"losses":117,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":44,"losses":17,"wins":23},"inclusionai/ling-3.0-flash":{"draws":50,"losses":14,"wins":22},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":53,"losses":39,"wins":44},"meta/muse-glimmer-30b":{"draws":40,"losses":18,"wins":18},"meta/muse-spark-1.2":{"draws":32,"losses":73,"wins":19},"meta/muse-spark-1.3":{"draws":36,"losses":74,"wins":16},"meta/muse-wonder":{"draws":26,"losses":85,"wins":15},"minimax/minimax-m3":{"draws":25,"losses":25,"wins":20},"mistralai/mistral-large-4-0":{"draws":27,"losses":36,"wins":19},"mistralai/mistral-medium-3-5":{"draws":35,"losses":10,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":17,"wins":10},"moonshotai/kimi-k3":{"draws":38,"losses":67,"wins":19},"nex-agi/nex-n2-pro":{"draws":25,"losses":14,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":55,"losses":27,"wins":26},"o3":{"draws":40,"losses":101,"wins":31},"openai/gpt-oss-120b":{"draws":47,"losses":38,"wins":27},"poolside/laguna-s-2.1":{"draws":54,"losses":41,"wins":29},"qwen/qwen3.7-max":{"draws":29,"losses":27,"wins":16},"qwen/qwen3.7-plus":{"draws":25,"losses":15,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":64,"wins":15},"qwen/qwen3.8-27b":{"draws":25,"losses":47,"wins":14},"qwen/qwen3.8-flash":{"draws":37,"losses":26,"wins":21},"qwen/qwen3.8-max":{"draws":41,"losses":61,"wins":24},"qwen/qwen3.8-max-0902":{"draws":46,"losses":68,"wins":12},"stealth/ox-alpha":{"draws":104,"losses":266,"wins":56},"stealth/space-bunny-alpha":{"draws":39,"losses":36,"wins":27},"stepfun/step-3.7-flash":{"draws":26,"losses":27,"wins":35},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":26,"losses":31,"wins":13},"tencent/hy4-preview":{"draws":43,"losses":69,"wins":10},"thinkingmachines/inkling":{"draws":60,"losses":56,"wins":58},"thinkingmachines/inkling-small":{"draws":60,"losses":24,"wins":42},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":0},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":9},"x-ai/grok-4.5":{"draws":31,"losses":81,"wins":14},"x-ai/grok-4.6":{"draws":40,"losses":78,"wins":8},"x-ai/grok-4.7":{"draws":6,"losses":93,"wins":13},"x-ai/grok-build-0.1":{"draws":18,"losses":14,"wins":10},"xiaomi/mimo-v2.5":{"draws":80,"losses":50,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":25,"losses":28,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":43,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":56,"wins":13},"z-ai/glm-5.2":{"draws":114,"losses":95,"wins":43},"z-ai/glm-5.3":{"draws":25,"losses":83,"wins":12},"z-ai/glm-5.3-flash":{"draws":30,"losses":80,"wins":16},"z-ai/glm-5.3-flashx":{"draws":36,"losses":71,"wins":19}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":33,"losses":31,"wins":62},"claude-fable-5":{"draws":22,"losses":85,"wins":31},"claude-fable-5-1":{"draws":8,"losses":141,"wins":7},"claude-haiku-5-5":{"draws":26,"losses":65,"wins":41},"claude-opus-4-5":{"draws":61,"losses":62,"wins":101},"claude-opus-4-8":{"draws":29,"losses":53,"wins":44},"claude-opus-5":{"draws":31,"losses":179,"wins":34},"claude-opus-5-5":{"draws":12,"losses":128,"wins":10},"claude-sonnet-5":{"draws":40,"losses":36,"wins":62},"claude-sonnet-5-5":{"draws":27,"losses":70,"wins":41},"cohere/north-mini-code":{"draws":3,"losses":9,"wins":40},"deepseek/deepseek-v4-flash":{"draws":52,"losses":34,"wins":120},"deepseek/deepseek-v4-pro":{"draws":24,"losses":45,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":38,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":53,"wins":50},"fireworks/ember-1":{"draws":37,"losses":53,"wins":48},"gemini-3.1-pro-preview":{"draws":33,"losses":48,"wins":57},"google/gemini-3.1-flash-lite":{"draws":21,"losses":9,"wins":60},"google/gemini-3.5-flash":{"draws":35,"losses":58,"wins":79},"google/gemini-3.5-flash-lite":{"draws":60,"losses":47,"wins":133},"google/gemini-3.6-flash":{"draws":54,"losses":103,"wins":107},"google/gemini-3.8-flash":{"draws":25,"losses":59,"wins":54},"google/gemma-4-31b-it":{"draws":23,"losses":17,"wins":40},"gpt-4.1":{"draws":17,"losses":8,"wins":21},"gpt-4.1-nano":{"draws":9,"losses":2,"wins":5},"gpt-5":{"draws":26,"losses":32,"wins":64},"gpt-5.4":{"draws":27,"losses":58,"wins":47},"gpt-5.4-mini":{"draws":27,"losses":20,"wins":45},"gpt-5.4-nano":{"draws":22,"losses":44,"wins":70},"gpt-5.5":{"draws":27,"losses":58,"wins":43},"gpt-5.6-luna":{"draws":36,"losses":36,"wins":66},"gpt-5.6-sol":{"draws":18,"losses":86,"wins":34},"gpt-5.6-terra":{"draws":42,"losses":38,"wins":52},"gpt-6-astra":{"draws":7,"losses":127,"wins":4},"gpt-6-luna":{"draws":40,"losses":38,"wins":60},"gpt-6-sol":{"draws":18,"losses":96,"wins":24},"gpt-6.1-sol":{"draws":9,"losses":111,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":34,"losses":11,"wins":51},"inclusionai/ling-3.0-flash":{"draws":27,"losses":11,"wins":58},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":29,"losses":26,"wins":93},"meta/muse-glimmer-30b":{"draws":32,"losses":19,"wins":73},"meta/muse-spark-1.2":{"draws":20,"losses":34,"wins":34},"meta/muse-spark-1.3":{"draws":26,"losses":62,"wins":50},"meta/muse-wonder":{"draws":26,"losses":71,"wins":41},"minimax/minimax-m3":{"draws":14,"losses":10,"wins":52},"mistralai/mistral-large-4-0":{"draws":16,"losses":27,"wins":45},"mistralai/mistral-medium-3-5":{"draws":21,"losses":11,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":12,"wins":15},"moonshotai/kimi-k3":{"draws":26,"losses":52,"wins":56},"nex-agi/nex-n2-pro":{"draws":11,"losses":11,"wins":46},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":19,"wins":68},"o3":{"draws":24,"losses":70,"wins":92},"openai/gpt-oss-120b":{"draws":32,"losses":14,"wins":76},"poolside/laguna-s-2.1":{"draws":29,"losses":19,"wins":86},"qwen/qwen3.7-max":{"draws":11,"losses":19,"wins":50},"qwen/qwen3.7-plus":{"draws":16,"losses":12,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":54,"wins":47},"qwen/qwen3.8-27b":{"draws":22,"losses":38,"wins":36},"qwen/qwen3.8-flash":{"draws":23,"losses":27,"wins":42},"qwen/qwen3.8-max":{"draws":36,"losses":51,"wins":51},"qwen/qwen3.8-max-0902":{"draws":31,"losses":55,"wins":52},"stealth/ox-alpha":{"draws":106,"losses":203,"wins":149},"stealth/space-bunny-alpha":{"draws":31,"losses":26,"wins":53},"stepfun/step-3.7-flash":{"draws":15,"losses":24,"wins":57},"stepfun/step-5-preview":{"draws":0,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":21,"losses":13,"wins":42},"tencent/hy4-preview":{"draws":19,"losses":60,"wins":53},"thinkingmachines/inkling":{"draws":50,"losses":35,"wins":101},"thinkingmachines/inkling-small":{"draws":37,"losses":27,"wins":74},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":4},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":22},"x-ai/grok-4.5":{"draws":33,"losses":68,"wins":37},"x-ai/grok-4.6":{"draws":31,"losses":76,"wins":31},"x-ai/grok-4.7":{"draws":9,"losses":84,"wins":29},"x-ai/grok-build-0.1":{"draws":10,"losses":8,"wins":28},"xiaomi/mimo-v2.5":{"draws":62,"losses":26,"wins":124},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":21,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":27,"wins":48},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":53,"wins":28},"z-ai/glm-5.2":{"draws":66,"losses":75,"wins":135},"z-ai/glm-5.3":{"draws":22,"losses":67,"wins":43},"z-ai/glm-5.3-flash":{"draws":20,"losses":61,"wins":57},"z-ai/glm-5.3-flashx":{"draws":29,"losses":60,"wins":49}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":22,"wins":81},"claude-fable-5":{"draws":26,"losses":77,"wins":41},"claude-fable-5-1":{"draws":11,"losses":136,"wins":15},"claude-haiku-5-5":{"draws":26,"losses":61,"wins":51},"claude-opus-4-5":{"draws":54,"losses":54,"wins":126},"claude-opus-4-8":{"draws":27,"losses":51,"wins":54},"claude-opus-5":{"draws":33,"losses":163,"wins":50},"claude-opus-5-5":{"draws":8,"losses":134,"wins":14},"claude-sonnet-5":{"draws":38,"losses":34,"wins":72},"claude-sonnet-5-5":{"draws":22,"losses":68,"wins":54},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":47},"deepseek/deepseek-v4-flash":{"draws":41,"losses":24,"wins":151},"deepseek/deepseek-v4-pro":{"draws":20,"losses":36,"wins":76},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":39,"wins":66},"deepseek/deepseek-v4.1-flash":{"draws":30,"losses":53,"wins":61},"fireworks/ember-1":{"draws":39,"losses":42,"wins":63},"gemini-3.1-pro-preview":{"draws":26,"losses":39,"wins":79},"google/gemini-3.1-flash-lite":{"draws":16,"losses":5,"wins":75},"google/gemini-3.5-flash":{"draws":33,"losses":48,"wins":99},"google/gemini-3.5-flash-lite":{"draws":52,"losses":36,"wins":164},"google/gemini-3.6-flash":{"draws":50,"losses":93,"wins":133},"google/gemini-3.8-flash":{"draws":34,"losses":59,"wins":51},"google/gemma-4-31b-it":{"draws":23,"losses":8,"wins":53},"gpt-4.1":{"draws":18,"losses":4,"wins":26},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":29,"losses":26,"wins":71},"gpt-5.4":{"draws":30,"losses":55,"wins":53},"gpt-5.4-mini":{"draws":19,"losses":11,"wins":66},"gpt-5.4-nano":{"draws":27,"losses":27,"wins":90},"gpt-5.5":{"draws":31,"losses":48,"wins":53},"gpt-5.6-luna":{"draws":36,"losses":29,"wins":79},"gpt-5.6-sol":{"draws":21,"losses":75,"wins":48},"gpt-5.6-terra":{"draws":33,"losses":40,"wins":65},"gpt-6-astra":{"draws":14,"losses":117,"wins":13},"gpt-6-luna":{"draws":25,"losses":36,"wins":83},"gpt-6-sol":{"draws":24,"losses":99,"wins":21},"gpt-6.1-sol":{"draws":14,"losses":116,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":2,"wins":1},"inception/mercury-2.5-preview":{"draws":29,"losses":8,"wins":65},"inclusionai/ling-3.0-flash":{"draws":16,"losses":10,"wins":76},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":32,"losses":21,"wins":103},"meta/muse-glimmer-30b":{"draws":36,"losses":16,"wins":74},"meta/muse-spark-1.2":{"draws":26,"losses":50,"wins":62},"meta/muse-spark-1.3":{"draws":16,"losses":40,"wins":40},"meta/muse-wonder":{"draws":28,"losses":74,"wins":42},"minimax/minimax-m3":{"draws":11,"losses":7,"wins":60},"mistralai/mistral-large-4-0":{"draws":24,"losses":22,"wins":44},"mistralai/mistral-medium-3-5":{"draws":18,"losses":4,"wins":62},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":15,"wins":12},"moonshotai/kimi-k3":{"draws":31,"losses":42,"wins":65},"nex-agi/nex-n2-pro":{"draws":11,"losses":6,"wins":55},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":12,"wins":84},"o3":{"draws":22,"losses":53,"wins":123},"openai/gpt-oss-120b":{"draws":32,"losses":12,"wins":82},"poolside/laguna-s-2.1":{"draws":31,"losses":26,"wins":81},"qwen/qwen3.7-max":{"draws":18,"losses":19,"wins":47},"qwen/qwen3.7-plus":{"draws":15,"losses":13,"wins":44},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":53,"wins":58},"qwen/qwen3.8-27b":{"draws":19,"losses":31,"wins":52},"qwen/qwen3.8-flash":{"draws":23,"losses":26,"wins":47},"qwen/qwen3.8-max":{"draws":34,"losses":40,"wins":70},"qwen/qwen3.8-max-0902":{"draws":39,"losses":53,"wins":52},"stealth/ox-alpha":{"draws":88,"losses":165,"wins":221},"stealth/space-bunny-alpha":{"draws":24,"losses":21,"wins":69},"stepfun/step-3.7-flash":{"draws":12,"losses":13,"wins":77},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":14,"losses":14,"wins":50},"tencent/hy4-preview":{"draws":28,"losses":50,"wins":60},"thinkingmachines/inkling":{"draws":33,"losses":18,"wins":141},"thinkingmachines/inkling-small":{"draws":37,"losses":13,"wins":94},"unbiased/pareto-26.10-preview":{"draws":2,"losses":42,"wins":4},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":26},"x-ai/grok-4.5":{"draws":23,"losses":60,"wins":61},"x-ai/grok-4.6":{"draws":32,"losses":60,"wins":52},"x-ai/grok-4.7":{"draws":11,"losses":84,"wins":31},"x-ai/grok-build-0.1":{"draws":12,"losses":8,"wins":28},"xiaomi/mimo-v2.5":{"draws":55,"losses":19,"wins":148},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":14,"wins":54},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":25,"wins":52},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":48,"wins":33},"z-ai/glm-5.2":{"draws":58,"losses":69,"wins":161},"z-ai/glm-5.3":{"draws":25,"losses":72,"wins":41},"z-ai/glm-5.3-flash":{"draws":27,"losses":66,"wins":51},"z-ai/glm-5.3-flashx":{"draws":28,"losses":57,"wins":59}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":16,"wins":86},"claude-fable-5":{"draws":25,"losses":62,"wins":57},"claude-fable-5-1":{"draws":13,"losses":118,"wins":31},"claude-haiku-5-5":{"draws":30,"losses":29,"wins":79},"claude-opus-4-5":{"draws":47,"losses":48,"wins":139},"claude-opus-4-8":{"draws":26,"losses":44,"wins":62},"claude-opus-5":{"draws":29,"losses":141,"wins":76},"claude-opus-5-5":{"draws":9,"losses":116,"wins":31},"claude-sonnet-5":{"draws":31,"losses":28,"wins":85},"claude-sonnet-5-5":{"draws":21,"losses":69,"wins":54},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":47},"deepseek/deepseek-v4-flash":{"draws":37,"losses":31,"wins":148},"deepseek/deepseek-v4-pro":{"draws":23,"losses":30,"wins":79},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":27,"wins":78},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":36,"wins":71},"fireworks/ember-1":{"draws":38,"losses":30,"wins":76},"gemini-3.1-pro-preview":{"draws":26,"losses":24,"wins":94},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":84},"google/gemini-3.5-flash":{"draws":30,"losses":29,"wins":121},"google/gemini-3.5-flash-lite":{"draws":43,"losses":27,"wins":182},"google/gemini-3.6-flash":{"draws":50,"losses":71,"wins":155},"google/gemini-3.8-flash":{"draws":36,"losses":40,"wins":68},"google/gemma-4-31b-it":{"draws":17,"losses":7,"wins":60},"gpt-4.1":{"draws":7,"losses":6,"wins":35},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":23,"losses":23,"wins":80},"gpt-5.4":{"draws":29,"losses":43,"wins":66},"gpt-5.4-mini":{"draws":24,"losses":10,"wins":62},"gpt-5.4-nano":{"draws":12,"losses":22,"wins":110},"gpt-5.5":{"draws":37,"losses":36,"wins":59},"gpt-5.6-luna":{"draws":28,"losses":25,"wins":91},"gpt-5.6-sol":{"draws":22,"losses":57,"wins":65},"gpt-5.6-terra":{"draws":31,"losses":30,"wins":77},"gpt-6-astra":{"draws":14,"losses":114,"wins":16},"gpt-6-luna":{"draws":34,"losses":33,"wins":77},"gpt-6-sol":{"draws":18,"losses":81,"wins":45},"gpt-6.1-sol":{"draws":19,"losses":96,"wins":29},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":4,"wins":70},"inclusionai/ling-3.0-flash":{"draws":18,"losses":5,"wins":79},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":31,"losses":20,"wins":105},"meta/muse-glimmer-30b":{"draws":26,"losses":15,"wins":85},"meta/muse-spark-1.2":{"draws":26,"losses":41,"wins":71},"meta/muse-spark-1.3":{"draws":28,"losses":42,"wins":74},"meta/muse-wonder":{"draws":18,"losses":39,"wins":39},"minimax/minimax-m3":{"draws":13,"losses":12,"wins":53},"mistralai/mistral-large-4-0":{"draws":19,"losses":23,"wins":48},"mistralai/mistral-medium-3-5":{"draws":16,"losses":6,"wins":62},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":8,"wins":21},"moonshotai/kimi-k3":{"draws":26,"losses":27,"wins":85},"nex-agi/nex-n2-pro":{"draws":13,"losses":6,"wins":53},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":8,"wins":82},"o3":{"draws":13,"losses":34,"wins":151},"openai/gpt-oss-120b":{"draws":23,"losses":10,"wins":93},"poolside/laguna-s-2.1":{"draws":22,"losses":11,"wins":105},"qwen/qwen3.7-max":{"draws":11,"losses":12,"wins":61},"qwen/qwen3.7-plus":{"draws":15,"losses":2,"wins":55},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":44,"wins":73},"qwen/qwen3.8-27b":{"draws":19,"losses":14,"wins":69},"qwen/qwen3.8-flash":{"draws":24,"losses":12,"wins":60},"qwen/qwen3.8-max":{"draws":31,"losses":32,"wins":81},"qwen/qwen3.8-max-0902":{"draws":33,"losses":33,"wins":78},"stealth/ox-alpha":{"draws":93,"losses":128,"wins":253},"stealth/space-bunny-alpha":{"draws":28,"losses":18,"wins":68},"stepfun/step-3.7-flash":{"draws":12,"losses":10,"wins":80},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":15,"losses":12,"wins":51},"tencent/hy4-preview":{"draws":28,"losses":39,"wins":71},"thinkingmachines/inkling":{"draws":44,"losses":22,"wins":126},"thinkingmachines/inkling-small":{"draws":33,"losses":15,"wins":96},"unbiased/pareto-26.10-preview":{"draws":4,"losses":35,"wins":9},"upstage/solar-mini4":{"draws":3,"losses":1,"wins":32},"x-ai/grok-4.5":{"draws":29,"losses":36,"wins":79},"x-ai/grok-4.6":{"draws":41,"losses":41,"wins":62},"x-ai/grok-4.7":{"draws":16,"losses":72,"wins":38},"x-ai/grok-build-0.1":{"draws":10,"losses":5,"wins":33},"xiaomi/mimo-v2.5":{"draws":45,"losses":17,"wins":160},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":15,"wins":56},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":22,"wins":63},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":36,"wins":43},"z-ai/glm-5.2":{"draws":65,"losses":45,"wins":178},"z-ai/glm-5.3":{"draws":17,"losses":59,"wins":62},"z-ai/glm-5.3-flash":{"draws":30,"losses":43,"wins":71},"z-ai/glm-5.3-flashx":{"draws":34,"losses":37,"wins":73}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":35,"wins":15},"claude-fable-5":{"draws":19,"losses":53,"wins":6},"claude-fable-5-1":{"draws":2,"losses":83,"wins":1},"claude-haiku-5-5":{"draws":8,"losses":53,"wins":15},"claude-opus-4-5":{"draws":39,"losses":77,"wins":12},"claude-opus-4-8":{"draws":16,"losses":48,"wins":10},"claude-opus-5":{"draws":15,"losses":116,"wins":7},"claude-opus-5-5":{"draws":2,"losses":83,"wins":1},"claude-sonnet-5":{"draws":21,"losses":42,"wins":15},"claude-sonnet-5-5":{"draws":13,"losses":52,"wins":13},"cohere/north-mini-code":{"draws":5,"losses":9,"wins":16},"deepseek/deepseek-v4-flash":{"draws":38,"losses":41,"wins":41},"deepseek/deepseek-v4-pro":{"draws":13,"losses":48,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":40,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":42,"wins":17},"fireworks/ember-1":{"draws":19,"losses":54,"wins":5},"gemini-3.1-pro-preview":{"draws":19,"losses":37,"wins":22},"google/gemini-3.1-flash-lite":{"draws":13,"losses":16,"wins":25},"google/gemini-3.5-flash":{"draws":23,"losses":52,"wins":23},"google/gemini-3.5-flash-lite":{"draws":38,"losses":50,"wins":46},"google/gemini-3.6-flash":{"draws":30,"losses":93,"wins":25},"google/gemini-3.8-flash":{"draws":17,"losses":55,"wins":6},"google/gemma-4-31b-it":{"draws":19,"losses":11,"wins":16},"gpt-4.1":{"draws":8,"losses":13,"wins":5},"gpt-4.1-nano":{"draws":5,"losses":1,"wins":2},"gpt-5":{"draws":19,"losses":34,"wins":17},"gpt-5.4":{"draws":15,"losses":43,"wins":16},"gpt-5.4-mini":{"draws":18,"losses":17,"wins":17},"gpt-5.4-nano":{"draws":18,"losses":39,"wins":27},"gpt-5.5":{"draws":24,"losses":37,"wins":11},"gpt-5.6-luna":{"draws":25,"losses":32,"wins":21},"gpt-5.6-sol":{"draws":13,"losses":61,"wins":4},"gpt-5.6-terra":{"draws":19,"losses":42,"wins":13},"gpt-6-astra":{"draws":1,"losses":75,"wins":2},"gpt-6-luna":{"draws":22,"losses":42,"wins":14},"gpt-6-sol":{"draws":9,"losses":62,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":70,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":9,"wins":19},"inclusionai/ling-3.0-flash":{"draws":21,"losses":10,"wins":23},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":19,"losses":35,"wins":30},"meta/muse-glimmer-30b":{"draws":25,"losses":20,"wins":25},"meta/muse-spark-1.2":{"draws":14,"losses":52,"wins":10},"meta/muse-spark-1.3":{"draws":11,"losses":60,"wins":7},"meta/muse-wonder":{"draws":13,"losses":53,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":8},"mistralai/mistral-large-4-0":{"draws":12,"losses":25,"wins":13},"mistralai/mistral-medium-3-5":{"draws":14,"losses":14,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":47,"wins":14},"nex-agi/nex-n2-pro":{"draws":10,"losses":11,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":20,"wins":25},"o3":{"draws":17,"losses":69,"wins":26},"openai/gpt-oss-120b":{"draws":22,"losses":27,"wins":21},"poolside/laguna-s-2.1":{"draws":26,"losses":30,"wins":22},"qwen/qwen3.7-max":{"draws":17,"losses":23,"wins":8},"qwen/qwen3.7-plus":{"draws":12,"losses":16,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":50,"wins":8},"qwen/qwen3.8-27b":{"draws":14,"losses":32,"wins":8},"qwen/qwen3.8-flash":{"draws":13,"losses":23,"wins":16},"qwen/qwen3.8-max":{"draws":23,"losses":41,"wins":14},"qwen/qwen3.8-max-0902":{"draws":21,"losses":49,"wins":8},"stealth/ox-alpha":{"draws":55,"losses":148,"wins":39},"stealth/space-bunny-alpha":{"draws":18,"losses":31,"wins":13},"stepfun/step-3.7-flash":{"draws":13,"losses":18,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":15,"losses":18,"wins":11},"tencent/hy4-preview":{"draws":17,"losses":50,"wins":7},"thinkingmachines/inkling":{"draws":26,"losses":44,"wins":34},"thinkingmachines/inkling-small":{"draws":25,"losses":19,"wins":34},"unbiased/pareto-26.10-preview":{"draws":0,"losses":26,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":10,"wins":6},"x-ai/grok-4.5":{"draws":14,"losses":59,"wins":5},"x-ai/grok-4.6":{"draws":20,"losses":54,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":61,"wins":9},"x-ai/grok-build-0.1":{"draws":8,"losses":10,"wins":8},"xiaomi/mimo-v2.5":{"draws":43,"losses":40,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":20,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":28,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":37,"wins":8},"z-ai/glm-5.2":{"draws":47,"losses":72,"wins":37},"z-ai/glm-5.3":{"draws":16,"losses":52,"wins":6},"z-ai/glm-5.3-flash":{"draws":18,"losses":45,"wins":15},"z-ai/glm-5.3-flashx":{"draws":20,"losses":46,"wins":12}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":24,"wins":33},"claude-fable-5":{"draws":18,"losses":49,"wins":23},"claude-fable-5-1":{"draws":4,"losses":92,"wins":6},"claude-haiku-5-5":{"draws":30,"losses":28,"wins":28},"claude-opus-4-5":{"draws":46,"losses":53,"wins":47},"claude-opus-4-8":{"draws":18,"losses":31,"wins":33},"claude-opus-5":{"draws":24,"losses":119,"wins":19},"claude-opus-5-5":{"draws":14,"losses":79,"wins":5},"claude-sonnet-5":{"draws":27,"losses":39,"wins":24},"claude-sonnet-5-5":{"draws":23,"losses":43,"wins":24},"cohere/north-mini-code":{"draws":9,"losses":5,"wins":20},"deepseek/deepseek-v4-flash":{"draws":45,"losses":20,"wins":69},"deepseek/deepseek-v4-pro":{"draws":26,"losses":26,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":28,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":31,"wins":26},"fireworks/ember-1":{"draws":26,"losses":31,"wins":33},"gemini-3.1-pro-preview":{"draws":21,"losses":34,"wins":35},"google/gemini-3.1-flash-lite":{"draws":17,"losses":2,"wins":39},"google/gemini-3.5-flash":{"draws":38,"losses":35,"wins":39},"google/gemini-3.5-flash-lite":{"draws":52,"losses":29,"wins":75},"google/gemini-3.6-flash":{"draws":41,"losses":72,"wins":59},"google/gemini-3.8-flash":{"draws":28,"losses":36,"wins":26},"google/gemma-4-31b-it":{"draws":19,"losses":9,"wins":24},"gpt-4.1":{"draws":12,"losses":8,"wins":10},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":5},"gpt-5":{"draws":30,"losses":16,"wins":34},"gpt-5.4":{"draws":30,"losses":40,"wins":16},"gpt-5.4-mini":{"draws":28,"losses":12,"wins":20},"gpt-5.4-nano":{"draws":16,"losses":24,"wins":48},"gpt-5.5":{"draws":29,"losses":33,"wins":22},"gpt-5.6-luna":{"draws":32,"losses":15,"wins":43},"gpt-5.6-sol":{"draws":19,"losses":51,"wins":20},"gpt-5.6-terra":{"draws":41,"losses":19,"wins":26},"gpt-6-astra":{"draws":9,"losses":76,"wins":5},"gpt-6-luna":{"draws":27,"losses":32,"wins":31},"gpt-6-sol":{"draws":15,"losses":61,"wins":14},"gpt-6.1-sol":{"draws":9,"losses":70,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":9,"wins":27},"inclusionai/ling-3.0-flash":{"draws":28,"losses":9,"wins":25},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":34,"losses":16,"wins":46},"meta/muse-glimmer-30b":{"draws":27,"losses":19,"wins":36},"meta/muse-spark-1.2":{"draws":16,"losses":45,"wins":27},"meta/muse-spark-1.3":{"draws":24,"losses":44,"wins":22},"meta/muse-wonder":{"draws":19,"losses":48,"wins":23},"minimax/minimax-m3":{"draws":12,"losses":13,"wins":25},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":9},"mistralai/mistral-medium-3-5":{"draws":22,"losses":7,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":8,"wins":10},"moonshotai/kimi-k3":{"draws":30,"losses":31,"wins":27},"nex-agi/nex-n2-pro":{"draws":13,"losses":5,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":18,"wins":32},"o3":{"draws":28,"losses":39,"wins":53},"openai/gpt-oss-120b":{"draws":31,"losses":14,"wins":35},"poolside/laguna-s-2.1":{"draws":32,"losses":20,"wins":36},"qwen/qwen3.7-max":{"draws":21,"losses":5,"wins":26},"qwen/qwen3.7-plus":{"draws":13,"losses":2,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":42,"wins":26},"qwen/qwen3.8-27b":{"draws":19,"losses":21,"wins":22},"qwen/qwen3.8-flash":{"draws":22,"losses":17,"wins":21},"qwen/qwen3.8-max":{"draws":31,"losses":29,"wins":30},"qwen/qwen3.8-max-0902":{"draws":32,"losses":40,"wins":18},"stealth/ox-alpha":{"draws":98,"losses":120,"wins":82},"stealth/space-bunny-alpha":{"draws":26,"losses":14,"wins":32},"stepfun/step-3.7-flash":{"draws":20,"losses":9,"wins":33},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":20,"losses":16,"wins":14},"tencent/hy4-preview":{"draws":22,"losses":36,"wins":28},"thinkingmachines/inkling":{"draws":42,"losses":22,"wins":58},"thinkingmachines/inkling-small":{"draws":31,"losses":14,"wins":45},"unbiased/pareto-26.10-preview":{"draws":3,"losses":24,"wins":3},"upstage/solar-mini4":{"draws":4,"losses":3,"wins":13},"x-ai/grok-4.5":{"draws":20,"losses":41,"wins":29},"x-ai/grok-4.6":{"draws":30,"losses":43,"wins":17},"x-ai/grok-4.7":{"draws":14,"losses":50,"wins":16},"x-ai/grok-build-0.1":{"draws":10,"losses":7,"wins":13},"xiaomi/mimo-v2.5":{"draws":58,"losses":19,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":11,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":20,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":28,"wins":19},"z-ai/glm-5.2":{"draws":71,"losses":37,"wins":72},"z-ai/glm-5.3":{"draws":15,"losses":51,"wins":20},"z-ai/glm-5.3-flash":{"draws":26,"losses":42,"wins":22},"z-ai/glm-5.3-flashx":{"draws":29,"losses":34,"wins":27}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":26,"wins":18},"claude-fable-5":{"draws":19,"losses":59,"wins":6},"claude-fable-5-1":{"draws":5,"losses":88,"wins":1},"claude-haiku-5-5":{"draws":22,"losses":54,"wins":4},"claude-opus-4-5":{"draws":44,"losses":80,"wins":12},"claude-opus-4-8":{"draws":25,"losses":45,"wins":6},"claude-opus-5":{"draws":22,"losses":110,"wins":12},"claude-opus-5-5":{"draws":7,"losses":85,"wins":0},"claude-sonnet-5":{"draws":32,"losses":42,"wins":10},"claude-sonnet-5-5":{"draws":19,"losses":57,"wins":8},"cohere/north-mini-code":{"draws":11,"losses":10,"wins":11},"deepseek/deepseek-v4-flash":{"draws":55,"losses":41,"wins":28},"deepseek/deepseek-v4-pro":{"draws":20,"losses":47,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":41,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":30,"losses":45,"wins":9},"fireworks/ember-1":{"draws":27,"losses":51,"wins":6},"gemini-3.1-pro-preview":{"draws":32,"losses":42,"wins":10},"google/gemini-3.1-flash-lite":{"draws":14,"losses":16,"wins":24},"google/gemini-3.5-flash":{"draws":31,"losses":58,"wins":15},"google/gemini-3.5-flash-lite":{"draws":54,"losses":63,"wins":31},"google/gemini-3.6-flash":{"draws":57,"losses":89,"wins":14},"google/gemini-3.8-flash":{"draws":20,"losses":59,"wins":5},"google/gemma-4-31b-it":{"draws":22,"losses":21,"wins":7},"gpt-4.1":{"draws":13,"losses":10,"wins":5},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":4},"gpt-5":{"draws":24,"losses":33,"wins":15},"gpt-5.4":{"draws":23,"losses":45,"wins":12},"gpt-5.4-mini":{"draws":24,"losses":24,"wins":8},"gpt-5.4-nano":{"draws":19,"losses":47,"wins":16},"gpt-5.5":{"draws":26,"losses":42,"wins":8},"gpt-5.6-luna":{"draws":34,"losses":38,"wins":12},"gpt-5.6-sol":{"draws":13,"losses":66,"wins":5},"gpt-5.6-terra":{"draws":26,"losses":46,"wins":8},"gpt-6-astra":{"draws":6,"losses":78,"wins":0},"gpt-6-luna":{"draws":30,"losses":47,"wins":7},"gpt-6-sol":{"draws":7,"losses":73,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":81,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":29,"losses":17,"wins":16},"inclusionai/ling-3.0-flash":{"draws":25,"losses":15,"wins":18},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":36,"losses":34,"wins":22},"meta/muse-glimmer-30b":{"draws":35,"losses":27,"wins":10},"meta/muse-spark-1.2":{"draws":21,"losses":48,"wins":11},"meta/muse-spark-1.3":{"draws":18,"losses":62,"wins":4},"meta/muse-wonder":{"draws":16,"losses":62,"wins":6},"minimax/minimax-m3":{"draws":14,"losses":16,"wins":14},"mistralai/mistral-large-4-0":{"draws":22,"losses":23,"wins":7},"mistralai/mistral-medium-3-5":{"draws":12,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":12,"wins":2},"moonshotai/kimi-k3":{"draws":25,"losses":46,"wins":9},"nex-agi/nex-n2-pro":{"draws":14,"losses":8,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":25,"wins":12},"o3":{"draws":27,"losses":70,"wins":13},"openai/gpt-oss-120b":{"draws":34,"losses":26,"wins":14},"poolside/laguna-s-2.1":{"draws":35,"losses":32,"wins":15},"qwen/qwen3.7-max":{"draws":24,"losses":20,"wins":4},"qwen/qwen3.7-plus":{"draws":17,"losses":13,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":56,"wins":3},"qwen/qwen3.8-27b":{"draws":20,"losses":34,"wins":4},"qwen/qwen3.8-flash":{"draws":22,"losses":29,"wins":5},"qwen/qwen3.8-max":{"draws":26,"losses":49,"wins":9},"qwen/qwen3.8-max-0902":{"draws":29,"losses":49,"wins":6},"stealth/ox-alpha":{"draws":72,"losses":171,"wins":39},"stealth/space-bunny-alpha":{"draws":24,"losses":30,"wins":12},"stepfun/step-3.7-flash":{"draws":21,"losses":24,"wins":11},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":16,"wins":12},"tencent/hy4-preview":{"draws":28,"losses":46,"wins":6},"thinkingmachines/inkling":{"draws":39,"losses":48,"wins":23},"thinkingmachines/inkling-small":{"draws":39,"losses":30,"wins":15},"unbiased/pareto-26.10-preview":{"draws":0,"losses":28,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":15,"wins":1},"x-ai/grok-4.5":{"draws":21,"losses":56,"wins":7},"x-ai/grok-4.6":{"draws":27,"losses":51,"wins":6},"x-ai/grok-4.7":{"draws":8,"losses":61,"wins":3},"x-ai/grok-build-0.1":{"draws":14,"losses":12,"wins":2},"xiaomi/mimo-v2.5":{"draws":58,"losses":45,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":23,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":33,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":42,"wins":7},"z-ai/glm-5.2":{"draws":74,"losses":75,"wins":19},"z-ai/glm-5.3":{"draws":15,"losses":63,"wins":4},"z-ai/glm-5.3-flash":{"draws":24,"losses":50,"wins":10},"z-ai/glm-5.3-flashx":{"draws":21,"losses":55,"wins":8}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":8,"wins":15},"claude-fable-5":{"draws":8,"losses":21,"wins":7},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":15},"claude-opus-4-5":{"draws":16,"losses":30,"wins":14},"claude-opus-4-8":{"draws":10,"losses":19,"wins":7},"claude-opus-5":{"draws":4,"losses":58,"wins":6},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":10,"losses":9,"wins":17},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":13,"losses":11,"wins":30},"deepseek/deepseek-v4-pro":{"draws":8,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":14,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":11},"fireworks/ember-1":{"draws":11,"losses":14,"wins":11},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":11},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":11,"losses":19,"wins":16},"google/gemini-3.5-flash-lite":{"draws":15,"losses":14,"wins":33},"google/gemini-3.6-flash":{"draws":19,"losses":33,"wins":16},"google/gemini-3.8-flash":{"draws":8,"losses":13,"wins":15},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":11},"gpt-4.1":{"draws":4,"losses":3,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":11,"wins":15},"gpt-5.4":{"draws":8,"losses":20,"wins":6},"gpt-5.4-mini":{"draws":7,"losses":5,"wins":12},"gpt-5.4-nano":{"draws":8,"losses":14,"wins":16},"gpt-5.5":{"draws":13,"losses":11,"wins":10},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":23,"wins":7},"gpt-5.6-terra":{"draws":10,"losses":13,"wins":11},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":12,"losses":14,"wins":10},"gpt-6-sol":{"draws":7,"losses":27,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":31,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":14},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":13},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":24},"meta/muse-glimmer-30b":{"draws":7,"losses":10,"wins":17},"meta/muse-spark-1.2":{"draws":9,"losses":15,"wins":12},"meta/muse-spark-1.3":{"draws":9,"losses":12,"wins":15},"meta/muse-wonder":{"draws":7,"losses":21,"wins":8},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":13},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":15},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":19},"o3":{"draws":5,"losses":21,"wins":24},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":7,"losses":12,"wins":15},"qwen/qwen3.7-max":{"draws":4,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":16,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.8-max":{"draws":9,"losses":16,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":24,"losses":49,"wins":29},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":14},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":15},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":9,"losses":17,"wins":8},"thinkingmachines/inkling":{"draws":10,"losses":10,"wins":28},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":9,"losses":22,"wins":4},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":24,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":11,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":3},"z-ai/glm-5.2":{"draws":16,"losses":26,"wins":30},"z-ai/glm-5.3":{"draws":9,"losses":21,"wins":4},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":13},"z-ai/glm-5.3-flashx":{"draws":12,"losses":12,"wins":12}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":30,"wins":60},"claude-fable-5":{"draws":26,"losses":86,"wins":26},"claude-fable-5-1":{"draws":7,"losses":137,"wins":12},"claude-haiku-5-5":{"draws":34,"losses":58,"wins":40},"claude-opus-4-5":{"draws":78,"losses":64,"wins":82},"claude-opus-4-8":{"draws":32,"losses":51,"wins":43},"claude-opus-5":{"draws":38,"losses":167,"wins":39},"claude-opus-5-5":{"draws":5,"losses":132,"wins":13},"claude-sonnet-5":{"draws":41,"losses":38,"wins":59},"claude-sonnet-5-5":{"draws":28,"losses":63,"wins":47},"cohere/north-mini-code":{"draws":11,"losses":8,"wins":33},"deepseek/deepseek-v4-flash":{"draws":61,"losses":42,"wins":103},"deepseek/deepseek-v4-pro":{"draws":28,"losses":44,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":49,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":57,"wins":41},"fireworks/ember-1":{"draws":45,"losses":56,"wins":37},"gemini-3.1-pro-preview":{"draws":36,"losses":40,"wins":62},"google/gemini-3.1-flash-lite":{"draws":23,"losses":11,"wins":56},"google/gemini-3.5-flash":{"draws":53,"losses":59,"wins":60},"google/gemini-3.5-flash-lite":{"draws":79,"losses":44,"wins":117},"google/gemini-3.6-flash":{"draws":71,"losses":103,"wins":90},"google/gemini-3.8-flash":{"draws":36,"losses":69,"wins":33},"google/gemma-4-31b-it":{"draws":29,"losses":13,"wins":38},"gpt-4.1":{"draws":13,"losses":12,"wins":21},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":8},"gpt-5":{"draws":34,"losses":40,"wins":48},"gpt-5.4":{"draws":27,"losses":68,"wins":37},"gpt-5.4-mini":{"draws":32,"losses":22,"wins":38},"gpt-5.4-nano":{"draws":35,"losses":32,"wins":69},"gpt-5.5":{"draws":37,"losses":44,"wins":47},"gpt-5.6-luna":{"draws":46,"losses":31,"wins":61},"gpt-5.6-sol":{"draws":22,"losses":85,"wins":31},"gpt-5.6-terra":{"draws":38,"losses":43,"wins":51},"gpt-6-astra":{"draws":9,"losses":119,"wins":10},"gpt-6-luna":{"draws":45,"losses":42,"wins":51},"gpt-6-sol":{"draws":15,"losses":97,"wins":26},"gpt-6.1-sol":{"draws":10,"losses":114,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":44,"losses":8,"wins":44},"inclusionai/ling-3.0-flash":{"draws":31,"losses":12,"wins":53},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":47,"losses":25,"wins":76},"meta/muse-glimmer-30b":{"draws":38,"losses":19,"wins":67},"meta/muse-spark-1.2":{"draws":26,"losses":56,"wins":52},"meta/muse-spark-1.3":{"draws":31,"losses":65,"wins":42},"meta/muse-wonder":{"draws":26,"losses":85,"wins":27},"minimax/minimax-m3":{"draws":15,"losses":14,"wins":47},"mistralai/mistral-large-4-0":{"draws":30,"losses":27,"wins":31},"mistralai/mistral-medium-3-5":{"draws":25,"losses":9,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":15,"wins":11},"moonshotai/kimi-k3":{"draws":28,"losses":30,"wins":30},"nex-agi/nex-n2-pro":{"draws":16,"losses":10,"wins":42},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":28,"wins":51},"o3":{"draws":33,"losses":71,"wins":82},"openai/gpt-oss-120b":{"draws":35,"losses":19,"wins":68},"poolside/laguna-s-2.1":{"draws":47,"losses":22,"wins":65},"qwen/qwen3.7-max":{"draws":19,"losses":20,"wins":41},"qwen/qwen3.7-plus":{"draws":24,"losses":16,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":50,"wins":50},"qwen/qwen3.8-27b":{"draws":28,"losses":27,"wins":41},"qwen/qwen3.8-flash":{"draws":30,"losses":29,"wins":33},"qwen/qwen3.8-max":{"draws":38,"losses":52,"wins":48},"qwen/qwen3.8-max-0902":{"draws":36,"losses":68,"wins":34},"stealth/ox-alpha":{"draws":112,"losses":180,"wins":166},"stealth/space-bunny-alpha":{"draws":37,"losses":20,"wins":53},"stepfun/step-3.7-flash":{"draws":23,"losses":16,"wins":57},"stepfun/step-5-preview":{"draws":2,"losses":7,"wins":3},"tencent/hy3-preview":{"draws":28,"losses":20,"wins":28},"tencent/hy4-preview":{"draws":33,"losses":55,"wins":44},"thinkingmachines/inkling":{"draws":54,"losses":39,"wins":93},"thinkingmachines/inkling-small":{"draws":48,"losses":21,"wins":69},"unbiased/pareto-26.10-preview":{"draws":2,"losses":43,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":33,"losses":62,"wins":43},"x-ai/grok-4.6":{"draws":34,"losses":70,"wins":34},"x-ai/grok-4.7":{"draws":13,"losses":82,"wins":27},"x-ai/grok-build-0.1":{"draws":17,"losses":4,"wins":25},"xiaomi/mimo-v2.5":{"draws":76,"losses":30,"wins":106},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":23,"wins":33},"xiaomi/mimo-v2.6-flash":{"draws":23,"losses":32,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":49,"wins":25},"z-ai/glm-5.2":{"draws":95,"losses":70,"wins":111},"z-ai/glm-5.3":{"draws":29,"losses":66,"wins":37},"z-ai/glm-5.3-flash":{"draws":34,"losses":61,"wins":43},"z-ai/glm-5.3-flashx":{"draws":41,"losses":63,"wins":34}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":36,"wins":11},"claude-fable-5":{"draws":15,"losses":56,"wins":1},"claude-fable-5-1":{"draws":4,"losses":78,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":43,"wins":10},"claude-opus-4-5":{"draws":28,"losses":73,"wins":15},"claude-opus-4-8":{"draws":16,"losses":44,"wins":4},"claude-opus-5":{"draws":3,"losses":107,"wins":6},"claude-opus-5-5":{"draws":6,"losses":74,"wins":0},"claude-sonnet-5":{"draws":24,"losses":38,"wins":10},"claude-sonnet-5-5":{"draws":15,"losses":47,"wins":10},"cohere/north-mini-code":{"draws":10,"losses":10,"wins":14},"deepseek/deepseek-v4-flash":{"draws":27,"losses":52,"wins":29},"deepseek/deepseek-v4-pro":{"draws":17,"losses":37,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":42,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":50,"wins":6},"fireworks/ember-1":{"draws":19,"losses":44,"wins":9},"gemini-3.1-pro-preview":{"draws":21,"losses":40,"wins":11},"google/gemini-3.1-flash-lite":{"draws":10,"losses":14,"wins":26},"google/gemini-3.5-flash":{"draws":24,"losses":49,"wins":17},"google/gemini-3.5-flash-lite":{"draws":36,"losses":58,"wins":34},"google/gemini-3.6-flash":{"draws":25,"losses":96,"wins":17},"google/gemini-3.8-flash":{"draws":14,"losses":51,"wins":7},"google/gemma-4-31b-it":{"draws":17,"losses":16,"wins":11},"gpt-4.1":{"draws":5,"losses":14,"wins":5},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":2},"gpt-5":{"draws":17,"losses":32,"wins":15},"gpt-5.4":{"draws":18,"losses":37,"wins":15},"gpt-5.4-mini":{"draws":19,"losses":17,"wins":12},"gpt-5.4-nano":{"draws":16,"losses":34,"wins":22},"gpt-5.5":{"draws":18,"losses":43,"wins":5},"gpt-5.6-luna":{"draws":21,"losses":40,"wins":11},"gpt-5.6-sol":{"draws":7,"losses":59,"wins":6},"gpt-5.6-terra":{"draws":19,"losses":41,"wins":8},"gpt-6-astra":{"draws":4,"losses":68,"wins":0},"gpt-6-luna":{"draws":15,"losses":46,"wins":11},"gpt-6-sol":{"draws":7,"losses":61,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":68,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":21,"losses":16,"wins":15},"inclusionai/ling-3.0-flash":{"draws":20,"losses":17,"wins":11},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":40,"wins":26},"meta/muse-glimmer-30b":{"draws":25,"losses":23,"wins":14},"meta/muse-spark-1.2":{"draws":11,"losses":46,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":55,"wins":6},"meta/muse-wonder":{"draws":13,"losses":53,"wins":6},"minimax/minimax-m3":{"draws":10,"losses":17,"wins":11},"mistralai/mistral-large-4-0":{"draws":13,"losses":26,"wins":5},"mistralai/mistral-medium-3-5":{"draws":14,"losses":22,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":9,"wins":1},"moonshotai/kimi-k3":{"draws":16,"losses":42,"wins":10},"nex-agi/nex-n2-pro":{"draws":4,"losses":8,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":28,"wins":12},"o3":{"draws":13,"losses":76,"wins":17},"openai/gpt-oss-120b":{"draws":19,"losses":24,"wins":23},"poolside/laguna-s-2.1":{"draws":29,"losses":31,"wins":12},"qwen/qwen3.7-max":{"draws":13,"losses":24,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":15,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":46,"wins":8},"qwen/qwen3.8-27b":{"draws":12,"losses":29,"wins":7},"qwen/qwen3.8-flash":{"draws":16,"losses":26,"wins":6},"qwen/qwen3.8-max":{"draws":21,"losses":45,"wins":6},"qwen/qwen3.8-max-0902":{"draws":21,"losses":42,"wins":9},"stealth/ox-alpha":{"draws":61,"losses":159,"wins":30},"stealth/space-bunny-alpha":{"draws":17,"losses":28,"wins":13},"stepfun/step-3.7-flash":{"draws":10,"losses":27,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":11,"wins":13},"tencent/hy4-preview":{"draws":17,"losses":47,"wins":6},"thinkingmachines/inkling":{"draws":26,"losses":40,"wins":28},"thinkingmachines/inkling-small":{"draws":24,"losses":31,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":10,"wins":5},"x-ai/grok-4.5":{"draws":14,"losses":49,"wins":9},"x-ai/grok-4.6":{"draws":19,"losses":50,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":54,"wins":4},"x-ai/grok-build-0.1":{"draws":9,"losses":11,"wins":4},"xiaomi/mimo-v2.5":{"draws":30,"losses":46,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":19,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":31,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":36,"wins":4},"z-ai/glm-5.2":{"draws":57,"losses":70,"wins":17},"z-ai/glm-5.3":{"draws":13,"losses":56,"wins":3},"z-ai/glm-5.3-flash":{"draws":17,"losses":48,"wins":7},"z-ai/glm-5.3-flashx":{"draws":14,"losses":53,"wins":5}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":47,"losses":34,"wins":35},"claude-fable-5":{"draws":27,"losses":89,"wins":10},"claude-fable-5-1":{"draws":7,"losses":129,"wins":0},"claude-haiku-5-5":{"draws":32,"losses":66,"wins":26},"claude-opus-4-5":{"draws":79,"losses":99,"wins":30},"claude-opus-4-8":{"draws":27,"losses":77,"wins":18},"claude-opus-5":{"draws":28,"losses":180,"wins":6},"claude-opus-5-5":{"draws":4,"losses":137,"wins":1},"claude-sonnet-5":{"draws":45,"losses":52,"wins":29},"claude-sonnet-5-5":{"draws":22,"losses":82,"wins":22},"cohere/north-mini-code":{"draws":21,"losses":11,"wins":16},"deepseek/deepseek-v4-flash":{"draws":76,"losses":66,"wins":52},"deepseek/deepseek-v4-pro":{"draws":40,"losses":55,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":44,"losses":55,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":58,"wins":22},"fireworks/ember-1":{"draws":49,"losses":59,"wins":18},"gemini-3.1-pro-preview":{"draws":48,"losses":50,"wins":28},"google/gemini-3.1-flash-lite":{"draws":26,"losses":22,"wins":42},"google/gemini-3.5-flash":{"draws":48,"losses":79,"wins":33},"google/gemini-3.5-flash-lite":{"draws":88,"losses":66,"wins":66},"google/gemini-3.6-flash":{"draws":76,"losses":128,"wins":34},"google/gemini-3.8-flash":{"draws":41,"losses":77,"wins":8},"google/gemma-4-31b-it":{"draws":40,"losses":18,"wins":18},"gpt-4.1":{"draws":18,"losses":17,"wins":7},"gpt-4.1-nano":{"draws":8,"losses":2,"wins":4},"gpt-5":{"draws":43,"losses":47,"wins":20},"gpt-5.4":{"draws":42,"losses":70,"wins":8},"gpt-5.4-mini":{"draws":39,"losses":24,"wins":21},"gpt-5.4-nano":{"draws":36,"losses":58,"wins":46},"gpt-5.5":{"draws":52,"losses":54,"wins":8},"gpt-5.6-luna":{"draws":51,"losses":42,"wins":33},"gpt-5.6-sol":{"draws":16,"losses":99,"wins":11},"gpt-5.6-terra":{"draws":46,"losses":55,"wins":19},"gpt-6-astra":{"draws":9,"losses":116,"wins":1},"gpt-6-luna":{"draws":42,"losses":59,"wins":25},"gpt-6-sol":{"draws":12,"losses":106,"wins":8},"gpt-6.1-sol":{"draws":8,"losses":112,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":44,"losses":22,"wins":26},"inclusionai/ling-3.0-flash":{"draws":45,"losses":21,"wins":26},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":53,"losses":42,"wins":43},"meta/muse-glimmer-30b":{"draws":55,"losses":26,"wins":27},"meta/muse-spark-1.2":{"draws":33,"losses":68,"wins":19},"meta/muse-spark-1.3":{"draws":30,"losses":84,"wins":12},"meta/muse-wonder":{"draws":36,"losses":82,"wins":8},"minimax/minimax-m3":{"draws":27,"losses":25,"wins":20},"mistralai/mistral-large-4-0":{"draws":28,"losses":32,"wins":18},"mistralai/mistral-medium-3-5":{"draws":37,"losses":12,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":19,"wins":5},"moonshotai/kimi-k3":{"draws":41,"losses":51,"wins":28},"nex-agi/nex-n2-pro":{"draws":22,"losses":12,"wins":28},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":19,"wins":19},"o3":{"draws":47,"losses":97,"wins":40},"openai/gpt-oss-120b":{"draws":46,"losses":36,"wins":28},"poolside/laguna-s-2.1":{"draws":58,"losses":35,"wins":31},"qwen/qwen3.7-max":{"draws":35,"losses":26,"wins":17},"qwen/qwen3.7-plus":{"draws":23,"losses":23,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":64,"wins":14},"qwen/qwen3.8-27b":{"draws":29,"losses":40,"wins":19},"qwen/qwen3.8-flash":{"draws":39,"losses":31,"wins":14},"qwen/qwen3.8-max":{"draws":48,"losses":56,"wins":22},"qwen/qwen3.8-max-0902":{"draws":49,"losses":65,"wins":12},"stealth/ox-alpha":{"draws":109,"losses":207,"wins":58},"stealth/space-bunny-alpha":{"draws":41,"losses":32,"wins":25},"stepfun/step-3.7-flash":{"draws":32,"losses":30,"wins":28},"stepfun/step-5-preview":{"draws":8,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":37,"losses":21,"wins":14},"tencent/hy4-preview":{"draws":42,"losses":64,"wins":14},"thinkingmachines/inkling":{"draws":52,"losses":51,"wins":59},"thinkingmachines/inkling-small":{"draws":59,"losses":32,"wins":35},"unbiased/pareto-26.10-preview":{"draws":1,"losses":41,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":14,"wins":13},"x-ai/grok-4.5":{"draws":31,"losses":85,"wins":10},"x-ai/grok-4.6":{"draws":47,"losses":66,"wins":13},"x-ai/grok-4.7":{"draws":7,"losses":98,"wins":9},"x-ai/grok-build-0.1":{"draws":21,"losses":12,"wins":9},"xiaomi/mimo-v2.5":{"draws":88,"losses":56,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":25,"losses":32,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":43,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":56,"wins":10},"z-ai/glm-5.2":{"draws":109,"losses":89,"wins":54},"z-ai/glm-5.3":{"draws":25,"losses":82,"wins":13},"z-ai/glm-5.3-flash":{"draws":33,"losses":59,"wins":34},"z-ai/glm-5.3-flashx":{"draws":31,"losses":74,"wins":21}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":42,"losses":55,"wins":87},"claude-fable-5":{"draws":20,"losses":149,"wins":29},"claude-fable-5-1":{"draws":5,"losses":204,"wins":9},"claude-haiku-5-5":{"draws":32,"losses":101,"wins":61},"claude-opus-4-5":{"draws":49,"losses":182,"wins":95},"claude-opus-4-8":{"draws":27,"losses":108,"wins":55},"claude-opus-5":{"draws":26,"losses":266,"wins":20},"claude-opus-5-5":{"draws":11,"losses":204,"wins":3},"claude-sonnet-5":{"draws":29,"losses":87,"wins":82},"claude-sonnet-5-5":{"draws":17,"losses":136,"wins":45},"cohere/north-mini-code":{"draws":17,"losses":13,"wins":58},"deepseek/deepseek-v4-flash":{"draws":51,"losses":77,"wins":178},"deepseek/deepseek-v4-pro":{"draws":24,"losses":91,"wins":69},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":99,"wins":54},"deepseek/deepseek-v4.1-flash":{"draws":45,"losses":91,"wins":62},"fireworks/ember-1":{"draws":40,"losses":110,"wins":48},"gemini-3.1-pro-preview":{"draws":33,"losses":75,"wins":90},"google/gemini-3.1-flash-lite":{"draws":23,"losses":12,"wins":123},"google/gemini-3.5-flash":{"draws":42,"losses":132,"wins":84},"google/gemini-3.5-flash-lite":{"draws":64,"losses":94,"wins":198},"google/gemini-3.6-flash":{"draws":56,"losses":204,"wins":124},"google/gemini-3.8-flash":{"draws":28,"losses":126,"wins":44},"google/gemma-4-31b-it":{"draws":26,"losses":21,"wins":71},"gpt-4.1":{"draws":13,"losses":27,"wins":26},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":10},"gpt-5":{"draws":32,"losses":84,"wins":64},"gpt-5.4":{"draws":22,"losses":128,"wins":46},"gpt-5.4-mini":{"draws":29,"losses":34,"wins":69},"gpt-5.4-nano":{"draws":22,"losses":100,"wins":104},"gpt-5.5":{"draws":40,"losses":100,"wins":44},"gpt-5.6-luna":{"draws":40,"losses":70,"wins":88},"gpt-5.6-sol":{"draws":14,"losses":153,"wins":31},"gpt-5.6-terra":{"draws":39,"losses":80,"wins":67},"gpt-6-astra":{"draws":7,"losses":189,"wins":2},"gpt-6-luna":{"draws":34,"losses":100,"wins":64},"gpt-6-sol":{"draws":10,"losses":171,"wins":17},"gpt-6.1-sol":{"draws":3,"losses":186,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":33,"losses":16,"wins":87},"inclusionai/ling-3.0-flash":{"draws":33,"losses":17,"wins":90},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":38,"losses":58,"wins":136},"meta/muse-glimmer-30b":{"draws":40,"losses":31,"wins":101},"meta/muse-spark-1.2":{"draws":24,"losses":92,"wins":70},"meta/muse-spark-1.3":{"draws":22,"losses":123,"wins":53},"meta/muse-wonder":{"draws":13,"losses":151,"wins":34},"minimax/minimax-m3":{"draws":17,"losses":26,"wins":69},"mistralai/mistral-large-4-0":{"draws":28,"losses":53,"wins":39},"mistralai/mistral-medium-3-5":{"draws":27,"losses":13,"wins":70},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":24,"wins":21},"moonshotai/kimi-k3":{"draws":33,"losses":82,"wins":71},"nex-agi/nex-n2-pro":{"draws":13,"losses":17,"wins":76},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":47,"losses":40,"wins":97},"o3":{"draws":30,"losses":119,"wins":119},"openai/gpt-oss-120b":{"draws":26,"losses":28,"wins":118},"poolside/laguna-s-2.1":{"draws":42,"losses":56,"wins":94},"qwen/qwen3.7-max":{"draws":26,"losses":42,"wins":56},"qwen/qwen3.7-plus":{"draws":15,"losses":28,"wins":67},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":109,"wins":58},"qwen/qwen3.8-27b":{"draws":14,"losses":72,"wins":58},"qwen/qwen3.8-flash":{"draws":28,"losses":58,"wins":46},"qwen/qwen3.8-max":{"draws":39,"losses":97,"wins":62},"qwen/qwen3.8-max-0902":{"draws":37,"losses":98,"wins":63},"stealth/ox-alpha":{"draws":92,"losses":312,"wins":200},"stealth/space-bunny-alpha":{"draws":26,"losses":56,"wins":78},"stepfun/step-3.7-flash":{"draws":28,"losses":42,"wins":90},"stepfun/step-5-preview":{"draws":8,"losses":10,"wins":2},"tencent/hy3-preview":{"draws":22,"losses":40,"wins":42},"tencent/hy4-preview":{"draws":32,"losses":105,"wins":59},"thinkingmachines/inkling":{"draws":42,"losses":57,"wins":167},"thinkingmachines/inkling-small":{"draws":44,"losses":42,"wins":112},"unbiased/pareto-26.10-preview":{"draws":0,"losses":63,"wins":3},"upstage/solar-mini4":{"draws":10,"losses":13,"wins":39},"x-ai/grok-4.5":{"draws":21,"losses":121,"wins":56},"x-ai/grok-4.6":{"draws":39,"losses":116,"wins":43},"x-ai/grok-4.7":{"draws":12,"losses":130,"wins":36},"x-ai/grok-build-0.1":{"draws":16,"losses":13,"wins":37},"xiaomi/mimo-v2.5":{"draws":60,"losses":63,"wins":193},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":45,"wins":57},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":74,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":95,"wins":26},"z-ai/glm-5.2":{"draws":79,"losses":148,"wins":169},"z-ai/glm-5.3":{"draws":19,"losses":134,"wins":35},"z-ai/glm-5.3-flash":{"draws":28,"losses":96,"wins":74},"z-ai/glm-5.3-flashx":{"draws":21,"losses":119,"wins":58}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":42,"wins":32},"claude-fable-5":{"draws":30,"losses":85,"wins":11},"claude-fable-5-1":{"draws":5,"losses":137,"wins":0},"claude-haiku-5-5":{"draws":30,"losses":78,"wins":12},"claude-opus-4-5":{"draws":66,"losses":106,"wins":32},"claude-opus-4-8":{"draws":36,"losses":68,"wins":10},"claude-opus-5":{"draws":32,"losses":177,"wins":11},"claude-opus-5-5":{"draws":8,"losses":130,"wins":0},"claude-sonnet-5":{"draws":38,"losses":71,"wins":17},"claude-sonnet-5-5":{"draws":26,"losses":82,"wins":18},"cohere/north-mini-code":{"draws":17,"losses":15,"wins":18},"deepseek/deepseek-v4-flash":{"draws":74,"losses":54,"wins":62},"deepseek/deepseek-v4-pro":{"draws":35,"losses":55,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":51,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":62,"wins":24},"fireworks/ember-1":{"draws":48,"losses":64,"wins":14},"gemini-3.1-pro-preview":{"draws":42,"losses":55,"wins":29},"google/gemini-3.1-flash-lite":{"draws":24,"losses":18,"wins":40},"google/gemini-3.5-flash":{"draws":45,"losses":77,"wins":34},"google/gemini-3.5-flash-lite":{"draws":70,"losses":74,"wins":74},"google/gemini-3.6-flash":{"draws":72,"losses":136,"wins":32},"google/gemini-3.8-flash":{"draws":28,"losses":90,"wins":8},"google/gemma-4-31b-it":{"draws":31,"losses":10,"wins":33},"gpt-4.1":{"draws":13,"losses":20,"wins":9},"gpt-4.1-nano":{"draws":12,"losses":0,"wins":4},"gpt-5":{"draws":35,"losses":56,"wins":21},"gpt-5.4":{"draws":33,"losses":67,"wins":20},"gpt-5.4-mini":{"draws":32,"losses":31,"wins":21},"gpt-5.4-nano":{"draws":35,"losses":44,"wins":47},"gpt-5.5":{"draws":44,"losses":56,"wins":16},"gpt-5.6-luna":{"draws":57,"losses":42,"wins":27},"gpt-5.6-sol":{"draws":15,"losses":104,"wins":7},"gpt-5.6-terra":{"draws":42,"losses":66,"wins":12},"gpt-6-astra":{"draws":12,"losses":114,"wins":0},"gpt-6-luna":{"draws":41,"losses":58,"wins":27},"gpt-6-sol":{"draws":19,"losses":101,"wins":6},"gpt-6.1-sol":{"draws":7,"losses":118,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":38,"losses":21,"wins":29},"inclusionai/ling-3.0-flash":{"draws":38,"losses":8,"wins":40},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":44,"losses":56,"wins":38},"meta/muse-glimmer-30b":{"draws":47,"losses":27,"wins":38},"meta/muse-spark-1.2":{"draws":32,"losses":76,"wins":14},"meta/muse-spark-1.3":{"draws":32,"losses":82,"wins":12},"meta/muse-wonder":{"draws":23,"losses":93,"wins":10},"minimax/minimax-m3":{"draws":22,"losses":21,"wins":27},"mistralai/mistral-large-4-0":{"draws":31,"losses":35,"wins":14},"mistralai/mistral-medium-3-5":{"draws":34,"losses":14,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":17,"wins":6},"moonshotai/kimi-k3":{"draws":35,"losses":68,"wins":19},"nex-agi/nex-n2-pro":{"draws":19,"losses":23,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":28,"wins":36},"o3":{"draws":26,"losses":118,"wins":28},"openai/gpt-oss-120b":{"draws":22,"losses":25,"wins":25},"poolside/laguna-s-2.1":{"draws":49,"losses":41,"wins":36},"qwen/qwen3.7-max":{"draws":29,"losses":31,"wins":14},"qwen/qwen3.7-plus":{"draws":21,"losses":21,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":42,"losses":72,"wins":12},"qwen/qwen3.8-27b":{"draws":22,"losses":46,"wins":18},"qwen/qwen3.8-flash":{"draws":27,"losses":34,"wins":23},"qwen/qwen3.8-max":{"draws":41,"losses":75,"wins":10},"qwen/qwen3.8-max-0902":{"draws":39,"losses":72,"wins":15},"stealth/ox-alpha":{"draws":110,"losses":256,"wins":58},"stealth/space-bunny-alpha":{"draws":33,"losses":44,"wins":23},"stepfun/step-3.7-flash":{"draws":31,"losses":36,"wins":21},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":27,"wins":19},"tencent/hy4-preview":{"draws":38,"losses":64,"wins":18},"thinkingmachines/inkling":{"draws":47,"losses":65,"wins":56},"thinkingmachines/inkling-small":{"draws":48,"losses":31,"wins":47},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":11},"x-ai/grok-4.5":{"draws":34,"losses":79,"wins":13},"x-ai/grok-4.6":{"draws":37,"losses":79,"wins":10},"x-ai/grok-4.7":{"draws":9,"losses":99,"wins":4},"x-ai/grok-build-0.1":{"draws":17,"losses":16,"wins":9},"xiaomi/mimo-v2.5":{"draws":66,"losses":54,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":27,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":53,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":62,"wins":6},"z-ai/glm-5.2":{"draws":95,"losses":108,"wins":49},"z-ai/glm-5.3":{"draws":31,"losses":87,"wins":4},"z-ai/glm-5.3-flash":{"draws":27,"losses":79,"wins":20},"z-ai/glm-5.3-flashx":{"draws":37,"losses":76,"wins":13}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":51,"losses":38,"wins":39},"claude-fable-5":{"draws":27,"losses":90,"wins":21},"claude-fable-5-1":{"draws":5,"losses":145,"wins":2},"claude-haiku-5-5":{"draws":34,"losses":61,"wins":35},"claude-opus-4-5":{"draws":78,"losses":105,"wins":39},"claude-opus-4-8":{"draws":37,"losses":69,"wins":16},"claude-opus-5":{"draws":24,"losses":210,"wins":14},"claude-opus-5-5":{"draws":10,"losses":144,"wins":0},"claude-sonnet-5":{"draws":43,"losses":69,"wins":26},"claude-sonnet-5-5":{"draws":25,"losses":87,"wins":26},"cohere/north-mini-code":{"draws":21,"losses":15,"wins":18},"deepseek/deepseek-v4-flash":{"draws":83,"losses":58,"wins":69},"deepseek/deepseek-v4-pro":{"draws":36,"losses":49,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":53,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":59,"losses":57,"wins":22},"fireworks/ember-1":{"draws":52,"losses":64,"wins":22},"gemini-3.1-pro-preview":{"draws":47,"losses":59,"wins":32},"google/gemini-3.1-flash-lite":{"draws":25,"losses":16,"wins":45},"google/gemini-3.5-flash":{"draws":43,"losses":93,"wins":34},"google/gemini-3.5-flash-lite":{"draws":81,"losses":62,"wins":95},"google/gemini-3.6-flash":{"draws":79,"losses":135,"wins":48},"google/gemini-3.8-flash":{"draws":31,"losses":93,"wins":14},"google/gemma-4-31b-it":{"draws":33,"losses":20,"wins":25},"gpt-4.1":{"draws":16,"losses":18,"wins":12},"gpt-4.1-nano":{"draws":13,"losses":3,"wins":2},"gpt-5":{"draws":49,"losses":44,"wins":33},"gpt-5.4":{"draws":35,"losses":81,"wins":16},"gpt-5.4-mini":{"draws":39,"losses":31,"wins":22},"gpt-5.4-nano":{"draws":40,"losses":50,"wins":54},"gpt-5.5":{"draws":52,"losses":55,"wins":21},"gpt-5.6-luna":{"draws":51,"losses":46,"wins":41},"gpt-5.6-sol":{"draws":19,"losses":111,"wins":8},"gpt-5.6-terra":{"draws":52,"losses":62,"wins":16},"gpt-6-astra":{"draws":7,"losses":131,"wins":0},"gpt-6-luna":{"draws":45,"losses":59,"wins":34},"gpt-6-sol":{"draws":22,"losses":105,"wins":11},"gpt-6.1-sol":{"draws":9,"losses":128,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":40,"losses":22,"wins":28},"inclusionai/ling-3.0-flash":{"draws":45,"losses":13,"wins":36},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":54,"losses":43,"wins":53},"meta/muse-glimmer-30b":{"draws":54,"losses":29,"wins":41},"meta/muse-spark-1.2":{"draws":29,"losses":86,"wins":19},"meta/muse-spark-1.3":{"draws":31,"losses":81,"wins":26},"meta/muse-wonder":{"draws":22,"losses":105,"wins":11},"minimax/minimax-m3":{"draws":26,"losses":22,"wins":30},"mistralai/mistral-large-4-0":{"draws":32,"losses":36,"wins":20},"mistralai/mistral-medium-3-5":{"draws":35,"losses":15,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":15,"wins":12},"moonshotai/kimi-k3":{"draws":47,"losses":65,"wins":22},"nex-agi/nex-n2-pro":{"draws":29,"losses":12,"wins":31},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":58,"losses":31,"wins":35},"o3":{"draws":42,"losses":94,"wins":56},"openai/gpt-oss-120b":{"draws":49,"losses":36,"wins":41},"poolside/laguna-s-2.1":{"draws":48,"losses":28,"wins":28},"qwen/qwen3.7-max":{"draws":33,"losses":29,"wins":20},"qwen/qwen3.7-plus":{"draws":24,"losses":13,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":78,"wins":15},"qwen/qwen3.8-27b":{"draws":28,"losses":44,"wins":22},"qwen/qwen3.8-flash":{"draws":40,"losses":33,"wins":19},"qwen/qwen3.8-max":{"draws":48,"losses":57,"wins":33},"qwen/qwen3.8-max-0902":{"draws":45,"losses":70,"wins":23},"stealth/ox-alpha":{"draws":130,"losses":264,"wins":84},"stealth/space-bunny-alpha":{"draws":33,"losses":40,"wins":33},"stepfun/step-3.7-flash":{"draws":37,"losses":29,"wins":32},"stepfun/step-5-preview":{"draws":8,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":28,"losses":26,"wins":22},"tencent/hy4-preview":{"draws":42,"losses":66,"wins":24},"thinkingmachines/inkling":{"draws":58,"losses":55,"wins":75},"thinkingmachines/inkling-small":{"draws":59,"losses":20,"wins":59},"unbiased/pareto-26.10-preview":{"draws":0,"losses":45,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":14,"wins":8},"x-ai/grok-4.5":{"draws":36,"losses":83,"wins":19},"x-ai/grok-4.6":{"draws":39,"losses":84,"wins":15},"x-ai/grok-4.7":{"draws":11,"losses":99,"wins":14},"x-ai/grok-build-0.1":{"draws":21,"losses":14,"wins":11},"xiaomi/mimo-v2.5":{"draws":66,"losses":57,"wins":79},"xiaomi/mimo-v2.5-pro":{"draws":25,"losses":25,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":51,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":64,"wins":18},"z-ai/glm-5.2":{"draws":119,"losses":92,"wins":65},"z-ai/glm-5.3":{"draws":25,"losses":92,"wins":15},"z-ai/glm-5.3-flash":{"draws":36,"losses":73,"wins":29},"z-ai/glm-5.3-flashx":{"draws":40,"losses":75,"wins":23}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":23,"wins":27},"claude-fable-5":{"draws":15,"losses":56,"wins":13},"claude-fable-5-1":{"draws":3,"losses":88,"wins":1},"claude-haiku-5-5":{"draws":27,"losses":35,"wins":20},"claude-opus-4-5":{"draws":44,"losses":62,"wins":32},"claude-opus-4-8":{"draws":24,"losses":35,"wins":21},"claude-opus-5":{"draws":17,"losses":111,"wins":12},"claude-opus-5-5":{"draws":6,"losses":86,"wins":0},"claude-sonnet-5":{"draws":27,"losses":40,"wins":17},"claude-sonnet-5-5":{"draws":18,"losses":44,"wins":22},"cohere/north-mini-code":{"draws":11,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":56,"losses":26,"wins":48},"deepseek/deepseek-v4-pro":{"draws":25,"losses":36,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":32,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":30,"losses":35,"wins":19},"fireworks/ember-1":{"draws":26,"losses":39,"wins":19},"gemini-3.1-pro-preview":{"draws":26,"losses":29,"wins":29},"google/gemini-3.1-flash-lite":{"draws":19,"losses":7,"wins":34},"google/gemini-3.5-flash":{"draws":32,"losses":41,"wins":33},"google/gemini-3.5-flash-lite":{"draws":41,"losses":42,"wins":63},"google/gemini-3.6-flash":{"draws":47,"losses":75,"wins":38},"google/gemini-3.8-flash":{"draws":27,"losses":37,"wins":20},"google/gemma-4-31b-it":{"draws":17,"losses":13,"wins":20},"gpt-4.1":{"draws":13,"losses":5,"wins":10},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":2},"gpt-5":{"draws":31,"losses":28,"wins":15},"gpt-5.4":{"draws":18,"losses":43,"wins":19},"gpt-5.4-mini":{"draws":19,"losses":15,"wins":22},"gpt-5.4-nano":{"draws":27,"losses":29,"wins":36},"gpt-5.5":{"draws":27,"losses":35,"wins":14},"gpt-5.6-luna":{"draws":31,"losses":21,"wins":32},"gpt-5.6-sol":{"draws":11,"losses":59,"wins":14},"gpt-5.6-terra":{"draws":24,"losses":40,"wins":16},"gpt-6-astra":{"draws":6,"losses":77,"wins":1},"gpt-6-luna":{"draws":22,"losses":35,"wins":27},"gpt-6-sol":{"draws":16,"losses":58,"wins":10},"gpt-6.1-sol":{"draws":7,"losses":75,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":25,"losses":12,"wins":23},"inclusionai/ling-3.0-flash":{"draws":29,"losses":7,"wins":24},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":30,"losses":18,"wins":44},"meta/muse-glimmer-30b":{"draws":29,"losses":16,"wins":27},"meta/muse-spark-1.2":{"draws":11,"losses":50,"wins":19},"meta/muse-spark-1.3":{"draws":18,"losses":47,"wins":19},"meta/muse-wonder":{"draws":11,"losses":61,"wins":12},"minimax/minimax-m3":{"draws":17,"losses":8,"wins":23},"mistralai/mistral-large-4-0":{"draws":21,"losses":26,"wins":5},"mistralai/mistral-medium-3-5":{"draws":24,"losses":4,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":9,"wins":9},"moonshotai/kimi-k3":{"draws":19,"losses":41,"wins":20},"nex-agi/nex-n2-pro":{"draws":13,"losses":5,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":17,"wins":26},"o3":{"draws":26,"losses":56,"wins":42},"openai/gpt-oss-120b":{"draws":29,"losses":14,"wins":31},"poolside/laguna-s-2.1":{"draws":33,"losses":20,"wins":29},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":13,"losses":12,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":38,"wins":17},"qwen/qwen3.8-27b":{"draws":16,"losses":26,"wins":18},"qwen/qwen3.8-flash":{"draws":20,"losses":20,"wins":16},"qwen/qwen3.8-max":{"draws":31,"losses":30,"wins":23},"qwen/qwen3.8-max-0902":{"draws":26,"losses":41,"wins":17},"stealth/ox-alpha":{"draws":64,"losses":136,"wins":58},"stealth/space-bunny-alpha":{"draws":21,"losses":22,"wins":23},"stepfun/step-3.7-flash":{"draws":16,"losses":12,"wins":34},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":19,"losses":10,"wins":17},"tencent/hy4-preview":{"draws":18,"losses":44,"wins":18},"thinkingmachines/inkling":{"draws":34,"losses":17,"wins":59},"thinkingmachines/inkling-small":{"draws":32,"losses":16,"wins":36},"unbiased/pareto-26.10-preview":{"draws":0,"losses":27,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":14},"x-ai/grok-4.5":{"draws":21,"losses":44,"wins":19},"x-ai/grok-4.6":{"draws":21,"losses":47,"wins":16},"x-ai/grok-4.7":{"draws":10,"losses":51,"wins":15},"x-ai/grok-build-0.1":{"draws":10,"losses":9,"wins":9},"xiaomi/mimo-v2.5":{"draws":53,"losses":27,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":11,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":28,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":34,"wins":13},"z-ai/glm-5.2":{"draws":55,"losses":60,"wins":53},"z-ai/glm-5.3":{"draws":19,"losses":48,"wins":13},"z-ai/glm-5.3-flash":{"draws":25,"losses":41,"wins":18},"z-ai/glm-5.3-flashx":{"draws":22,"losses":42,"wins":20}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":22,"wins":20},"claude-fable-5":{"draws":13,"losses":51,"wins":8},"claude-fable-5-1":{"draws":5,"losses":72,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":50,"wins":8},"claude-opus-4-5":{"draws":40,"losses":52,"wins":28},"claude-opus-4-8":{"draws":16,"losses":43,"wins":13},"claude-opus-5":{"draws":16,"losses":92,"wins":8},"claude-opus-5-5":{"draws":5,"losses":71,"wins":0},"claude-sonnet-5":{"draws":20,"losses":35,"wins":17},"claude-sonnet-5-5":{"draws":17,"losses":43,"wins":12},"cohere/north-mini-code":{"draws":6,"losses":8,"wins":12},"deepseek/deepseek-v4-flash":{"draws":35,"losses":42,"wins":35},"deepseek/deepseek-v4-pro":{"draws":16,"losses":35,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":27,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":40,"wins":7},"fireworks/ember-1":{"draws":23,"losses":38,"wins":11},"gemini-3.1-pro-preview":{"draws":23,"losses":35,"wins":14},"google/gemini-3.1-flash-lite":{"draws":13,"losses":13,"wins":30},"google/gemini-3.5-flash":{"draws":22,"losses":51,"wins":19},"google/gemini-3.5-flash-lite":{"draws":37,"losses":49,"wins":40},"google/gemini-3.6-flash":{"draws":39,"losses":77,"wins":22},"google/gemini-3.8-flash":{"draws":19,"losses":46,"wins":7},"google/gemma-4-31b-it":{"draws":16,"losses":13,"wins":15},"gpt-4.1":{"draws":8,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":18,"losses":35,"wins":9},"gpt-5.4":{"draws":12,"losses":49,"wins":7},"gpt-5.4-mini":{"draws":16,"losses":14,"wins":18},"gpt-5.4-nano":{"draws":18,"losses":33,"wins":31},"gpt-5.5":{"draws":26,"losses":32,"wins":6},"gpt-5.6-luna":{"draws":26,"losses":28,"wins":18},"gpt-5.6-sol":{"draws":15,"losses":50,"wins":7},"gpt-5.6-terra":{"draws":27,"losses":30,"wins":11},"gpt-6-astra":{"draws":3,"losses":69,"wins":0},"gpt-6-luna":{"draws":25,"losses":35,"wins":12},"gpt-6-sol":{"draws":10,"losses":55,"wins":7},"gpt-6.1-sol":{"draws":2,"losses":66,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":10,"wins":22},"inclusionai/ling-3.0-flash":{"draws":20,"losses":14,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":33,"wins":28},"meta/muse-glimmer-30b":{"draws":25,"losses":20,"wins":15},"meta/muse-spark-1.2":{"draws":16,"losses":40,"wins":12},"meta/muse-spark-1.3":{"draws":15,"losses":44,"wins":13},"meta/muse-wonder":{"draws":15,"losses":55,"wins":2},"minimax/minimax-m3":{"draws":12,"losses":14,"wins":16},"mistralai/mistral-large-4-0":{"draws":13,"losses":29,"wins":2},"mistralai/mistral-medium-3-5":{"draws":17,"losses":10,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":12,"wins":2},"moonshotai/kimi-k3":{"draws":24,"losses":28,"wins":16},"nex-agi/nex-n2-pro":{"draws":9,"losses":10,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":22,"wins":23},"o3":{"draws":15,"losses":67,"wins":28},"openai/gpt-oss-120b":{"draws":21,"losses":20,"wins":21},"poolside/laguna-s-2.1":{"draws":24,"losses":29,"wins":13},"qwen/qwen3.7-max":{"draws":13,"losses":21,"wins":12},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":35,"wins":9},"qwen/qwen3.8-27b":{"draws":11,"losses":28,"wins":15},"qwen/qwen3.8-flash":{"draws":16,"losses":16,"wins":16},"qwen/qwen3.8-max":{"draws":27,"losses":29,"wins":16},"qwen/qwen3.8-max-0902":{"draws":26,"losses":37,"wins":9},"stealth/ox-alpha":{"draws":44,"losses":131,"wins":27},"stealth/space-bunny-alpha":{"draws":18,"losses":31,"wins":9},"stepfun/step-3.7-flash":{"draws":12,"losses":21,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":13,"wins":11},"tencent/hy4-preview":{"draws":16,"losses":41,"wins":11},"thinkingmachines/inkling":{"draws":27,"losses":29,"wins":38},"thinkingmachines/inkling-small":{"draws":28,"losses":24,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":22,"wins":2},"upstage/solar-mini4":{"draws":3,"losses":10,"wins":9},"x-ai/grok-4.5":{"draws":18,"losses":46,"wins":8},"x-ai/grok-4.6":{"draws":21,"losses":45,"wins":6},"x-ai/grok-4.7":{"draws":6,"losses":53,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":8,"wins":9},"xiaomi/mimo-v2.5":{"draws":42,"losses":37,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":22,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":29,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":35,"wins":6},"z-ai/glm-5.2":{"draws":45,"losses":70,"wins":29},"z-ai/glm-5.3":{"draws":15,"losses":46,"wins":6},"z-ai/glm-5.3-flash":{"draws":19,"losses":43,"wins":10},"z-ai/glm-5.3-flashx":{"draws":17,"losses":45,"wins":10}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":25,"wins":66},"claude-fable-5":{"draws":36,"losses":74,"wins":34},"claude-fable-5-1":{"draws":13,"losses":143,"wins":6},"claude-haiku-5-5":{"draws":36,"losses":55,"wins":47},"claude-opus-4-5":{"draws":87,"losses":59,"wins":88},"claude-opus-4-8":{"draws":38,"losses":44,"wins":50},"claude-opus-5":{"draws":29,"losses":176,"wins":41},"claude-opus-5-5":{"draws":11,"losses":127,"wins":18},"claude-sonnet-5":{"draws":45,"losses":37,"wins":62},"claude-sonnet-5-5":{"draws":32,"losses":63,"wins":49},"cohere/north-mini-code":{"draws":8,"losses":3,"wins":43},"deepseek/deepseek-v4-flash":{"draws":71,"losses":32,"wins":113},"deepseek/deepseek-v4-pro":{"draws":36,"losses":36,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":43,"wins":56},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":57,"wins":50},"fireworks/ember-1":{"draws":50,"losses":47,"wins":47},"gemini-3.1-pro-preview":{"draws":36,"losses":46,"wins":62},"google/gemini-3.1-flash-lite":{"draws":25,"losses":3,"wins":68},"google/gemini-3.5-flash":{"draws":48,"losses":56,"wins":76},"google/gemini-3.5-flash-lite":{"draws":82,"losses":43,"wins":127},"google/gemini-3.6-flash":{"draws":73,"losses":107,"wins":96},"google/gemini-3.8-flash":{"draws":36,"losses":67,"wins":41},"google/gemma-4-31b-it":{"draws":29,"losses":10,"wins":45},"gpt-4.1":{"draws":18,"losses":6,"wins":24},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":11},"gpt-5":{"draws":39,"losses":33,"wins":54},"gpt-5.4":{"draws":29,"losses":56,"wins":53},"gpt-5.4-mini":{"draws":34,"losses":13,"wins":49},"gpt-5.4-nano":{"draws":36,"losses":29,"wins":79},"gpt-5.5":{"draws":40,"losses":47,"wins":45},"gpt-5.6-luna":{"draws":51,"losses":27,"wins":66},"gpt-5.6-sol":{"draws":23,"losses":85,"wins":36},"gpt-5.6-terra":{"draws":48,"losses":29,"wins":61},"gpt-6-astra":{"draws":5,"losses":133,"wins":6},"gpt-6-luna":{"draws":37,"losses":48,"wins":59},"gpt-6-sol":{"draws":19,"losses":93,"wins":32},"gpt-6.1-sol":{"draws":11,"losses":113,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":40,"losses":6,"wins":56},"inclusionai/ling-3.0-flash":{"draws":41,"losses":4,"wins":57},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":43,"losses":22,"wins":91},"meta/muse-glimmer-30b":{"draws":47,"losses":15,"wins":64},"meta/muse-spark-1.2":{"draws":37,"losses":47,"wins":54},"meta/muse-spark-1.3":{"draws":33,"losses":58,"wins":53},"meta/muse-wonder":{"draws":27,"losses":73,"wins":44},"minimax/minimax-m3":{"draws":20,"losses":8,"wins":50},"mistralai/mistral-large-4-0":{"draws":22,"losses":26,"wins":42},"mistralai/mistral-medium-3-5":{"draws":25,"losses":3,"wins":56},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":9,"wins":16},"moonshotai/kimi-k3":{"draws":38,"losses":50,"wins":50},"nex-agi/nex-n2-pro":{"draws":18,"losses":8,"wins":46},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":14,"wins":64},"o3":{"draws":31,"losses":58,"wins":109},"openai/gpt-oss-120b":{"draws":42,"losses":12,"wins":72},"poolside/laguna-s-2.1":{"draws":45,"losses":15,"wins":78},"qwen/qwen3.7-max":{"draws":29,"losses":17,"wins":38},"qwen/qwen3.7-plus":{"draws":28,"losses":9,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":35,"wins":35},"qwen/qwen3.8-27b":{"draws":40,"losses":26,"wins":36},"qwen/qwen3.8-flash":{"draws":27,"losses":30,"wins":39},"qwen/qwen3.8-max":{"draws":45,"losses":49,"wins":50},"qwen/qwen3.8-max-0902":{"draws":47,"losses":53,"wins":44},"stealth/ox-alpha":{"draws":122,"losses":176,"wins":176},"stealth/space-bunny-alpha":{"draws":40,"losses":27,"wins":47},"stepfun/step-3.7-flash":{"draws":18,"losses":15,"wins":69},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":8},"tencent/hy3-preview":{"draws":28,"losses":16,"wins":34},"tencent/hy4-preview":{"draws":40,"losses":52,"wins":46},"thinkingmachines/inkling":{"draws":59,"losses":25,"wins":108},"thinkingmachines/inkling-small":{"draws":47,"losses":17,"wins":80},"unbiased/pareto-26.10-preview":{"draws":2,"losses":42,"wins":4},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":26},"x-ai/grok-4.5":{"draws":34,"losses":60,"wins":50},"x-ai/grok-4.6":{"draws":34,"losses":61,"wins":49},"x-ai/grok-4.7":{"draws":10,"losses":86,"wins":30},"x-ai/grok-build-0.1":{"draws":17,"losses":6,"wins":25},"xiaomi/mimo-v2.5":{"draws":88,"losses":26,"wins":108},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":19,"wins":42},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":35,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":41,"wins":31},"z-ai/glm-5.2":{"draws":105,"losses":70,"wins":113},"z-ai/glm-5.3":{"draws":27,"losses":83,"wins":28},"z-ai/glm-5.3-flash":{"draws":32,"losses":63,"wins":49},"z-ai/glm-5.3-flashx":{"draws":38,"losses":61,"wins":45}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":23,"wins":48},"claude-fable-5":{"draws":20,"losses":66,"wins":16},"claude-fable-5-1":{"draws":6,"losses":107,"wins":1},"claude-haiku-5-5":{"draws":22,"losses":47,"wins":29},"claude-opus-4-5":{"draws":51,"losses":48,"wins":67},"claude-opus-4-8":{"draws":20,"losses":43,"wins":31},"claude-opus-5":{"draws":28,"losses":125,"wins":13},"claude-opus-5-5":{"draws":5,"losses":98,"wins":3},"claude-sonnet-5":{"draws":26,"losses":38,"wins":38},"claude-sonnet-5-5":{"draws":17,"losses":60,"wins":25},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":25},"deepseek/deepseek-v4-flash":{"draws":39,"losses":35,"wins":80},"deepseek/deepseek-v4-pro":{"draws":26,"losses":31,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":31,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":49,"wins":29},"fireworks/ember-1":{"draws":29,"losses":35,"wins":38},"gemini-3.1-pro-preview":{"draws":23,"losses":32,"wins":47},"google/gemini-3.1-flash-lite":{"draws":14,"losses":11,"wins":45},"google/gemini-3.5-flash":{"draws":22,"losses":57,"wins":49},"google/gemini-3.5-flash-lite":{"draws":37,"losses":43,"wins":100},"google/gemini-3.6-flash":{"draws":44,"losses":90,"wins":64},"google/gemini-3.8-flash":{"draws":17,"losses":63,"wins":22},"google/gemma-4-31b-it":{"draws":19,"losses":10,"wins":29},"gpt-4.1":{"draws":9,"losses":11,"wins":14},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":6},"gpt-5":{"draws":18,"losses":30,"wins":40},"gpt-5.4":{"draws":22,"losses":56,"wins":20},"gpt-5.4-mini":{"draws":17,"losses":19,"wins":32},"gpt-5.4-nano":{"draws":22,"losses":34,"wins":48},"gpt-5.5":{"draws":28,"losses":38,"wins":26},"gpt-5.6-luna":{"draws":32,"losses":25,"wins":45},"gpt-5.6-sol":{"draws":17,"losses":67,"wins":18},"gpt-5.6-terra":{"draws":36,"losses":33,"wins":29},"gpt-6-astra":{"draws":4,"losses":97,"wins":1},"gpt-6-luna":{"draws":26,"losses":41,"wins":35},"gpt-6-sol":{"draws":17,"losses":71,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":91,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":22,"losses":7,"wins":43},"inclusionai/ling-3.0-flash":{"draws":15,"losses":13,"wins":46},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":23,"losses":18,"wins":67},"meta/muse-glimmer-30b":{"draws":25,"losses":14,"wins":47},"meta/muse-spark-1.2":{"draws":22,"losses":36,"wins":38},"meta/muse-spark-1.3":{"draws":19,"losses":52,"wins":31},"meta/muse-wonder":{"draws":19,"losses":69,"wins":14},"minimax/minimax-m3":{"draws":14,"losses":8,"wins":32},"mistralai/mistral-large-4-0":{"draws":19,"losses":22,"wins":21},"mistralai/mistral-medium-3-5":{"draws":20,"losses":4,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":10},"moonshotai/kimi-k3":{"draws":28,"losses":41,"wins":27},"nex-agi/nex-n2-pro":{"draws":12,"losses":7,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":19,"wins":40},"o3":{"draws":14,"losses":58,"wins":72},"openai/gpt-oss-120b":{"draws":22,"losses":18,"wins":46},"poolside/laguna-s-2.1":{"draws":28,"losses":22,"wins":44},"qwen/qwen3.7-max":{"draws":16,"losses":18,"wins":26},"qwen/qwen3.7-plus":{"draws":11,"losses":15,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":36,"wins":26},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":18},"qwen/qwen3.8-flash":{"draws":18,"losses":28,"wins":22},"qwen/qwen3.8-max":{"draws":33,"losses":34,"wins":35},"qwen/qwen3.8-max-0902":{"draws":26,"losses":49,"wins":27},"stealth/ox-alpha":{"draws":74,"losses":151,"wins":107},"stealth/space-bunny-alpha":{"draws":21,"losses":20,"wins":39},"stepfun/step-3.7-flash":{"draws":13,"losses":26,"wins":37},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":15,"losses":13,"wins":26},"tencent/hy4-preview":{"draws":26,"losses":45,"wins":27},"thinkingmachines/inkling":{"draws":37,"losses":30,"wins":71},"thinkingmachines/inkling-small":{"draws":30,"losses":16,"wins":56},"unbiased/pareto-26.10-preview":{"draws":0,"losses":34,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":7,"wins":18},"x-ai/grok-4.5":{"draws":24,"losses":53,"wins":25},"x-ai/grok-4.6":{"draws":27,"losses":52,"wins":23},"x-ai/grok-4.7":{"draws":11,"losses":58,"wins":19},"x-ai/grok-build-0.1":{"draws":13,"losses":1,"wins":20},"xiaomi/mimo-v2.5":{"draws":44,"losses":29,"wins":87},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":20,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":26,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":36,"wins":20},"z-ai/glm-5.2":{"draws":66,"losses":70,"wins":68},"z-ai/glm-5.3":{"draws":26,"losses":58,"wins":12},"z-ai/glm-5.3-flash":{"draws":20,"losses":51,"wins":31},"z-ai/glm-5.3-flashx":{"draws":24,"losses":53,"wins":25}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":19,"wins":39},"claude-fable-5":{"draws":24,"losses":54,"wins":18},"claude-fable-5-1":{"draws":6,"losses":97,"wins":5},"claude-haiku-5-5":{"draws":28,"losses":45,"wins":19},"claude-opus-4-5":{"draws":57,"losses":53,"wins":46},"claude-opus-4-8":{"draws":31,"losses":41,"wins":16},"claude-opus-5":{"draws":23,"losses":127,"wins":14},"claude-opus-5-5":{"draws":9,"losses":92,"wins":3},"claude-sonnet-5":{"draws":32,"losses":33,"wins":31},"claude-sonnet-5-5":{"draws":17,"losses":49,"wins":30},"cohere/north-mini-code":{"draws":11,"losses":7,"wins":18},"deepseek/deepseek-v4-flash":{"draws":51,"losses":29,"wins":64},"deepseek/deepseek-v4-pro":{"draws":22,"losses":30,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":31,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":41,"wins":19},"fireworks/ember-1":{"draws":34,"losses":33,"wins":29},"gemini-3.1-pro-preview":{"draws":36,"losses":30,"wins":30},"google/gemini-3.1-flash-lite":{"draws":21,"losses":10,"wins":33},"google/gemini-3.5-flash":{"draws":37,"losses":48,"wins":35},"google/gemini-3.5-flash-lite":{"draws":58,"losses":30,"wins":80},"google/gemini-3.6-flash":{"draws":60,"losses":77,"wins":47},"google/gemini-3.8-flash":{"draws":25,"losses":45,"wins":26},"google/gemma-4-31b-it":{"draws":27,"losses":6,"wins":23},"gpt-4.1":{"draws":11,"losses":5,"wins":16},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":7},"gpt-5":{"draws":25,"losses":29,"wins":30},"gpt-5.4":{"draws":21,"losses":43,"wins":28},"gpt-5.4-mini":{"draws":25,"losses":14,"wins":25},"gpt-5.4-nano":{"draws":27,"losses":26,"wins":43},"gpt-5.5":{"draws":34,"losses":36,"wins":18},"gpt-5.6-luna":{"draws":31,"losses":28,"wins":37},"gpt-5.6-sol":{"draws":19,"losses":58,"wins":19},"gpt-5.6-terra":{"draws":30,"losses":33,"wins":29},"gpt-6-astra":{"draws":13,"losses":80,"wins":3},"gpt-6-luna":{"draws":28,"losses":35,"wins":33},"gpt-6-sol":{"draws":9,"losses":69,"wins":18},"gpt-6.1-sol":{"draws":7,"losses":82,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":31,"losses":6,"wins":31},"inclusionai/ling-3.0-flash":{"draws":27,"losses":5,"wins":36},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":35,"losses":22,"wins":47},"meta/muse-glimmer-30b":{"draws":37,"losses":21,"wins":26},"meta/muse-spark-1.2":{"draws":23,"losses":42,"wins":27},"meta/muse-spark-1.3":{"draws":23,"losses":47,"wins":26},"meta/muse-wonder":{"draws":24,"losses":60,"wins":12},"minimax/minimax-m3":{"draws":13,"losses":16,"wins":23},"mistralai/mistral-large-4-0":{"draws":22,"losses":21,"wins":17},"mistralai/mistral-medium-3-5":{"draws":22,"losses":5,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":9},"moonshotai/kimi-k3":{"draws":30,"losses":33,"wins":29},"nex-agi/nex-n2-pro":{"draws":16,"losses":6,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":14,"wins":31},"o3":{"draws":28,"losses":46,"wins":58},"openai/gpt-oss-120b":{"draws":27,"losses":23,"wins":34},"poolside/laguna-s-2.1":{"draws":40,"losses":19,"wins":33},"qwen/qwen3.7-max":{"draws":20,"losses":16,"wins":20},"qwen/qwen3.7-plus":{"draws":16,"losses":16,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":39,"wins":30},"qwen/qwen3.8-27b":{"draws":18,"losses":22,"wins":28},"qwen/qwen3.8-flash":{"draws":18,"losses":7,"wins":7},"qwen/qwen3.8-max":{"draws":33,"losses":37,"wins":26},"qwen/qwen3.8-max-0902":{"draws":33,"losses":34,"wins":29},"stealth/ox-alpha":{"draws":93,"losses":124,"wins":99},"stealth/space-bunny-alpha":{"draws":28,"losses":18,"wins":30},"stepfun/step-3.7-flash":{"draws":18,"losses":13,"wins":37},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":12,"wins":22},"tencent/hy4-preview":{"draws":27,"losses":39,"wins":26},"thinkingmachines/inkling":{"draws":43,"losses":25,"wins":60},"thinkingmachines/inkling-small":{"draws":42,"losses":18,"wins":36},"unbiased/pareto-26.10-preview":{"draws":2,"losses":26,"wins":4},"upstage/solar-mini4":{"draws":4,"losses":5,"wins":15},"x-ai/grok-4.5":{"draws":25,"losses":44,"wins":27},"x-ai/grok-4.6":{"draws":36,"losses":44,"wins":16},"x-ai/grok-4.7":{"draws":8,"losses":63,"wins":13},"x-ai/grok-build-0.1":{"draws":17,"losses":4,"wins":11},"xiaomi/mimo-v2.5":{"draws":60,"losses":31,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":12,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":22,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":35,"wins":16},"z-ai/glm-5.2":{"draws":71,"losses":54,"wins":67},"z-ai/glm-5.3":{"draws":25,"losses":53,"wins":14},"z-ai/glm-5.3-flash":{"draws":24,"losses":41,"wins":31},"z-ai/glm-5.3-flashx":{"draws":32,"losses":42,"wins":22}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":47,"losses":33,"wins":52},"claude-fable-5":{"draws":26,"losses":81,"wins":37},"claude-fable-5-1":{"draws":8,"losses":151,"wins":3},"claude-haiku-5-5":{"draws":34,"losses":67,"wins":37},"claude-opus-4-5":{"draws":76,"losses":65,"wins":93},"claude-opus-4-8":{"draws":26,"losses":61,"wins":45},"claude-opus-5":{"draws":36,"losses":180,"wins":30},"claude-opus-5-5":{"draws":13,"losses":131,"wins":12},"claude-sonnet-5":{"draws":46,"losses":44,"wins":54},"claude-sonnet-5-5":{"draws":23,"losses":80,"wins":41},"cohere/north-mini-code":{"draws":10,"losses":4,"wins":40},"deepseek/deepseek-v4-flash":{"draws":70,"losses":36,"wins":110},"deepseek/deepseek-v4-pro":{"draws":37,"losses":36,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":41,"losses":39,"wins":52},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":55,"wins":48},"fireworks/ember-1":{"draws":44,"losses":58,"wins":42},"gemini-3.1-pro-preview":{"draws":43,"losses":46,"wins":55},"google/gemini-3.1-flash-lite":{"draws":29,"losses":1,"wins":66},"google/gemini-3.5-flash":{"draws":57,"losses":62,"wins":61},"google/gemini-3.5-flash-lite":{"draws":84,"losses":47,"wins":121},"google/gemini-3.6-flash":{"draws":72,"losses":115,"wins":89},"google/gemini-3.8-flash":{"draws":38,"losses":60,"wins":46},"google/gemma-4-31b-it":{"draws":33,"losses":8,"wins":43},"gpt-4.1":{"draws":19,"losses":13,"wins":16},"gpt-4.1-nano":{"draws":10,"losses":1,"wins":7},"gpt-5":{"draws":41,"losses":29,"wins":56},"gpt-5.4":{"draws":38,"losses":51,"wins":49},"gpt-5.4-mini":{"draws":41,"losses":18,"wins":37},"gpt-5.4-nano":{"draws":33,"losses":37,"wins":74},"gpt-5.5":{"draws":44,"losses":48,"wins":40},"gpt-5.6-luna":{"draws":48,"losses":31,"wins":65},"gpt-5.6-sol":{"draws":26,"losses":88,"wins":30},"gpt-5.6-terra":{"draws":58,"losses":36,"wins":44},"gpt-6-astra":{"draws":13,"losses":129,"wins":2},"gpt-6-luna":{"draws":37,"losses":50,"wins":57},"gpt-6-sol":{"draws":17,"losses":99,"wins":28},"gpt-6.1-sol":{"draws":11,"losses":124,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":3},"inception/mercury-2.5-preview":{"draws":43,"losses":8,"wins":51},"inclusionai/ling-3.0-flash":{"draws":41,"losses":14,"wins":47},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":49,"losses":28,"wins":79},"meta/muse-glimmer-30b":{"draws":41,"losses":24,"wins":61},"meta/muse-spark-1.2":{"draws":36,"losses":51,"wins":51},"meta/muse-spark-1.3":{"draws":34,"losses":70,"wins":40},"meta/muse-wonder":{"draws":31,"losses":81,"wins":32},"minimax/minimax-m3":{"draws":23,"losses":14,"wins":41},"mistralai/mistral-large-4-0":{"draws":31,"losses":30,"wins":29},"mistralai/mistral-medium-3-5":{"draws":26,"losses":9,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":11,"wins":16},"moonshotai/kimi-k3":{"draws":38,"losses":48,"wins":52},"nex-agi/nex-n2-pro":{"draws":21,"losses":6,"wins":45},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":22,"wins":56},"o3":{"draws":39,"losses":62,"wins":97},"openai/gpt-oss-120b":{"draws":41,"losses":10,"wins":75},"poolside/laguna-s-2.1":{"draws":48,"losses":33,"wins":57},"qwen/qwen3.7-max":{"draws":31,"losses":23,"wins":30},"qwen/qwen3.7-plus":{"draws":27,"losses":16,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":50,"wins":49},"qwen/qwen3.8-27b":{"draws":33,"losses":35,"wins":34},"qwen/qwen3.8-flash":{"draws":33,"losses":26,"wins":37},"qwen/qwen3.8-max":{"draws":28,"losses":34,"wins":34},"qwen/qwen3.8-max-0902":{"draws":37,"losses":63,"wins":44},"stealth/ox-alpha":{"draws":127,"losses":191,"wins":156},"stealth/space-bunny-alpha":{"draws":37,"losses":31,"wins":46},"stepfun/step-3.7-flash":{"draws":26,"losses":17,"wins":59},"stepfun/step-5-preview":{"draws":4,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":30,"losses":13,"wins":35},"tencent/hy4-preview":{"draws":37,"losses":58,"wins":43},"thinkingmachines/inkling":{"draws":61,"losses":33,"wins":98},"thinkingmachines/inkling-small":{"draws":44,"losses":39,"wins":61},"unbiased/pareto-26.10-preview":{"draws":1,"losses":44,"wins":3},"upstage/solar-mini4":{"draws":5,"losses":9,"wins":22},"x-ai/grok-4.5":{"draws":32,"losses":65,"wins":47},"x-ai/grok-4.6":{"draws":40,"losses":64,"wins":40},"x-ai/grok-4.7":{"draws":12,"losses":88,"wins":26},"x-ai/grok-build-0.1":{"draws":19,"losses":9,"wins":20},"xiaomi/mimo-v2.5":{"draws":76,"losses":41,"wins":105},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":23,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":38,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":52,"wins":19},"z-ai/glm-5.2":{"draws":97,"losses":77,"wins":114},"z-ai/glm-5.3":{"draws":28,"losses":80,"wins":30},"z-ai/glm-5.3-flash":{"draws":34,"losses":57,"wins":53},"z-ai/glm-5.3-flashx":{"draws":40,"losses":56,"wins":48}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":37,"losses":21,"wins":74},"claude-fable-5":{"draws":29,"losses":81,"wins":34},"claude-fable-5-1":{"draws":5,"losses":142,"wins":15},"claude-haiku-5-5":{"draws":40,"losses":50,"wins":48},"claude-opus-4-5":{"draws":66,"losses":77,"wins":91},"claude-opus-4-8":{"draws":33,"losses":51,"wins":48},"claude-opus-5":{"draws":35,"losses":169,"wins":42},"claude-opus-5-5":{"draws":16,"losses":128,"wins":12},"claude-sonnet-5":{"draws":42,"losses":36,"wins":66},"claude-sonnet-5-5":{"draws":26,"losses":67,"wins":51},"cohere/north-mini-code":{"draws":10,"losses":5,"wins":39},"deepseek/deepseek-v4-flash":{"draws":64,"losses":29,"wins":123},"deepseek/deepseek-v4-pro":{"draws":34,"losses":34,"wins":64},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":39,"wins":54},"deepseek/deepseek-v4.1-flash":{"draws":49,"losses":51,"wins":44},"fireworks/ember-1":{"draws":44,"losses":42,"wins":58},"gemini-3.1-pro-preview":{"draws":39,"losses":37,"wins":68},"google/gemini-3.1-flash-lite":{"draws":28,"losses":2,"wins":66},"google/gemini-3.5-flash":{"draws":49,"losses":47,"wins":84},"google/gemini-3.5-flash-lite":{"draws":76,"losses":36,"wins":140},"google/gemini-3.6-flash":{"draws":76,"losses":95,"wins":105},"google/gemini-3.8-flash":{"draws":39,"losses":59,"wins":46},"google/gemma-4-31b-it":{"draws":29,"losses":9,"wins":46},"gpt-4.1":{"draws":18,"losses":7,"wins":23},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":10},"gpt-5":{"draws":38,"losses":30,"wins":58},"gpt-5.4":{"draws":31,"losses":62,"wins":45},"gpt-5.4-mini":{"draws":38,"losses":14,"wins":44},"gpt-5.4-nano":{"draws":38,"losses":35,"wins":71},"gpt-5.5":{"draws":47,"losses":42,"wins":43},"gpt-5.6-luna":{"draws":51,"losses":32,"wins":61},"gpt-5.6-sol":{"draws":23,"losses":87,"wins":34},"gpt-5.6-terra":{"draws":48,"losses":37,"wins":53},"gpt-6-astra":{"draws":9,"losses":129,"wins":6},"gpt-6-luna":{"draws":41,"losses":47,"wins":56},"gpt-6-sol":{"draws":16,"losses":100,"wins":28},"gpt-6.1-sol":{"draws":12,"losses":121,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":44,"losses":10,"wins":48},"inclusionai/ling-3.0-flash":{"draws":39,"losses":9,"wins":54},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":32,"losses":23,"wins":101},"meta/muse-glimmer-30b":{"draws":46,"losses":12,"wins":68},"meta/muse-spark-1.2":{"draws":31,"losses":52,"wins":55},"meta/muse-spark-1.3":{"draws":39,"losses":52,"wins":53},"meta/muse-wonder":{"draws":33,"losses":78,"wins":33},"minimax/minimax-m3":{"draws":21,"losses":8,"wins":49},"mistralai/mistral-large-4-0":{"draws":32,"losses":18,"wins":40},"mistralai/mistral-medium-3-5":{"draws":29,"losses":6,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":8,"wins":17},"moonshotai/kimi-k3":{"draws":36,"losses":34,"wins":68},"nex-agi/nex-n2-pro":{"draws":21,"losses":9,"wins":42},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":12,"wins":65},"o3":{"draws":37,"losses":63,"wins":98},"openai/gpt-oss-120b":{"draws":39,"losses":15,"wins":72},"poolside/laguna-s-2.1":{"draws":45,"losses":23,"wins":70},"qwen/qwen3.7-max":{"draws":26,"losses":17,"wins":41},"qwen/qwen3.7-plus":{"draws":26,"losses":9,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":44,"wins":53},"qwen/qwen3.8-27b":{"draws":26,"losses":27,"wins":49},"qwen/qwen3.8-flash":{"draws":33,"losses":29,"wins":34},"qwen/qwen3.8-max":{"draws":37,"losses":44,"wins":63},"qwen/qwen3.8-max-0902":{"draws":24,"losses":36,"wins":36},"stealth/ox-alpha":{"draws":113,"losses":176,"wins":185},"stealth/space-bunny-alpha":{"draws":36,"losses":19,"wins":59},"stepfun/step-3.7-flash":{"draws":27,"losses":19,"wins":56},"stepfun/step-5-preview":{"draws":5,"losses":5,"wins":2},"tencent/hy3-preview":{"draws":27,"losses":14,"wins":37},"tencent/hy4-preview":{"draws":34,"losses":54,"wins":50},"thinkingmachines/inkling":{"draws":54,"losses":30,"wins":108},"thinkingmachines/inkling-small":{"draws":49,"losses":15,"wins":80},"unbiased/pareto-26.10-preview":{"draws":2,"losses":41,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":29},"x-ai/grok-4.5":{"draws":31,"losses":61,"wins":52},"x-ai/grok-4.6":{"draws":44,"losses":66,"wins":34},"x-ai/grok-4.7":{"draws":18,"losses":81,"wins":27},"x-ai/grok-build-0.1":{"draws":16,"losses":7,"wins":25},"xiaomi/mimo-v2.5":{"draws":83,"losses":28,"wins":111},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":20,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":39,"wins":32},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":52,"wins":30},"z-ai/glm-5.2":{"draws":97,"losses":57,"wins":134},"z-ai/glm-5.3":{"draws":35,"losses":73,"wins":30},"z-ai/glm-5.3-flash":{"draws":40,"losses":52,"wins":52},"z-ai/glm-5.3-flashx":{"draws":36,"losses":57,"wins":51}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":102,"losses":87,"wins":251},"claude-fable-5":{"draws":86,"losses":276,"wins":112},"claude-fable-5-1":{"draws":32,"losses":492,"wins":26},"claude-haiku-5-5":{"draws":96,"losses":173,"wins":165},"claude-opus-4-5":{"draws":203,"losses":213,"wins":334},"claude-opus-4-8":{"draws":85,"losses":153,"wins":156},"claude-opus-5":{"draws":130,"losses":579,"wins":123},"claude-opus-5-5":{"draws":49,"losses":427,"wins":30},"claude-sonnet-5":{"draws":109,"losses":133,"wins":232},"claude-sonnet-5-5":{"draws":85,"losses":225,"wins":164},"cohere/north-mini-code":{"draws":30,"losses":21,"wins":127},"deepseek/deepseek-v4-flash":{"draws":175,"losses":123,"wins":398},"deepseek/deepseek-v4-pro":{"draws":107,"losses":132,"wins":203},"deepseek/deepseek-v4-pro-0813":{"draws":109,"losses":151,"wins":180},"deepseek/deepseek-v4.1-flash":{"draws":110,"losses":182,"wins":181},"fireworks/ember-1":{"draws":124,"losses":171,"wins":179},"gemini-3.1-pro-preview":{"draws":106,"losses":145,"wins":223},"google/gemini-3.1-flash-lite":{"draws":52,"losses":29,"wins":191},"google/gemini-3.5-flash":{"draws":115,"losses":202,"wins":259},"google/gemini-3.5-flash-lite":{"draws":180,"losses":163,"wins":483},"google/gemini-3.6-flash":{"draws":195,"losses":361,"wins":360},"google/gemini-3.8-flash":{"draws":103,"losses":223,"wins":148},"google/gemma-4-31b-it":{"draws":60,"losses":40,"wins":160},"gpt-4.1":{"draws":43,"losses":36,"wins":79},"gpt-4.1-nano":{"draws":33,"losses":5,"wins":34},"gpt-5":{"draws":102,"losses":124,"wins":198},"gpt-5.4":{"draws":124,"losses":179,"wins":155},"gpt-5.4-mini":{"draws":94,"losses":60,"wins":162},"gpt-5.4-nano":{"draws":83,"losses":116,"wins":225},"gpt-5.5":{"draws":123,"losses":156,"wins":163},"gpt-5.6-luna":{"draws":146,"losses":100,"wins":228},"gpt-5.6-sol":{"draws":74,"losses":286,"wins":114},"gpt-5.6-terra":{"draws":135,"losses":126,"wins":195},"gpt-6-astra":{"draws":35,"losses":419,"wins":20},"gpt-6-luna":{"draws":112,"losses":154,"wins":208},"gpt-6-sol":{"draws":61,"losses":340,"wins":73},"gpt-6.1-sol":{"draws":44,"losses":400,"wins":30},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":1,"wins":8},"inception/mercury-2.5-preview":{"draws":102,"losses":33,"wins":175},"inclusionai/ling-3.0-flash":{"draws":94,"losses":26,"wins":208},"inclusionai/ling-3.1-flash":{"draws":6,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":120,"losses":73,"wins":317},"meta/muse-glimmer-30b":{"draws":104,"losses":56,"wins":266},"meta/muse-spark-1.2":{"draws":106,"losses":149,"wins":203},"meta/muse-spark-1.3":{"draws":88,"losses":221,"wins":165},"meta/muse-wonder":{"draws":93,"losses":253,"wins":128},"minimax/minimax-m3":{"draws":55,"losses":39,"wins":148},"mistralai/mistral-large-4-0":{"draws":98,"losses":82,"wins":120},"mistralai/mistral-medium-3-5":{"draws":72,"losses":39,"wins":171},"moonshotai/kimi-k2.7-code":{"draws":24,"losses":29,"wins":49},"moonshotai/kimi-k3":{"draws":112,"losses":166,"wins":180},"nex-agi/nex-n2-pro":{"draws":61,"losses":30,"wins":159},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":109,"losses":58,"wins":207},"o3":{"draws":92,"losses":200,"wins":312},"openai/gpt-oss-120b":{"draws":110,"losses":58,"wins":256},"poolside/laguna-s-2.1":{"draws":130,"losses":84,"wins":264},"qwen/qwen3.7-max":{"draws":64,"losses":58,"wins":136},"qwen/qwen3.7-plus":{"draws":44,"losses":27,"wins":131},"qwen/qwen3.8-2.4t-a95b":{"draws":122,"losses":176,"wins":176},"qwen/qwen3.8-27b":{"draws":74,"losses":107,"wins":151},"qwen/qwen3.8-flash":{"draws":93,"losses":99,"wins":124},"qwen/qwen3.8-max":{"draws":127,"losses":156,"wins":191},"qwen/qwen3.8-max-0902":{"draws":113,"losses":185,"wins":176},"stealth/ox-alpha":{"draws":296,"losses":672,"wins":672},"stealth/space-bunny-alpha":{"draws":99,"losses":83,"wins":188},"stepfun/step-3.7-flash":{"draws":57,"losses":57,"wins":218},"stepfun/step-5-preview":{"draws":8,"losses":15,"wins":9},"tencent/hy3-preview":{"draws":72,"losses":46,"wins":124},"tencent/hy4-preview":{"draws":103,"losses":197,"wins":158},"thinkingmachines/inkling":{"draws":163,"losses":120,"wins":375},"thinkingmachines/inkling-small":{"draws":134,"losses":68,"wins":272},"unbiased/pareto-26.10-preview":{"draws":10,"losses":141,"wins":7},"upstage/solar-mini4":{"draws":13,"losses":15,"wins":74},"x-ai/grok-4.5":{"draws":100,"losses":206,"wins":168},"x-ai/grok-4.6":{"draws":137,"losses":192,"wins":145},"x-ai/grok-4.7":{"draws":46,"losses":280,"wins":74},"x-ai/grok-build-0.1":{"draws":40,"losses":17,"wins":101},"xiaomi/mimo-v2.5":{"draws":171,"losses":95,"wins":380},"xiaomi/mimo-v2.5-pro":{"draws":48,"losses":58,"wins":136},"xiaomi/mimo-v2.6-flash":{"draws":57,"losses":109,"wins":132},"xiaomi/mimo-v2.6-pro":{"draws":57,"losses":154,"wins":105},"z-ai/glm-5.2":{"draws":256,"losses":220,"wins":472},"z-ai/glm-5.3":{"draws":81,"losses":260,"wins":117},"z-ai/glm-5.3-flash":{"draws":84,"losses":210,"wins":180},"z-ai/glm-5.3-flashx":{"draws":86,"losses":221,"wins":167}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":31,"wins":38},"claude-fable-5":{"draws":31,"losses":68,"wins":15},"claude-fable-5-1":{"draws":6,"losses":121,"wins":3},"claude-haiku-5-5":{"draws":33,"losses":54,"wins":23},"claude-opus-4-5":{"draws":58,"losses":79,"wins":49},"claude-opus-4-8":{"draws":30,"losses":52,"wins":24},"claude-opus-5":{"draws":31,"losses":151,"wins":14},"claude-opus-5-5":{"draws":5,"losses":116,"wins":1},"claude-sonnet-5":{"draws":30,"losses":47,"wins":37},"claude-sonnet-5-5":{"draws":22,"losses":68,"wins":24},"cohere/north-mini-code":{"draws":11,"losses":7,"wins":28},"deepseek/deepseek-v4-flash":{"draws":60,"losses":38,"wins":70},"deepseek/deepseek-v4-pro":{"draws":31,"losses":47,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":46,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":53,"wins":25},"fireworks/ember-1":{"draws":36,"losses":55,"wins":23},"gemini-3.1-pro-preview":{"draws":36,"losses":44,"wins":34},"google/gemini-3.1-flash-lite":{"draws":21,"losses":12,"wins":47},"google/gemini-3.5-flash":{"draws":43,"losses":68,"wins":33},"google/gemini-3.5-flash-lite":{"draws":58,"losses":60,"wins":84},"google/gemini-3.6-flash":{"draws":57,"losses":118,"wins":45},"google/gemini-3.8-flash":{"draws":31,"losses":66,"wins":17},"google/gemma-4-31b-it":{"draws":26,"losses":16,"wins":26},"gpt-4.1":{"draws":15,"losses":10,"wins":13},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":5},"gpt-5":{"draws":26,"losses":39,"wins":35},"gpt-5.4":{"draws":33,"losses":61,"wins":16},"gpt-5.4-mini":{"draws":28,"losses":15,"wins":33},"gpt-5.4-nano":{"draws":26,"losses":39,"wins":47},"gpt-5.5":{"draws":41,"losses":46,"wins":19},"gpt-5.6-luna":{"draws":43,"losses":31,"wins":40},"gpt-5.6-sol":{"draws":20,"losses":80,"wins":14},"gpt-5.6-terra":{"draws":37,"losses":39,"wins":32},"gpt-6-astra":{"draws":6,"losses":108,"wins":0},"gpt-6-luna":{"draws":41,"losses":50,"wins":23},"gpt-6-sol":{"draws":16,"losses":87,"wins":11},"gpt-6.1-sol":{"draws":9,"losses":100,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":37,"losses":10,"wins":35},"inclusionai/ling-3.0-flash":{"draws":34,"losses":11,"wins":31},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":40,"losses":29,"wins":57},"meta/muse-glimmer-30b":{"draws":39,"losses":27,"wins":36},"meta/muse-spark-1.2":{"draws":31,"losses":53,"wins":26},"meta/muse-spark-1.3":{"draws":24,"losses":69,"wins":21},"meta/muse-wonder":{"draws":28,"losses":68,"wins":18},"minimax/minimax-m3":{"draws":18,"losses":13,"wins":31},"mistralai/mistral-large-4-0":{"draws":26,"losses":32,"wins":14},"mistralai/mistral-medium-3-5":{"draws":24,"losses":12,"wins":30},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":14,"wins":7},"moonshotai/kimi-k3":{"draws":37,"losses":53,"wins":20},"nex-agi/nex-n2-pro":{"draws":17,"losses":13,"wins":28},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":25,"wins":32},"o3":{"draws":26,"losses":78,"wins":56},"openai/gpt-oss-120b":{"draws":33,"losses":23,"wins":44},"poolside/laguna-s-2.1":{"draws":33,"losses":33,"wins":40},"qwen/qwen3.7-max":{"draws":21,"losses":23,"wins":22},"qwen/qwen3.7-plus":{"draws":18,"losses":9,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":47,"wins":27},"qwen/qwen3.8-27b":{"draws":21,"losses":39,"wins":20},"qwen/qwen3.8-flash":{"draws":28,"losses":30,"wins":18},"qwen/qwen3.8-max":{"draws":37,"losses":46,"wins":31},"qwen/qwen3.8-max-0902":{"draws":36,"losses":59,"wins":19},"stealth/ox-alpha":{"draws":99,"losses":188,"wins":83},"stealth/space-bunny-alpha":{"draws":20,"losses":18,"wins":18},"stepfun/step-3.7-flash":{"draws":21,"losses":23,"wins":36},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":24,"losses":17,"wins":21},"tencent/hy4-preview":{"draws":33,"losses":51,"wins":26},"thinkingmachines/inkling":{"draws":50,"losses":44,"wins":60},"thinkingmachines/inkling-small":{"draws":38,"losses":29,"wins":47},"unbiased/pareto-26.10-preview":{"draws":1,"losses":37,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":9,"wins":16},"x-ai/grok-4.5":{"draws":31,"losses":63,"wins":20},"x-ai/grok-4.6":{"draws":36,"losses":59,"wins":19},"x-ai/grok-4.7":{"draws":10,"losses":73,"wins":17},"x-ai/grok-build-0.1":{"draws":12,"losses":10,"wins":16},"xiaomi/mimo-v2.5":{"draws":71,"losses":38,"wins":69},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":15,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":36,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":38,"wins":19},"z-ai/glm-5.2":{"draws":89,"losses":74,"wins":65},"z-ai/glm-5.3":{"draws":25,"losses":76,"wins":9},"z-ai/glm-5.3-flash":{"draws":30,"losses":67,"wins":17},"z-ai/glm-5.3-flashx":{"draws":33,"losses":59,"wins":22}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":36,"wins":33},"claude-fable-5":{"draws":15,"losses":80,"wins":7},"claude-fable-5-1":{"draws":3,"losses":111,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":67,"wins":16},"claude-opus-4-5":{"draws":32,"losses":95,"wins":39},"claude-opus-4-8":{"draws":16,"losses":61,"wins":17},"claude-opus-5":{"draws":14,"losses":141,"wins":7},"claude-opus-5-5":{"draws":4,"losses":106,"wins":0},"claude-sonnet-5":{"draws":24,"losses":50,"wins":28},"claude-sonnet-5-5":{"draws":11,"losses":65,"wins":26},"cohere/north-mini-code":{"draws":10,"losses":5,"wins":25},"deepseek/deepseek-v4-flash":{"draws":41,"losses":60,"wins":57},"deepseek/deepseek-v4-pro":{"draws":19,"losses":54,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":52,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":60,"wins":16},"fireworks/ember-1":{"draws":23,"losses":61,"wins":18},"gemini-3.1-pro-preview":{"draws":25,"losses":45,"wins":32},"google/gemini-3.1-flash-lite":{"draws":15,"losses":10,"wins":49},"google/gemini-3.5-flash":{"draws":24,"losses":80,"wins":26},"google/gemini-3.5-flash-lite":{"draws":51,"losses":69,"wins":60},"google/gemini-3.6-flash":{"draws":37,"losses":129,"wins":32},"google/gemini-3.8-flash":{"draws":20,"losses":73,"wins":9},"google/gemma-4-31b-it":{"draws":18,"losses":13,"wins":27},"gpt-4.1":{"draws":9,"losses":19,"wins":6},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":6},"gpt-5":{"draws":27,"losses":47,"wins":18},"gpt-5.4":{"draws":20,"losses":64,"wins":16},"gpt-5.4-mini":{"draws":24,"losses":22,"wins":22},"gpt-5.4-nano":{"draws":20,"losses":57,"wins":33},"gpt-5.5":{"draws":27,"losses":54,"wins":13},"gpt-5.6-luna":{"draws":30,"losses":41,"wins":31},"gpt-5.6-sol":{"draws":11,"losses":84,"wins":7},"gpt-5.6-terra":{"draws":28,"losses":50,"wins":20},"gpt-6-astra":{"draws":6,"losses":96,"wins":0},"gpt-6-luna":{"draws":22,"losses":57,"wins":23},"gpt-6-sol":{"draws":13,"losses":85,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":99,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":22,"losses":8,"wins":38},"inclusionai/ling-3.0-flash":{"draws":30,"losses":16,"wins":30},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":28,"losses":38,"wins":48},"meta/muse-glimmer-30b":{"draws":26,"losses":35,"wins":27},"meta/muse-spark-1.2":{"draws":15,"losses":57,"wins":24},"meta/muse-spark-1.3":{"draws":12,"losses":77,"wins":13},"meta/muse-wonder":{"draws":12,"losses":80,"wins":10},"minimax/minimax-m3":{"draws":13,"losses":25,"wins":18},"mistralai/mistral-large-4-0":{"draws":20,"losses":33,"wins":9},"mistralai/mistral-medium-3-5":{"draws":21,"losses":11,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":15,"wins":5},"moonshotai/kimi-k3":{"draws":23,"losses":57,"wins":16},"nex-agi/nex-n2-pro":{"draws":10,"losses":15,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":28,"wins":30},"o3":{"draws":28,"losses":90,"wins":42},"openai/gpt-oss-120b":{"draws":31,"losses":21,"wins":36},"poolside/laguna-s-2.1":{"draws":37,"losses":32,"wins":29},"qwen/qwen3.7-max":{"draws":16,"losses":34,"wins":12},"qwen/qwen3.7-plus":{"draws":12,"losses":21,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":69,"wins":15},"qwen/qwen3.8-27b":{"draws":13,"losses":37,"wins":26},"qwen/qwen3.8-flash":{"draws":18,"losses":37,"wins":13},"qwen/qwen3.8-max":{"draws":26,"losses":59,"wins":17},"qwen/qwen3.8-max-0902":{"draws":27,"losses":56,"wins":19},"stealth/ox-alpha":{"draws":57,"losses":218,"wins":57},"stealth/space-bunny-alpha":{"draws":21,"losses":36,"wins":23},"stepfun/step-3.7-flash":{"draws":10,"losses":19,"wins":19},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":22,"wins":12},"tencent/hy4-preview":{"draws":22,"losses":61,"wins":17},"thinkingmachines/inkling":{"draws":38,"losses":38,"wins":62},"thinkingmachines/inkling-small":{"draws":32,"losses":33,"wins":37},"unbiased/pareto-26.10-preview":{"draws":1,"losses":33,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":9,"wins":19},"x-ai/grok-4.5":{"draws":12,"losses":71,"wins":19},"x-ai/grok-4.6":{"draws":24,"losses":64,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":75,"wins":10},"x-ai/grok-build-0.1":{"draws":10,"losses":9,"wins":15},"xiaomi/mimo-v2.5":{"draws":46,"losses":54,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":32,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":44,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":52,"wins":8},"z-ai/glm-5.2":{"draws":56,"losses":99,"wins":49},"z-ai/glm-5.3":{"draws":15,"losses":78,"wins":3},"z-ai/glm-5.3-flash":{"draws":19,"losses":63,"wins":20},"z-ai/glm-5.3-flashx":{"draws":17,"losses":71,"wins":14}},"stepfun/step-5-preview":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":4,"wins":4},"claude-fable-5":{"draws":2,"losses":5,"wins":5},"claude-fable-5-1":{"draws":0,"losses":10,"wins":2},"claude-haiku-5-5":{"draws":3,"losses":4,"wins":5},"claude-opus-4-5":{"draws":3,"losses":7,"wins":10},"claude-opus-4-8":{"draws":2,"losses":6,"wins":4},"claude-opus-5":{"draws":0,"losses":17,"wins":7},"claude-opus-5-5":{"draws":0,"losses":16,"wins":4},"claude-sonnet-5":{"draws":3,"losses":3,"wins":6},"claude-sonnet-5-5":{"draws":0,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":6,"losses":4,"wins":10},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":1,"wins":7},"fireworks/ember-1":{"draws":3,"losses":5,"wins":4},"gemini-3.1-pro-preview":{"draws":4,"losses":4,"wins":4},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":10},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":10},"google/gemini-3.6-flash":{"draws":6,"losses":5,"wins":9},"google/gemini-3.8-flash":{"draws":3,"losses":5,"wins":4},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":4},"gpt-4.1":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":5,"losses":0,"wins":7},"gpt-5.4":{"draws":5,"losses":1,"wins":6},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":4},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":9},"gpt-5.5":{"draws":6,"losses":3,"wins":3},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":8},"gpt-5.6-sol":{"draws":0,"losses":10,"wins":2},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":6},"gpt-6-astra":{"draws":0,"losses":8,"wins":4},"gpt-6-luna":{"draws":3,"losses":3,"wins":6},"gpt-6-sol":{"draws":1,"losses":8,"wins":3},"gpt-6.1-sol":{"draws":0,"losses":10,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":5},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":1,"wins":8},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":0,"losses":6,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":5,"wins":5},"meta/muse-wonder":{"draws":2,"losses":4,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":4},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":8},"o3":{"draws":8,"losses":2,"wins":10},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":8,"wins":2},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":4},"qwen/qwen3.8-max":{"draws":4,"losses":5,"wins":3},"qwen/qwen3.8-max-0902":{"draws":5,"losses":2,"wins":5},"stealth/ox-alpha":{"draws":8,"losses":9,"wins":15},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":4,"losses":4,"wins":4},"thinkingmachines/inkling":{"draws":3,"losses":3,"wins":6},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":6},"unbiased/pareto-26.10-preview":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":8,"wins":4},"x-ai/grok-4.6":{"draws":4,"losses":4,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":11,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":0,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":8,"losses":3,"wins":13},"z-ai/glm-5.3":{"draws":1,"losses":6,"wins":5},"z-ai/glm-5.3-flash":{"draws":5,"losses":0,"wins":7},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":8}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":26,"wins":23},"claude-fable-5":{"draws":22,"losses":45,"wins":11},"claude-fable-5-1":{"draws":8,"losses":74,"wins":4},"claude-haiku-5-5":{"draws":25,"losses":31,"wins":20},"claude-opus-4-5":{"draws":46,"losses":52,"wins":30},"claude-opus-4-8":{"draws":20,"losses":38,"wins":16},"claude-opus-5":{"draws":25,"losses":106,"wins":11},"claude-opus-5-5":{"draws":8,"losses":78,"wins":0},"claude-sonnet-5":{"draws":25,"losses":31,"wins":22},"claude-sonnet-5-5":{"draws":19,"losses":49,"wins":10},"cohere/north-mini-code":{"draws":9,"losses":6,"wins":13},"deepseek/deepseek-v4-flash":{"draws":35,"losses":39,"wins":42},"deepseek/deepseek-v4-pro":{"draws":24,"losses":30,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":25,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":37,"wins":15},"fireworks/ember-1":{"draws":30,"losses":36,"wins":12},"gemini-3.1-pro-preview":{"draws":22,"losses":34,"wins":22},"google/gemini-3.1-flash-lite":{"draws":17,"losses":11,"wins":24},"google/gemini-3.5-flash":{"draws":28,"losses":41,"wins":29},"google/gemini-3.5-flash-lite":{"draws":48,"losses":30,"wins":58},"google/gemini-3.6-flash":{"draws":47,"losses":70,"wins":31},"google/gemini-3.8-flash":{"draws":31,"losses":39,"wins":8},"google/gemma-4-31b-it":{"draws":21,"losses":9,"wins":16},"gpt-4.1":{"draws":10,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":2},"gpt-5":{"draws":20,"losses":21,"wins":27},"gpt-5.4":{"draws":28,"losses":33,"wins":13},"gpt-5.4-mini":{"draws":21,"losses":14,"wins":17},"gpt-5.4-nano":{"draws":20,"losses":23,"wins":37},"gpt-5.5":{"draws":33,"losses":30,"wins":9},"gpt-5.6-luna":{"draws":29,"losses":21,"wins":28},"gpt-5.6-sol":{"draws":14,"losses":55,"wins":9},"gpt-5.6-terra":{"draws":31,"losses":28,"wins":15},"gpt-6-astra":{"draws":11,"losses":67,"wins":0},"gpt-6-luna":{"draws":26,"losses":32,"wins":20},"gpt-6-sol":{"draws":15,"losses":58,"wins":5},"gpt-6.1-sol":{"draws":7,"losses":68,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":28,"losses":12,"wins":16},"inclusionai/ling-3.0-flash":{"draws":22,"losses":7,"wins":25},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":25,"wins":32},"meta/muse-glimmer-30b":{"draws":26,"losses":13,"wins":31},"meta/muse-spark-1.2":{"draws":21,"losses":42,"wins":13},"meta/muse-spark-1.3":{"draws":14,"losses":50,"wins":14},"meta/muse-wonder":{"draws":15,"losses":51,"wins":12},"minimax/minimax-m3":{"draws":15,"losses":11,"wins":18},"mistralai/mistral-large-4-0":{"draws":20,"losses":14,"wins":16},"mistralai/mistral-medium-3-5":{"draws":18,"losses":12,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":8,"wins":6},"moonshotai/kimi-k3":{"draws":28,"losses":28,"wins":20},"nex-agi/nex-n2-pro":{"draws":12,"losses":13,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":14,"wins":21},"o3":{"draws":22,"losses":42,"wins":40},"openai/gpt-oss-120b":{"draws":22,"losses":19,"wins":27},"poolside/laguna-s-2.1":{"draws":28,"losses":22,"wins":26},"qwen/qwen3.7-max":{"draws":19,"losses":17,"wins":10},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":34,"wins":16},"qwen/qwen3.8-27b":{"draws":15,"losses":26,"wins":13},"qwen/qwen3.8-flash":{"draws":18,"losses":22,"wins":12},"qwen/qwen3.8-max":{"draws":30,"losses":35,"wins":13},"qwen/qwen3.8-max-0902":{"draws":27,"losses":37,"wins":14},"stealth/ox-alpha":{"draws":72,"losses":124,"wins":46},"stealth/space-bunny-alpha":{"draws":24,"losses":21,"wins":17},"stepfun/step-3.7-flash":{"draws":18,"losses":12,"wins":22},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":6,"losses":7,"wins":7},"tencent/hy4-preview":{"draws":24,"losses":31,"wins":19},"thinkingmachines/inkling":{"draws":31,"losses":26,"wins":47},"thinkingmachines/inkling-small":{"draws":32,"losses":16,"wins":30},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":2},"upstage/solar-mini4":{"draws":4,"losses":7,"wins":7},"x-ai/grok-4.5":{"draws":24,"losses":47,"wins":7},"x-ai/grok-4.6":{"draws":22,"losses":46,"wins":10},"x-ai/grok-4.7":{"draws":12,"losses":55,"wins":3},"x-ai/grok-build-0.1":{"draws":9,"losses":5,"wins":12},"xiaomi/mimo-v2.5":{"draws":49,"losses":32,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":14,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":26,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":33,"wins":10},"z-ai/glm-5.2":{"draws":53,"losses":56,"wins":47},"z-ai/glm-5.3":{"draws":14,"losses":50,"wins":10},"z-ai/glm-5.3-flash":{"draws":21,"losses":43,"wins":14},"z-ai/glm-5.3-flashx":{"draws":16,"losses":48,"wins":14}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":15,"wins":72},"claude-fable-5":{"draws":25,"losses":81,"wins":32},"claude-fable-5-1":{"draws":9,"losses":135,"wins":12},"claude-haiku-5-5":{"draws":30,"losses":48,"wins":54},"claude-opus-4-5":{"draws":62,"losses":60,"wins":102},"claude-opus-4-8":{"draws":31,"losses":45,"wins":50},"claude-opus-5":{"draws":24,"losses":175,"wins":35},"claude-opus-5-5":{"draws":12,"losses":125,"wins":13},"claude-sonnet-5":{"draws":40,"losses":34,"wins":64},"claude-sonnet-5-5":{"draws":24,"losses":67,"wins":47},"cohere/north-mini-code":{"draws":15,"losses":3,"wins":36},"deepseek/deepseek-v4-flash":{"draws":56,"losses":34,"wins":116},"deepseek/deepseek-v4-pro":{"draws":32,"losses":36,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":43,"wins":56},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":41,"wins":56},"fireworks/ember-1":{"draws":42,"losses":42,"wins":54},"gemini-3.1-pro-preview":{"draws":33,"losses":40,"wins":65},"google/gemini-3.1-flash-lite":{"draws":23,"losses":3,"wins":68},"google/gemini-3.5-flash":{"draws":39,"losses":46,"wins":89},"google/gemini-3.5-flash-lite":{"draws":62,"losses":49,"wins":133},"google/gemini-3.6-flash":{"draws":59,"losses":102,"wins":105},"google/gemini-3.8-flash":{"draws":33,"losses":52,"wins":53},"google/gemma-4-31b-it":{"draws":26,"losses":11,"wins":43},"gpt-4.1":{"draws":13,"losses":9,"wins":24},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":11},"gpt-5":{"draws":37,"losses":35,"wins":50},"gpt-5.4":{"draws":31,"losses":58,"wins":45},"gpt-5.4-mini":{"draws":34,"losses":11,"wins":47},"gpt-5.4-nano":{"draws":23,"losses":29,"wins":86},"gpt-5.5":{"draws":44,"losses":40,"wins":44},"gpt-5.6-luna":{"draws":43,"losses":26,"wins":69},"gpt-5.6-sol":{"draws":20,"losses":73,"wins":45},"gpt-5.6-terra":{"draws":37,"losses":36,"wins":59},"gpt-6-astra":{"draws":9,"losses":124,"wins":5},"gpt-6-luna":{"draws":39,"losses":35,"wins":64},"gpt-6-sol":{"draws":19,"losses":93,"wins":26},"gpt-6.1-sol":{"draws":7,"losses":118,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":39,"losses":7,"wins":50},"inclusionai/ling-3.0-flash":{"draws":37,"losses":5,"wins":56},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":40,"losses":21,"wins":91},"meta/muse-glimmer-30b":{"draws":43,"losses":10,"wins":69},"meta/muse-spark-1.2":{"draws":19,"losses":53,"wins":60},"meta/muse-spark-1.3":{"draws":28,"losses":60,"wins":50},"meta/muse-wonder":{"draws":28,"losses":71,"wins":39},"minimax/minimax-m3":{"draws":17,"losses":7,"wins":50},"mistralai/mistral-large-4-0":{"draws":22,"losses":28,"wins":36},"mistralai/mistral-medium-3-5":{"draws":28,"losses":6,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":8,"wins":17},"moonshotai/kimi-k3":{"draws":33,"losses":44,"wins":55},"nex-agi/nex-n2-pro":{"draws":17,"losses":6,"wins":47},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":14,"wins":64},"o3":{"draws":32,"losses":59,"wins":105},"openai/gpt-oss-120b":{"draws":38,"losses":18,"wins":64},"poolside/laguna-s-2.1":{"draws":42,"losses":24,"wins":66},"qwen/qwen3.7-max":{"draws":18,"losses":18,"wins":44},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":46,"wins":52},"qwen/qwen3.8-27b":{"draws":26,"losses":27,"wins":45},"qwen/qwen3.8-flash":{"draws":27,"losses":26,"wins":39},"qwen/qwen3.8-max":{"draws":37,"losses":43,"wins":58},"qwen/qwen3.8-max-0902":{"draws":34,"losses":50,"wins":54},"stealth/ox-alpha":{"draws":103,"losses":158,"wins":197},"stealth/space-bunny-alpha":{"draws":33,"losses":26,"wins":51},"stepfun/step-3.7-flash":{"draws":22,"losses":17,"wins":61},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":24,"losses":19,"wins":31},"tencent/hy4-preview":{"draws":20,"losses":34,"wins":34},"thinkingmachines/inkling":{"draws":50,"losses":29,"wins":107},"thinkingmachines/inkling-small":{"draws":44,"losses":13,"wins":81},"unbiased/pareto-26.10-preview":{"draws":2,"losses":41,"wins":3},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":26},"x-ai/grok-4.5":{"draws":31,"losses":54,"wins":53},"x-ai/grok-4.6":{"draws":43,"losses":62,"wins":33},"x-ai/grok-4.7":{"draws":12,"losses":73,"wins":35},"x-ai/grok-build-0.1":{"draws":17,"losses":5,"wins":24},"xiaomi/mimo-v2.5":{"draws":68,"losses":19,"wins":125},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":14,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":35,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":43,"wins":33},"z-ai/glm-5.2":{"draws":75,"losses":56,"wins":145},"z-ai/glm-5.3":{"draws":23,"losses":85,"wins":24},"z-ai/glm-5.3-flash":{"draws":25,"losses":62,"wins":51},"z-ai/glm-5.3-flashx":{"draws":32,"losses":49,"wins":57}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":61,"losses":71,"wins":46},"claude-fable-5":{"draws":40,"losses":141,"wins":11},"claude-fable-5-1":{"draws":9,"losses":209,"wins":0},"claude-haiku-5-5":{"draws":49,"losses":110,"wins":23},"claude-opus-4-5":{"draws":102,"losses":160,"wins":48},"claude-opus-4-8":{"draws":43,"losses":108,"wins":21},"claude-opus-5":{"draws":48,"losses":261,"wins":29},"claude-opus-5-5":{"draws":18,"losses":186,"wins":0},"claude-sonnet-5":{"draws":62,"losses":102,"wins":28},"claude-sonnet-5-5":{"draws":41,"losses":110,"wins":41},"cohere/north-mini-code":{"draws":18,"losses":21,"wins":33},"deepseek/deepseek-v4-flash":{"draws":94,"losses":92,"wins":98},"deepseek/deepseek-v4-pro":{"draws":56,"losses":93,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":58,"losses":75,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":63,"losses":99,"wins":30},"fireworks/ember-1":{"draws":60,"losses":107,"wins":25},"gemini-3.1-pro-preview":{"draws":57,"losses":87,"wins":48},"google/gemini-3.1-flash-lite":{"draws":34,"losses":34,"wins":58},"google/gemini-3.5-flash":{"draws":57,"losses":135,"wins":48},"google/gemini-3.5-flash-lite":{"draws":94,"losses":131,"wins":113},"google/gemini-3.6-flash":{"draws":103,"losses":213,"wins":56},"google/gemini-3.8-flash":{"draws":50,"losses":123,"wins":19},"google/gemma-4-31b-it":{"draws":40,"losses":32,"wins":36},"gpt-4.1":{"draws":17,"losses":27,"wins":20},"gpt-4.1-nano":{"draws":14,"losses":1,"wins":7},"gpt-5":{"draws":40,"losses":93,"wins":39},"gpt-5.4":{"draws":49,"losses":108,"wins":29},"gpt-5.4-mini":{"draws":48,"losses":43,"wins":37},"gpt-5.4-nano":{"draws":42,"losses":77,"wins":69},"gpt-5.5":{"draws":55,"losses":98,"wins":27},"gpt-5.6-luna":{"draws":63,"losses":85,"wins":44},"gpt-5.6-sol":{"draws":28,"losses":147,"wins":17},"gpt-5.6-terra":{"draws":55,"losses":91,"wins":36},"gpt-6-astra":{"draws":11,"losses":178,"wins":3},"gpt-6-luna":{"draws":56,"losses":96,"wins":40},"gpt-6-sol":{"draws":25,"losses":154,"wins":13},"gpt-6.1-sol":{"draws":13,"losses":173,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":7,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":52,"losses":32,"wins":44},"inclusionai/ling-3.0-flash":{"draws":51,"losses":27,"wins":52},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":55,"losses":74,"wins":77},"meta/muse-glimmer-30b":{"draws":60,"losses":58,"wins":56},"meta/muse-spark-1.2":{"draws":50,"losses":101,"wins":35},"meta/muse-spark-1.3":{"draws":33,"losses":141,"wins":18},"meta/muse-wonder":{"draws":44,"losses":126,"wins":22},"minimax/minimax-m3":{"draws":26,"losses":34,"wins":44},"mistralai/mistral-large-4-0":{"draws":42,"losses":58,"wins":22},"mistralai/mistral-medium-3-5":{"draws":39,"losses":23,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":28,"wins":10},"moonshotai/kimi-k3":{"draws":54,"losses":93,"wins":39},"nex-agi/nex-n2-pro":{"draws":26,"losses":28,"wins":40},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":52,"losses":59,"wins":51},"o3":{"draws":42,"losses":167,"wins":57},"openai/gpt-oss-120b":{"draws":47,"losses":56,"wins":65},"poolside/laguna-s-2.1":{"draws":58,"losses":75,"wins":55},"qwen/qwen3.7-max":{"draws":34,"losses":59,"wins":17},"qwen/qwen3.7-plus":{"draws":27,"losses":38,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":59,"losses":108,"wins":25},"qwen/qwen3.8-27b":{"draws":37,"losses":71,"wins":30},"qwen/qwen3.8-flash":{"draws":43,"losses":60,"wins":25},"qwen/qwen3.8-max":{"draws":61,"losses":98,"wins":33},"qwen/qwen3.8-max-0902":{"draws":54,"losses":108,"wins":30},"stealth/ox-alpha":{"draws":163,"losses":375,"wins":120},"stealth/space-bunny-alpha":{"draws":50,"losses":60,"wins":44},"stepfun/step-3.7-flash":{"draws":38,"losses":62,"wins":38},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":31,"losses":47,"wins":26},"tencent/hy4-preview":{"draws":50,"losses":107,"wins":29},"thinkingmachines/inkling":{"draws":68,"losses":68,"wins":68},"thinkingmachines/inkling-small":{"draws":70,"losses":47,"wins":75},"unbiased/pareto-26.10-preview":{"draws":0,"losses":63,"wins":1},"upstage/solar-mini4":{"draws":11,"losses":22,"wins":15},"x-ai/grok-4.5":{"draws":53,"losses":115,"wins":24},"x-ai/grok-4.6":{"draws":64,"losses":107,"wins":21},"x-ai/grok-4.7":{"draws":21,"losses":134,"wins":13},"x-ai/grok-build-0.1":{"draws":22,"losses":26,"wins":16},"xiaomi/mimo-v2.5":{"draws":95,"losses":113,"wins":82},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":58,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":30,"losses":69,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":89,"wins":14},"z-ai/glm-5.2":{"draws":119,"losses":172,"wins":93},"z-ai/glm-5.3":{"draws":35,"losses":127,"wins":20},"z-ai/glm-5.3-flash":{"draws":40,"losses":121,"wins":31},"z-ai/glm-5.3-flashx":{"draws":44,"losses":123,"wins":25}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":50,"losses":52,"wins":30},"claude-fable-5":{"draws":29,"losses":101,"wins":14},"claude-fable-5-1":{"draws":7,"losses":155,"wins":0},"claude-haiku-5-5":{"draws":33,"losses":92,"wins":13},"claude-opus-4-5":{"draws":79,"losses":122,"wins":33},"claude-opus-4-8":{"draws":40,"losses":80,"wins":12},"claude-opus-5":{"draws":38,"losses":196,"wins":12},"claude-opus-5-5":{"draws":10,"losses":146,"wins":0},"claude-sonnet-5":{"draws":47,"losses":73,"wins":24},"claude-sonnet-5-5":{"draws":32,"losses":91,"wins":21},"cohere/north-mini-code":{"draws":19,"losses":13,"wins":22},"deepseek/deepseek-v4-flash":{"draws":93,"losses":76,"wins":47},"deepseek/deepseek-v4-pro":{"draws":47,"losses":68,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":42,"losses":66,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":73,"wins":25},"fireworks/ember-1":{"draws":50,"losses":77,"wins":17},"gemini-3.1-pro-preview":{"draws":45,"losses":70,"wins":29},"google/gemini-3.1-flash-lite":{"draws":34,"losses":29,"wins":33},"google/gemini-3.5-flash":{"draws":53,"losses":97,"wins":30},"google/gemini-3.5-flash-lite":{"draws":88,"losses":92,"wins":72},"google/gemini-3.6-flash":{"draws":82,"losses":150,"wins":44},"google/gemini-3.8-flash":{"draws":43,"losses":84,"wins":17},"google/gemma-4-31b-it":{"draws":35,"losses":24,"wins":25},"gpt-4.1":{"draws":17,"losses":18,"wins":13},"gpt-4.1-nano":{"draws":11,"losses":2,"wins":5},"gpt-5":{"draws":52,"losses":55,"wins":19},"gpt-5.4":{"draws":43,"losses":80,"wins":15},"gpt-5.4-mini":{"draws":44,"losses":30,"wins":22},"gpt-5.4-nano":{"draws":49,"losses":56,"wins":39},"gpt-5.5":{"draws":50,"losses":64,"wins":18},"gpt-5.6-luna":{"draws":58,"losses":49,"wins":37},"gpt-5.6-sol":{"draws":22,"losses":109,"wins":13},"gpt-5.6-terra":{"draws":46,"losses":70,"wins":22},"gpt-6-astra":{"draws":9,"losses":135,"wins":0},"gpt-6-luna":{"draws":40,"losses":72,"wins":32},"gpt-6-sol":{"draws":18,"losses":118,"wins":8},"gpt-6.1-sol":{"draws":6,"losses":138,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":49,"losses":22,"wins":31},"inclusionai/ling-3.0-flash":{"draws":50,"losses":19,"wins":33},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":54,"losses":55,"wins":47},"meta/muse-glimmer-30b":{"draws":60,"losses":42,"wins":24},"meta/muse-spark-1.2":{"draws":37,"losses":74,"wins":27},"meta/muse-spark-1.3":{"draws":37,"losses":94,"wins":13},"meta/muse-wonder":{"draws":33,"losses":96,"wins":15},"minimax/minimax-m3":{"draws":25,"losses":34,"wins":19},"mistralai/mistral-large-4-0":{"draws":31,"losses":45,"wins":14},"mistralai/mistral-medium-3-5":{"draws":39,"losses":15,"wins":30},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":17,"wins":8},"moonshotai/kimi-k3":{"draws":48,"losses":69,"wins":21},"nex-agi/nex-n2-pro":{"draws":24,"losses":17,"wins":31},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":59,"losses":35,"wins":32},"o3":{"draws":44,"losses":112,"wins":42},"openai/gpt-oss-120b":{"draws":48,"losses":47,"wins":31},"poolside/laguna-s-2.1":{"draws":59,"losses":59,"wins":20},"qwen/qwen3.7-max":{"draws":32,"losses":36,"wins":16},"qwen/qwen3.7-plus":{"draws":28,"losses":20,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":80,"wins":17},"qwen/qwen3.8-27b":{"draws":30,"losses":56,"wins":16},"qwen/qwen3.8-flash":{"draws":42,"losses":36,"wins":18},"qwen/qwen3.8-max":{"draws":44,"losses":61,"wins":39},"qwen/qwen3.8-max-0902":{"draws":49,"losses":80,"wins":15},"stealth/ox-alpha":{"draws":134,"losses":272,"wins":68},"stealth/space-bunny-alpha":{"draws":38,"losses":47,"wins":29},"stepfun/step-3.7-flash":{"draws":32,"losses":37,"wins":33},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":32,"losses":30,"wins":16},"tencent/hy4-preview":{"draws":44,"losses":81,"wins":13},"thinkingmachines/inkling":{"draws":70,"losses":75,"wins":47},"thinkingmachines/inkling-small":{"draws":38,"losses":29,"wins":29},"unbiased/pareto-26.10-preview":{"draws":1,"losses":47,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":20,"wins":10},"x-ai/grok-4.5":{"draws":36,"losses":91,"wins":17},"x-ai/grok-4.6":{"draws":44,"losses":84,"wins":16},"x-ai/grok-4.7":{"draws":15,"losses":109,"wins":2},"x-ai/grok-build-0.1":{"draws":20,"losses":14,"wins":14},"xiaomi/mimo-v2.5":{"draws":91,"losses":71,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":28,"losses":33,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":27,"losses":54,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":71,"wins":12},"z-ai/glm-5.2":{"draws":109,"losses":123,"wins":56},"z-ai/glm-5.3":{"draws":25,"losses":103,"wins":10},"z-ai/glm-5.3-flash":{"draws":35,"losses":88,"wins":21},"z-ai/glm-5.3-flashx":{"draws":36,"losses":85,"wins":23}},"unbiased/pareto-26.10-preview":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":42},"claude-fable-5":{"draws":5,"losses":10,"wins":33},"claude-fable-5-1":{"draws":3,"losses":22,"wins":29},"claude-haiku-5-5":{"draws":2,"losses":9,"wins":35},"claude-opus-4-5":{"draws":1,"losses":1,"wins":76},"claude-opus-4-8":{"draws":2,"losses":1,"wins":41},"claude-opus-5":{"draws":3,"losses":29,"wins":50},"claude-opus-5-5":{"draws":1,"losses":26,"wins":25},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":2,"losses":9,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":71},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":43},"fireworks/ember-1":{"draws":1,"losses":1,"wins":46},"gemini-3.1-pro-preview":{"draws":1,"losses":1,"wins":46},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":0,"losses":5,"wins":55},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":81},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":78},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":42},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":1,"wins":40},"gpt-5.4":{"draws":2,"losses":6,"wins":38},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":47},"gpt-5.5":{"draws":1,"losses":4,"wins":39},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":42},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":43},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":39},"gpt-6-astra":{"draws":6,"losses":22,"wins":20},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":5,"losses":9,"wins":34},"gpt-6.1-sol":{"draws":2,"losses":18,"wins":28},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":2,"wins":49},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":42},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":42},"meta/muse-wonder":{"draws":4,"losses":9,"wins":35},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"mistralai/mistral-large-4-0":{"draws":3,"losses":3,"wins":24},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":43},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":41},"o3":{"draws":0,"losses":3,"wins":63},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":42},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":45},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":27},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":42},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":34},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":26},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":41},"stealth/ox-alpha":{"draws":10,"losses":7,"wins":141},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":24},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":41},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":63},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":6,"wins":41},"x-ai/grok-4.6":{"draws":4,"losses":4,"wins":40},"x-ai/grok-4.7":{"draws":3,"losses":8,"wins":31},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":6,"wins":25},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":88},"z-ai/glm-5.3":{"draws":4,"losses":5,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":39},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":42}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":14,"wins":15},"claude-fable-5":{"draws":4,"losses":28,"wins":4},"claude-fable-5-1":{"draws":3,"losses":37,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":27,"wins":4},"claude-opus-4-5":{"draws":9,"losses":39,"wins":12},"claude-opus-4-8":{"draws":6,"losses":27,"wins":3},"claude-opus-5":{"draws":7,"losses":40,"wins":1},"claude-opus-5-5":{"draws":2,"losses":34,"wins":0},"claude-sonnet-5":{"draws":6,"losses":22,"wins":8},"claude-sonnet-5-5":{"draws":4,"losses":26,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":10,"losses":28,"wins":16},"deepseek/deepseek-v4-pro":{"draws":6,"losses":22,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":26,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":26,"wins":4},"fireworks/ember-1":{"draws":5,"losses":23,"wins":8},"gemini-3.1-pro-preview":{"draws":5,"losses":18,"wins":13},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":19},"google/gemini-3.5-flash":{"draws":7,"losses":29,"wins":12},"google/gemini-3.5-flash-lite":{"draws":20,"losses":23,"wins":25},"google/gemini-3.6-flash":{"draws":14,"losses":49,"wins":9},"google/gemini-3.8-flash":{"draws":3,"losses":29,"wins":4},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":11},"gpt-4.1":{"draws":2,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":3},"gpt-5":{"draws":4,"losses":23,"wins":3},"gpt-5.4":{"draws":3,"losses":29,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":11,"wins":8},"gpt-5.4-nano":{"draws":3,"losses":22,"wins":15},"gpt-5.5":{"draws":5,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":7,"losses":17,"wins":12},"gpt-5.6-sol":{"draws":2,"losses":32,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":25,"wins":4},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":1,"losses":25,"wins":10},"gpt-6-sol":{"draws":1,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":11,"wins":11},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":11},"meituan/longcat-2.0":{"draws":9,"losses":17,"wins":16},"meta/muse-glimmer-30b":{"draws":7,"losses":9,"wins":12},"meta/muse-spark-1.2":{"draws":4,"losses":22,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":26,"wins":8},"meta/muse-wonder":{"draws":3,"losses":32,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":10},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":3},"mistralai/mistral-medium-3-5":{"draws":4,"losses":1,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":24,"wins":6},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":13,"wins":14},"o3":{"draws":10,"losses":39,"wins":13},"openai/gpt-oss-120b":{"draws":6,"losses":11,"wins":11},"poolside/laguna-s-2.1":{"draws":6,"losses":8,"wins":14},"qwen/qwen3.7-max":{"draws":2,"losses":14,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":9,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":26,"wins":4},"qwen/qwen3.8-27b":{"draws":5,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":4,"losses":15,"wins":5},"qwen/qwen3.8-max":{"draws":5,"losses":22,"wins":9},"qwen/qwen3.8-max-0902":{"draws":2,"losses":29,"wins":5},"stealth/ox-alpha":{"draws":13,"losses":74,"wins":15},"stealth/space-bunny-alpha":{"draws":5,"losses":16,"wins":9},"stepfun/step-3.7-flash":{"draws":2,"losses":19,"wins":9},"tencent/hy3-preview":{"draws":4,"losses":7,"wins":7},"tencent/hy4-preview":{"draws":6,"losses":26,"wins":4},"thinkingmachines/inkling":{"draws":11,"losses":15,"wins":22},"thinkingmachines/inkling-small":{"draws":6,"losses":10,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":25,"wins":6},"x-ai/grok-4.6":{"draws":6,"losses":24,"wins":6},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":6,"wins":3},"xiaomi/mimo-v2.5":{"draws":16,"losses":16,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":13,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":20,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":4},"z-ai/glm-5.2":{"draws":8,"losses":48,"wins":16},"z-ai/glm-5.3":{"draws":2,"losses":32,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":22,"wins":8},"z-ai/glm-5.3-flashx":{"draws":5,"losses":27,"wins":4}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":18,"wins":84},"claude-fable-5":{"draws":21,"losses":74,"wins":49},"claude-fable-5-1":{"draws":10,"losses":141,"wins":11},"claude-haiku-5-5":{"draws":30,"losses":48,"wins":60},"claude-opus-4-5":{"draws":66,"losses":64,"wins":104},"claude-opus-4-8":{"draws":35,"losses":46,"wins":51},"claude-opus-5":{"draws":35,"losses":169,"wins":42},"claude-opus-5-5":{"draws":17,"losses":123,"wins":16},"claude-sonnet-5":{"draws":39,"losses":34,"wins":71},"claude-sonnet-5-5":{"draws":31,"losses":63,"wins":50},"cohere/north-mini-code":{"draws":8,"losses":3,"wins":43},"deepseek/deepseek-v4-flash":{"draws":40,"losses":34,"wins":142},"deepseek/deepseek-v4-pro":{"draws":34,"losses":39,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":43,"wins":60},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":48,"wins":65},"fireworks/ember-1":{"draws":33,"losses":40,"wins":71},"gemini-3.1-pro-preview":{"draws":31,"losses":40,"wins":73},"google/gemini-3.1-flash-lite":{"draws":19,"losses":3,"wins":74},"google/gemini-3.5-flash":{"draws":31,"losses":63,"wins":86},"google/gemini-3.5-flash-lite":{"draws":64,"losses":43,"wins":145},"google/gemini-3.6-flash":{"draws":60,"losses":100,"wins":116},"google/gemini-3.8-flash":{"draws":25,"losses":52,"wins":67},"google/gemma-4-31b-it":{"draws":19,"losses":10,"wins":55},"gpt-4.1":{"draws":11,"losses":8,"wins":29},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":25,"losses":34,"wins":67},"gpt-5.4":{"draws":33,"losses":59,"wins":46},"gpt-5.4-mini":{"draws":30,"losses":14,"wins":52},"gpt-5.4-nano":{"draws":30,"losses":30,"wins":84},"gpt-5.5":{"draws":35,"losses":46,"wins":51},"gpt-5.6-luna":{"draws":37,"losses":36,"wins":71},"gpt-5.6-sol":{"draws":19,"losses":82,"wins":43},"gpt-5.6-terra":{"draws":39,"losses":30,"wins":69},"gpt-6-astra":{"draws":9,"losses":121,"wins":14},"gpt-6-luna":{"draws":34,"losses":44,"wins":66},"gpt-6-sol":{"draws":20,"losses":92,"wins":32},"gpt-6.1-sol":{"draws":10,"losses":118,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":34,"losses":4,"wins":64},"inclusionai/ling-3.0-flash":{"draws":24,"losses":6,"wins":72},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":31,"losses":24,"wins":101},"meta/muse-glimmer-30b":{"draws":31,"losses":14,"wins":81},"meta/muse-spark-1.2":{"draws":33,"losses":37,"wins":68},"meta/muse-spark-1.3":{"draws":23,"losses":61,"wins":60},"meta/muse-wonder":{"draws":29,"losses":79,"wins":36},"minimax/minimax-m3":{"draws":14,"losses":5,"wins":59},"mistralai/mistral-large-4-0":{"draws":20,"losses":29,"wins":41},"mistralai/mistral-medium-3-5":{"draws":21,"losses":7,"wins":56},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":4,"wins":22},"moonshotai/kimi-k3":{"draws":33,"losses":43,"wins":62},"nex-agi/nex-n2-pro":{"draws":14,"losses":9,"wins":49},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":10,"wins":85},"o3":{"draws":21,"losses":56,"wins":121},"openai/gpt-oss-120b":{"draws":34,"losses":13,"wins":79},"poolside/laguna-s-2.1":{"draws":36,"losses":19,"wins":83},"qwen/qwen3.7-max":{"draws":21,"losses":19,"wins":44},"qwen/qwen3.7-plus":{"draws":18,"losses":8,"wins":46},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":50,"wins":60},"qwen/qwen3.8-27b":{"draws":24,"losses":25,"wins":53},"qwen/qwen3.8-flash":{"draws":25,"losses":27,"wins":44},"qwen/qwen3.8-max":{"draws":32,"losses":47,"wins":65},"qwen/qwen3.8-max-0902":{"draws":31,"losses":52,"wins":61},"stealth/ox-alpha":{"draws":100,"losses":168,"wins":206},"stealth/space-bunny-alpha":{"draws":31,"losses":20,"wins":63},"stepfun/step-3.7-flash":{"draws":12,"losses":19,"wins":71},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":24,"losses":7,"wins":47},"tencent/hy4-preview":{"draws":31,"losses":53,"wins":54},"thinkingmachines/inkling":{"draws":53,"losses":24,"wins":115},"thinkingmachines/inkling-small":{"draws":36,"losses":17,"wins":91},"unbiased/pareto-26.10-preview":{"draws":1,"losses":41,"wins":6},"upstage/solar-mini4":{"draws":5,"losses":6,"wins":25},"x-ai/grok-4.5":{"draws":34,"losses":31,"wins":31},"x-ai/grok-4.6":{"draws":42,"losses":54,"wins":48},"x-ai/grok-4.7":{"draws":17,"losses":82,"wins":27},"x-ai/grok-build-0.1":{"draws":13,"losses":5,"wins":30},"xiaomi/mimo-v2.5":{"draws":60,"losses":18,"wins":144},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":21,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":31,"wins":46},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":44,"wins":35},"z-ai/glm-5.2":{"draws":72,"losses":58,"wins":158},"z-ai/glm-5.3":{"draws":27,"losses":79,"wins":32},"z-ai/glm-5.3-flash":{"draws":20,"losses":65,"wins":59},"z-ai/glm-5.3-flashx":{"draws":25,"losses":60,"wins":59}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":15,"wins":82},"claude-fable-5":{"draws":33,"losses":61,"wins":50},"claude-fable-5-1":{"draws":9,"losses":132,"wins":21},"claude-haiku-5-5":{"draws":36,"losses":42,"wins":60},"claude-opus-4-5":{"draws":59,"losses":51,"wins":124},"claude-opus-4-8":{"draws":32,"losses":42,"wins":58},"claude-opus-5":{"draws":37,"losses":157,"wins":51},"claude-opus-5-5":{"draws":18,"losses":123,"wins":15},"claude-sonnet-5":{"draws":39,"losses":32,"wins":73},"claude-sonnet-5-5":{"draws":24,"losses":61,"wins":59},"cohere/north-mini-code":{"draws":11,"losses":2,"wins":41},"deepseek/deepseek-v4-flash":{"draws":58,"losses":21,"wins":137},"deepseek/deepseek-v4-pro":{"draws":33,"losses":26,"wins":73},"deepseek/deepseek-v4-pro-0813":{"draws":42,"losses":28,"wins":62},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":43,"wins":61},"fireworks/ember-1":{"draws":40,"losses":43,"wins":61},"gemini-3.1-pro-preview":{"draws":40,"losses":28,"wins":76},"google/gemini-3.1-flash-lite":{"draws":18,"losses":6,"wins":72},"google/gemini-3.5-flash":{"draws":48,"losses":35,"wins":97},"google/gemini-3.5-flash-lite":{"draws":62,"losses":31,"wins":159},"google/gemini-3.6-flash":{"draws":71,"losses":82,"wins":123},"google/gemini-3.8-flash":{"draws":42,"losses":49,"wins":53},"google/gemma-4-31b-it":{"draws":24,"losses":6,"wins":54},"gpt-4.1":{"draws":19,"losses":6,"wins":23},"gpt-4.1-nano":{"draws":10,"losses":2,"wins":6},"gpt-5":{"draws":40,"losses":18,"wins":68},"gpt-5.4":{"draws":40,"losses":47,"wins":51},"gpt-5.4-mini":{"draws":32,"losses":14,"wins":50},"gpt-5.4-nano":{"draws":23,"losses":24,"wins":97},"gpt-5.5":{"draws":41,"losses":36,"wins":55},"gpt-5.6-luna":{"draws":37,"losses":23,"wins":84},"gpt-5.6-sol":{"draws":28,"losses":61,"wins":55},"gpt-5.6-terra":{"draws":46,"losses":21,"wins":71},"gpt-6-astra":{"draws":11,"losses":119,"wins":14},"gpt-6-luna":{"draws":39,"losses":24,"wins":81},"gpt-6-sol":{"draws":21,"losses":92,"wins":31},"gpt-6.1-sol":{"draws":16,"losses":114,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":31,"losses":7,"wins":64},"inclusionai/ling-3.0-flash":{"draws":35,"losses":5,"wins":62},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":42,"losses":20,"wins":94},"meta/muse-glimmer-30b":{"draws":40,"losses":8,"wins":78},"meta/muse-spark-1.2":{"draws":31,"losses":31,"wins":76},"meta/muse-spark-1.3":{"draws":32,"losses":52,"wins":60},"meta/muse-wonder":{"draws":41,"losses":62,"wins":41},"minimax/minimax-m3":{"draws":20,"losses":4,"wins":54},"mistralai/mistral-large-4-0":{"draws":30,"losses":17,"wins":43},"mistralai/mistral-medium-3-5":{"draws":27,"losses":6,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":8,"wins":18},"moonshotai/kimi-k3":{"draws":34,"losses":34,"wins":70},"nex-agi/nex-n2-pro":{"draws":19,"losses":3,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":47,"losses":13,"wins":66},"o3":{"draws":39,"losses":43,"wins":116},"openai/gpt-oss-120b":{"draws":37,"losses":10,"wins":79},"poolside/laguna-s-2.1":{"draws":39,"losses":15,"wins":84},"qwen/qwen3.7-max":{"draws":21,"losses":16,"wins":47},"qwen/qwen3.7-plus":{"draws":21,"losses":6,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":49,"wins":61},"qwen/qwen3.8-27b":{"draws":27,"losses":23,"wins":52},"qwen/qwen3.8-flash":{"draws":36,"losses":16,"wins":44},"qwen/qwen3.8-max":{"draws":40,"losses":40,"wins":64},"qwen/qwen3.8-max-0902":{"draws":44,"losses":34,"wins":66},"stealth/ox-alpha":{"draws":137,"losses":145,"wins":192},"stealth/space-bunny-alpha":{"draws":36,"losses":19,"wins":59},"stepfun/step-3.7-flash":{"draws":24,"losses":14,"wins":64},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":22,"losses":10,"wins":46},"tencent/hy4-preview":{"draws":43,"losses":33,"wins":62},"thinkingmachines/inkling":{"draws":64,"losses":21,"wins":107},"thinkingmachines/inkling-small":{"draws":44,"losses":16,"wins":84},"unbiased/pareto-26.10-preview":{"draws":4,"losses":40,"wins":4},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":42,"losses":48,"wins":54},"x-ai/grok-4.6":{"draws":38,"losses":29,"wins":29},"x-ai/grok-4.7":{"draws":16,"losses":79,"wins":31},"x-ai/grok-build-0.1":{"draws":15,"losses":6,"wins":27},"xiaomi/mimo-v2.5":{"draws":74,"losses":19,"wins":129},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":10,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":32,"wins":39},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":41,"wins":34},"z-ai/glm-5.2":{"draws":78,"losses":49,"wins":161},"z-ai/glm-5.3":{"draws":29,"losses":66,"wins":43},"z-ai/glm-5.3-flash":{"draws":37,"losses":50,"wins":57},"z-ai/glm-5.3-flashx":{"draws":33,"losses":52,"wins":59}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":17,"wins":91},"claude-fable-5":{"draws":7,"losses":43,"wins":76},"claude-fable-5-1":{"draws":6,"losses":95,"wins":39},"claude-haiku-5-5":{"draws":12,"losses":20,"wins":90},"claude-opus-4-5":{"draws":17,"losses":34,"wins":155},"claude-opus-4-8":{"draws":16,"losses":30,"wins":72},"claude-opus-5":{"draws":22,"losses":100,"wins":98},"claude-opus-5-5":{"draws":11,"losses":96,"wins":31},"claude-sonnet-5":{"draws":12,"losses":24,"wins":90},"claude-sonnet-5-5":{"draws":15,"losses":47,"wins":64},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":45},"deepseek/deepseek-v4-flash":{"draws":20,"losses":15,"wins":157},"deepseek/deepseek-v4-pro":{"draws":10,"losses":21,"wins":85},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":22,"wins":83},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":32,"wins":83},"fireworks/ember-1":{"draws":11,"losses":27,"wins":88},"gemini-3.1-pro-preview":{"draws":14,"losses":23,"wins":89},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":79},"google/gemini-3.5-flash":{"draws":15,"losses":24,"wins":119},"google/gemini-3.5-flash-lite":{"draws":20,"losses":28,"wins":170},"google/gemini-3.6-flash":{"draws":14,"losses":53,"wins":173},"google/gemini-3.8-flash":{"draws":14,"losses":27,"wins":85},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":62},"gpt-4.1":{"draws":4,"losses":4,"wins":34},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":10},"gpt-5":{"draws":10,"losses":18,"wins":84},"gpt-5.4":{"draws":13,"losses":28,"wins":79},"gpt-5.4-mini":{"draws":14,"losses":4,"wins":66},"gpt-5.4-nano":{"draws":17,"losses":11,"wins":104},"gpt-5.5":{"draws":11,"losses":36,"wins":69},"gpt-5.6-luna":{"draws":13,"losses":17,"wins":96},"gpt-5.6-sol":{"draws":16,"losses":44,"wins":66},"gpt-5.6-terra":{"draws":13,"losses":21,"wins":86},"gpt-6-astra":{"draws":12,"losses":92,"wins":22},"gpt-6-luna":{"draws":10,"losses":20,"wins":96},"gpt-6-sol":{"draws":13,"losses":53,"wins":60},"gpt-6.1-sol":{"draws":6,"losses":79,"wins":41},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":72},"inclusionai/ling-3.0-flash":{"draws":9,"losses":5,"wins":74},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":8,"wins":120},"meta/muse-glimmer-30b":{"draws":6,"losses":13,"wins":93},"meta/muse-spark-1.2":{"draws":9,"losses":29,"wins":84},"meta/muse-spark-1.3":{"draws":11,"losses":31,"wins":84},"meta/muse-wonder":{"draws":16,"losses":38,"wins":72},"minimax/minimax-m3":{"draws":2,"losses":9,"wins":61},"mistralai/mistral-large-4-0":{"draws":14,"losses":16,"wins":50},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":61},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":24},"moonshotai/kimi-k3":{"draws":13,"losses":27,"wins":82},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":54},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":9,"wins":98},"o3":{"draws":12,"losses":36,"wins":130},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":99},"poolside/laguna-s-2.1":{"draws":11,"losses":14,"wins":99},"qwen/qwen3.7-max":{"draws":10,"losses":15,"wins":51},"qwen/qwen3.7-plus":{"draws":6,"losses":7,"wins":53},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":30,"wins":86},"qwen/qwen3.8-27b":{"draws":11,"losses":19,"wins":58},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":63},"qwen/qwen3.8-max":{"draws":12,"losses":26,"wins":88},"qwen/qwen3.8-max-0902":{"draws":18,"losses":27,"wins":81},"stealth/ox-alpha":{"draws":46,"losses":74,"wins":280},"stealth/space-bunny-alpha":{"draws":10,"losses":17,"wins":73},"stepfun/step-3.7-flash":{"draws":5,"losses":10,"wins":75},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":12,"losses":3,"wins":55},"tencent/hy4-preview":{"draws":12,"losses":35,"wins":73},"thinkingmachines/inkling":{"draws":21,"losses":13,"wins":134},"thinkingmachines/inkling-small":{"draws":15,"losses":2,"wins":109},"unbiased/pareto-26.10-preview":{"draws":3,"losses":31,"wins":8},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":23},"x-ai/grok-4.5":{"draws":17,"losses":27,"wins":82},"x-ai/grok-4.6":{"draws":16,"losses":31,"wins":79},"x-ai/grok-4.7":{"draws":2,"losses":35,"wins":35},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":35},"xiaomi/mimo-v2.5":{"draws":22,"losses":16,"wins":160},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":60},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":18,"wins":55},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":20,"wins":58},"z-ai/glm-5.2":{"draws":29,"losses":37,"wins":186},"z-ai/glm-5.3":{"draws":16,"losses":33,"wins":71},"z-ai/glm-5.3-flash":{"draws":15,"losses":34,"wins":77},"z-ai/glm-5.3-flashx":{"draws":15,"losses":28,"wins":83}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":18,"wins":10},"claude-fable-5":{"draws":11,"losses":31,"wins":6},"claude-fable-5-1":{"draws":0,"losses":53,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":29,"wins":4},"claude-opus-4-5":{"draws":27,"losses":40,"wins":11},"claude-opus-4-8":{"draws":10,"losses":28,"wins":6},"claude-opus-5":{"draws":13,"losses":65,"wins":4},"claude-opus-5-5":{"draws":1,"losses":51,"wins":0},"claude-sonnet-5":{"draws":19,"losses":26,"wins":3},"claude-sonnet-5-5":{"draws":9,"losses":33,"wins":6},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":27,"losses":27,"wins":18},"deepseek/deepseek-v4-pro":{"draws":18,"losses":17,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":21,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":27,"wins":5},"fireworks/ember-1":{"draws":18,"losses":24,"wins":6},"gemini-3.1-pro-preview":{"draws":17,"losses":19,"wins":12},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":19,"losses":31,"wins":10},"google/gemini-3.5-flash-lite":{"draws":34,"losses":26,"wins":24},"google/gemini-3.6-flash":{"draws":30,"losses":57,"wins":5},"google/gemini-3.8-flash":{"draws":13,"losses":32,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":8,"wins":9},"gpt-4.1":{"draws":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":18,"wins":9},"gpt-5.4":{"draws":12,"losses":28,"wins":6},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":11,"losses":23,"wins":14},"gpt-5.5":{"draws":23,"losses":14,"wins":7},"gpt-5.6-luna":{"draws":19,"losses":18,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":4},"gpt-5.6-terra":{"draws":17,"losses":24,"wins":5},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":20,"losses":24,"wins":4},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":8,"wins":8},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":16,"wins":17},"meta/muse-glimmer-30b":{"draws":18,"losses":10,"wins":14},"meta/muse-spark-1.2":{"draws":10,"losses":28,"wins":8},"meta/muse-spark-1.3":{"draws":12,"losses":28,"wins":8},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":8,"wins":10},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":14,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":17,"losses":25,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":9,"wins":12},"o3":{"draws":16,"losses":37,"wins":13},"openai/gpt-oss-120b":{"draws":17,"losses":9,"wins":16},"poolside/laguna-s-2.1":{"draws":21,"losses":11,"wins":14},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":7,"losses":9,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":25,"wins":6},"qwen/qwen3.8-27b":{"draws":13,"losses":20,"wins":1},"qwen/qwen3.8-flash":{"draws":17,"losses":11,"wins":4},"qwen/qwen3.8-max":{"draws":19,"losses":20,"wins":9},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"stealth/ox-alpha":{"draws":40,"losses":101,"wins":17},"stealth/space-bunny-alpha":{"draws":12,"losses":16,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":15,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":12,"wins":5},"tencent/hy4-preview":{"draws":17,"losses":24,"wins":5},"thinkingmachines/inkling":{"draws":22,"losses":16,"wins":26},"thinkingmachines/inkling-small":{"draws":20,"losses":14,"wins":14},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":30,"wins":5},"x-ai/grok-4.6":{"draws":15,"losses":27,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"xiaomi/mimo-v2.5":{"draws":31,"losses":20,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":12,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":21,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":42,"losses":36,"wins":18},"z-ai/glm-5.3":{"draws":11,"losses":34,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":28,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":30,"wins":6}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":72,"losses":80,"wins":52},"claude-fable-5":{"draws":43,"losses":174,"wins":5},"claude-fable-5-1":{"draws":12,"losses":227,"wins":5},"claude-haiku-5-5":{"draws":56,"losses":133,"wins":31},"claude-opus-4-5":{"draws":132,"losses":183,"wins":53},"claude-opus-4-8":{"draws":63,"losses":131,"wins":24},"claude-opus-5":{"draws":57,"losses":295,"wins":26},"claude-opus-5-5":{"draws":11,"losses":227,"wins":4},"claude-sonnet-5":{"draws":80,"losses":103,"wins":39},"claude-sonnet-5-5":{"draws":49,"losses":146,"wins":27},"cohere/north-mini-code":{"draws":25,"losses":24,"wins":31},"deepseek/deepseek-v4-flash":{"draws":121,"losses":109,"wins":104},"deepseek/deepseek-v4-pro":{"draws":72,"losses":97,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":71,"losses":96,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":76,"losses":118,"wins":28},"fireworks/ember-1":{"draws":83,"losses":112,"wins":27},"gemini-3.1-pro-preview":{"draws":73,"losses":100,"wins":49},"google/gemini-3.1-flash-lite":{"draws":56,"losses":36,"wins":70},"google/gemini-3.5-flash":{"draws":83,"losses":150,"wins":51},"google/gemini-3.5-flash-lite":{"draws":125,"losses":141,"wins":126},"google/gemini-3.6-flash":{"draws":130,"losses":245,"wins":49},"google/gemini-3.8-flash":{"draws":63,"losses":140,"wins":19},"google/gemma-4-31b-it":{"draws":61,"losses":32,"wins":41},"gpt-4.1":{"draws":29,"losses":28,"wins":17},"gpt-4.1-nano":{"draws":11,"losses":2,"wins":9},"gpt-5":{"draws":63,"losses":90,"wins":37},"gpt-5.4":{"draws":57,"losses":134,"wins":21},"gpt-5.4-mini":{"draws":57,"losses":51,"wins":40},"gpt-5.4-nano":{"draws":55,"losses":107,"wins":74},"gpt-5.5":{"draws":85,"losses":97,"wins":20},"gpt-5.6-luna":{"draws":91,"losses":84,"wins":47},"gpt-5.6-sol":{"draws":37,"losses":172,"wins":13},"gpt-5.6-terra":{"draws":80,"losses":117,"wins":15},"gpt-6-astra":{"draws":13,"losses":207,"wins":2},"gpt-6-luna":{"draws":79,"losses":113,"wins":30},"gpt-6-sol":{"draws":35,"losses":170,"wins":17},"gpt-6.1-sol":{"draws":19,"losses":195,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":12,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":79,"losses":21,"wins":66},"inclusionai/ling-3.0-flash":{"draws":71,"losses":34,"wins":55},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":81,"losses":79,"wins":78},"meta/muse-glimmer-30b":{"draws":80,"losses":62,"wins":50},"meta/muse-spark-1.2":{"draws":62,"losses":124,"wins":26},"meta/muse-spark-1.3":{"draws":55,"losses":148,"wins":19},"meta/muse-wonder":{"draws":45,"losses":160,"wins":17},"minimax/minimax-m3":{"draws":43,"losses":41,"wins":40},"mistralai/mistral-large-4-0":{"draws":58,"losses":61,"wins":19},"mistralai/mistral-medium-3-5":{"draws":58,"losses":25,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":21,"losses":30,"wins":11},"moonshotai/kimi-k3":{"draws":76,"losses":106,"wins":30},"nex-agi/nex-n2-pro":{"draws":30,"losses":26,"wins":46},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":88,"losses":64,"wins":56},"o3":{"draws":60,"losses":193,"wins":63},"openai/gpt-oss-120b":{"draws":66,"losses":68,"wins":54},"poolside/laguna-s-2.1":{"draws":66,"losses":79,"wins":57},"qwen/qwen3.7-max":{"draws":53,"losses":54,"wins":27},"qwen/qwen3.7-plus":{"draws":42,"losses":43,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":88,"losses":108,"wins":26},"qwen/qwen3.8-27b":{"draws":44,"losses":87,"wins":29},"qwen/qwen3.8-flash":{"draws":60,"losses":57,"wins":31},"qwen/qwen3.8-max":{"draws":76,"losses":105,"wins":41},"qwen/qwen3.8-max-0902":{"draws":83,"losses":111,"wins":28},"stealth/ox-alpha":{"draws":171,"losses":380,"wins":95},"stealth/space-bunny-alpha":{"draws":71,"losses":69,"wins":38},"stepfun/step-3.7-flash":{"draws":46,"losses":56,"wins":54},"stepfun/step-5-preview":{"draws":8,"losses":12,"wins":0},"tencent/hy3-preview":{"draws":49,"losses":47,"wins":32},"tencent/hy4-preview":{"draws":68,"losses":125,"wins":19},"thinkingmachines/inkling":{"draws":95,"losses":82,"wins":113},"thinkingmachines/inkling-small":{"draws":91,"losses":60,"wins":71},"unbiased/pareto-26.10-preview":{"draws":4,"losses":70,"wins":0},"upstage/solar-mini4":{"draws":16,"losses":30,"wins":16},"x-ai/grok-4.5":{"draws":60,"losses":144,"wins":18},"x-ai/grok-4.6":{"draws":74,"losses":129,"wins":19},"x-ai/grok-4.7":{"draws":22,"losses":160,"wins":16},"x-ai/grok-build-0.1":{"draws":31,"losses":23,"wins":20},"xiaomi/mimo-v2.5":{"draws":120,"losses":92,"wins":92},"xiaomi/mimo-v2.5-pro":{"draws":42,"losses":57,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":38,"losses":83,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":36,"losses":98,"wins":14},"z-ai/glm-5.2":{"draws":166,"losses":188,"wins":90},"z-ai/glm-5.3":{"draws":48,"losses":158,"wins":4},"z-ai/glm-5.3-flash":{"draws":56,"losses":130,"wins":36},"z-ai/glm-5.3-flashx":{"draws":72,"losses":134,"wins":16}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":23,"wins":24},"claude-fable-5":{"draws":9,"losses":65,"wins":4},"claude-fable-5-1":{"draws":2,"losses":84,"wins":0},"claude-haiku-5-5":{"draws":17,"losses":41,"wins":18},"claude-opus-4-5":{"draws":31,"losses":59,"wins":38},"claude-opus-4-8":{"draws":16,"losses":43,"wins":15},"claude-opus-5":{"draws":13,"losses":110,"wins":5},"claude-opus-5-5":{"draws":3,"losses":82,"wins":1},"claude-sonnet-5":{"draws":13,"losses":44,"wins":21},"claude-sonnet-5-5":{"draws":15,"losses":50,"wins":13},"cohere/north-mini-code":{"draws":10,"losses":7,"wins":15},"deepseek/deepseek-v4-flash":{"draws":38,"losses":38,"wins":44},"deepseek/deepseek-v4-pro":{"draws":13,"losses":37,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":37,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":36,"wins":20},"fireworks/ember-1":{"draws":25,"losses":35,"wins":18},"gemini-3.1-pro-preview":{"draws":20,"losses":34,"wins":24},"google/gemini-3.1-flash-lite":{"draws":11,"losses":2,"wins":45},"google/gemini-3.5-flash":{"draws":22,"losses":48,"wins":30},"google/gemini-3.5-flash-lite":{"draws":41,"losses":48,"wins":49},"google/gemini-3.6-flash":{"draws":33,"losses":88,"wins":29},"google/gemini-3.8-flash":{"draws":18,"losses":48,"wins":12},"google/gemma-4-31b-it":{"draws":19,"losses":5,"wins":22},"gpt-4.1":{"draws":7,"losses":12,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":22,"losses":28,"wins":20},"gpt-5.4":{"draws":13,"losses":50,"wins":13},"gpt-5.4-mini":{"draws":15,"losses":20,"wins":17},"gpt-5.4-nano":{"draws":18,"losses":30,"wins":38},"gpt-5.5":{"draws":24,"losses":36,"wins":12},"gpt-5.6-luna":{"draws":28,"losses":22,"wins":28},"gpt-5.6-sol":{"draws":10,"losses":54,"wins":14},"gpt-5.6-terra":{"draws":19,"losses":43,"wins":12},"gpt-6-astra":{"draws":3,"losses":74,"wins":1},"gpt-6-luna":{"draws":20,"losses":40,"wins":18},"gpt-6-sol":{"draws":5,"losses":64,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":70,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":12,"wins":25},"inclusionai/ling-3.0-flash":{"draws":22,"losses":7,"wins":27},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":27,"losses":21,"wins":40},"meta/muse-glimmer-30b":{"draws":25,"losses":15,"wins":28},"meta/muse-spark-1.2":{"draws":10,"losses":43,"wins":21},"meta/muse-spark-1.3":{"draws":10,"losses":54,"wins":14},"meta/muse-wonder":{"draws":7,"losses":56,"wins":15},"minimax/minimax-m3":{"draws":11,"losses":13,"wins":20},"mistralai/mistral-large-4-0":{"draws":12,"losses":25,"wins":11},"mistralai/mistral-medium-3-5":{"draws":15,"losses":6,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":11,"wins":5},"moonshotai/kimi-k3":{"draws":18,"losses":33,"wins":23},"nex-agi/nex-n2-pro":{"draws":12,"losses":9,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":15,"wins":32},"o3":{"draws":20,"losses":57,"wins":45},"openai/gpt-oss-120b":{"draws":20,"losses":21,"wins":27},"poolside/laguna-s-2.1":{"draws":25,"losses":26,"wins":25},"qwen/qwen3.7-max":{"draws":15,"losses":22,"wins":11},"qwen/qwen3.7-plus":{"draws":12,"losses":8,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":42,"wins":19},"qwen/qwen3.8-27b":{"draws":10,"losses":26,"wins":20},"qwen/qwen3.8-flash":{"draws":15,"losses":25,"wins":12},"qwen/qwen3.8-max":{"draws":11,"losses":44,"wins":23},"qwen/qwen3.8-max-0902":{"draws":18,"losses":40,"wins":20},"stealth/ox-alpha":{"draws":48,"losses":136,"wins":58},"stealth/space-bunny-alpha":{"draws":24,"losses":23,"wins":15},"stepfun/step-3.7-flash":{"draws":12,"losses":16,"wins":32},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":14,"wins":14},"tencent/hy4-preview":{"draws":18,"losses":44,"wins":14},"thinkingmachines/inkling":{"draws":22,"losses":24,"wins":58},"thinkingmachines/inkling-small":{"draws":28,"losses":17,"wins":33},"unbiased/pareto-26.10-preview":{"draws":0,"losses":25,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":13},"x-ai/grok-4.5":{"draws":13,"losses":44,"wins":21},"x-ai/grok-4.6":{"draws":18,"losses":50,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":60,"wins":7},"x-ai/grok-build-0.1":{"draws":11,"losses":3,"wins":12},"xiaomi/mimo-v2.5":{"draws":42,"losses":25,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":27,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":29,"wins":16},"z-ai/glm-5.2":{"draws":52,"losses":55,"wins":49},"z-ai/glm-5.3":{"draws":14,"losses":55,"wins":5},"z-ai/glm-5.3-flash":{"draws":14,"losses":51,"wins":13},"z-ai/glm-5.3-flashx":{"draws":24,"losses":40,"wins":14}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":19,"wins":49},"claude-fable-5":{"draws":18,"losses":50,"wins":22},"claude-fable-5-1":{"draws":5,"losses":85,"wins":10},"claude-haiku-5-5":{"draws":21,"losses":38,"wins":27},"claude-opus-4-5":{"draws":33,"losses":45,"wins":68},"claude-opus-4-8":{"draws":16,"losses":28,"wins":38},"claude-opus-5":{"draws":16,"losses":119,"wins":17},"claude-opus-5-5":{"draws":9,"losses":87,"wins":2},"claude-sonnet-5":{"draws":16,"losses":24,"wins":50},"claude-sonnet-5-5":{"draws":10,"losses":46,"wins":34},"cohere/north-mini-code":{"draws":9,"losses":3,"wins":22},"deepseek/deepseek-v4-flash":{"draws":33,"losses":26,"wins":79},"deepseek/deepseek-v4-pro":{"draws":19,"losses":27,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":37,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":33,"wins":32},"fireworks/ember-1":{"draws":18,"losses":36,"wins":36},"gemini-3.1-pro-preview":{"draws":17,"losses":31,"wins":42},"google/gemini-3.1-flash-lite":{"draws":12,"losses":4,"wins":44},"google/gemini-3.5-flash":{"draws":20,"losses":40,"wins":52},"google/gemini-3.5-flash-lite":{"draws":27,"losses":24,"wins":105},"google/gemini-3.6-flash":{"draws":25,"losses":74,"wins":73},"google/gemini-3.8-flash":{"draws":22,"losses":40,"wins":28},"google/gemma-4-31b-it":{"draws":11,"losses":9,"wins":32},"gpt-4.1":{"draws":10,"losses":3,"wins":17},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":6},"gpt-5":{"draws":18,"losses":29,"wins":33},"gpt-5.4":{"draws":23,"losses":36,"wins":27},"gpt-5.4-mini":{"draws":14,"losses":14,"wins":32},"gpt-5.4-nano":{"draws":25,"losses":19,"wins":50},"gpt-5.5":{"draws":26,"losses":33,"wins":23},"gpt-5.6-luna":{"draws":22,"losses":25,"wins":43},"gpt-5.6-sol":{"draws":9,"losses":62,"wins":19},"gpt-5.6-terra":{"draws":20,"losses":34,"wins":32},"gpt-6-astra":{"draws":3,"losses":81,"wins":6},"gpt-6-luna":{"draws":22,"losses":33,"wins":35},"gpt-6-sol":{"draws":10,"losses":62,"wins":18},"gpt-6.1-sol":{"draws":4,"losses":79,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":4,"wins":41},"inclusionai/ling-3.0-flash":{"draws":18,"losses":5,"wins":41},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":19,"wins":54},"meta/muse-glimmer-30b":{"draws":19,"losses":16,"wins":43},"meta/muse-spark-1.2":{"draws":11,"losses":48,"wins":27},"meta/muse-spark-1.3":{"draws":13,"losses":52,"wins":25},"meta/muse-wonder":{"draws":5,"losses":63,"wins":22},"minimax/minimax-m3":{"draws":12,"losses":10,"wins":28},"mistralai/mistral-large-4-0":{"draws":17,"losses":19,"wins":20},"mistralai/mistral-medium-3-5":{"draws":12,"losses":7,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":11},"moonshotai/kimi-k3":{"draws":23,"losses":31,"wins":32},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":31},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":15,"wins":43},"o3":{"draws":18,"losses":36,"wins":74},"openai/gpt-oss-120b":{"draws":20,"losses":7,"wins":53},"poolside/laguna-s-2.1":{"draws":25,"losses":14,"wins":51},"qwen/qwen3.7-max":{"draws":15,"losses":11,"wins":28},"qwen/qwen3.7-plus":{"draws":11,"losses":6,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":33,"wins":35},"qwen/qwen3.8-27b":{"draws":15,"losses":23,"wins":26},"qwen/qwen3.8-flash":{"draws":16,"losses":22,"wins":22},"qwen/qwen3.8-max":{"draws":21,"losses":31,"wins":38},"qwen/qwen3.8-max-0902":{"draws":19,"losses":32,"wins":39},"stealth/ox-alpha":{"draws":57,"losses":132,"wins":109},"stealth/space-bunny-alpha":{"draws":18,"losses":16,"wins":36},"stepfun/step-3.7-flash":{"draws":15,"losses":7,"wins":44},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":12,"wins":26},"tencent/hy4-preview":{"draws":14,"losses":37,"wins":35},"thinkingmachines/inkling":{"draws":30,"losses":21,"wins":69},"thinkingmachines/inkling-small":{"draws":27,"losses":9,"wins":54},"unbiased/pareto-26.10-preview":{"draws":0,"losses":29,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":20},"x-ai/grok-4.5":{"draws":13,"losses":46,"wins":31},"x-ai/grok-4.6":{"draws":19,"losses":39,"wins":32},"x-ai/grok-4.7":{"draws":7,"losses":55,"wins":18},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":38,"losses":15,"wins":83},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":9,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":30,"wins":17},"z-ai/glm-5.2":{"draws":39,"losses":50,"wins":91},"z-ai/glm-5.3":{"draws":14,"losses":54,"wins":18},"z-ai/glm-5.3-flash":{"draws":18,"losses":41,"wins":31},"z-ai/glm-5.3-flashx":{"draws":21,"losses":35,"wins":34}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":18,"wins":57},"claude-fable-5":{"draws":8,"losses":47,"wins":41},"claude-fable-5-1":{"draws":14,"losses":84,"wins":10},"claude-haiku-5-5":{"draws":17,"losses":32,"wins":43},"claude-opus-4-5":{"draws":39,"losses":33,"wins":84},"claude-opus-4-8":{"draws":11,"losses":35,"wins":42},"claude-opus-5":{"draws":26,"losses":99,"wins":39},"claude-opus-5-5":{"draws":10,"losses":80,"wins":14},"claude-sonnet-5":{"draws":15,"losses":24,"wins":57},"claude-sonnet-5-5":{"draws":13,"losses":46,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":5,"wins":31},"deepseek/deepseek-v4-flash":{"draws":25,"losses":24,"wins":95},"deepseek/deepseek-v4-pro":{"draws":16,"losses":25,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":27,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":30,"wins":43},"fireworks/ember-1":{"draws":21,"losses":30,"wins":45},"gemini-3.1-pro-preview":{"draws":16,"losses":24,"wins":56},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":50},"google/gemini-3.5-flash":{"draws":21,"losses":37,"wins":62},"google/gemini-3.5-flash-lite":{"draws":21,"losses":29,"wins":118},"google/gemini-3.6-flash":{"draws":38,"losses":60,"wins":86},"google/gemini-3.8-flash":{"draws":20,"losses":27,"wins":49},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":41},"gpt-4.1":{"draws":6,"losses":7,"wins":19},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":8},"gpt-5":{"draws":11,"losses":22,"wins":51},"gpt-5.4":{"draws":17,"losses":37,"wins":38},"gpt-5.4-mini":{"draws":15,"losses":9,"wins":40},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":66},"gpt-5.5":{"draws":20,"losses":31,"wins":37},"gpt-5.6-luna":{"draws":17,"losses":17,"wins":62},"gpt-5.6-sol":{"draws":17,"losses":44,"wins":35},"gpt-5.6-terra":{"draws":24,"losses":24,"wins":44},"gpt-6-astra":{"draws":9,"losses":80,"wins":7},"gpt-6-luna":{"draws":19,"losses":27,"wins":50},"gpt-6-sol":{"draws":18,"losses":54,"wins":24},"gpt-6.1-sol":{"draws":14,"losses":62,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":1,"wins":48},"inclusionai/ling-3.0-flash":{"draws":14,"losses":5,"wins":49},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":19,"losses":10,"wins":75},"meta/muse-glimmer-30b":{"draws":15,"losses":13,"wins":56},"meta/muse-spark-1.2":{"draws":11,"losses":28,"wins":53},"meta/muse-spark-1.3":{"draws":15,"losses":33,"wins":48},"meta/muse-wonder":{"draws":17,"losses":43,"wins":36},"minimax/minimax-m3":{"draws":7,"losses":8,"wins":37},"mistralai/mistral-large-4-0":{"draws":13,"losses":19,"wins":28},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":16},"moonshotai/kimi-k3":{"draws":18,"losses":25,"wins":49},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":10,"wins":56},"o3":{"draws":11,"losses":26,"wins":95},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":62},"poolside/laguna-s-2.1":{"draws":10,"losses":18,"wins":64},"qwen/qwen3.7-max":{"draws":9,"losses":13,"wins":34},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":31,"wins":41},"qwen/qwen3.8-27b":{"draws":12,"losses":20,"wins":36},"qwen/qwen3.8-flash":{"draws":13,"losses":16,"wins":35},"qwen/qwen3.8-max":{"draws":25,"losses":19,"wins":52},"qwen/qwen3.8-max-0902":{"draws":14,"losses":30,"wins":52},"stealth/ox-alpha":{"draws":57,"losses":105,"wins":154},"stealth/space-bunny-alpha":{"draws":19,"losses":19,"wins":38},"stepfun/step-3.7-flash":{"draws":8,"losses":8,"wins":52},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":9,"losses":10,"wins":33},"tencent/hy4-preview":{"draws":16,"losses":33,"wins":43},"thinkingmachines/inkling":{"draws":25,"losses":14,"wins":89},"thinkingmachines/inkling-small":{"draws":13,"losses":12,"wins":71},"unbiased/pareto-26.10-preview":{"draws":1,"losses":25,"wins":6},"upstage/solar-mini4":{"draws":4,"losses":4,"wins":16},"x-ai/grok-4.5":{"draws":17,"losses":35,"wins":44},"x-ai/grok-4.6":{"draws":21,"losses":34,"wins":41},"x-ai/grok-4.7":{"draws":6,"losses":58,"wins":20},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":22},"xiaomi/mimo-v2.5":{"draws":36,"losses":14,"wins":98},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":16,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":17,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":15},"z-ai/glm-5.2":{"draws":49,"losses":37,"wins":106},"z-ai/glm-5.3":{"draws":15,"losses":43,"wins":34},"z-ai/glm-5.3-flash":{"draws":16,"losses":30,"wins":50},"z-ai/glm-5.3-flashx":{"draws":17,"losses":35,"wins":44}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":96,"losses":72,"wins":96},"claude-fable-5":{"draws":61,"losses":185,"wins":42},"claude-fable-5-1":{"draws":20,"losses":296,"wins":8},"claude-haiku-5-5":{"draws":64,"losses":148,"wins":64},"claude-opus-4-5":{"draws":149,"losses":185,"wins":134},"claude-opus-4-8":{"draws":74,"losses":133,"wins":57},"claude-opus-5":{"draws":76,"losses":383,"wins":33},"claude-opus-5-5":{"draws":18,"losses":283,"wins":11},"claude-sonnet-5":{"draws":79,"losses":121,"wins":88},"claude-sonnet-5-5":{"draws":55,"losses":167,"wins":66},"cohere/north-mini-code":{"draws":36,"losses":14,"wins":58},"deepseek/deepseek-v4-flash":{"draws":156,"losses":99,"wins":177},"deepseek/deepseek-v4-pro":{"draws":90,"losses":99,"wins":75},"deepseek/deepseek-v4-pro-0813":{"draws":89,"losses":93,"wins":82},"deepseek/deepseek-v4.1-flash":{"draws":103,"losses":122,"wins":63},"fireworks/ember-1":{"draws":94,"losses":128,"wins":66},"gemini-3.1-pro-preview":{"draws":85,"losses":109,"wins":94},"google/gemini-3.1-flash-lite":{"draws":42,"losses":24,"wins":126},"google/gemini-3.5-flash":{"draws":100,"losses":151,"wins":109},"google/gemini-3.5-flash-lite":{"draws":173,"losses":134,"wins":197},"google/gemini-3.6-flash":{"draws":153,"losses":247,"wins":152},"google/gemini-3.8-flash":{"draws":78,"losses":153,"wins":57},"google/gemma-4-31b-it":{"draws":69,"losses":29,"wins":70},"gpt-4.1":{"draws":35,"losses":23,"wins":38},"gpt-4.1-nano":{"draws":21,"losses":0,"wins":15},"gpt-5":{"draws":86,"losses":92,"wins":74},"gpt-5.4":{"draws":81,"losses":136,"wins":59},"gpt-5.4-mini":{"draws":87,"losses":35,"wins":70},"gpt-5.4-nano":{"draws":71,"losses":97,"wins":120},"gpt-5.5":{"draws":101,"losses":115,"wins":48},"gpt-5.6-luna":{"draws":109,"losses":69,"wins":110},"gpt-5.6-sol":{"draws":37,"losses":206,"wins":45},"gpt-5.6-terra":{"draws":117,"losses":96,"wins":63},"gpt-6-astra":{"draws":19,"losses":258,"wins":11},"gpt-6-luna":{"draws":102,"losses":113,"wins":73},"gpt-6-sol":{"draws":43,"losses":211,"wins":34},"gpt-6.1-sol":{"draws":30,"losses":248,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":87,"losses":19,"wins":98},"inclusionai/ling-3.0-flash":{"draws":101,"losses":25,"wins":78},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":93,"losses":73,"wins":146},"meta/muse-glimmer-30b":{"draws":114,"losses":43,"wins":95},"meta/muse-spark-1.2":{"draws":66,"losses":135,"wins":75},"meta/muse-spark-1.3":{"draws":58,"losses":161,"wins":69},"meta/muse-wonder":{"draws":65,"losses":178,"wins":45},"minimax/minimax-m3":{"draws":47,"losses":37,"wins":72},"mistralai/mistral-large-4-0":{"draws":71,"losses":72,"wins":37},"mistralai/mistral-medium-3-5":{"draws":74,"losses":19,"wins":75},"moonshotai/kimi-k2.7-code":{"draws":16,"losses":30,"wins":26},"moonshotai/kimi-k3":{"draws":95,"losses":111,"wins":70},"nex-agi/nex-n2-pro":{"draws":57,"losses":17,"wins":70},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":109,"losses":54,"wins":89},"o3":{"draws":79,"losses":169,"wins":148},"openai/gpt-oss-120b":{"draws":95,"losses":49,"wins":108},"poolside/laguna-s-2.1":{"draws":119,"losses":65,"wins":92},"qwen/qwen3.7-max":{"draws":55,"losses":53,"wins":60},"qwen/qwen3.7-plus":{"draws":45,"losses":29,"wins":70},"qwen/qwen3.8-2.4t-a95b":{"draws":105,"losses":113,"wins":70},"qwen/qwen3.8-27b":{"draws":66,"losses":68,"wins":70},"qwen/qwen3.8-flash":{"draws":71,"losses":67,"wins":54},"qwen/qwen3.8-max":{"draws":97,"losses":114,"wins":77},"qwen/qwen3.8-max-0902":{"draws":97,"losses":134,"wins":57},"stealth/ox-alpha":{"draws":256,"losses":472,"wins":220},"stealth/space-bunny-alpha":{"draws":89,"losses":65,"wins":74},"stepfun/step-3.7-flash":{"draws":56,"losses":49,"wins":99},"stepfun/step-5-preview":{"draws":8,"losses":13,"wins":3},"tencent/hy3-preview":{"draws":53,"losses":47,"wins":56},"tencent/hy4-preview":{"draws":75,"losses":145,"wins":56},"thinkingmachines/inkling":{"draws":119,"losses":93,"wins":172},"thinkingmachines/inkling-small":{"draws":109,"losses":56,"wins":123},"unbiased/pareto-26.10-preview":{"draws":4,"losses":88,"wins":4},"upstage/solar-mini4":{"draws":8,"losses":16,"wins":48},"x-ai/grok-4.5":{"draws":72,"losses":158,"wins":58},"x-ai/grok-4.6":{"draws":78,"losses":161,"wins":49},"x-ai/grok-4.7":{"draws":29,"losses":186,"wins":37},"x-ai/grok-build-0.1":{"draws":42,"losses":18,"wins":36},"xiaomi/mimo-v2.5":{"draws":166,"losses":90,"wins":188},"xiaomi/mimo-v2.5-pro":{"draws":52,"losses":49,"wins":55},"xiaomi/mimo-v2.6-flash":{"draws":39,"losses":91,"wins":50},"xiaomi/mimo-v2.6-pro":{"draws":49,"losses":106,"wins":37},"z-ai/glm-5.2":{"draws":180,"losses":150,"wins":150},"z-ai/glm-5.3":{"draws":64,"losses":173,"wins":39},"z-ai/glm-5.3-flash":{"draws":75,"losses":154,"wins":59},"z-ai/glm-5.3-flashx":{"draws":82,"losses":143,"wins":63}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":17,"wins":84},"claude-fable-5":{"draws":22,"losses":52,"wins":64},"claude-fable-5-1":{"draws":11,"losses":123,"wins":22},"claude-haiku-5-5":{"draws":24,"losses":32,"wins":76},"claude-opus-4-5":{"draws":48,"losses":33,"wins":143},"claude-opus-4-8":{"draws":21,"losses":32,"wins":73},"claude-opus-5":{"draws":32,"losses":139,"wins":63},"claude-opus-5-5":{"draws":8,"losses":116,"wins":26},"claude-sonnet-5":{"draws":28,"losses":19,"wins":91},"claude-sonnet-5-5":{"draws":24,"losses":52,"wins":62},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":44},"deepseek/deepseek-v4-flash":{"draws":46,"losses":12,"wins":148},"deepseek/deepseek-v4-pro":{"draws":23,"losses":25,"wins":78},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":24,"wins":77},"deepseek/deepseek-v4.1-flash":{"draws":28,"losses":27,"wins":83},"fireworks/ember-1":{"draws":26,"losses":27,"wins":85},"gemini-3.1-pro-preview":{"draws":25,"losses":31,"wins":82},"google/gemini-3.1-flash-lite":{"draws":15,"losses":1,"wins":76},"google/gemini-3.5-flash":{"draws":30,"losses":36,"wins":106},"google/gemini-3.5-flash-lite":{"draws":41,"losses":17,"wins":184},"google/gemini-3.6-flash":{"draws":52,"losses":59,"wins":153},"google/gemini-3.8-flash":{"draws":30,"losses":37,"wins":71},"google/gemma-4-31b-it":{"draws":22,"losses":7,"wins":53},"gpt-4.1":{"draws":7,"losses":8,"wins":31},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":11},"gpt-5":{"draws":19,"losses":22,"wins":79},"gpt-5.4":{"draws":25,"losses":38,"wins":69},"gpt-5.4-mini":{"draws":21,"losses":9,"wins":62},"gpt-5.4-nano":{"draws":20,"losses":20,"wins":96},"gpt-5.5":{"draws":31,"losses":23,"wins":72},"gpt-5.6-luna":{"draws":28,"losses":15,"wins":95},"gpt-5.6-sol":{"draws":23,"losses":60,"wins":55},"gpt-5.6-terra":{"draws":36,"losses":21,"wins":75},"gpt-6-astra":{"draws":18,"losses":109,"wins":11},"gpt-6-luna":{"draws":26,"losses":27,"wins":85},"gpt-6-sol":{"draws":21,"losses":70,"wins":47},"gpt-6.1-sol":{"draws":21,"losses":92,"wins":25},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":28,"losses":3,"wins":69},"inclusionai/ling-3.0-flash":{"draws":22,"losses":3,"wins":71},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":28,"losses":11,"wins":113},"meta/muse-glimmer-30b":{"draws":25,"losses":12,"wins":83},"meta/muse-spark-1.2":{"draws":22,"losses":43,"wins":67},"meta/muse-spark-1.3":{"draws":25,"losses":41,"wins":72},"meta/muse-wonder":{"draws":17,"losses":62,"wins":59},"minimax/minimax-m3":{"draws":16,"losses":6,"wins":52},"mistralai/mistral-large-4-0":{"draws":15,"losses":20,"wins":51},"mistralai/mistral-medium-3-5":{"draws":15,"losses":4,"wins":63},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":4,"wins":21},"moonshotai/kimi-k3":{"draws":29,"losses":37,"wins":66},"nex-agi/nex-n2-pro":{"draws":13,"losses":3,"wins":56},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":13,"wins":82},"o3":{"draws":19,"losses":35,"wins":134},"openai/gpt-oss-120b":{"draws":31,"losses":4,"wins":87},"poolside/laguna-s-2.1":{"draws":25,"losses":15,"wins":92},"qwen/qwen3.7-max":{"draws":19,"losses":13,"wins":48},"qwen/qwen3.7-plus":{"draws":15,"losses":6,"wins":46},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":28,"wins":83},"qwen/qwen3.8-27b":{"draws":26,"losses":12,"wins":58},"qwen/qwen3.8-flash":{"draws":25,"losses":14,"wins":53},"qwen/qwen3.8-max":{"draws":28,"losses":30,"wins":80},"qwen/qwen3.8-max-0902":{"draws":35,"losses":30,"wins":73},"stealth/ox-alpha":{"draws":81,"losses":117,"wins":260},"stealth/space-bunny-alpha":{"draws":25,"losses":9,"wins":76},"stepfun/step-3.7-flash":{"draws":15,"losses":3,"wins":78},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":6},"tencent/hy3-preview":{"draws":14,"losses":10,"wins":50},"tencent/hy4-preview":{"draws":23,"losses":24,"wins":85},"thinkingmachines/inkling":{"draws":35,"losses":20,"wins":127},"thinkingmachines/inkling-small":{"draws":25,"losses":10,"wins":103},"unbiased/pareto-26.10-preview":{"draws":4,"losses":37,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":32},"x-ai/grok-4.5":{"draws":27,"losses":32,"wins":79},"x-ai/grok-4.6":{"draws":29,"losses":43,"wins":66},"x-ai/grok-4.7":{"draws":16,"losses":71,"wins":33},"x-ai/grok-build-0.1":{"draws":11,"losses":1,"wins":34},"xiaomi/mimo-v2.5":{"draws":48,"losses":4,"wins":158},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":5,"wins":55},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":18,"wins":54},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":34,"wins":43},"z-ai/glm-5.2":{"draws":64,"losses":39,"wins":173},"z-ai/glm-5.3":{"draws":20,"losses":34,"wins":34},"z-ai/glm-5.3-flash":{"draws":33,"losses":32,"wins":73},"z-ai/glm-5.3-flashx":{"draws":27,"losses":33,"wins":78}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":26,"wins":75},"claude-fable-5":{"draws":25,"losses":74,"wins":45},"claude-fable-5-1":{"draws":8,"losses":138,"wins":16},"claude-haiku-5-5":{"draws":27,"losses":54,"wins":57},"claude-opus-4-5":{"draws":55,"losses":56,"wins":123},"claude-opus-4-8":{"draws":19,"losses":53,"wins":60},"claude-opus-5":{"draws":35,"losses":164,"wins":47},"claude-opus-5-5":{"draws":13,"losses":133,"wins":10},"claude-sonnet-5":{"draws":26,"losses":41,"wins":77},"claude-sonnet-5-5":{"draws":20,"losses":69,"wins":55},"cohere/north-mini-code":{"draws":10,"losses":8,"wins":36},"deepseek/deepseek-v4-flash":{"draws":58,"losses":39,"wins":119},"deepseek/deepseek-v4-pro":{"draws":24,"losses":36,"wins":72},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":39,"wins":71},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":53,"wins":59},"fireworks/ember-1":{"draws":31,"losses":46,"wins":67},"gemini-3.1-pro-preview":{"draws":36,"losses":42,"wins":66},"google/gemini-3.1-flash-lite":{"draws":21,"losses":12,"wins":63},"google/gemini-3.5-flash":{"draws":28,"losses":60,"wins":92},"google/gemini-3.5-flash-lite":{"draws":56,"losses":47,"wins":149},"google/gemini-3.6-flash":{"draws":42,"losses":93,"wins":141},"google/gemini-3.8-flash":{"draws":24,"losses":65,"wins":55},"google/gemma-4-31b-it":{"draws":25,"losses":14,"wins":45},"gpt-4.1":{"draws":6,"losses":14,"wins":28},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":9},"gpt-5":{"draws":26,"losses":29,"wins":71},"gpt-5.4":{"draws":21,"losses":62,"wins":55},"gpt-5.4-mini":{"draws":28,"losses":17,"wins":51},"gpt-5.4-nano":{"draws":25,"losses":38,"wins":81},"gpt-5.5":{"draws":26,"losses":48,"wins":58},"gpt-5.6-luna":{"draws":39,"losses":28,"wins":77},"gpt-5.6-sol":{"draws":25,"losses":72,"wins":47},"gpt-5.6-terra":{"draws":34,"losses":41,"wins":63},"gpt-6-astra":{"draws":13,"losses":123,"wins":8},"gpt-6-luna":{"draws":38,"losses":35,"wins":71},"gpt-6-sol":{"draws":19,"losses":90,"wins":35},"gpt-6.1-sol":{"draws":13,"losses":115,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":26,"losses":11,"wins":65},"inclusionai/ling-3.0-flash":{"draws":34,"losses":12,"wins":56},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":29,"wins":94},"meta/muse-glimmer-30b":{"draws":30,"losses":16,"wins":80},"meta/muse-spark-1.2":{"draws":20,"losses":57,"wins":61},"meta/muse-spark-1.3":{"draws":27,"losses":51,"wins":66},"meta/muse-wonder":{"draws":30,"losses":71,"wins":43},"minimax/minimax-m3":{"draws":18,"losses":15,"wins":45},"mistralai/mistral-large-4-0":{"draws":26,"losses":22,"wins":42},"mistralai/mistral-medium-3-5":{"draws":24,"losses":10,"wins":50},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":17},"moonshotai/kimi-k3":{"draws":34,"losses":43,"wins":61},"nex-agi/nex-n2-pro":{"draws":17,"losses":7,"wins":48},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":34,"wins":59},"o3":{"draws":28,"losses":74,"wins":96},"openai/gpt-oss-120b":{"draws":27,"losses":20,"wins":79},"poolside/laguna-s-2.1":{"draws":36,"losses":29,"wins":73},"qwen/qwen3.7-max":{"draws":25,"losses":18,"wins":41},"qwen/qwen3.7-plus":{"draws":19,"losses":10,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":49,"wins":63},"qwen/qwen3.8-27b":{"draws":20,"losses":31,"wins":51},"qwen/qwen3.8-flash":{"draws":24,"losses":31,"wins":41},"qwen/qwen3.8-max":{"draws":34,"losses":53,"wins":57},"qwen/qwen3.8-max-0902":{"draws":40,"losses":52,"wins":52},"stealth/ox-alpha":{"draws":84,"losses":180,"wins":210},"stealth/space-bunny-alpha":{"draws":30,"losses":17,"wins":67},"stepfun/step-3.7-flash":{"draws":19,"losses":20,"wins":63},"stepfun/step-5-preview":{"draws":5,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":21,"losses":14,"wins":43},"tencent/hy4-preview":{"draws":25,"losses":51,"wins":62},"thinkingmachines/inkling":{"draws":40,"losses":31,"wins":121},"thinkingmachines/inkling-small":{"draws":35,"losses":21,"wins":88},"unbiased/pareto-26.10-preview":{"draws":3,"losses":39,"wins":6},"upstage/solar-mini4":{"draws":6,"losses":8,"wins":22},"x-ai/grok-4.5":{"draws":20,"losses":59,"wins":65},"x-ai/grok-4.6":{"draws":37,"losses":57,"wins":50},"x-ai/grok-4.7":{"draws":15,"losses":77,"wins":34},"x-ai/grok-build-0.1":{"draws":12,"losses":8,"wins":28},"xiaomi/mimo-v2.5":{"draws":56,"losses":36,"wins":130},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":13,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":31,"wins":41},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":50,"wins":30},"z-ai/glm-5.2":{"draws":75,"losses":59,"wins":154},"z-ai/glm-5.3":{"draws":33,"losses":73,"wins":32},"z-ai/glm-5.3-flash":{"draws":16,"losses":40,"wins":40},"z-ai/glm-5.3-flashx":{"draws":35,"losses":51,"wins":58}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":25,"wins":83},"claude-fable-5":{"draws":29,"losses":73,"wins":42},"claude-fable-5-1":{"draws":15,"losses":134,"wins":13},"claude-haiku-5-5":{"draws":27,"losses":60,"wins":51},"claude-opus-4-5":{"draws":53,"losses":55,"wins":126},"claude-opus-4-8":{"draws":25,"losses":59,"wins":48},"claude-opus-5":{"draws":36,"losses":166,"wins":44},"claude-opus-5-5":{"draws":15,"losses":131,"wins":10},"claude-sonnet-5":{"draws":39,"losses":33,"wins":72},"claude-sonnet-5-5":{"draws":25,"losses":65,"wins":54},"cohere/north-mini-code":{"draws":11,"losses":4,"wins":39},"deepseek/deepseek-v4-flash":{"draws":58,"losses":32,"wins":126},"deepseek/deepseek-v4-pro":{"draws":32,"losses":40,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":39,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":43,"wins":61},"fireworks/ember-1":{"draws":35,"losses":50,"wins":59},"gemini-3.1-pro-preview":{"draws":35,"losses":35,"wins":74},"google/gemini-3.1-flash-lite":{"draws":25,"losses":7,"wins":64},"google/gemini-3.5-flash":{"draws":47,"losses":44,"wins":89},"google/gemini-3.5-flash-lite":{"draws":65,"losses":48,"wins":139},"google/gemini-3.6-flash":{"draws":67,"losses":96,"wins":113},"google/gemini-3.8-flash":{"draws":30,"losses":62,"wins":52},"google/gemma-4-31b-it":{"draws":28,"losses":11,"wins":45},"gpt-4.1":{"draws":11,"losses":7,"wins":30},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":13},"gpt-5":{"draws":38,"losses":32,"wins":56},"gpt-5.4":{"draws":34,"losses":50,"wins":54},"gpt-5.4-mini":{"draws":27,"losses":13,"wins":56},"gpt-5.4-nano":{"draws":30,"losses":33,"wins":81},"gpt-5.5":{"draws":42,"losses":44,"wins":46},"gpt-5.6-luna":{"draws":42,"losses":29,"wins":73},"gpt-5.6-sol":{"draws":23,"losses":81,"wins":40},"gpt-5.6-terra":{"draws":38,"losses":37,"wins":63},"gpt-6-astra":{"draws":14,"losses":121,"wins":9},"gpt-6-luna":{"draws":30,"losses":42,"wins":72},"gpt-6-sol":{"draws":20,"losses":87,"wins":37},"gpt-6.1-sol":{"draws":19,"losses":107,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":29,"losses":5,"wins":68},"inclusionai/ling-3.0-flash":{"draws":34,"losses":8,"wins":60},"inclusionai/ling-3.1-flash":{"draws":4,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":36,"losses":19,"wins":101},"meta/muse-glimmer-30b":{"draws":36,"losses":19,"wins":71},"meta/muse-spark-1.2":{"draws":29,"losses":49,"wins":60},"meta/muse-spark-1.3":{"draws":28,"losses":59,"wins":57},"meta/muse-wonder":{"draws":34,"losses":73,"wins":37},"minimax/minimax-m3":{"draws":20,"losses":12,"wins":46},"mistralai/mistral-large-4-0":{"draws":29,"losses":27,"wins":34},"mistralai/mistral-medium-3-5":{"draws":21,"losses":8,"wins":55},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":12,"wins":12},"moonshotai/kimi-k3":{"draws":41,"losses":34,"wins":63},"nex-agi/nex-n2-pro":{"draws":14,"losses":5,"wins":53},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":21,"wins":74},"o3":{"draws":21,"losses":58,"wins":119},"openai/gpt-oss-120b":{"draws":37,"losses":13,"wins":76},"poolside/laguna-s-2.1":{"draws":40,"losses":23,"wins":75},"qwen/qwen3.7-max":{"draws":22,"losses":20,"wins":42},"qwen/qwen3.7-plus":{"draws":17,"losses":10,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":45,"wins":61},"qwen/qwen3.8-27b":{"draws":24,"losses":25,"wins":53},"qwen/qwen3.8-flash":{"draws":32,"losses":22,"wins":42},"qwen/qwen3.8-max":{"draws":40,"losses":48,"wins":56},"qwen/qwen3.8-max-0902":{"draws":36,"losses":51,"wins":57},"stealth/ox-alpha":{"draws":86,"losses":167,"wins":221},"stealth/space-bunny-alpha":{"draws":33,"losses":22,"wins":59},"stepfun/step-3.7-flash":{"draws":17,"losses":14,"wins":71},"stepfun/step-5-preview":{"draws":4,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":14,"wins":48},"tencent/hy4-preview":{"draws":32,"losses":57,"wins":49},"thinkingmachines/inkling":{"draws":44,"losses":25,"wins":123},"thinkingmachines/inkling-small":{"draws":36,"losses":23,"wins":85},"unbiased/pareto-26.10-preview":{"draws":3,"losses":42,"wins":3},"upstage/solar-mini4":{"draws":5,"losses":4,"wins":27},"x-ai/grok-4.5":{"draws":25,"losses":59,"wins":60},"x-ai/grok-4.6":{"draws":33,"losses":59,"wins":52},"x-ai/grok-4.7":{"draws":15,"losses":83,"wins":28},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":30},"xiaomi/mimo-v2.5":{"draws":72,"losses":16,"wins":134},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":14,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":34,"wins":35},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":44,"wins":35},"z-ai/glm-5.2":{"draws":82,"losses":63,"wins":143},"z-ai/glm-5.3":{"draws":27,"losses":78,"wins":33},"z-ai/glm-5.3-flash":{"draws":35,"losses":58,"wins":51},"z-ai/glm-5.3-flashx":{"draws":32,"losses":32,"wins":32}}},"versus_totals_tracks":{"highest":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":8,"wins":10},"claude-fable-5":{"draws":9,"losses":35,"wins":4},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":27,"wins":5},"claude-opus-4-5":{"draws":32,"losses":30,"wins":16},"claude-opus-4-8":{"draws":14,"losses":24,"wins":6},"claude-opus-5":{"draws":9,"losses":65,"wins":8},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":17,"losses":23,"wins":8},"claude-sonnet-5-5":{"draws":10,"losses":27,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":25,"losses":19,"wins":28},"deepseek/deepseek-v4-pro":{"draws":7,"losses":20,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":22,"wins":8},"fireworks/ember-1":{"draws":17,"losses":24,"wins":7},"gemini-3.1-pro-preview":{"draws":16,"losses":16,"wins":16},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":16,"losses":28,"wins":16},"google/gemini-3.5-flash-lite":{"draws":38,"losses":18,"wins":28},"google/gemini-3.6-flash":{"draws":31,"losses":41,"wins":20},"google/gemini-3.8-flash":{"draws":14,"losses":27,"wins":7},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":10},"gpt-4.1":{"draws":7,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":18,"losses":15,"wins":9},"gpt-5.4":{"draws":12,"losses":25,"wins":9},"gpt-5.4-mini":{"draws":15,"losses":7,"wins":10},"gpt-5.4-nano":{"draws":14,"losses":17,"wins":17},"gpt-5.5":{"draws":21,"losses":14,"wins":9},"gpt-5.6-luna":{"draws":22,"losses":13,"wins":13},"gpt-5.6-sol":{"draws":11,"losses":30,"wins":7},"gpt-5.6-terra":{"draws":15,"losses":21,"wins":10},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":15,"losses":17,"wins":16},"gpt-6-sol":{"draws":7,"losses":36,"wins":5},"gpt-6.1-sol":{"draws":5,"losses":40,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":7,"wins":12},"inclusionai/ling-3.0-flash":{"draws":17,"losses":3,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":10,"wins":24},"meta/muse-glimmer-30b":{"draws":20,"losses":9,"wins":13},"meta/muse-spark-1.2":{"draws":14,"losses":20,"wins":12},"meta/muse-spark-1.3":{"draws":16,"losses":25,"wins":7},"meta/muse-wonder":{"draws":12,"losses":29,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":14},"mistralai/mistral-large-4-0":{"draws":12,"losses":9,"wins":9},"mistralai/mistral-medium-3-5":{"draws":14,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":16,"losses":22,"wins":8},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":12,"wins":11},"o3":{"draws":18,"losses":27,"wins":21},"openai/gpt-oss-120b":{"draws":19,"losses":7,"wins":16},"poolside/laguna-s-2.1":{"draws":25,"losses":8,"wins":13},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":19,"wins":12},"qwen/qwen3.8-27b":{"draws":9,"losses":19,"wins":6},"qwen/qwen3.8-flash":{"draws":13,"losses":13,"wins":6},"qwen/qwen3.8-max":{"draws":18,"losses":16,"wins":14},"qwen/qwen3.8-max-0902":{"draws":17,"losses":23,"wins":8},"stealth/ox-alpha":{"draws":43,"losses":84,"wins":31},"stealth/space-bunny-alpha":{"draws":18,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":9,"losses":10,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":16,"losses":24,"wins":6},"thinkingmachines/inkling":{"draws":27,"losses":10,"wins":27},"thinkingmachines/inkling-small":{"draws":22,"losses":9,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":14,"losses":27,"wins":7},"x-ai/grok-4.6":{"draws":11,"losses":33,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":31,"wins":9},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":26,"losses":14,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":7,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":20,"wins":8},"z-ai/glm-5.2":{"draws":38,"losses":30,"wins":28},"z-ai/glm-5.3":{"draws":11,"losses":32,"wins":3},"z-ai/glm-5.3-flash":{"draws":14,"losses":26,"wins":8},"z-ai/glm-5.3-flashx":{"draws":10,"losses":29,"wins":9}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":4,"wins":36},"claude-fable-5":{"draws":1,"losses":12,"wins":19},"claude-fable-5-1":{"draws":9,"losses":35,"wins":10},"claude-haiku-5-5":{"draws":8,"losses":14,"wins":24},"claude-opus-4-5":{"draws":3,"losses":8,"wins":67},"claude-opus-4-8":{"draws":4,"losses":12,"wins":28},"claude-opus-5":{"draws":10,"losses":42,"wins":30},"claude-opus-5-5":{"draws":7,"losses":38,"wins":7},"claude-sonnet-5":{"draws":7,"losses":4,"wins":37},"claude-sonnet-5-5":{"draws":1,"losses":19,"wins":28},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":7,"losses":3,"wins":62},"deepseek/deepseek-v4-pro":{"draws":2,"losses":9,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":8,"wins":33},"fireworks/ember-1":{"draws":6,"losses":5,"wins":37},"gemini-3.1-pro-preview":{"draws":6,"losses":8,"wins":34},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":28},"google/gemini-3.5-flash":{"draws":7,"losses":3,"wins":50},"google/gemini-3.5-flash-lite":{"draws":9,"losses":4,"wins":71},"google/gemini-3.6-flash":{"draws":10,"losses":15,"wins":67},"google/gemini-3.8-flash":{"draws":8,"losses":18,"wins":22},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":24},"gpt-4.1":{"draws":3,"losses":5,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":6,"losses":9,"wins":27},"gpt-5.4":{"draws":7,"losses":17,"wins":22},"gpt-5.4-mini":{"draws":6,"losses":4,"wins":22},"gpt-5.4-nano":{"draws":3,"losses":5,"wins":40},"gpt-5.5":{"draws":4,"losses":17,"wins":23},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":38},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":28},"gpt-5.6-terra":{"draws":10,"losses":6,"wins":30},"gpt-6-astra":{"draws":8,"losses":32,"wins":8},"gpt-6-luna":{"draws":8,"losses":11,"wins":29},"gpt-6-sol":{"draws":5,"losses":25,"wins":18},"gpt-6.1-sol":{"draws":3,"losses":32,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":2,"losses":1,"wins":31},"inclusionai/ling-3.0-flash":{"draws":5,"losses":0,"wins":29},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":5,"wins":39},"meta/muse-glimmer-30b":{"draws":9,"losses":1,"wins":32},"meta/muse-spark-1.2":{"draws":1,"losses":8,"wins":37},"meta/muse-spark-1.3":{"draws":6,"losses":8,"wins":34},"meta/muse-wonder":{"draws":5,"losses":15,"wins":28},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":19},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":5,"losses":9,"wins":32},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":28},"o3":{"draws":7,"losses":11,"wins":48},"openai/gpt-oss-120b":{"draws":6,"losses":2,"wins":34},"poolside/laguna-s-2.1":{"draws":9,"losses":3,"wins":34},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":10,"wins":33},"qwen/qwen3.8-27b":{"draws":2,"losses":3,"wins":29},"qwen/qwen3.8-flash":{"draws":7,"losses":3,"wins":22},"qwen/qwen3.8-max":{"draws":6,"losses":9,"wins":33},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":32},"stealth/ox-alpha":{"draws":22,"losses":18,"wins":118},"stealth/space-bunny-alpha":{"draws":7,"losses":2,"wins":29},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":29},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":18},"tencent/hy4-preview":{"draws":7,"losses":8,"wins":31},"thinkingmachines/inkling":{"draws":6,"losses":3,"wins":55},"thinkingmachines/inkling-small":{"draws":8,"losses":1,"wins":39},"unbiased/pareto-26.10-preview":{"draws":3,"losses":9,"wins":4},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":2,"losses":11,"wins":35},"x-ai/grok-4.6":{"draws":10,"losses":14,"wins":24},"x-ai/grok-4.7":{"draws":3,"losses":22,"wins":17},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":8,"losses":1,"wins":65},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":4,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":20},"z-ai/glm-5.2":{"draws":12,"losses":10,"wins":74},"z-ai/glm-5.3":{"draws":10,"losses":12,"wins":24},"z-ai/glm-5.3-flash":{"draws":10,"losses":8,"wins":30},"z-ai/glm-5.3-flashx":{"draws":11,"losses":8,"wins":29}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":58},"claude-fable-5":{"draws":3,"losses":4,"wins":59},"claude-fable-5-1":{"draws":7,"losses":10,"wins":39},"claude-haiku-5-5":{"draws":4,"losses":0,"wins":58},"claude-opus-4-5":{"draws":1,"losses":2,"wins":103},"claude-opus-4-8":{"draws":0,"losses":3,"wins":55},"claude-opus-5":{"draws":7,"losses":20,"wins":87},"claude-opus-5-5":{"draws":8,"losses":32,"wins":30},"claude-sonnet-5":{"draws":0,"losses":1,"wins":65},"claude-sonnet-5-5":{"draws":2,"losses":12,"wins":52},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":25},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":94},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":1,"wins":61},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":4,"wins":59},"fireworks/ember-1":{"draws":0,"losses":1,"wins":65},"gemini-3.1-pro-preview":{"draws":0,"losses":3,"wins":63},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":41},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":80},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":114},"google/gemini-3.6-flash":{"draws":3,"losses":4,"wins":121},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":60},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":37},"gpt-4.1":{"draws":0,"losses":0,"wins":22},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":0,"losses":0,"wins":58},"gpt-5.4":{"draws":1,"losses":3,"wins":60},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":44},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":58},"gpt-5.5":{"draws":0,"losses":3,"wins":59},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":65},"gpt-5.6-sol":{"draws":2,"losses":6,"wins":58},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":64},"gpt-6-astra":{"draws":3,"losses":25,"wins":38},"gpt-6-luna":{"draws":1,"losses":1,"wins":64},"gpt-6-sol":{"draws":2,"losses":11,"wins":53},"gpt-6.1-sol":{"draws":2,"losses":23,"wins":41},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":44},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":44},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":69},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":60},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":60},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":60},"meta/muse-wonder":{"draws":4,"losses":7,"wins":55},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":33},"mistralai/mistral-large-4-0":{"draws":0,"losses":4,"wins":38},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":15},"moonshotai/kimi-k3":{"draws":1,"losses":3,"wins":60},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":50},"o3":{"draws":0,"losses":1,"wins":85},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":57},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":58},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":35},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":0,"wins":66},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":46},"qwen/qwen3.8-flash":{"draws":0,"losses":1,"wins":43},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":65},"qwen/qwen3.8-max-0902":{"draws":1,"losses":3,"wins":62},"stealth/ox-alpha":{"draws":10,"losses":3,"wins":221},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":53},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":46},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":31},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":60},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":90},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":65},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":12},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":16},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":64},"x-ai/grok-4.6":{"draws":2,"losses":6,"wins":58},"x-ai/grok-4.7":{"draws":1,"losses":6,"wins":49},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":95},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":33},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":38},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":3,"wins":37},"z-ai/glm-5.2":{"draws":3,"losses":1,"wins":128},"z-ai/glm-5.3":{"draws":3,"losses":3,"wins":58},"z-ai/glm-5.3-flash":{"draws":1,"losses":5,"wins":60},"z-ai/glm-5.3-flashx":{"draws":6,"losses":1,"wins":59}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":3,"wins":34},"claude-fable-5":{"draws":5,"losses":11,"wins":26},"claude-fable-5-1":{"draws":4,"losses":39,"wins":3},"claude-haiku-5-5":{"draws":5,"losses":3,"wins":20},"claude-opus-4-5":{"draws":12,"losses":6,"wins":52},"claude-opus-4-8":{"draws":7,"losses":10,"wins":25},"claude-opus-5":{"draws":10,"losses":38,"wins":22},"claude-opus-5-5":{"draws":6,"losses":32,"wins":8},"claude-sonnet-5":{"draws":5,"losses":4,"wins":33},"claude-sonnet-5-5":{"draws":5,"losses":13,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":52},"deepseek/deepseek-v4-pro":{"draws":6,"losses":5,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":4,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":8,"wins":25},"fireworks/ember-1":{"draws":5,"losses":8,"wins":29},"gemini-3.1-pro-preview":{"draws":4,"losses":9,"wins":29},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":5,"losses":9,"wins":40},"google/gemini-3.5-flash-lite":{"draws":6,"losses":5,"wins":63},"google/gemini-3.6-flash":{"draws":10,"losses":18,"wins":52},"google/gemini-3.8-flash":{"draws":7,"losses":9,"wins":26},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":23},"gpt-4.1":{"draws":1,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":3,"losses":4,"wins":29},"gpt-5.4":{"draws":2,"losses":9,"wins":29},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":22},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":39},"gpt-5.5":{"draws":5,"losses":10,"wins":23},"gpt-5.6-luna":{"draws":5,"losses":2,"wins":35},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":22},"gpt-5.6-terra":{"draws":4,"losses":10,"wins":26},"gpt-6-astra":{"draws":4,"losses":33,"wins":5},"gpt-6-luna":{"draws":6,"losses":6,"wins":30},"gpt-6-sol":{"draws":12,"losses":15,"wins":15},"gpt-6.1-sol":{"draws":5,"losses":30,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":31},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":39},"meta/muse-glimmer-30b":{"draws":4,"losses":2,"wins":30},"meta/muse-spark-1.2":{"draws":5,"losses":5,"wins":30},"meta/muse-spark-1.3":{"draws":4,"losses":4,"wins":34},"meta/muse-wonder":{"draws":9,"losses":16,"wins":17},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":21},"mistralai/mistral-large-4-0":{"draws":4,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":2,"losses":9,"wins":29},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":32},"o3":{"draws":2,"losses":11,"wins":49},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":31},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":30},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":18},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":8,"wins":28},"qwen/qwen3.8-27b":{"draws":3,"losses":6,"wins":21},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":20},"qwen/qwen3.8-max":{"draws":3,"losses":8,"wins":31},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":26},"stealth/ox-alpha":{"draws":17,"losses":21,"wins":80},"stealth/space-bunny-alpha":{"draws":6,"losses":5,"wins":23},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":4,"losses":9,"wins":27},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":45},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":40},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":6},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":4,"losses":13,"wins":25},"x-ai/grok-4.6":{"draws":4,"losses":11,"wins":27},"x-ai/grok-4.7":{"draws":4,"losses":22,"wins":12},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":6,"losses":6,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":7,"wins":16},"z-ai/glm-5.2":{"draws":5,"losses":9,"wins":70},"z-ai/glm-5.3":{"draws":5,"losses":16,"wins":19},"z-ai/glm-5.3-flash":{"draws":3,"losses":10,"wins":29},"z-ai/glm-5.3-flashx":{"draws":3,"losses":9,"wins":30}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":5,"wins":27},"claude-fable-5":{"draws":7,"losses":33,"wins":8},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":20,"losses":19,"wins":23},"claude-opus-4-8":{"draws":14,"losses":17,"wins":13},"claude-opus-5":{"draws":11,"losses":63,"wins":8},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":20,"losses":10,"wins":18},"claude-sonnet-5-5":{"draws":10,"losses":25,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":23,"losses":11,"wins":38},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":16,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":19,"wins":13},"fireworks/ember-1":{"draws":16,"losses":15,"wins":17},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":22},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":21},"google/gemini-3.5-flash":{"draws":15,"losses":22,"wins":23},"google/gemini-3.5-flash-lite":{"draws":29,"losses":20,"wins":35},"google/gemini-3.6-flash":{"draws":25,"losses":42,"wins":25},"google/gemini-3.8-flash":{"draws":14,"losses":28,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":7,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":13,"wins":17},"gpt-5.4":{"draws":14,"losses":23,"wins":9},"gpt-5.4-mini":{"draws":15,"losses":6,"wins":11},"gpt-5.4-nano":{"draws":16,"losses":12,"wins":20},"gpt-5.5":{"draws":16,"losses":18,"wins":10},"gpt-5.6-luna":{"draws":16,"losses":11,"wins":21},"gpt-5.6-sol":{"draws":6,"losses":31,"wins":11},"gpt-5.6-terra":{"draws":16,"losses":11,"wins":19},"gpt-6-astra":{"draws":1,"losses":45,"wins":2},"gpt-6-luna":{"draws":14,"losses":17,"wins":17},"gpt-6-sol":{"draws":7,"losses":37,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"wins":17},"inclusionai/ling-3.0-flash":{"draws":12,"losses":5,"wins":17},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":12,"losses":9,"wins":31},"meta/muse-glimmer-30b":{"draws":16,"losses":3,"wins":23},"meta/muse-spark-1.2":{"draws":11,"losses":24,"wins":11},"meta/muse-spark-1.3":{"draws":10,"losses":26,"wins":12},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":8,"losses":3,"wins":15},"mistralai/mistral-large-4-0":{"draws":11,"losses":11,"wins":8},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":18,"wins":15},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":4,"wins":20},"o3":{"draws":12,"losses":17,"wins":37},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":15,"losses":7,"wins":24},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":19,"wins":11},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":14},"qwen/qwen3.8-flash":{"draws":10,"losses":11,"wins":11},"qwen/qwen3.8-max":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-max-0902":{"draws":14,"losses":20,"wins":14},"stealth/ox-alpha":{"draws":39,"losses":63,"wins":56},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":22},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":9},"tencent/hy4-preview":{"draws":13,"losses":19,"wins":14},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":36},"thinkingmachines/inkling-small":{"draws":20,"losses":8,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":15,"losses":21,"wins":12},"x-ai/grok-4.6":{"draws":13,"losses":27,"wins":8},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":27,"losses":10,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":20,"wins":10},"z-ai/glm-5.2":{"draws":31,"losses":24,"wins":41},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":10,"losses":25,"wins":13},"z-ai/glm-5.3-flashx":{"draws":17,"losses":19,"wins":12}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":5,"wins":31},"claude-fable-5":{"draws":6,"losses":15,"wins":21},"claude-fable-5-1":{"draws":3,"losses":34,"wins":9},"claude-haiku-5-5":{"draws":6,"losses":10,"wins":26},"claude-opus-4-5":{"draws":13,"losses":11,"wins":46},"claude-opus-4-8":{"draws":3,"losses":4,"wins":21},"claude-opus-5":{"draws":13,"losses":36,"wins":21},"claude-opus-5-5":{"draws":9,"losses":28,"wins":9},"claude-sonnet-5":{"draws":8,"losses":5,"wins":29},"claude-sonnet-5-5":{"draws":10,"losses":11,"wins":21},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":5,"losses":4,"wins":55},"deepseek/deepseek-v4-pro":{"draws":3,"losses":6,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":5,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":13,"wins":24},"fireworks/ember-1":{"draws":10,"losses":6,"wins":26},"gemini-3.1-pro-preview":{"draws":8,"losses":6,"wins":28},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":6,"losses":8,"wins":40},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":63},"google/gemini-3.6-flash":{"draws":13,"losses":21,"wins":46},"google/gemini-3.8-flash":{"draws":8,"losses":11,"wins":23},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":21},"gpt-4.1":{"draws":4,"losses":0,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":3,"losses":5,"wins":28},"gpt-5.4":{"draws":4,"losses":14,"wins":22},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":6,"losses":3,"wins":37},"gpt-5.5":{"draws":8,"losses":13,"wins":17},"gpt-5.6-luna":{"draws":9,"losses":4,"wins":29},"gpt-5.6-sol":{"draws":3,"losses":12,"wins":27},"gpt-5.6-terra":{"draws":3,"losses":5,"wins":32},"gpt-6-astra":{"draws":5,"losses":33,"wins":4},"gpt-6-luna":{"draws":9,"losses":4,"wins":29},"gpt-6-sol":{"draws":8,"losses":18,"wins":16},"gpt-6.1-sol":{"draws":5,"losses":28,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":2,"wins":25},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":29},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":37},"meta/muse-glimmer-30b":{"draws":3,"losses":1,"wins":32},"meta/muse-spark-1.2":{"draws":5,"losses":7,"wins":28},"meta/muse-spark-1.3":{"draws":7,"losses":11,"wins":24},"meta/muse-wonder":{"draws":7,"losses":14,"wins":21},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":20},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":16},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":23},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":34},"o3":{"draws":6,"losses":7,"wins":49},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":3,"losses":2,"wins":33},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":16},"qwen/qwen3.7-plus":{"draws":1,"losses":3,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":13,"wins":22},"qwen/qwen3.8-27b":{"draws":4,"losses":5,"wins":21},"qwen/qwen3.8-flash":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.8-max":{"draws":1,"losses":9,"wins":32},"qwen/qwen3.8-max-0902":{"draws":9,"losses":12,"wins":21},"stealth/ox-alpha":{"draws":25,"losses":21,"wins":72},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":22},"stepfun/step-3.7-flash":{"draws":1,"losses":4,"wins":25},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":17},"tencent/hy4-preview":{"draws":5,"losses":9,"wins":26},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":46},"thinkingmachines/inkling-small":{"draws":5,"losses":3,"wins":34},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":9,"wins":24},"x-ai/grok-4.6":{"draws":8,"losses":13,"wins":21},"x-ai/grok-4.7":{"draws":7,"losses":19,"wins":12},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":13},"xiaomi/mimo-v2.5":{"draws":12,"losses":4,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":9,"wins":17},"z-ai/glm-5.2":{"draws":10,"losses":8,"wins":66},"z-ai/glm-5.3":{"draws":6,"losses":14,"wins":20},"z-ai/glm-5.3-flash":{"draws":2,"losses":12,"wins":28},"z-ai/glm-5.3-flashx":{"draws":8,"losses":4,"wins":30}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":7,"wins":63},"claude-fable-5":{"draws":5,"losses":18,"wins":55},"claude-fable-5-1":{"draws":10,"losses":39,"wins":39},"claude-haiku-5-5":{"draws":1,"losses":11,"wins":62},"claude-opus-4-5":{"draws":9,"losses":11,"wins":106},"claude-opus-4-8":{"draws":4,"losses":13,"wins":53},"claude-opus-5":{"draws":12,"losses":37,"wins":77},"claude-opus-5-5":{"draws":5,"losses":45,"wins":36},"claude-sonnet-5":{"draws":3,"losses":6,"wins":69},"claude-sonnet-5-5":{"draws":3,"losses":17,"wins":58},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":26},"deepseek/deepseek-v4-flash":{"draws":1,"losses":8,"wins":105},"deepseek/deepseek-v4-pro":{"draws":3,"losses":5,"wins":66},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":3,"wins":62},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":8,"wins":62},"fireworks/ember-1":{"draws":3,"losses":14,"wins":61},"gemini-3.1-pro-preview":{"draws":4,"losses":5,"wins":69},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":42},"google/gemini-3.5-flash":{"draws":9,"losses":5,"wins":82},"google/gemini-3.5-flash-lite":{"draws":5,"losses":6,"wins":123},"google/gemini-3.6-flash":{"draws":11,"losses":19,"wins":118},"google/gemini-3.8-flash":{"draws":3,"losses":12,"wins":63},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":40},"gpt-4.1":{"draws":0,"losses":1,"wins":25},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":0,"losses":4,"wins":66},"gpt-5.4":{"draws":3,"losses":8,"wins":63},"gpt-5.4-mini":{"draws":3,"losses":3,"wins":46},"gpt-5.4-nano":{"draws":1,"losses":6,"wins":67},"gpt-5.5":{"draws":4,"losses":9,"wins":61},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":72},"gpt-5.6-sol":{"draws":6,"losses":13,"wins":59},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":69},"gpt-6-astra":{"draws":8,"losses":47,"wins":23},"gpt-6-luna":{"draws":11,"losses":5,"wins":62},"gpt-6-sol":{"draws":7,"losses":25,"wins":46},"gpt-6.1-sol":{"draws":13,"losses":36,"wins":29},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":4,"losses":1,"wins":47},"inclusionai/ling-3.0-flash":{"draws":1,"losses":5,"wins":46},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":7,"wins":71},"meta/muse-glimmer-30b":{"draws":4,"losses":2,"wins":68},"meta/muse-spark-1.2":{"draws":2,"losses":5,"wins":71},"meta/muse-spark-1.3":{"draws":5,"losses":9,"wins":64},"meta/muse-wonder":{"draws":5,"losses":17,"wins":56},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":41},"mistralai/mistral-large-4-0":{"draws":4,"losses":4,"wins":44},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":40},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":19},"moonshotai/kimi-k3":{"draws":7,"losses":7,"wins":64},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":62},"o3":{"draws":2,"losses":6,"wins":88},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":59},"poolside/laguna-s-2.1":{"draws":1,"losses":5,"wins":74},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":39},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":32},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":7,"wins":69},"qwen/qwen3.8-27b":{"draws":3,"losses":3,"wins":46},"qwen/qwen3.8-flash":{"draws":1,"losses":2,"wins":49},"qwen/qwen3.8-max":{"draws":2,"losses":6,"wins":70},"qwen/qwen3.8-max-0902":{"draws":4,"losses":9,"wins":65},"stealth/ox-alpha":{"draws":20,"losses":23,"wins":223},"stealth/space-bunny-alpha":{"draws":5,"losses":2,"wins":55},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":46},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":38},"tencent/hy4-preview":{"draws":4,"losses":7,"wins":63},"thinkingmachines/inkling":{"draws":6,"losses":8,"wins":94},"thinkingmachines/inkling-small":{"draws":4,"losses":6,"wins":68},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":14},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":13},"x-ai/grok-4.5":{"draws":7,"losses":12,"wins":59},"x-ai/grok-4.6":{"draws":6,"losses":9,"wins":63},"x-ai/grok-4.7":{"draws":6,"losses":18,"wins":46},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":25},"xiaomi/mimo-v2.5":{"draws":4,"losses":7,"wins":109},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":44},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":7,"wins":41},"z-ai/glm-5.2":{"draws":11,"losses":9,"wins":136},"z-ai/glm-5.3":{"draws":5,"losses":8,"wins":61},"z-ai/glm-5.3-flash":{"draws":7,"losses":9,"wins":62},"z-ai/glm-5.3-flashx":{"draws":7,"losses":7,"wins":64}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":43},"claude-fable-5":{"draws":1,"losses":3,"wins":44},"claude-fable-5-1":{"draws":4,"losses":8,"wins":42},"claude-haiku-5-5":{"draws":2,"losses":1,"wins":43},"claude-opus-4-5":{"draws":0,"losses":0,"wins":78},"claude-opus-4-8":{"draws":2,"losses":2,"wins":40},"claude-opus-5":{"draws":5,"losses":9,"wins":68},"claude-opus-5-5":{"draws":3,"losses":7,"wins":26},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":4,"losses":5,"wins":39},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":72},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":3,"wins":45},"fireworks/ember-1":{"draws":0,"losses":0,"wins":48},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":47},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":58},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":83},"google/gemini-3.6-flash":{"draws":1,"losses":3,"wins":88},"google/gemini-3.8-flash":{"draws":1,"losses":2,"wins":45},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":0,"wins":42},"gpt-5.4":{"draws":0,"losses":4,"wins":42},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":30},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":0,"losses":4,"wins":40},"gpt-5.6-luna":{"draws":1,"losses":2,"wins":45},"gpt-5.6-sol":{"draws":1,"losses":3,"wins":44},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":46},"gpt-6-astra":{"draws":4,"losses":15,"wins":29},"gpt-6-luna":{"draws":1,"losses":0,"wins":47},"gpt-6-sol":{"draws":2,"losses":1,"wins":45},"gpt-6.1-sol":{"draws":8,"losses":7,"wins":33},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":52},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":1,"losses":3,"wins":42},"meta/muse-spark-1.3":{"draws":1,"losses":3,"wins":44},"meta/muse-wonder":{"draws":1,"losses":4,"wins":43},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"mistralai/mistral-large-4-0":{"draws":1,"losses":0,"wins":29},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":0,"losses":3,"wins":43},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":42},"o3":{"draws":1,"losses":1,"wins":64},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":42},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":45},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":27},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":5,"wins":43},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":33},"qwen/qwen3.8-flash":{"draws":0,"losses":1,"wins":31},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":46},"qwen/qwen3.8-max-0902":{"draws":3,"losses":2,"wins":43},"stealth/ox-alpha":{"draws":2,"losses":1,"wins":155},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":38},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":26},"tencent/hy4-preview":{"draws":0,"losses":1,"wins":45},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":63},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10-preview":{"draws":1,"losses":3,"wins":12},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":2,"losses":2,"wins":44},"x-ai/grok-4.6":{"draws":3,"losses":1,"wins":44},"x-ai/grok-4.7":{"draws":1,"losses":2,"wins":39},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":27},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":94},"z-ai/glm-5.3":{"draws":1,"losses":3,"wins":42},"z-ai/glm-5.3-flash":{"draws":2,"losses":1,"wins":45},"z-ai/glm-5.3-flashx":{"draws":2,"losses":3,"wins":43}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":4,"wins":29},"claude-fable-5":{"draws":8,"losses":26,"wins":14},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":17,"wins":23},"claude-opus-4-5":{"draws":23,"losses":21,"wins":34},"claude-opus-4-8":{"draws":10,"losses":14,"wins":20},"claude-opus-5":{"draws":10,"losses":60,"wins":12},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"claude-sonnet-5":{"draws":9,"losses":4,"wins":19},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":18},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":47},"deepseek/deepseek-v4-pro":{"draws":9,"losses":12,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":15,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"wins":20},"fireworks/ember-1":{"draws":11,"losses":17,"wins":20},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":25},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":14,"losses":21,"wins":25},"google/gemini-3.5-flash-lite":{"draws":18,"losses":10,"wins":56},"google/gemini-3.6-flash":{"draws":13,"losses":33,"wins":46},"google/gemini-3.8-flash":{"draws":9,"losses":21,"wins":18},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":5,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":7,"wins":23},"gpt-5.4":{"draws":11,"losses":19,"wins":16},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":16},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":30},"gpt-5.5":{"draws":12,"losses":18,"wins":14},"gpt-5.6-luna":{"draws":12,"losses":14,"wins":22},"gpt-5.6-sol":{"draws":7,"losses":32,"wins":9},"gpt-5.6-terra":{"draws":12,"losses":11,"wins":23},"gpt-6-astra":{"draws":2,"losses":41,"wins":5},"gpt-6-luna":{"draws":10,"losses":19,"wins":19},"gpt-6-sol":{"draws":8,"losses":31,"wins":9},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":3,"wins":21},"inclusionai/ling-3.0-flash":{"draws":10,"losses":2,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":6,"wins":37},"meta/muse-glimmer-30b":{"draws":8,"losses":6,"wins":28},"meta/muse-spark-1.2":{"draws":14,"losses":15,"wins":17},"meta/muse-spark-1.3":{"draws":9,"losses":22,"wins":17},"meta/muse-wonder":{"draws":11,"losses":23,"wins":14},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":8,"losses":5,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":16},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":11,"wins":21},"o3":{"draws":6,"losses":23,"wins":37},"openai/gpt-oss-120b":{"draws":10,"losses":4,"wins":28},"poolside/laguna-s-2.1":{"draws":9,"losses":3,"wins":34},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":18,"wins":18},"qwen/qwen3.8-27b":{"draws":9,"losses":8,"wins":17},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":13},"qwen/qwen3.8-max":{"draws":10,"losses":14,"wins":24},"qwen/qwen3.8-max-0902":{"draws":11,"losses":20,"wins":17},"stealth/ox-alpha":{"draws":35,"losses":58,"wins":65},"stealth/space-bunny-alpha":{"draws":7,"losses":9,"wins":22},"stepfun/step-3.7-flash":{"draws":5,"losses":7,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":5,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":19,"wins":19},"thinkingmachines/inkling":{"draws":19,"losses":8,"wins":37},"thinkingmachines/inkling-small":{"draws":11,"losses":7,"wins":30},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":16,"losses":20,"wins":12},"x-ai/grok-4.6":{"draws":11,"losses":22,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":21,"wins":16},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":18,"losses":8,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":5,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":20,"losses":26,"wins":50},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":4,"losses":25,"wins":19},"z-ai/glm-5.3-flashx":{"draws":10,"losses":19,"wins":19}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":0,"wins":37},"claude-fable-5":{"draws":5,"losses":2,"wins":41},"claude-fable-5-1":{"draws":7,"losses":16,"wins":31},"claude-haiku-5-5":{"draws":5,"losses":2,"wins":39},"claude-opus-4-5":{"draws":8,"losses":2,"wins":68},"claude-opus-4-8":{"draws":5,"losses":1,"wins":38},"claude-opus-5":{"draws":6,"losses":16,"wins":60},"claude-opus-5-5":{"draws":10,"losses":17,"wins":25},"claude-sonnet-5":{"draws":1,"losses":0,"wins":47},"claude-sonnet-5-5":{"draws":1,"losses":1,"wins":30},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":3,"losses":0,"wins":69},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":1,"wins":41},"fireworks/ember-1":{"draws":5,"losses":0,"wins":43},"gemini-3.1-pro-preview":{"draws":0,"losses":3,"wins":45},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":3,"losses":2,"wins":55},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":78},"google/gemini-3.6-flash":{"draws":10,"losses":5,"wins":77},"google/gemini-3.8-flash":{"draws":5,"losses":4,"wins":39},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":0,"wins":39},"gpt-5.4":{"draws":9,"losses":1,"wins":36},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":4,"losses":1,"wins":39},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":47},"gpt-5.6-sol":{"draws":3,"losses":3,"wins":42},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":42},"gpt-6-astra":{"draws":7,"losses":16,"wins":25},"gpt-6-luna":{"draws":8,"losses":1,"wins":39},"gpt-6-sol":{"draws":7,"losses":6,"wins":35},"gpt-6.1-sol":{"draws":2,"losses":14,"wins":32},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":49},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":2,"losses":1,"wins":43},"meta/muse-spark-1.3":{"draws":3,"losses":1,"wins":44},"meta/muse-wonder":{"draws":5,"losses":1,"wins":42},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":23},"mistralai/mistral-large-4-0":{"draws":3,"losses":0,"wins":27},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":4,"losses":2,"wins":40},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":39},"o3":{"draws":2,"losses":1,"wins":63},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":40},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":42},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":26},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":0,"wins":44},"qwen/qwen3.8-27b":{"draws":3,"losses":1,"wins":30},"qwen/qwen3.8-flash":{"draws":3,"losses":3,"wins":26},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":46},"qwen/qwen3.8-max-0902":{"draws":5,"losses":2,"wins":41},"stealth/ox-alpha":{"draws":10,"losses":4,"wins":144},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":35},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":3,"losses":0,"wins":43},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":57},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"unbiased/pareto-26.10-preview":{"draws":2,"losses":5,"wins":9},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":6,"losses":1,"wins":41},"x-ai/grok-4.6":{"draws":5,"losses":0,"wins":43},"x-ai/grok-4.7":{"draws":2,"losses":3,"wins":37},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":1,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":2,"wins":27},"z-ai/glm-5.2":{"draws":5,"losses":1,"wins":90},"z-ai/glm-5.3":{"draws":6,"losses":4,"wins":36},"z-ai/glm-5.3-flash":{"draws":5,"losses":4,"wins":39},"z-ai/glm-5.3-flashx":{"draws":6,"losses":3,"wins":39}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":9,"wins":12},"claude-fable-5":{"draws":7,"losses":28,"wins":7},"claude-fable-5-1":{"draws":2,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":22,"wins":6},"claude-opus-4-5":{"draws":20,"losses":31,"wins":17},"claude-opus-4-8":{"draws":10,"losses":21,"wins":7},"claude-opus-5":{"draws":12,"losses":49,"wins":9},"claude-opus-5-5":{"draws":4,"losses":40,"wins":2},"claude-sonnet-5":{"draws":15,"losses":18,"wins":9},"claude-sonnet-5-5":{"draws":11,"losses":26,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":6},"deepseek/deepseek-v4-flash":{"draws":16,"losses":14,"wins":20},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":12,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":18,"wins":6},"fireworks/ember-1":{"draws":15,"losses":19,"wins":8},"gemini-3.1-pro-preview":{"draws":16,"losses":13,"wins":13},"google/gemini-3.1-flash-lite":{"draws":10,"losses":3,"wins":13},"google/gemini-3.5-flash":{"draws":18,"losses":21,"wins":13},"google/gemini-3.5-flash-lite":{"draws":29,"losses":25,"wins":18},"google/gemini-3.6-flash":{"draws":25,"losses":44,"wins":11},"google/gemini-3.8-flash":{"draws":10,"losses":25,"wins":7},"google/gemma-4-31b-it":{"draws":14,"losses":1,"wins":9},"gpt-4.1":{"draws":6,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":13,"wins":8},"gpt-5.4":{"draws":15,"losses":16,"wins":9},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":7},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":12},"gpt-5.5":{"draws":16,"losses":18,"wins":4},"gpt-5.6-luna":{"draws":20,"losses":9,"wins":13},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":7},"gpt-5.6-terra":{"draws":17,"losses":14,"wins":11},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":19,"losses":13,"wins":10},"gpt-6-sol":{"draws":9,"losses":28,"wins":5},"gpt-6.1-sol":{"draws":6,"losses":35,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":2,"wins":12},"inclusionai/ling-3.0-flash":{"draws":15,"losses":9,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":7,"wins":19},"meta/muse-glimmer-30b":{"draws":23,"losses":5,"wins":8},"meta/muse-spark-1.2":{"draws":13,"losses":20,"wins":7},"meta/muse-spark-1.3":{"draws":12,"losses":25,"wins":5},"meta/muse-wonder":{"draws":8,"losses":25,"wins":9},"minimax/minimax-m3":{"draws":9,"losses":6,"wins":7},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":5},"mistralai/mistral-medium-3-5":{"draws":15,"losses":3,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":1},"moonshotai/kimi-k3":{"draws":13,"losses":17,"wins":10},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":8,"wins":12},"o3":{"draws":13,"losses":22,"wins":19},"openai/gpt-oss-120b":{"draws":18,"losses":12,"wins":6},"poolside/laguna-s-2.1":{"draws":19,"losses":10,"wins":9},"qwen/qwen3.7-max":{"draws":15,"losses":6,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":15,"wins":11},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":15,"losses":20,"wins":7},"qwen/qwen3.8-max-0902":{"draws":19,"losses":15,"wins":8},"stealth/ox-alpha":{"draws":40,"losses":70,"wins":30},"stealth/space-bunny-alpha":{"draws":17,"losses":7,"wins":8},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":18,"wins":10},"thinkingmachines/inkling":{"draws":28,"losses":11,"wins":15},"thinkingmachines/inkling-small":{"draws":22,"losses":7,"wins":13},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":11,"losses":22,"wins":9},"x-ai/grok-4.6":{"draws":14,"losses":22,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":31,"losses":16,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":3,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":13,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":12,"wins":8},"z-ai/glm-5.2":{"draws":37,"losses":27,"wins":20},"z-ai/glm-5.3":{"draws":8,"losses":30,"wins":2},"z-ai/glm-5.3-flash":{"draws":14,"losses":20,"wins":8},"z-ai/glm-5.3-flashx":{"draws":16,"losses":19,"wins":7}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":10,"wins":24},"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":22,"losses":25,"wins":31},"claude-opus-4-8":{"draws":10,"losses":20,"wins":14},"claude-opus-5":{"draws":9,"losses":64,"wins":9},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":13,"losses":20,"wins":15},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":15,"wins":36},"deepseek/deepseek-v4-pro":{"draws":8,"losses":9,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":16,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":16,"wins":19},"fireworks/ember-1":{"draws":15,"losses":16,"wins":17},"gemini-3.1-pro-preview":{"draws":13,"losses":14,"wins":21},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":16,"losses":24,"wins":20},"google/gemini-3.5-flash-lite":{"draws":25,"losses":21,"wins":38},"google/gemini-3.6-flash":{"draws":23,"losses":38,"wins":31},"google/gemini-3.8-flash":{"draws":11,"losses":27,"wins":10},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":13},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":10,"wins":21},"gpt-5.4":{"draws":15,"losses":21,"wins":10},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":11},"gpt-5.4-nano":{"draws":5,"losses":15,"wins":28},"gpt-5.5":{"draws":15,"losses":23,"wins":6},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":19},"gpt-5.6-sol":{"draws":8,"losses":28,"wins":12},"gpt-5.6-terra":{"draws":14,"losses":17,"wins":15},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":12,"losses":20,"wins":16},"gpt-6-sol":{"draws":6,"losses":32,"wins":10},"gpt-6.1-sol":{"draws":5,"losses":42,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":2,"wins":16},"inclusionai/ling-3.0-flash":{"draws":11,"losses":7,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":15,"wins":28},"meta/muse-glimmer-30b":{"draws":12,"losses":11,"wins":19},"meta/muse-spark-1.2":{"draws":10,"losses":22,"wins":14},"meta/muse-spark-1.3":{"draws":9,"losses":27,"wins":12},"meta/muse-wonder":{"draws":14,"losses":23,"wins":11},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":17},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":1,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":6,"losses":23,"wins":17},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":7,"wins":22},"o3":{"draws":8,"losses":23,"wins":35},"openai/gpt-oss-120b":{"draws":14,"losses":10,"wins":18},"poolside/laguna-s-2.1":{"draws":12,"losses":18,"wins":16},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":15},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":24,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":17,"wins":7},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":13},"qwen/qwen3.8-max":{"draws":13,"losses":20,"wins":15},"qwen/qwen3.8-max-0902":{"draws":11,"losses":24,"wins":13},"stealth/ox-alpha":{"draws":35,"losses":79,"wins":44},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":10,"losses":21,"wins":15},"thinkingmachines/inkling":{"draws":19,"losses":10,"wins":35},"thinkingmachines/inkling-small":{"draws":16,"losses":2,"wins":30},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":12,"losses":19,"wins":17},"x-ai/grok-4.6":{"draws":11,"losses":27,"wins":10},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":29,"losses":12,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":8},"z-ai/glm-5.2":{"draws":31,"losses":29,"wins":36},"z-ai/glm-5.3":{"draws":11,"losses":27,"wins":8},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":18,"wins":19}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":26},"claude-fable-5":{"draws":6,"losses":29,"wins":13},"claude-fable-5-1":{"draws":0,"losses":53,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":21,"wins":14},"claude-opus-4-5":{"draws":16,"losses":20,"wins":42},"claude-opus-4-8":{"draws":12,"losses":13,"wins":19},"claude-opus-5":{"draws":6,"losses":67,"wins":9},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":14,"losses":11,"wins":23},"claude-sonnet-5-5":{"draws":7,"losses":24,"wins":17},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":12},"deepseek/deepseek-v4-flash":{"draws":16,"losses":15,"wins":41},"deepseek/deepseek-v4-pro":{"draws":10,"losses":13,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":9,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":24,"wins":15},"fireworks/ember-1":{"draws":10,"losses":13,"wins":25},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":27},"google/gemini-3.1-flash-lite":{"draws":7,"losses":5,"wins":20},"google/gemini-3.5-flash":{"draws":12,"losses":20,"wins":28},"google/gemini-3.5-flash-lite":{"draws":21,"losses":7,"wins":56},"google/gemini-3.6-flash":{"draws":18,"losses":35,"wins":39},"google/gemini-3.8-flash":{"draws":8,"losses":20,"wins":20},"google/gemma-4-31b-it":{"draws":12,"losses":0,"wins":16},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":10,"wins":26},"gpt-5.4":{"draws":8,"losses":19,"wins":19},"gpt-5.4-mini":{"draws":10,"losses":4,"wins":18},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":28},"gpt-5.5":{"draws":8,"losses":22,"wins":14},"gpt-5.6-luna":{"draws":16,"losses":8,"wins":24},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":12},"gpt-5.6-terra":{"draws":13,"losses":12,"wins":21},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":12,"losses":13,"wins":23},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":4,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":3,"wins":20},"inclusionai/ling-3.0-flash":{"draws":9,"losses":4,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":9,"wins":34},"meta/muse-glimmer-30b":{"draws":11,"losses":5,"wins":26},"meta/muse-spark-1.2":{"draws":10,"losses":15,"wins":21},"meta/muse-spark-1.3":{"draws":11,"losses":17,"wins":20},"meta/muse-wonder":{"draws":7,"losses":29,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"mistralai/mistral-large-4-0":{"draws":10,"losses":7,"wins":13},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":12,"losses":10,"wins":24},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":5,"wins":22},"o3":{"draws":8,"losses":12,"wins":46},"openai/gpt-oss-120b":{"draws":12,"losses":7,"wins":23},"poolside/laguna-s-2.1":{"draws":8,"losses":7,"wins":31},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":15},"qwen/qwen3.7-plus":{"draws":3,"losses":6,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":18,"wins":22},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":15},"qwen/qwen3.8-flash":{"draws":4,"losses":12,"wins":16},"qwen/qwen3.8-max":{"draws":11,"losses":14,"wins":23},"qwen/qwen3.8-max-0902":{"draws":11,"losses":16,"wins":21},"stealth/ox-alpha":{"draws":29,"losses":54,"wins":75},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":23},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":24},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":4,"losses":20,"wins":22},"thinkingmachines/inkling":{"draws":12,"losses":13,"wins":39},"thinkingmachines/inkling-small":{"draws":13,"losses":8,"wins":27},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":19,"wins":20},"x-ai/grok-4.6":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":28,"wins":11},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":22,"losses":9,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":19,"wins":11},"z-ai/glm-5.2":{"draws":22,"losses":29,"wins":45},"z-ai/glm-5.3":{"draws":7,"losses":26,"wins":13},"z-ai/glm-5.3-flash":{"draws":7,"losses":24,"wins":17},"z-ai/glm-5.3-flashx":{"draws":12,"losses":17,"wins":19}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":31},"claude-fable-5":{"draws":12,"losses":16,"wins":20},"claude-fable-5-1":{"draws":6,"losses":42,"wins":6},"claude-haiku-5-5":{"draws":14,"losses":11,"wins":21},"claude-opus-4-5":{"draws":15,"losses":12,"wins":51},"claude-opus-4-8":{"draws":7,"losses":11,"wins":26},"claude-opus-5":{"draws":7,"losses":56,"wins":19},"claude-opus-5-5":{"draws":4,"losses":41,"wins":7},"claude-sonnet-5":{"draws":13,"losses":7,"wins":28},"claude-sonnet-5-5":{"draws":8,"losses":20,"wins":20},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":15,"losses":1,"wins":56},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":6,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":11,"wins":15},"fireworks/ember-1":{"draws":11,"losses":10,"wins":27},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":25},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":13,"losses":8,"wins":39},"google/gemini-3.5-flash-lite":{"draws":14,"losses":7,"wins":63},"google/gemini-3.6-flash":{"draws":19,"losses":24,"wins":49},"google/gemini-3.8-flash":{"draws":8,"losses":10,"wins":30},"google/gemma-4-31b-it":{"draws":7,"losses":1,"wins":20},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":4,"wins":25},"gpt-5.4":{"draws":10,"losses":11,"wins":25},"gpt-5.4-mini":{"draws":11,"losses":2,"wins":19},"gpt-5.4-nano":{"draws":6,"losses":5,"wins":37},"gpt-5.5":{"draws":11,"losses":8,"wins":25},"gpt-5.6-luna":{"draws":12,"losses":3,"wins":33},"gpt-5.6-sol":{"draws":5,"losses":20,"wins":23},"gpt-5.6-terra":{"draws":16,"losses":4,"wins":26},"gpt-6-astra":{"draws":7,"losses":38,"wins":3},"gpt-6-luna":{"draws":11,"losses":7,"wins":30},"gpt-6-sol":{"draws":8,"losses":27,"wins":13},"gpt-6.1-sol":{"draws":2,"losses":37,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":21},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":27},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":3,"wins":38},"meta/muse-glimmer-30b":{"draws":12,"losses":3,"wins":27},"meta/muse-spark-1.2":{"draws":9,"losses":11,"wins":26},"meta/muse-spark-1.3":{"draws":10,"losses":12,"wins":26},"meta/muse-wonder":{"draws":12,"losses":17,"wins":19},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"mistralai/mistral-large-4-0":{"draws":9,"losses":6,"wins":15},"mistralai/mistral-medium-3-5":{"draws":8,"losses":0,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":31},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":3,"wins":27},"o3":{"draws":10,"losses":13,"wins":43},"openai/gpt-oss-120b":{"draws":6,"losses":2,"wins":34},"poolside/laguna-s-2.1":{"draws":13,"losses":3,"wins":30},"qwen/qwen3.7-max":{"draws":9,"losses":4,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":9,"wins":27},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":23},"qwen/qwen3.8-flash":{"draws":9,"losses":3,"wins":20},"qwen/qwen3.8-max":{"draws":11,"losses":11,"wins":26},"qwen/qwen3.8-max-0902":{"draws":12,"losses":10,"wins":26},"stealth/ox-alpha":{"draws":31,"losses":41,"wins":86},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":26},"stepfun/step-3.7-flash":{"draws":7,"losses":4,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":1,"wins":18},"tencent/hy4-preview":{"draws":9,"losses":13,"wins":24},"thinkingmachines/inkling":{"draws":17,"losses":4,"wins":43},"thinkingmachines/inkling-small":{"draws":10,"losses":3,"wins":35},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":6,"losses":13,"wins":29},"x-ai/grok-4.6":{"draws":10,"losses":12,"wins":26},"x-ai/grok-4.7":{"draws":1,"losses":24,"wins":17},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":16,"losses":3,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":5,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":23,"losses":10,"wins":63},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":12},"z-ai/glm-5.3-flash":{"draws":9,"losses":13,"wins":26},"z-ai/glm-5.3-flashx":{"draws":13,"losses":12,"wins":23}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":4,"wins":31},"claude-fable-5":{"draws":5,"losses":27,"wins":16},"claude-fable-5-1":{"draws":2,"losses":47,"wins":5},"claude-haiku-5-5":{"draws":8,"losses":14,"wins":24},"claude-opus-4-5":{"draws":18,"losses":13,"wins":47},"claude-opus-4-8":{"draws":10,"losses":11,"wins":23},"claude-opus-5":{"draws":8,"losses":49,"wins":25},"claude-opus-5-5":{"draws":3,"losses":43,"wins":6},"claude-sonnet-5":{"draws":10,"losses":8,"wins":30},"claude-sonnet-5-5":{"draws":8,"losses":20,"wins":20},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":16,"losses":6,"wins":50},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":7,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":9,"wins":27},"fireworks/ember-1":{"draws":7,"losses":6,"wins":19},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":30},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":11,"losses":14,"wins":35},"google/gemini-3.5-flash-lite":{"draws":21,"losses":11,"wins":52},"google/gemini-3.6-flash":{"draws":16,"losses":27,"wins":49},"google/gemini-3.8-flash":{"draws":11,"losses":15,"wins":22},"google/gemma-4-31b-it":{"draws":7,"losses":3,"wins":18},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":7,"wins":30},"gpt-5.4":{"draws":8,"losses":14,"wins":24},"gpt-5.4-mini":{"draws":9,"losses":2,"wins":21},"gpt-5.4-nano":{"draws":5,"losses":10,"wins":33},"gpt-5.5":{"draws":8,"losses":12,"wins":24},"gpt-5.6-luna":{"draws":9,"losses":10,"wins":29},"gpt-5.6-sol":{"draws":7,"losses":22,"wins":19},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":26},"gpt-6-astra":{"draws":4,"losses":40,"wins":4},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":9,"losses":28,"wins":11},"gpt-6.1-sol":{"draws":1,"losses":39,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":35},"meta/muse-glimmer-30b":{"draws":5,"losses":4,"wins":33},"meta/muse-spark-1.2":{"draws":11,"losses":9,"wins":26},"meta/muse-spark-1.3":{"draws":8,"losses":18,"wins":22},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":20},"mistralai/mistral-large-4-0":{"draws":6,"losses":8,"wins":16},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":8,"wins":29},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":29},"o3":{"draws":7,"losses":6,"wins":53},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":8,"losses":5,"wins":33},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":10,"wins":22},"qwen/qwen3.8-27b":{"draws":5,"losses":12,"wins":17},"qwen/qwen3.8-flash":{"draws":7,"losses":9,"wins":16},"qwen/qwen3.8-max":{"draws":11,"losses":12,"wins":25},"qwen/qwen3.8-max-0902":{"draws":8,"losses":15,"wins":25},"stealth/ox-alpha":{"draws":23,"losses":44,"wins":91},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":25},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":16},"tencent/hy4-preview":{"draws":8,"losses":15,"wins":23},"thinkingmachines/inkling":{"draws":12,"losses":2,"wins":50},"thinkingmachines/inkling-small":{"draws":12,"losses":1,"wins":35},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":8,"losses":20,"wins":20},"x-ai/grok-4.6":{"draws":8,"losses":17,"wins":23},"x-ai/grok-4.7":{"draws":2,"losses":29,"wins":11},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":18,"losses":5,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":17},"z-ai/glm-5.2":{"draws":19,"losses":15,"wins":62},"z-ai/glm-5.3":{"draws":6,"losses":26,"wins":14},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":25},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":24}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":31},"claude-fable-5":{"draws":4,"losses":26,"wins":18},"claude-fable-5-1":{"draws":1,"losses":48,"wins":5},"claude-haiku-5-5":{"draws":5,"losses":15,"wins":26},"claude-opus-4-5":{"draws":10,"losses":19,"wins":49},"claude-opus-4-8":{"draws":7,"losses":11,"wins":26},"claude-opus-5":{"draws":5,"losses":52,"wins":25},"claude-opus-5-5":{"draws":1,"losses":42,"wins":9},"claude-sonnet-5":{"draws":7,"losses":12,"wins":29},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":11,"losses":10,"wins":51},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":8,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":12,"wins":29},"fireworks/ember-1":{"draws":5,"losses":12,"wins":31},"gemini-3.1-pro-preview":{"draws":5,"losses":6,"wins":21},"google/gemini-3.1-flash-lite":{"draws":4,"losses":5,"wins":23},"google/gemini-3.5-flash":{"draws":9,"losses":15,"wins":36},"google/gemini-3.5-flash-lite":{"draws":13,"losses":11,"wins":60},"google/gemini-3.6-flash":{"draws":10,"losses":23,"wins":59},"google/gemini-3.8-flash":{"draws":6,"losses":15,"wins":27},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":21},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":4,"losses":5,"wins":33},"gpt-5.4":{"draws":3,"losses":16,"wins":27},"gpt-5.4-mini":{"draws":9,"losses":3,"wins":20},"gpt-5.4-nano":{"draws":7,"losses":8,"wins":33},"gpt-5.5":{"draws":5,"losses":18,"wins":21},"gpt-5.6-luna":{"draws":7,"losses":10,"wins":31},"gpt-5.6-sol":{"draws":4,"losses":20,"wins":24},"gpt-5.6-terra":{"draws":8,"losses":10,"wins":28},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":5,"losses":7,"wins":36},"gpt-6-sol":{"draws":5,"losses":26,"wins":17},"gpt-6.1-sol":{"draws":5,"losses":33,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":5,"wins":23},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":7,"wins":39},"meta/muse-glimmer-30b":{"draws":7,"losses":2,"wins":33},"meta/muse-spark-1.2":{"draws":9,"losses":9,"wins":28},"meta/muse-spark-1.3":{"draws":4,"losses":21,"wins":23},"meta/muse-wonder":{"draws":9,"losses":20,"wins":19},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":20},"mistralai/mistral-large-4-0":{"draws":5,"losses":6,"wins":19},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":6,"losses":15,"wins":25},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":5,"wins":30},"o3":{"draws":2,"losses":16,"wins":48},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":31},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":37},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":14,"wins":29},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":21},"qwen/qwen3.8-flash":{"draws":6,"losses":7,"wins":19},"qwen/qwen3.8-max":{"draws":11,"losses":13,"wins":24},"qwen/qwen3.8-max-0902":{"draws":9,"losses":16,"wins":23},"stealth/ox-alpha":{"draws":22,"losses":45,"wins":91},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":21},"tencent/hy4-preview":{"draws":2,"losses":15,"wins":29},"thinkingmachines/inkling":{"draws":13,"losses":8,"wins":43},"thinkingmachines/inkling-small":{"draws":7,"losses":6,"wins":35},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":8},"x-ai/grok-4.5":{"draws":7,"losses":16,"wins":25},"x-ai/grok-4.6":{"draws":10,"losses":17,"wins":21},"x-ai/grok-4.7":{"draws":5,"losses":23,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":10,"losses":7,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":14,"wins":14},"z-ai/glm-5.2":{"draws":12,"losses":19,"wins":65},"z-ai/glm-5.3":{"draws":6,"losses":17,"wins":23},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":27},"z-ai/glm-5.3-flashx":{"draws":9,"losses":15,"wins":24}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":7},"claude-fable-5":{"draws":4,"losses":25,"wins":1},"claude-fable-5-1":{"draws":2,"losses":32,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":19,"wins":4},"claude-opus-4-5":{"draws":11,"losses":36,"wins":3},"claude-opus-4-8":{"draws":6,"losses":22,"wins":2},"claude-opus-5":{"draws":6,"losses":38,"wins":2},"claude-opus-5-5":{"draws":2,"losses":32,"wins":0},"claude-sonnet-5":{"draws":10,"losses":18,"wins":2},"claude-sonnet-5-5":{"draws":3,"losses":24,"wins":3},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":15,"losses":19,"wins":10},"deepseek/deepseek-v4-pro":{"draws":8,"losses":18,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":15,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"wins":2},"fireworks/ember-1":{"draws":8,"losses":21,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":14,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":12,"losses":25,"wins":3},"google/gemini-3.5-flash-lite":{"draws":21,"losses":26,"wins":9},"google/gemini-3.6-flash":{"draws":13,"losses":41,"wins":4},"google/gemini-3.8-flash":{"draws":7,"losses":21,"wins":2},"google/gemma-4-31b-it":{"draws":8,"losses":8,"wins":4},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":15,"wins":1},"gpt-5.4":{"draws":8,"losses":17,"wins":5},"gpt-5.4-mini":{"draws":7,"losses":11,"wins":2},"gpt-5.4-nano":{"draws":6,"losses":20,"wins":6},"gpt-5.5":{"draws":8,"losses":18,"wins":2},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":9},"gpt-5.6-sol":{"draws":3,"losses":24,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":14,"wins":3},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":8,"losses":18,"wins":4},"gpt-6-sol":{"draws":3,"losses":27,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":29,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":8,"wins":7},"inclusionai/ling-3.0-flash":{"draws":10,"losses":4,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":15,"wins":11},"meta/muse-glimmer-30b":{"draws":12,"losses":6,"wins":8},"meta/muse-spark-1.2":{"draws":6,"losses":20,"wins":2},"meta/muse-spark-1.3":{"draws":5,"losses":21,"wins":4},"meta/muse-wonder":{"draws":1,"losses":28,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":6},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":7,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":1},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":8,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":9,"wins":7},"o3":{"draws":10,"losses":34,"wins":6},"openai/gpt-oss-120b":{"draws":10,"losses":7,"wins":9},"poolside/laguna-s-2.1":{"draws":10,"losses":11,"wins":5},"qwen/qwen3.7-max":{"draws":5,"losses":10,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":6,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":20,"wins":2},"qwen/qwen3.8-27b":{"draws":4,"losses":12,"wins":4},"qwen/qwen3.8-flash":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.8-max":{"draws":8,"losses":21,"wins":1},"qwen/qwen3.8-max-0902":{"draws":9,"losses":19,"wins":2},"stealth/ox-alpha":{"draws":21,"losses":57,"wins":8},"stealth/space-bunny-alpha":{"draws":10,"losses":11,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":12,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":4},"tencent/hy4-preview":{"draws":9,"losses":20,"wins":1},"thinkingmachines/inkling":{"draws":10,"losses":15,"wins":13},"thinkingmachines/inkling-small":{"draws":11,"losses":7,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":23,"wins":2},"x-ai/grok-4.6":{"draws":5,"losses":23,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":25,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":21,"losses":18,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":12,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":12,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":14,"wins":4},"z-ai/glm-5.2":{"draws":16,"losses":37,"wins":7},"z-ai/glm-5.3":{"draws":4,"losses":25,"wins":1},"z-ai/glm-5.3-flash":{"draws":6,"losses":18,"wins":6},"z-ai/glm-5.3-flashx":{"draws":7,"losses":20,"wins":3}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":8,"wins":31},"claude-fable-5":{"draws":7,"losses":26,"wins":15},"claude-fable-5-1":{"draws":3,"losses":45,"wins":6},"claude-haiku-5-5":{"draws":12,"losses":14,"wins":20},"claude-opus-4-5":{"draws":25,"losses":10,"wins":43},"claude-opus-4-8":{"draws":8,"losses":17,"wins":19},"claude-opus-5":{"draws":12,"losses":57,"wins":13},"claude-opus-5-5":{"draws":4,"losses":41,"wins":7},"claude-sonnet-5":{"draws":11,"losses":13,"wins":24},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":18},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":9,"losses":9,"wins":54},"deepseek/deepseek-v4-pro":{"draws":8,"losses":14,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":8,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":12,"wins":28},"fireworks/ember-1":{"draws":9,"losses":12,"wins":27},"gemini-3.1-pro-preview":{"draws":6,"losses":9,"wins":33},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":10,"losses":4,"wins":30},"google/gemini-3.5-flash-lite":{"draws":18,"losses":9,"wins":57},"google/gemini-3.6-flash":{"draws":14,"losses":22,"wins":56},"google/gemini-3.8-flash":{"draws":5,"losses":21,"wins":22},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":17},"gpt-4.1":{"draws":2,"losses":1,"wins":13},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":7,"losses":9,"wins":26},"gpt-5.4":{"draws":8,"losses":19,"wins":19},"gpt-5.4-mini":{"draws":10,"losses":3,"wins":19},"gpt-5.4-nano":{"draws":5,"losses":7,"wins":36},"gpt-5.5":{"draws":11,"losses":11,"wins":22},"gpt-5.6-luna":{"draws":8,"losses":9,"wins":31},"gpt-5.6-sol":{"draws":5,"losses":23,"wins":20},"gpt-5.6-terra":{"draws":14,"losses":11,"wins":21},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":7,"losses":13,"wins":28},"gpt-6-sol":{"draws":8,"losses":29,"wins":11},"gpt-6.1-sol":{"draws":4,"losses":33,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":23},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":28},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":45},"meta/muse-glimmer-30b":{"draws":10,"losses":3,"wins":29},"meta/muse-spark-1.2":{"draws":8,"losses":13,"wins":25},"meta/muse-spark-1.3":{"draws":7,"losses":20,"wins":21},"meta/muse-wonder":{"draws":9,"losses":25,"wins":14},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":20},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":6,"losses":16,"wins":24},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":4,"wins":29},"o3":{"draws":7,"losses":11,"wins":48},"openai/gpt-oss-120b":{"draws":11,"losses":3,"wins":28},"poolside/laguna-s-2.1":{"draws":2,"losses":5,"wins":39},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":14},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":14,"wins":25},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":22},"qwen/qwen3.8-flash":{"draws":6,"losses":5,"wins":21},"qwen/qwen3.8-max":{"draws":14,"losses":11,"wins":23},"qwen/qwen3.8-max-0902":{"draws":10,"losses":20,"wins":18},"stealth/ox-alpha":{"draws":29,"losses":47,"wins":82},"stealth/space-bunny-alpha":{"draws":8,"losses":3,"wins":27},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":17},"tencent/hy4-preview":{"draws":6,"losses":20,"wins":20},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":47},"thinkingmachines/inkling-small":{"draws":10,"losses":2,"wins":36},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":6,"losses":14,"wins":28},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":20},"x-ai/grok-4.7":{"draws":2,"losses":27,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":10,"losses":5,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":6,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":9,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":15},"z-ai/glm-5.2":{"draws":16,"losses":20,"wins":60},"z-ai/glm-5.3":{"draws":7,"losses":25,"wins":14},"z-ai/glm-5.3-flash":{"draws":4,"losses":19,"wins":25},"z-ai/glm-5.3-flashx":{"draws":11,"losses":19,"wins":18}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":24,"wins":25},"claude-fable-5":{"draws":12,"losses":56,"wins":10},"claude-fable-5-1":{"draws":6,"losses":84,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":48,"wins":11},"claude-opus-4-5":{"draws":35,"losses":55,"wins":36},"claude-opus-4-8":{"draws":15,"losses":45,"wins":10},"claude-opus-5":{"draws":12,"losses":105,"wins":11},"claude-opus-5-5":{"draws":8,"losses":74,"wins":0},"claude-sonnet-5":{"draws":19,"losses":37,"wins":22},"claude-sonnet-5-5":{"draws":16,"losses":48,"wins":14},"cohere/north-mini-code":{"draws":10,"losses":8,"wins":14},"deepseek/deepseek-v4-flash":{"draws":32,"losses":32,"wins":50},"deepseek/deepseek-v4-pro":{"draws":17,"losses":37,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":32,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":33,"wins":22},"fireworks/ember-1":{"draws":29,"losses":35,"wins":14},"gemini-3.1-pro-preview":{"draws":17,"losses":36,"wins":25},"google/gemini-3.1-flash-lite":{"draws":11,"losses":12,"wins":31},"google/gemini-3.5-flash":{"draws":23,"losses":48,"wins":27},"google/gemini-3.5-flash-lite":{"draws":32,"losses":42,"wins":40},"google/gemini-3.6-flash":{"draws":39,"losses":83,"wins":30},"google/gemini-3.8-flash":{"draws":11,"losses":60,"wins":7},"google/gemma-4-31b-it":{"draws":15,"losses":12,"wins":19},"gpt-4.1":{"draws":8,"losses":8,"wins":10},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":19,"losses":30,"wins":19},"gpt-5.4":{"draws":14,"losses":47,"wins":15},"gpt-5.4-mini":{"draws":18,"losses":16,"wins":18},"gpt-5.4-nano":{"draws":12,"losses":27,"wins":35},"gpt-5.5":{"draws":24,"losses":33,"wins":15},"gpt-5.6-luna":{"draws":26,"losses":27,"wins":25},"gpt-5.6-sol":{"draws":14,"losses":57,"wins":7},"gpt-5.6-terra":{"draws":22,"losses":35,"wins":17},"gpt-6-astra":{"draws":4,"losses":73,"wins":1},"gpt-6-luna":{"draws":22,"losses":40,"wins":16},"gpt-6-sol":{"draws":11,"losses":63,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":74,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":21,"losses":8,"wins":27},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":26},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":24,"wins":43},"meta/muse-glimmer-30b":{"draws":23,"losses":18,"wins":27},"meta/muse-spark-1.2":{"draws":17,"losses":42,"wins":15},"meta/muse-spark-1.3":{"draws":12,"losses":53,"wins":13},"meta/muse-wonder":{"draws":10,"losses":59,"wins":9},"minimax/minimax-m3":{"draws":12,"losses":15,"wins":13},"mistralai/mistral-large-4-0":{"draws":14,"losses":21,"wins":13},"mistralai/mistral-medium-3-5":{"draws":13,"losses":11,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":10,"wins":2},"moonshotai/kimi-k3":{"draws":18,"losses":39,"wins":17},"nex-agi/nex-n2-pro":{"draws":11,"losses":10,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":21,"wins":21},"o3":{"draws":17,"losses":61,"wins":32},"openai/gpt-oss-120b":{"draws":20,"losses":21,"wins":27},"poolside/laguna-s-2.1":{"draws":23,"losses":30,"wins":19},"qwen/qwen3.7-max":{"draws":9,"losses":19,"wins":16},"qwen/qwen3.7-plus":{"draws":10,"losses":11,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":38,"wins":18},"qwen/qwen3.8-27b":{"draws":9,"losses":34,"wins":13},"qwen/qwen3.8-flash":{"draws":15,"losses":28,"wins":9},"qwen/qwen3.8-max":{"draws":26,"losses":38,"wins":14},"qwen/qwen3.8-max-0902":{"draws":20,"losses":43,"wins":15},"stealth/ox-alpha":{"draws":45,"losses":163,"wins":60},"stealth/space-bunny-alpha":{"draws":13,"losses":30,"wins":21},"stepfun/step-3.7-flash":{"draws":13,"losses":19,"wins":24},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":17,"wins":12},"tencent/hy4-preview":{"draws":12,"losses":45,"wins":19},"thinkingmachines/inkling":{"draws":26,"losses":33,"wins":47},"thinkingmachines/inkling-small":{"draws":27,"losses":29,"wins":22},"unbiased/pareto-26.10-preview":{"draws":0,"losses":25,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":7,"wins":9},"x-ai/grok-4.5":{"draws":20,"losses":41,"wins":17},"x-ai/grok-4.6":{"draws":19,"losses":46,"wins":13},"x-ai/grok-4.7":{"draws":4,"losses":53,"wins":9},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.5":{"draws":38,"losses":38,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":15,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":33,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":38,"wins":9},"z-ai/glm-5.2":{"draws":43,"losses":66,"wins":47},"z-ai/glm-5.3":{"draws":10,"losses":59,"wins":7},"z-ai/glm-5.3-flash":{"draws":15,"losses":50,"wins":13},"z-ai/glm-5.3-flashx":{"draws":16,"losses":45,"wins":17}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":12,"wins":57},"claude-fable-5":{"draws":12,"losses":43,"wins":41},"claude-fable-5-1":{"draws":7,"losses":93,"wins":8},"claude-haiku-5-5":{"draws":22,"losses":24,"wins":46},"claude-opus-4-5":{"draws":39,"losses":27,"wins":90},"claude-opus-4-8":{"draws":16,"losses":30,"wins":42},"claude-opus-5":{"draws":27,"losses":103,"wins":34},"claude-opus-5-5":{"draws":14,"losses":83,"wins":7},"claude-sonnet-5":{"draws":13,"losses":22,"wins":61},"claude-sonnet-5-5":{"draws":21,"losses":34,"wins":41},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":29},"deepseek/deepseek-v4-flash":{"draws":23,"losses":7,"wins":114},"deepseek/deepseek-v4-pro":{"draws":18,"losses":20,"wins":50},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":18,"wins":51},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":26,"wins":48},"fireworks/ember-1":{"draws":23,"losses":26,"wins":47},"gemini-3.1-pro-preview":{"draws":16,"losses":25,"wins":55},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":54},"google/gemini-3.5-flash":{"draws":24,"losses":34,"wins":62},"google/gemini-3.5-flash-lite":{"draws":35,"losses":20,"wins":113},"google/gemini-3.6-flash":{"draws":25,"losses":41,"wins":86},"google/gemini-3.8-flash":{"draws":21,"losses":40,"wins":35},"google/gemma-4-31b-it":{"draws":15,"losses":2,"wins":39},"gpt-4.1":{"draws":6,"losses":6,"wins":20},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":9},"gpt-5":{"draws":10,"losses":20,"wins":54},"gpt-5.4":{"draws":18,"losses":34,"wins":40},"gpt-5.4-mini":{"draws":15,"losses":5,"wins":44},"gpt-5.4-nano":{"draws":13,"losses":12,"wins":71},"gpt-5.5":{"draws":20,"losses":25,"wins":43},"gpt-5.6-luna":{"draws":20,"losses":18,"wins":58},"gpt-5.6-sol":{"draws":16,"losses":42,"wins":38},"gpt-5.6-terra":{"draws":23,"losses":16,"wins":53},"gpt-6-astra":{"draws":5,"losses":79,"wins":12},"gpt-6-luna":{"draws":26,"losses":14,"wins":56},"gpt-6-sol":{"draws":14,"losses":55,"wins":27},"gpt-6.1-sol":{"draws":9,"losses":74,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":3,"wins":48},"inclusionai/ling-3.0-flash":{"draws":17,"losses":5,"wins":46},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":18,"losses":9,"wins":77},"meta/muse-glimmer-30b":{"draws":18,"losses":8,"wins":58},"meta/muse-spark-1.2":{"draws":16,"losses":28,"wins":48},"meta/muse-spark-1.3":{"draws":16,"losses":37,"wins":43},"meta/muse-wonder":{"draws":21,"losses":44,"wins":31},"minimax/minimax-m3":{"draws":7,"losses":9,"wins":36},"mistralai/mistral-large-4-0":{"draws":13,"losses":15,"wins":32},"mistralai/mistral-medium-3-5":{"draws":16,"losses":2,"wins":38},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":16},"moonshotai/kimi-k3":{"draws":22,"losses":20,"wins":50},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":38},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":9,"wins":60},"o3":{"draws":15,"losses":25,"wins":92},"openai/gpt-oss-120b":{"draws":15,"losses":8,"wins":61},"poolside/laguna-s-2.1":{"draws":20,"losses":13,"wins":59},"qwen/qwen3.7-max":{"draws":19,"losses":7,"wins":30},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":34},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":27,"wins":49},"qwen/qwen3.8-27b":{"draws":16,"losses":13,"wins":39},"qwen/qwen3.8-flash":{"draws":16,"losses":13,"wins":35},"qwen/qwen3.8-max":{"draws":22,"losses":19,"wins":55},"qwen/qwen3.8-max-0902":{"draws":27,"losses":34,"wins":35},"stealth/ox-alpha":{"draws":54,"losses":98,"wins":164},"stealth/space-bunny-alpha":{"draws":13,"losses":9,"wins":54},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":58},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":30},"tencent/hy4-preview":{"draws":18,"losses":22,"wins":52},"thinkingmachines/inkling":{"draws":33,"losses":16,"wins":79},"thinkingmachines/inkling-small":{"draws":22,"losses":5,"wins":69},"unbiased/pareto-26.10-preview":{"draws":2,"losses":25,"wins":5},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":19},"x-ai/grok-4.5":{"draws":19,"losses":32,"wins":45},"x-ai/grok-4.6":{"draws":21,"losses":31,"wins":44},"x-ai/grok-4.7":{"draws":8,"losses":55,"wins":21},"x-ai/grok-build-0.1":{"draws":9,"losses":1,"wins":22},"xiaomi/mimo-v2.5":{"draws":33,"losses":8,"wins":107},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":8,"wins":38},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":21,"wins":32},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":30,"wins":22},"z-ai/glm-5.2":{"draws":43,"losses":27,"wins":122},"z-ai/glm-5.3":{"draws":19,"losses":40,"wins":33},"z-ai/glm-5.3-flash":{"draws":13,"losses":40,"wins":43},"z-ai/glm-5.3-flashx":{"draws":26,"losses":34,"wins":36}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":4,"wins":34},"claude-fable-5":{"draws":7,"losses":23,"wins":18},"claude-fable-5-1":{"draws":4,"losses":44,"wins":6},"claude-haiku-5-5":{"draws":10,"losses":14,"wins":22},"claude-opus-4-5":{"draws":11,"losses":20,"wins":47},"claude-opus-4-8":{"draws":6,"losses":12,"wins":26},"claude-opus-5":{"draws":3,"losses":58,"wins":21},"claude-opus-5-5":{"draws":4,"losses":36,"wins":12},"claude-sonnet-5":{"draws":5,"losses":12,"wins":31},"claude-sonnet-5-5":{"draws":4,"losses":22,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":60},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":14,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":17,"wins":23},"fireworks/ember-1":{"draws":5,"losses":17,"wins":26},"gemini-3.1-pro-preview":{"draws":4,"losses":10,"wins":34},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":8,"losses":8,"wins":44},"google/gemini-3.5-flash-lite":{"draws":6,"losses":8,"wins":70},"google/gemini-3.6-flash":{"draws":13,"losses":23,"wins":56},"google/gemini-3.8-flash":{"draws":4,"losses":13,"wins":15},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":21},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":6,"losses":8,"wins":28},"gpt-5.4":{"draws":6,"losses":17,"wins":23},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":27},"gpt-5.4-nano":{"draws":8,"losses":9,"wins":31},"gpt-5.5":{"draws":9,"losses":17,"wins":18},"gpt-5.6-luna":{"draws":8,"losses":8,"wins":32},"gpt-5.6-sol":{"draws":4,"losses":20,"wins":24},"gpt-5.6-terra":{"draws":10,"losses":14,"wins":22},"gpt-6-astra":{"draws":6,"losses":38,"wins":4},"gpt-6-luna":{"draws":12,"losses":7,"wins":29},"gpt-6-sol":{"draws":7,"losses":26,"wins":15},"gpt-6.1-sol":{"draws":7,"losses":32,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":3,"wins":25},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":26},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":7,"losses":4,"wins":41},"meta/muse-glimmer-30b":{"draws":5,"losses":6,"wins":31},"meta/muse-spark-1.2":{"draws":3,"losses":13,"wins":30},"meta/muse-spark-1.3":{"draws":10,"losses":17,"wins":21},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":21},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":8,"losses":10,"wins":28},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":28},"o3":{"draws":7,"losses":10,"wins":49},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":36},"poolside/laguna-s-2.1":{"draws":5,"losses":3,"wins":38},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":14,"wins":29},"qwen/qwen3.8-27b":{"draws":2,"losses":7,"wins":25},"qwen/qwen3.8-flash":{"draws":5,"losses":10,"wins":17},"qwen/qwen3.8-max":{"draws":9,"losses":19,"wins":20},"qwen/qwen3.8-max-0902":{"draws":11,"losses":14,"wins":23},"stealth/ox-alpha":{"draws":24,"losses":42,"wins":92},"stealth/space-bunny-alpha":{"draws":6,"losses":8,"wins":24},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":26},"stepfun/step-5-preview":{"draws":1,"losses":0,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":20,"wins":20},"thinkingmachines/inkling":{"draws":10,"losses":7,"wins":47},"thinkingmachines/inkling-small":{"draws":10,"losses":10,"wins":28},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":4},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":4,"losses":22,"wins":22},"x-ai/grok-4.6":{"draws":6,"losses":16,"wins":26},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":9,"losses":14,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":5,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":8},"z-ai/glm-5.2":{"draws":14,"losses":17,"wins":65},"z-ai/glm-5.3":{"draws":10,"losses":24,"wins":12},"z-ai/glm-5.3-flash":{"draws":9,"losses":15,"wins":24},"z-ai/glm-5.3-flashx":{"draws":10,"losses":16,"wins":22}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":9,"wins":17},"claude-fable-5":{"draws":11,"losses":27,"wins":10},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":22,"wins":11},"claude-opus-4-5":{"draws":33,"losses":18,"wins":27},"claude-opus-4-8":{"draws":14,"losses":16,"wins":14},"claude-opus-5":{"draws":9,"losses":64,"wins":9},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":16,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":11,"losses":28,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":26,"losses":5,"wins":41},"deepseek/deepseek-v4-pro":{"draws":15,"losses":17,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":11,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":16,"wins":10},"fireworks/ember-1":{"draws":15,"losses":18,"wins":15},"gemini-3.1-pro-preview":{"draws":16,"losses":19,"wins":13},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":17,"losses":19,"wins":24},"google/gemini-3.5-flash-lite":{"draws":35,"losses":15,"wins":34},"google/gemini-3.6-flash":{"draws":27,"losses":40,"wins":25},"google/gemini-3.8-flash":{"draws":12,"losses":24,"wins":12},"google/gemma-4-31b-it":{"draws":13,"losses":1,"wins":14},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":4,"wins":13},"gpt-5.4":{"draws":10,"losses":22,"wins":14},"gpt-5.4-mini":{"draws":9,"losses":9,"wins":14},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":32},"gpt-5.5":{"draws":19,"losses":15,"wins":10},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":19},"gpt-5.6-sol":{"draws":10,"losses":31,"wins":7},"gpt-5.6-terra":{"draws":13,"losses":15,"wins":18},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":19,"losses":12,"wins":17},"gpt-6-sol":{"draws":9,"losses":33,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":44,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"wins":17},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":12,"wins":26},"meta/muse-glimmer-30b":{"draws":19,"losses":4,"wins":19},"meta/muse-spark-1.2":{"draws":13,"losses":18,"wins":15},"meta/muse-spark-1.3":{"draws":16,"losses":20,"wins":12},"meta/muse-wonder":{"draws":9,"losses":32,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":14},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":12,"losses":4,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":17,"losses":13,"wins":16},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":3,"wins":20},"o3":{"draws":11,"losses":22,"wins":33},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":20},"poolside/laguna-s-2.1":{"draws":19,"losses":13,"wins":14},"qwen/qwen3.7-max":{"draws":13,"losses":4,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":16,"wins":15},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":14},"qwen/qwen3.8-flash":{"draws":10,"losses":8,"wins":14},"qwen/qwen3.8-max":{"draws":24,"losses":11,"wins":13},"qwen/qwen3.8-max-0902":{"draws":15,"losses":20,"wins":13},"stealth/ox-alpha":{"draws":41,"losses":68,"wins":49},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":10,"losses":6,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":11},"tencent/hy4-preview":{"draws":16,"losses":15,"wins":15},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":36},"thinkingmachines/inkling-small":{"draws":20,"losses":5,"wins":23},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.6":{"draws":17,"losses":24,"wins":7},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":26,"losses":12,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":9},"z-ai/glm-5.2":{"draws":36,"losses":21,"wins":39},"z-ai/glm-5.3":{"draws":7,"losses":30,"wins":9},"z-ai/glm-5.3-flash":{"draws":12,"losses":24,"wins":12},"z-ai/glm-5.3-flashx":{"draws":19,"losses":13,"wins":16}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":28},"claude-fable-5":{"draws":10,"losses":13,"wins":19},"claude-fable-5-1":{"draws":5,"losses":35,"wins":8},"claude-haiku-5-5":{"draws":6,"losses":12,"wins":22},"claude-opus-4-5":{"draws":11,"losses":10,"wins":47},"claude-opus-4-8":{"draws":5,"losses":10,"wins":23},"claude-opus-5":{"draws":8,"losses":45,"wins":17},"claude-opus-5-5":{"draws":4,"losses":36,"wins":6},"claude-sonnet-5":{"draws":6,"losses":7,"wins":29},"claude-sonnet-5-5":{"draws":9,"losses":12,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":9,"losses":4,"wins":49},"deepseek/deepseek-v4-pro":{"draws":9,"losses":7,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":6,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":7,"wins":27},"fireworks/ember-1":{"draws":5,"losses":9,"wins":28},"gemini-3.1-pro-preview":{"draws":4,"losses":10,"wins":28},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":4,"losses":7,"wins":43},"google/gemini-3.5-flash-lite":{"draws":9,"losses":5,"wins":62},"google/gemini-3.6-flash":{"draws":15,"losses":12,"wins":55},"google/gemini-3.8-flash":{"draws":2,"losses":13,"wins":27},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":19},"gpt-4.1":{"draws":2,"losses":0,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":3,"wins":33},"gpt-5.4":{"draws":5,"losses":2,"wins":21},"gpt-5.4-mini":{"draws":7,"losses":0,"wins":21},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":36},"gpt-5.5":{"draws":9,"losses":9,"wins":22},"gpt-5.6-luna":{"draws":7,"losses":3,"wins":32},"gpt-5.6-sol":{"draws":7,"losses":15,"wins":20},"gpt-5.6-terra":{"draws":4,"losses":5,"wins":31},"gpt-6-astra":{"draws":2,"losses":35,"wins":5},"gpt-6-luna":{"draws":8,"losses":8,"wins":26},"gpt-6-sol":{"draws":2,"losses":29,"wins":11},"gpt-6.1-sol":{"draws":1,"losses":31,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":20},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":24},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":7,"losses":2,"wins":39},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":33},"meta/muse-spark-1.2":{"draws":5,"losses":11,"wins":24},"meta/muse-spark-1.3":{"draws":7,"losses":8,"wins":27},"meta/muse-wonder":{"draws":5,"losses":17,"wins":20},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":15},"mistralai/mistral-large-4-0":{"draws":4,"losses":3,"wins":19},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":5,"losses":8,"wins":27},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":26},"o3":{"draws":2,"losses":6,"wins":56},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":29},"poolside/laguna-s-2.1":{"draws":5,"losses":1,"wins":34},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":21},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":11,"wins":26},"qwen/qwen3.8-27b":{"draws":5,"losses":2,"wins":23},"qwen/qwen3.8-flash":{"draws":5,"losses":2,"wins":21},"qwen/qwen3.8-max":{"draws":7,"losses":11,"wins":24},"qwen/qwen3.8-max-0902":{"draws":5,"losses":10,"wins":27},"stealth/ox-alpha":{"draws":34,"losses":28,"wins":80},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":28},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":26},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":2,"wins":15},"tencent/hy4-preview":{"draws":5,"losses":8,"wins":29},"thinkingmachines/inkling":{"draws":11,"losses":8,"wins":39},"thinkingmachines/inkling-small":{"draws":8,"losses":3,"wins":31},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":3},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":9,"losses":8,"wins":25},"x-ai/grok-4.6":{"draws":9,"losses":9,"wins":24},"x-ai/grok-4.7":{"draws":3,"losses":21,"wins":12},"x-ai/grok-build-0.1":{"draws":1,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":10,"losses":2,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":10,"wins":14},"z-ai/glm-5.2":{"draws":18,"losses":11,"wins":55},"z-ai/glm-5.3":{"draws":4,"losses":17,"wins":19},"z-ai/glm-5.3-flash":{"draws":4,"losses":10,"wins":28},"z-ai/glm-5.3-flashx":{"draws":6,"losses":13,"wins":23}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":3,"wins":26},"claude-fable-5":{"draws":7,"losses":17,"wins":18},"claude-fable-5-1":{"draws":0,"losses":37,"wins":11},"claude-haiku-5-5":{"draws":9,"losses":9,"wins":22},"claude-opus-4-5":{"draws":15,"losses":9,"wins":44},"claude-opus-4-8":{"draws":7,"losses":7,"wins":24},"claude-opus-5":{"draws":5,"losses":34,"wins":31},"claude-opus-5-5":{"draws":2,"losses":35,"wins":9},"claude-sonnet-5":{"draws":7,"losses":7,"wins":28},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":17},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":12,"losses":2,"wins":48},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":6,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":8,"wins":22},"fireworks/ember-1":{"draws":8,"losses":8,"wins":26},"gemini-3.1-pro-preview":{"draws":8,"losses":5,"wins":29},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":10,"losses":11,"wins":33},"google/gemini-3.5-flash-lite":{"draws":18,"losses":6,"wins":52},"google/gemini-3.6-flash":{"draws":20,"losses":15,"wins":47},"google/gemini-3.8-flash":{"draws":12,"losses":7,"wins":23},"google/gemma-4-31b-it":{"draws":7,"losses":0,"wins":17},"gpt-4.1":{"draws":1,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":5,"wins":24},"gpt-5.4":{"draws":14,"losses":11,"wins":17},"gpt-5.4-mini":{"draws":9,"losses":1,"wins":18},"gpt-5.4-nano":{"draws":3,"losses":7,"wins":32},"gpt-5.5":{"draws":10,"losses":5,"wins":11},"gpt-5.6-luna":{"draws":11,"losses":5,"wins":26},"gpt-5.6-sol":{"draws":6,"losses":13,"wins":23},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":25},"gpt-6-astra":{"draws":0,"losses":37,"wins":5},"gpt-6-luna":{"draws":15,"losses":3,"wins":24},"gpt-6-sol":{"draws":4,"losses":23,"wins":15},"gpt-6.1-sol":{"draws":2,"losses":25,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":19},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":23},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":5,"wins":33},"meta/muse-glimmer-30b":{"draws":9,"losses":4,"wins":25},"meta/muse-spark-1.2":{"draws":4,"losses":7,"wins":29},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":24},"meta/muse-wonder":{"draws":8,"losses":14,"wins":20},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":15},"mistralai/mistral-large-4-0":{"draws":4,"losses":7,"wins":15},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":14,"wins":19},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":1,"wins":23},"o3":{"draws":7,"losses":7,"wins":50},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":25},"poolside/laguna-s-2.1":{"draws":8,"losses":4,"wins":28},"qwen/qwen3.7-max":{"draws":3,"losses":3,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":8,"wins":26},"qwen/qwen3.8-27b":{"draws":5,"losses":4,"wins":21},"qwen/qwen3.8-flash":{"draws":6,"losses":2,"wins":20},"qwen/qwen3.8-max":{"draws":11,"losses":9,"wins":22},"qwen/qwen3.8-max-0902":{"draws":9,"losses":11,"wins":22},"stealth/ox-alpha":{"draws":31,"losses":30,"wins":81},"stealth/space-bunny-alpha":{"draws":9,"losses":3,"wins":22},"stepfun/step-3.7-flash":{"draws":5,"losses":0,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":0,"wins":14},"tencent/hy4-preview":{"draws":11,"losses":10,"wins":21},"thinkingmachines/inkling":{"draws":9,"losses":5,"wins":44},"thinkingmachines/inkling-small":{"draws":10,"losses":2,"wins":30},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":12,"losses":6,"wins":24},"x-ai/grok-4.6":{"draws":12,"losses":11,"wins":19},"x-ai/grok-4.7":{"draws":4,"losses":17,"wins":15},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":1,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":4,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":13},"z-ai/glm-5.2":{"draws":24,"losses":7,"wins":53},"z-ai/glm-5.3":{"draws":7,"losses":23,"wins":10},"z-ai/glm-5.3-flash":{"draws":4,"losses":20,"wins":18},"z-ai/glm-5.3-flashx":{"draws":10,"losses":9,"wins":23}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":9,"wins":19},"claude-fable-5":{"draws":13,"losses":23,"wins":12},"claude-fable-5-1":{"draws":2,"losses":47,"wins":5},"claude-haiku-5-5":{"draws":14,"losses":17,"wins":15},"claude-opus-4-5":{"draws":30,"losses":17,"wins":31},"claude-opus-4-8":{"draws":15,"losses":10,"wins":19},"claude-opus-5":{"draws":8,"losses":64,"wins":10},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":14,"losses":13,"wins":21},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":15},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":28,"losses":3,"wins":41},"deepseek/deepseek-v4-pro":{"draws":13,"losses":9,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":7,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":14,"wins":13},"fireworks/ember-1":{"draws":18,"losses":8,"wins":22},"gemini-3.1-pro-preview":{"draws":14,"losses":13,"wins":21},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":21},"google/gemini-3.5-flash":{"draws":21,"losses":10,"wins":29},"google/gemini-3.5-flash-lite":{"draws":30,"losses":12,"wins":42},"google/gemini-3.6-flash":{"draws":24,"losses":32,"wins":36},"google/gemini-3.8-flash":{"draws":14,"losses":16,"wins":18},"google/gemma-4-31b-it":{"draws":12,"losses":2,"wins":14},"gpt-4.1":{"draws":8,"losses":0,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":7,"wins":21},"gpt-5.4":{"draws":19,"losses":18,"wins":9},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":30},"gpt-5.5":{"draws":18,"losses":13,"wins":13},"gpt-5.6-luna":{"draws":13,"losses":5,"wins":14},"gpt-5.6-sol":{"draws":10,"losses":24,"wins":14},"gpt-5.6-terra":{"draws":17,"losses":7,"wins":22},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":14,"losses":15,"wins":19},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":16,"losses":1,"wins":17},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":17},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":7,"wins":31},"meta/muse-glimmer-30b":{"draws":16,"losses":4,"wins":22},"meta/muse-spark-1.2":{"draws":9,"losses":20,"wins":17},"meta/muse-spark-1.3":{"draws":12,"losses":19,"wins":17},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":13},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":13,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":13,"wins":17},"nex-agi/nex-n2-pro":{"draws":7,"losses":1,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":1,"wins":22},"o3":{"draws":17,"losses":14,"wins":35},"openai/gpt-oss-120b":{"draws":19,"losses":4,"wins":19},"poolside/laguna-s-2.1":{"draws":19,"losses":5,"wins":22},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":11,"wins":20},"qwen/qwen3.8-27b":{"draws":11,"losses":10,"wins":13},"qwen/qwen3.8-flash":{"draws":10,"losses":11,"wins":11},"qwen/qwen3.8-max":{"draws":18,"losses":15,"wins":15},"qwen/qwen3.8-max-0902":{"draws":18,"losses":9,"wins":21},"stealth/ox-alpha":{"draws":44,"losses":57,"wins":57},"stealth/space-bunny-alpha":{"draws":16,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":18,"losses":12,"wins":16},"thinkingmachines/inkling":{"draws":21,"losses":5,"wins":38},"thinkingmachines/inkling-small":{"draws":19,"losses":6,"wins":23},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":9,"losses":14,"wins":25},"x-ai/grok-4.6":{"draws":13,"losses":20,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":29,"losses":3,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":6,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":8,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":10},"z-ai/glm-5.2":{"draws":39,"losses":23,"wins":34},"z-ai/glm-5.3":{"draws":10,"losses":27,"wins":9},"z-ai/glm-5.3-flash":{"draws":12,"losses":21,"wins":15},"z-ai/glm-5.3-flashx":{"draws":14,"losses":17,"wins":17}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":3,"wins":37},"claude-fable-5":{"draws":4,"losses":15,"wins":29},"claude-fable-5-1":{"draws":5,"losses":34,"wins":15},"claude-haiku-5-5":{"draws":7,"losses":5,"wins":34},"claude-opus-4-5":{"draws":6,"losses":16,"wins":56},"claude-opus-4-8":{"draws":5,"losses":5,"wins":34},"claude-opus-5":{"draws":8,"losses":40,"wins":34},"claude-opus-5-5":{"draws":6,"losses":31,"wins":15},"claude-sonnet-5":{"draws":0,"losses":3,"wins":45},"claude-sonnet-5-5":{"draws":2,"losses":15,"wins":31},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":3,"losses":3,"wins":66},"deepseek/deepseek-v4-pro":{"draws":1,"losses":4,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":2,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":4,"wins":39},"fireworks/ember-1":{"draws":5,"losses":8,"wins":35},"gemini-3.1-pro-preview":{"draws":5,"losses":1,"wins":42},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":2,"losses":8,"wins":50},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":78},"google/gemini-3.6-flash":{"draws":10,"losses":15,"wins":67},"google/gemini-3.8-flash":{"draws":4,"losses":10,"wins":34},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":25},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":0,"losses":3,"wins":39},"gpt-5.4":{"draws":2,"losses":12,"wins":32},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":27},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":46},"gpt-5.5":{"draws":5,"losses":11,"wins":28},"gpt-5.6-luna":{"draws":2,"losses":6,"wins":40},"gpt-5.6-sol":{"draws":2,"losses":3,"wins":27},"gpt-5.6-terra":{"draws":3,"losses":5,"wins":38},"gpt-6-astra":{"draws":6,"losses":36,"wins":6},"gpt-6-luna":{"draws":9,"losses":2,"wins":37},"gpt-6-sol":{"draws":6,"losses":17,"wins":25},"gpt-6.1-sol":{"draws":5,"losses":32,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":4,"wins":46},"meta/muse-glimmer-30b":{"draws":2,"losses":1,"wins":39},"meta/muse-spark-1.2":{"draws":2,"losses":2,"wins":42},"meta/muse-spark-1.3":{"draws":5,"losses":9,"wins":34},"meta/muse-wonder":{"draws":2,"losses":16,"wins":30},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"mistralai/mistral-large-4-0":{"draws":4,"losses":4,"wins":22},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":1,"losses":5,"wins":40},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":39},"o3":{"draws":1,"losses":8,"wins":57},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":37},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":44},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":6,"wins":38},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":27},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":26},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":42},"qwen/qwen3.8-max-0902":{"draws":2,"losses":7,"wins":39},"stealth/ox-alpha":{"draws":14,"losses":16,"wins":128},"stealth/space-bunny-alpha":{"draws":3,"losses":2,"wins":33},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":24},"tencent/hy4-preview":{"draws":3,"losses":14,"wins":29},"thinkingmachines/inkling":{"draws":2,"losses":4,"wins":58},"thinkingmachines/inkling-small":{"draws":1,"losses":1,"wins":46},"unbiased/pareto-26.10-preview":{"draws":2,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":4,"losses":5,"wins":39},"x-ai/grok-4.6":{"draws":6,"losses":12,"wins":30},"x-ai/grok-4.7":{"draws":5,"losses":18,"wins":19},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":7,"wins":22},"z-ai/glm-5.2":{"draws":5,"losses":4,"wins":87},"z-ai/glm-5.3":{"draws":6,"losses":13,"wins":27},"z-ai/glm-5.3-flash":{"draws":5,"losses":12,"wins":31},"z-ai/glm-5.3-flashx":{"draws":6,"losses":9,"wins":33}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":5,"wins":27},"claude-fable-5":{"draws":15,"losses":23,"wins":10},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":26,"losses":25,"wins":27},"claude-opus-4-8":{"draws":6,"losses":19,"wins":19},"claude-opus-5":{"draws":10,"losses":64,"wins":8},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":18,"losses":11,"wins":19},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":19,"losses":9,"wins":44},"deepseek/deepseek-v4-pro":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":10,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":20,"wins":9},"fireworks/ember-1":{"draws":15,"losses":14,"wins":19},"gemini-3.1-pro-preview":{"draws":15,"losses":14,"wins":19},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":20,"losses":10,"wins":30},"google/gemini-3.5-flash-lite":{"draws":23,"losses":11,"wins":50},"google/gemini-3.6-flash":{"draws":31,"losses":33,"wins":28},"google/gemini-3.8-flash":{"draws":12,"losses":22,"wins":14},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":11,"losses":11,"wins":20},"gpt-5.4":{"draws":12,"losses":20,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":5,"wins":15},"gpt-5.4-nano":{"draws":7,"losses":8,"wins":33},"gpt-5.5":{"draws":13,"losses":18,"wins":13},"gpt-5.6-luna":{"draws":14,"losses":13,"wins":21},"gpt-5.6-sol":{"draws":7,"losses":29,"wins":12},"gpt-5.6-terra":{"draws":9,"losses":11,"wins":10},"gpt-6-astra":{"draws":3,"losses":44,"wins":1},"gpt-6-luna":{"draws":13,"losses":17,"wins":18},"gpt-6-sol":{"draws":11,"losses":29,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.0-flash":{"draws":9,"losses":0,"wins":25},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":10,"wins":29},"meta/muse-glimmer-30b":{"draws":15,"losses":7,"wins":20},"meta/muse-spark-1.2":{"draws":12,"losses":22,"wins":12},"meta/muse-spark-1.3":{"draws":11,"losses":21,"wins":16},"meta/muse-wonder":{"draws":8,"losses":26,"wins":14},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":19},"mistralai/mistral-large-4-0":{"draws":15,"losses":8,"wins":7},"mistralai/mistral-medium-3-5":{"draws":9,"losses":3,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":15,"losses":11,"wins":20},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":6,"wins":25},"o3":{"draws":11,"losses":19,"wins":36},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":27},"poolside/laguna-s-2.1":{"draws":12,"losses":7,"wins":27},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":17},"qwen/qwen3.7-plus":{"draws":9,"losses":3,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":22,"wins":13},"qwen/qwen3.8-27b":{"draws":11,"losses":8,"wins":15},"qwen/qwen3.8-flash":{"draws":7,"losses":8,"wins":17},"qwen/qwen3.8-max":{"draws":18,"losses":17,"wins":13},"qwen/qwen3.8-max-0902":{"draws":10,"losses":21,"wins":17},"stealth/ox-alpha":{"draws":39,"losses":62,"wins":57},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":19},"stepfun/step-3.7-flash":{"draws":7,"losses":4,"wins":23},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":13},"tencent/hy4-preview":{"draws":10,"losses":18,"wins":18},"thinkingmachines/inkling":{"draws":16,"losses":9,"wins":39},"thinkingmachines/inkling-small":{"draws":13,"losses":5,"wins":30},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":13,"losses":20,"wins":15},"x-ai/grok-4.6":{"draws":14,"losses":26,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":29,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":25,"losses":2,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":14,"wins":11},"z-ai/glm-5.2":{"draws":37,"losses":21,"wins":38},"z-ai/glm-5.3":{"draws":13,"losses":22,"wins":11},"z-ai/glm-5.3-flash":{"draws":9,"losses":20,"wins":19},"z-ai/glm-5.3-flashx":{"draws":13,"losses":20,"wins":15}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":42},"claude-fable-5":{"draws":2,"losses":8,"wins":38},"claude-fable-5-1":{"draws":2,"losses":14,"wins":38},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":42},"claude-opus-4-5":{"draws":1,"losses":6,"wins":71},"claude-opus-4-8":{"draws":1,"losses":2,"wins":41},"claude-opus-5":{"draws":3,"losses":9,"wins":70},"claude-opus-5-5":{"draws":6,"losses":14,"wins":32},"claude-sonnet-5":{"draws":0,"losses":2,"wins":46},"claude-sonnet-5-5":{"draws":2,"losses":6,"wins":40},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":72},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":1,"wins":46},"fireworks/ember-1":{"draws":0,"losses":1,"wins":47},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":47},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":58},"google/gemini-3.5-flash-lite":{"draws":3,"losses":0,"wins":81},"google/gemini-3.6-flash":{"draws":2,"losses":4,"wins":86},"google/gemini-3.8-flash":{"draws":3,"losses":2,"wins":43},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":1,"wins":41},"gpt-5.4":{"draws":0,"losses":3,"wins":43},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":32},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":0,"losses":4,"wins":40},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":46},"gpt-5.6-sol":{"draws":4,"losses":2,"wins":42},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":46},"gpt-6-astra":{"draws":1,"losses":6,"wins":25},"gpt-6-luna":{"draws":3,"losses":0,"wins":45},"gpt-6-sol":{"draws":6,"losses":4,"wins":38},"gpt-6.1-sol":{"draws":5,"losses":7,"wins":36},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":52},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":46},"meta/muse-spark-1.3":{"draws":0,"losses":2,"wins":46},"meta/muse-wonder":{"draws":3,"losses":3,"wins":42},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"mistralai/mistral-large-4-0":{"draws":2,"losses":1,"wins":27},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":44},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":41},"o3":{"draws":1,"losses":1,"wins":64},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":42},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":46},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":28},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":1,"wins":46},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":33},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":30},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":47},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":46},"stealth/ox-alpha":{"draws":4,"losses":4,"wins":150},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":38},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":25},"tencent/hy4-preview":{"draws":0,"losses":3,"wins":43},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":62},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10-preview":{"draws":3,"losses":5,"wins":8},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":46},"x-ai/grok-4.6":{"draws":0,"losses":1,"wins":47},"x-ai/grok-4.7":{"draws":3,"losses":3,"wins":36},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":73},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":3,"wins":28},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":94},"z-ai/glm-5.3":{"draws":3,"losses":4,"wins":39},"z-ai/glm-5.3-flash":{"draws":3,"losses":1,"wins":44},"z-ai/glm-5.3-flashx":{"draws":0,"losses":3,"wins":45}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":13,"wins":24},"claude-fable-5":{"draws":9,"losses":26,"wins":13},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":5,"losses":20,"wins":21},"claude-opus-4-5":{"draws":18,"losses":22,"wins":38},"claude-opus-4-8":{"draws":7,"losses":17,"wins":20},"claude-opus-5":{"draws":11,"losses":60,"wins":11},"claude-opus-5-5":{"draws":8,"losses":43,"wins":1},"claude-sonnet-5":{"draws":8,"losses":14,"wins":26},"claude-sonnet-5-5":{"draws":6,"losses":21,"wins":21},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":10,"losses":13,"wins":49},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":12,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":19,"wins":21},"fireworks/ember-1":{"draws":6,"losses":21,"wins":21},"gemini-3.1-pro-preview":{"draws":3,"losses":22,"wins":23},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":28},"google/gemini-3.5-flash":{"draws":10,"losses":21,"wins":29},"google/gemini-3.5-flash-lite":{"draws":12,"losses":19,"wins":53},"google/gemini-3.6-flash":{"draws":16,"losses":36,"wins":40},"google/gemini-3.8-flash":{"draws":9,"losses":21,"wins":18},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":19},"gpt-4.1":{"draws":1,"losses":6,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":14,"wins":23},"gpt-5.4":{"draws":11,"losses":18,"wins":17},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":3,"losses":13,"wins":32},"gpt-5.5":{"draws":9,"losses":18,"wins":17},"gpt-5.6-luna":{"draws":9,"losses":11,"wins":28},"gpt-5.6-sol":{"draws":11,"losses":26,"wins":11},"gpt-5.6-terra":{"draws":8,"losses":14,"wins":24},"gpt-6-astra":{"draws":8,"losses":36,"wins":4},"gpt-6-luna":{"draws":5,"losses":13,"wins":14},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":39,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":24},"inclusionai/ling-3.0-flash":{"draws":2,"losses":6,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":8,"wins":39},"meta/muse-glimmer-30b":{"draws":4,"losses":8,"wins":30},"meta/muse-spark-1.2":{"draws":11,"losses":17,"wins":18},"meta/muse-spark-1.3":{"draws":8,"losses":20,"wins":20},"meta/muse-wonder":{"draws":7,"losses":26,"wins":15},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":18},"mistralai/mistral-large-4-0":{"draws":5,"losses":9,"wins":16},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":16,"wins":22},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":9,"wins":31},"o3":{"draws":2,"losses":20,"wins":44},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":29},"poolside/laguna-s-2.1":{"draws":4,"losses":14,"wins":28},"qwen/qwen3.7-max":{"draws":2,"losses":8,"wins":18},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-27b":{"draws":3,"losses":9,"wins":22},"qwen/qwen3.8-flash":{"draws":3,"losses":8,"wins":21},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":25},"qwen/qwen3.8-max-0902":{"draws":9,"losses":16,"wins":23},"stealth/ox-alpha":{"draws":30,"losses":57,"wins":71},"stealth/space-bunny-alpha":{"draws":7,"losses":8,"wins":23},"stepfun/step-3.7-flash":{"draws":4,"losses":8,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":20,"wins":20},"thinkingmachines/inkling":{"draws":8,"losses":11,"wins":45},"thinkingmachines/inkling-small":{"draws":4,"losses":10,"wins":34},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":21,"wins":19},"x-ai/grok-4.6":{"draws":11,"losses":26,"wins":11},"x-ai/grok-4.7":{"draws":3,"losses":29,"wins":10},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":13,"losses":14,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":11,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":18,"wins":10},"z-ai/glm-5.2":{"draws":20,"losses":27,"wins":49},"z-ai/glm-5.3":{"draws":7,"losses":27,"wins":12},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":9,"losses":17,"wins":22}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":7,"wins":36},"claude-fable-5":{"draws":4,"losses":10,"wins":34},"claude-fable-5-1":{"draws":4,"losses":24,"wins":26},"claude-haiku-5-5":{"draws":5,"losses":8,"wins":33},"claude-opus-4-5":{"draws":3,"losses":11,"wins":64},"claude-opus-4-8":{"draws":3,"losses":10,"wins":31},"claude-opus-5":{"draws":12,"losses":25,"wins":45},"claude-opus-5-5":{"draws":6,"losses":27,"wins":19},"claude-sonnet-5":{"draws":1,"losses":6,"wins":41},"claude-sonnet-5-5":{"draws":5,"losses":10,"wins":33},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":7,"wins":61},"deepseek/deepseek-v4-pro":{"draws":2,"losses":8,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":6,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":7,"wins":36},"fireworks/ember-1":{"draws":3,"losses":6,"wins":39},"gemini-3.1-pro-preview":{"draws":6,"losses":7,"wins":35},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":28},"google/gemini-3.5-flash":{"draws":6,"losses":8,"wins":46},"google/gemini-3.5-flash-lite":{"draws":4,"losses":10,"wins":70},"google/gemini-3.6-flash":{"draws":6,"losses":17,"wins":69},"google/gemini-3.8-flash":{"draws":4,"losses":6,"wins":38},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":26},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":6,"wins":36},"gpt-5.4":{"draws":3,"losses":6,"wins":37},"gpt-5.4-mini":{"draws":1,"losses":4,"wins":27},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":42},"gpt-5.5":{"draws":3,"losses":7,"wins":34},"gpt-5.6-luna":{"draws":1,"losses":6,"wins":41},"gpt-5.6-sol":{"draws":3,"losses":8,"wins":37},"gpt-5.6-terra":{"draws":2,"losses":7,"wins":37},"gpt-6-astra":{"draws":4,"losses":32,"wins":12},"gpt-6-luna":{"draws":6,"losses":4,"wins":38},"gpt-6-sol":{"draws":3,"losses":9,"wins":20},"gpt-6.1-sol":{"draws":5,"losses":23,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":2,"wins":31},"inclusionai/ling-3.0-flash":{"draws":4,"losses":5,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":5,"wins":45},"meta/muse-glimmer-30b":{"draws":2,"losses":6,"wins":34},"meta/muse-spark-1.2":{"draws":2,"losses":6,"wins":38},"meta/muse-spark-1.3":{"draws":2,"losses":6,"wins":40},"meta/muse-wonder":{"draws":2,"losses":8,"wins":38},"minimax/minimax-m3":{"draws":1,"losses":4,"wins":21},"mistralai/mistral-large-4-0":{"draws":3,"losses":5,"wins":22},"mistralai/mistral-medium-3-5":{"draws":1,"losses":1,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":0,"losses":7,"wins":39},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":36},"o3":{"draws":0,"losses":9,"wins":57},"openai/gpt-oss-120b":{"draws":2,"losses":4,"wins":36},"poolside/laguna-s-2.1":{"draws":1,"losses":6,"wins":39},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":21},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":8,"wins":38},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":27},"qwen/qwen3.8-flash":{"draws":1,"losses":5,"wins":26},"qwen/qwen3.8-max":{"draws":0,"losses":8,"wins":40},"qwen/qwen3.8-max-0902":{"draws":0,"losses":9,"wins":39},"stealth/ox-alpha":{"draws":13,"losses":20,"wins":125},"stealth/space-bunny-alpha":{"draws":0,"losses":4,"wins":34},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":30},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":22},"tencent/hy4-preview":{"draws":4,"losses":6,"wins":36},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":55},"thinkingmachines/inkling-small":{"draws":1,"losses":2,"wins":45},"unbiased/pareto-26.10-preview":{"draws":2,"losses":9,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":1,"losses":10,"wins":37},"x-ai/grok-4.6":{"draws":2,"losses":6,"wins":40},"x-ai/grok-4.7":{"draws":5,"losses":12,"wins":25},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":14},"xiaomi/mimo-v2.5":{"draws":5,"losses":10,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":3,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":23},"z-ai/glm-5.2":{"draws":5,"losses":13,"wins":78},"z-ai/glm-5.3":{"draws":5,"losses":12,"wins":29},"z-ai/glm-5.3-flash":{"draws":4,"losses":10,"wins":34},"z-ai/glm-5.3-flashx":{"draws":6,"losses":6,"wins":36}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":44},"claude-fable-5":{"draws":3,"losses":5,"wins":40},"claude-fable-5-1":{"draws":6,"losses":16,"wins":32},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":42},"claude-opus-4-5":{"draws":0,"losses":2,"wins":76},"claude-opus-4-8":{"draws":1,"losses":1,"wins":42},"claude-opus-5":{"draws":7,"losses":14,"wins":61},"claude-opus-5-5":{"draws":5,"losses":22,"wins":25},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":2,"losses":7,"wins":39},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":71},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":5,"wins":42},"fireworks/ember-1":{"draws":0,"losses":2,"wins":46},"gemini-3.1-pro-preview":{"draws":0,"losses":2,"wins":46},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":1,"losses":4,"wins":55},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":84},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":82},"google/gemini-3.8-flash":{"draws":3,"losses":3,"wins":42},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":1,"wins":41},"gpt-5.4":{"draws":3,"losses":6,"wins":37},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":31},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":47},"gpt-5.5":{"draws":1,"losses":5,"wins":38},"gpt-5.6-luna":{"draws":0,"losses":3,"wins":45},"gpt-5.6-sol":{"draws":2,"losses":8,"wins":38},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":44},"gpt-6-astra":{"draws":8,"losses":16,"wins":24},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":5,"losses":4,"wins":39},"gpt-6.1-sol":{"draws":2,"losses":7,"wins":23},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":51},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":42},"meta/muse-spark-1.3":{"draws":2,"losses":0,"wins":46},"meta/muse-wonder":{"draws":4,"losses":4,"wins":40},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"mistralai/mistral-large-4-0":{"draws":2,"losses":1,"wins":27},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":42},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":40},"o3":{"draws":0,"losses":2,"wins":64},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":41},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":46},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":28},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":32},"qwen/qwen3.8-flash":{"draws":0,"losses":2,"wins":30},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":47},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":45},"stealth/ox-alpha":{"draws":3,"losses":4,"wins":151},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":38},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":26},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":41},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":62},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10-preview":{"draws":1,"losses":6,"wins":9},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":46},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":42},"x-ai/grok-4.7":{"draws":1,"losses":5,"wins":36},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":2,"wins":27},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":94},"z-ai/glm-5.3":{"draws":6,"losses":3,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":2,"wins":43},"z-ai/glm-5.3-flashx":{"draws":2,"losses":4,"wins":42}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":11,"wins":7},"claude-fable-5":{"draws":9,"losses":27,"wins":0},"claude-fable-5-1":{"draws":2,"losses":38,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":27,"wins":0},"claude-opus-4-5":{"draws":28,"losses":30,"wins":2},"claude-opus-4-8":{"draws":10,"losses":24,"wins":2},"claude-opus-5":{"draws":11,"losses":45,"wins":2},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":12,"losses":23,"wins":1},"claude-sonnet-5-5":{"draws":11,"losses":24,"wins":1},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":2},"deepseek/deepseek-v4-flash":{"draws":25,"losses":26,"wins":5},"deepseek/deepseek-v4-pro":{"draws":13,"losses":17,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":17,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":18,"wins":2},"fireworks/ember-1":{"draws":15,"losses":20,"wins":1},"gemini-3.1-pro-preview":{"draws":16,"losses":15,"wins":5},"google/gemini-3.1-flash-lite":{"draws":12,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":20,"losses":25,"wins":1},"google/gemini-3.5-flash-lite":{"draws":30,"losses":27,"wins":5},"google/gemini-3.6-flash":{"draws":26,"losses":39,"wins":3},"google/gemini-3.8-flash":{"draws":9,"losses":26,"wins":1},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":8},"gpt-4.1":{"draws":5,"losses":5,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":13,"losses":16,"wins":1},"gpt-5.4":{"draws":13,"losses":21,"wins":0},"gpt-5.4-mini":{"draws":9,"losses":10,"wins":5},"gpt-5.4-nano":{"draws":15,"losses":19,"wins":4},"gpt-5.5":{"draws":13,"losses":17,"wins":2},"gpt-5.6-luna":{"draws":19,"losses":11,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":0},"gpt-5.6-terra":{"draws":12,"losses":22,"wins":2},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":17,"losses":17,"wins":2},"gpt-6-sol":{"draws":4,"losses":30,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":13,"losses":10,"wins":7},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":17,"wins":4},"meta/muse-glimmer-30b":{"draws":16,"losses":10,"wins":4},"meta/muse-spark-1.2":{"draws":12,"losses":20,"wins":2},"meta/muse-spark-1.3":{"draws":12,"losses":21,"wins":3},"meta/muse-wonder":{"draws":8,"losses":28,"wins":0},"minimax/minimax-m3":{"draws":12,"losses":7,"wins":1},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":3},"mistralai/mistral-medium-3-5":{"draws":10,"losses":6,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":0},"moonshotai/kimi-k3":{"draws":18,"losses":12,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":10,"wins":8},"o3":{"draws":11,"losses":37,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":9,"wins":9},"poolside/laguna-s-2.1":{"draws":16,"losses":10,"wins":4},"qwen/qwen3.7-max":{"draws":10,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":17,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":11,"losses":11,"wins":2},"qwen/qwen3.8-max":{"draws":17,"losses":17,"wins":2},"qwen/qwen3.8-max-0902":{"draws":17,"losses":16,"wins":3},"stealth/ox-alpha":{"draws":34,"losses":57,"wins":9},"stealth/space-bunny-alpha":{"draws":16,"losses":11,"wins":1},"stepfun/step-3.7-flash":{"draws":10,"losses":13,"wins":3},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":3},"tencent/hy4-preview":{"draws":14,"losses":19,"wins":1},"thinkingmachines/inkling":{"draws":17,"losses":20,"wins":7},"thinkingmachines/inkling-small":{"draws":18,"losses":13,"wins":5},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":12,"losses":24,"wins":0},"x-ai/grok-4.6":{"draws":12,"losses":22,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":29,"losses":27,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":10,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":15,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":0},"z-ai/glm-5.2":{"draws":32,"losses":34,"wins":6},"z-ai/glm-5.3":{"draws":10,"losses":24,"wins":0},"z-ai/glm-5.3-flash":{"draws":9,"losses":23,"wins":4},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":2}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":8,"wins":15},"claude-fable-5":{"draws":8,"losses":32,"wins":2},"claude-fable-5-1":{"draws":3,"losses":43,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":17,"wins":8},"claude-opus-4-5":{"draws":28,"losses":27,"wins":13},"claude-opus-4-8":{"draws":12,"losses":18,"wins":8},"claude-opus-5":{"draws":8,"losses":66,"wins":6},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":15,"losses":18,"wins":9},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":12},"cohere/north-mini-code":{"draws":8,"losses":3,"wins":5},"deepseek/deepseek-v4-flash":{"draws":32,"losses":10,"wins":20},"deepseek/deepseek-v4-pro":{"draws":12,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":16,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":14,"wins":9},"fireworks/ember-1":{"draws":16,"losses":17,"wins":9},"gemini-3.1-pro-preview":{"draws":16,"losses":18,"wins":8},"google/gemini-3.1-flash-lite":{"draws":13,"losses":2,"wins":11},"google/gemini-3.5-flash":{"draws":19,"losses":21,"wins":12},"google/gemini-3.5-flash-lite":{"draws":29,"losses":21,"wins":22},"google/gemini-3.6-flash":{"draws":29,"losses":31,"wins":20},"google/gemini-3.8-flash":{"draws":11,"losses":25,"wins":6},"google/gemma-4-31b-it":{"draws":15,"losses":4,"wins":5},"gpt-4.1":{"draws":7,"losses":4,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":18,"losses":12,"wins":8},"gpt-5.4":{"draws":11,"losses":22,"wins":7},"gpt-5.4-mini":{"draws":17,"losses":7,"wins":4},"gpt-5.4-nano":{"draws":16,"losses":9,"wins":15},"gpt-5.5":{"draws":21,"losses":16,"wins":3},"gpt-5.6-luna":{"draws":20,"losses":10,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":30,"wins":5},"gpt-5.6-terra":{"draws":20,"losses":15,"wins":5},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":17,"losses":17,"wins":8},"gpt-6-sol":{"draws":4,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":9},"inclusionai/ling-3.0-flash":{"draws":19,"losses":6,"wins":3},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":6,"wins":17},"meta/muse-glimmer-30b":{"draws":15,"losses":2,"wins":9},"meta/muse-spark-1.2":{"draws":13,"losses":21,"wins":8},"meta/muse-spark-1.3":{"draws":14,"losses":20,"wins":8},"meta/muse-wonder":{"draws":12,"losses":25,"wins":5},"minimax/minimax-m3":{"draws":12,"losses":4,"wins":8},"mistralai/mistral-large-4-0":{"draws":10,"losses":11,"wins":7},"mistralai/mistral-medium-3-5":{"draws":14,"losses":1,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":15,"losses":19,"wins":8},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":5,"wins":10},"o3":{"draws":13,"losses":27,"wins":14},"openai/gpt-oss-120b":{"draws":16,"losses":10,"wins":12},"poolside/laguna-s-2.1":{"draws":19,"losses":12,"wins":11},"qwen/qwen3.7-max":{"draws":11,"losses":4,"wins":9},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":14,"wins":9},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":5},"qwen/qwen3.8-flash":{"draws":12,"losses":7,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":11},"qwen/qwen3.8-max-0902":{"draws":16,"losses":20,"wins":6},"stealth/ox-alpha":{"draws":35,"losses":80,"wins":27},"stealth/space-bunny-alpha":{"draws":14,"losses":7,"wins":13},"stepfun/step-3.7-flash":{"draws":9,"losses":3,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":5},"tencent/hy4-preview":{"draws":16,"losses":18,"wins":6},"thinkingmachines/inkling":{"draws":21,"losses":14,"wins":23},"thinkingmachines/inkling-small":{"draws":22,"losses":3,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":13,"losses":23,"wins":6},"x-ai/grok-4.6":{"draws":12,"losses":26,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":30,"wins":6},"x-ai/grok-build-0.1":{"draws":8,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":26,"losses":10,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":4,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":13,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":6},"z-ai/glm-5.2":{"draws":41,"losses":28,"wins":15},"z-ai/glm-5.3":{"draws":12,"losses":23,"wins":5},"z-ai/glm-5.3-flash":{"draws":11,"losses":24,"wins":7},"z-ai/glm-5.3-flashx":{"draws":12,"losses":20,"wins":10}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":9,"wins":29},"claude-fable-5":{"draws":8,"losses":26,"wins":14},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":8,"losses":19,"wins":19},"claude-opus-4-5":{"draws":18,"losses":18,"wins":42},"claude-opus-4-8":{"draws":8,"losses":14,"wins":22},"claude-opus-5":{"draws":13,"losses":60,"wins":9},"claude-opus-5-5":{"draws":4,"losses":43,"wins":5},"claude-sonnet-5":{"draws":11,"losses":7,"wins":30},"claude-sonnet-5-5":{"draws":6,"losses":21,"wins":21},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":9,"wins":50},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":9,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":16,"wins":21},"fireworks/ember-1":{"draws":12,"losses":15,"wins":21},"gemini-3.1-pro-preview":{"draws":10,"losses":14,"wins":24},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":10,"losses":17,"wins":33},"google/gemini-3.5-flash-lite":{"draws":16,"losses":15,"wins":53},"google/gemini-3.6-flash":{"draws":16,"losses":30,"wins":46},"google/gemini-3.8-flash":{"draws":7,"losses":18,"wins":23},"google/gemma-4-31b-it":{"draws":5,"losses":5,"wins":18},"gpt-4.1":{"draws":7,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":6,"losses":5,"wins":31},"gpt-5.4":{"draws":9,"losses":20,"wins":17},"gpt-5.4-mini":{"draws":7,"losses":7,"wins":18},"gpt-5.4-nano":{"draws":6,"losses":15,"wins":27},"gpt-5.5":{"draws":8,"losses":20,"wins":16},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":25},"gpt-5.6-sol":{"draws":7,"losses":26,"wins":15},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":24},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":11,"losses":11,"wins":26},"gpt-6-sol":{"draws":7,"losses":31,"wins":10},"gpt-6.1-sol":{"draws":3,"losses":34,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":6,"wins":18},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":3,"wins":43},"meta/muse-glimmer-30b":{"draws":9,"losses":5,"wins":28},"meta/muse-spark-1.2":{"draws":7,"losses":8,"wins":15},"meta/muse-spark-1.3":{"draws":6,"losses":21,"wins":21},"meta/muse-wonder":{"draws":9,"losses":21,"wins":18},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":19},"mistralai/mistral-medium-3-5":{"draws":5,"losses":4,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":8,"losses":15,"wins":23},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":9,"wins":26},"o3":{"draws":6,"losses":21,"wins":39},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":26},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":34},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-27b":{"draws":5,"losses":9,"wins":20},"qwen/qwen3.8-flash":{"draws":5,"losses":6,"wins":21},"qwen/qwen3.8-max":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-max-0902":{"draws":7,"losses":16,"wins":25},"stealth/ox-alpha":{"draws":30,"losses":57,"wins":71},"stealth/space-bunny-alpha":{"draws":9,"losses":10,"wins":19},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":17},"tencent/hy4-preview":{"draws":4,"losses":18,"wins":24},"thinkingmachines/inkling":{"draws":14,"losses":12,"wins":38},"thinkingmachines/inkling-small":{"draws":10,"losses":9,"wins":29},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":11,"losses":20,"wins":17},"x-ai/grok-4.6":{"draws":10,"losses":22,"wins":16},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":18,"losses":7,"wins":49},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":8,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":13},"z-ai/glm-5.2":{"draws":20,"losses":24,"wins":52},"z-ai/glm-5.3":{"draws":6,"losses":19,"wins":21},"z-ai/glm-5.3-flash":{"draws":5,"losses":18,"wins":25},"z-ai/glm-5.3-flashx":{"draws":10,"losses":19,"wins":19}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":6,"wins":33},"claude-fable-5":{"draws":6,"losses":21,"wins":21},"claude-fable-5-1":{"draws":4,"losses":41,"wins":9},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":12,"losses":11,"wins":55},"claude-opus-4-8":{"draws":7,"losses":10,"wins":27},"claude-opus-5":{"draws":11,"losses":51,"wins":20},"claude-opus-5-5":{"draws":1,"losses":42,"wins":9},"claude-sonnet-5":{"draws":6,"losses":8,"wins":34},"claude-sonnet-5-5":{"draws":5,"losses":19,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":8,"losses":2,"wins":62},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":9,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":11,"wins":29},"fireworks/ember-1":{"draws":8,"losses":7,"wins":33},"gemini-3.1-pro-preview":{"draws":6,"losses":11,"wins":31},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":25},"google/gemini-3.5-flash":{"draws":9,"losses":11,"wins":40},"google/gemini-3.5-flash-lite":{"draws":11,"losses":5,"wins":68},"google/gemini-3.6-flash":{"draws":11,"losses":21,"wins":60},"google/gemini-3.8-flash":{"draws":10,"losses":16,"wins":22},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":21},"gpt-4.1":{"draws":6,"losses":0,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":2,"wins":31},"gpt-5.4":{"draws":11,"losses":13,"wins":22},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":29},"gpt-5.4-nano":{"draws":4,"losses":7,"wins":37},"gpt-5.5":{"draws":6,"losses":12,"wins":26},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":33},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":28},"gpt-5.6-terra":{"draws":7,"losses":8,"wins":31},"gpt-6-astra":{"draws":5,"losses":36,"wins":7},"gpt-6-luna":{"draws":6,"losses":6,"wins":36},"gpt-6-sol":{"draws":8,"losses":27,"wins":13},"gpt-6.1-sol":{"draws":4,"losses":39,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":3,"wins":27},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":30},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":7,"losses":8,"wins":37},"meta/muse-glimmer-30b":{"draws":5,"losses":6,"wins":31},"meta/muse-spark-1.2":{"draws":6,"losses":11,"wins":29},"meta/muse-spark-1.3":{"draws":5,"losses":3,"wins":24},"meta/muse-wonder":{"draws":8,"losses":21,"wins":19},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":23},"mistralai/mistral-large-4-0":{"draws":7,"losses":5,"wins":18},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":10,"wins":28},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":34},"o3":{"draws":3,"losses":9,"wins":54},"openai/gpt-oss-120b":{"draws":7,"losses":2,"wins":33},"poolside/laguna-s-2.1":{"draws":6,"losses":4,"wins":36},"qwen/qwen3.7-max":{"draws":3,"losses":3,"wins":22},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":13,"wins":27},"qwen/qwen3.8-27b":{"draws":6,"losses":7,"wins":21},"qwen/qwen3.8-flash":{"draws":4,"losses":8,"wins":20},"qwen/qwen3.8-max":{"draws":6,"losses":12,"wins":30},"qwen/qwen3.8-max-0902":{"draws":11,"losses":15,"wins":22},"stealth/ox-alpha":{"draws":23,"losses":31,"wins":104},"stealth/space-bunny-alpha":{"draws":7,"losses":2,"wins":29},"stepfun/step-3.7-flash":{"draws":1,"losses":4,"wins":29},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":19},"tencent/hy4-preview":{"draws":6,"losses":11,"wins":29},"thinkingmachines/inkling":{"draws":5,"losses":6,"wins":53},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":42},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":13,"wins":27},"x-ai/grok-4.6":{"draws":9,"losses":14,"wins":25},"x-ai/grok-4.7":{"draws":5,"losses":24,"wins":13},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":13},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":5,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":15},"z-ai/glm-5.2":{"draws":10,"losses":15,"wins":71},"z-ai/glm-5.3":{"draws":10,"losses":16,"wins":20},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":25},"z-ai/glm-5.3-flashx":{"draws":5,"losses":14,"wins":29}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":2,"wins":35},"claude-fable-5":{"draws":6,"losses":17,"wins":25},"claude-fable-5-1":{"draws":5,"losses":35,"wins":14},"claude-haiku-5-5":{"draws":6,"losses":6,"wins":34},"claude-opus-4-5":{"draws":9,"losses":9,"wins":60},"claude-opus-4-8":{"draws":9,"losses":8,"wins":27},"claude-opus-5":{"draws":11,"losses":34,"wins":37},"claude-opus-5-5":{"draws":4,"losses":36,"wins":12},"claude-sonnet-5":{"draws":6,"losses":5,"wins":37},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":7,"losses":3,"wins":62},"deepseek/deepseek-v4-pro":{"draws":7,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":4,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":5,"wins":31},"fireworks/ember-1":{"draws":12,"losses":5,"wins":31},"gemini-3.1-pro-preview":{"draws":9,"losses":7,"wins":32},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":47},"google/gemini-3.5-flash-lite":{"draws":8,"losses":5,"wins":71},"google/gemini-3.6-flash":{"draws":7,"losses":12,"wins":73},"google/gemini-3.8-flash":{"draws":9,"losses":12,"wins":27},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":26},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":5,"losses":4,"wins":33},"gpt-5.4":{"draws":7,"losses":7,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":1,"wins":25},"gpt-5.4-nano":{"draws":1,"losses":4,"wins":43},"gpt-5.5":{"draws":8,"losses":10,"wins":26},"gpt-5.6-luna":{"draws":7,"losses":5,"wins":36},"gpt-5.6-sol":{"draws":5,"losses":13,"wins":30},"gpt-5.6-terra":{"draws":10,"losses":5,"wins":31},"gpt-6-astra":{"draws":6,"losses":33,"wins":9},"gpt-6-luna":{"draws":7,"losses":5,"wins":36},"gpt-6-sol":{"draws":4,"losses":23,"wins":21},"gpt-6.1-sol":{"draws":9,"losses":26,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":25},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":5,"wins":40},"meta/muse-glimmer-30b":{"draws":7,"losses":1,"wins":34},"meta/muse-spark-1.2":{"draws":1,"losses":10,"wins":35},"meta/muse-spark-1.3":{"draws":6,"losses":6,"wins":36},"meta/muse-wonder":{"draws":6,"losses":7,"wins":19},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":21},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":34},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":34},"o3":{"draws":3,"losses":7,"wins":56},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":38},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":42},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":26},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":10,"wins":32},"qwen/qwen3.8-27b":{"draws":2,"losses":0,"wins":32},"qwen/qwen3.8-flash":{"draws":5,"losses":2,"wins":25},"qwen/qwen3.8-max":{"draws":4,"losses":5,"wins":39},"qwen/qwen3.8-max-0902":{"draws":9,"losses":7,"wins":32},"stealth/ox-alpha":{"draws":21,"losses":21,"wins":116},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":32},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":22},"tencent/hy4-preview":{"draws":6,"losses":8,"wins":32},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":52},"thinkingmachines/inkling-small":{"draws":6,"losses":2,"wins":40},"unbiased/pareto-26.10-preview":{"draws":2,"losses":9,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":5,"losses":10,"wins":33},"x-ai/grok-4.6":{"draws":14,"losses":7,"wins":27},"x-ai/grok-4.7":{"draws":6,"losses":22,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":9,"losses":1,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":15,"losses":6,"wins":75},"z-ai/glm-5.3":{"draws":2,"losses":16,"wins":28},"z-ai/glm-5.3-flash":{"draws":11,"losses":10,"wins":27},"z-ai/glm-5.3-flashx":{"draws":9,"losses":6,"wins":33}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":10,"wins":23},"claude-fable-5":{"draws":8,"losses":25,"wins":15},"claude-fable-5-1":{"draws":1,"losses":49,"wins":4},"claude-haiku-5-5":{"draws":14,"losses":11,"wins":21},"claude-opus-4-5":{"draws":22,"losses":22,"wins":34},"claude-opus-4-8":{"draws":7,"losses":14,"wins":23},"claude-opus-5":{"draws":13,"losses":57,"wins":12},"claude-opus-5-5":{"draws":9,"losses":38,"wins":5},"claude-sonnet-5":{"draws":14,"losses":18,"wins":16},"claude-sonnet-5-5":{"draws":9,"losses":23,"wins":16},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":19,"losses":8,"wins":45},"deepseek/deepseek-v4-pro":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":14,"wins":19},"fireworks/ember-1":{"draws":10,"losses":14,"wins":24},"gemini-3.1-pro-preview":{"draws":7,"losses":15,"wins":26},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":19,"losses":15,"wins":26},"google/gemini-3.5-flash-lite":{"draws":17,"losses":14,"wins":53},"google/gemini-3.6-flash":{"draws":14,"losses":30,"wins":48},"google/gemini-3.8-flash":{"draws":14,"losses":15,"wins":19},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":11,"losses":6,"wins":25},"gpt-5.4":{"draws":15,"losses":18,"wins":13},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":7,"losses":10,"wins":31},"gpt-5.5":{"draws":10,"losses":16,"wins":18},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":28},"gpt-5.6-sol":{"draws":9,"losses":24,"wins":15},"gpt-5.6-terra":{"draws":20,"losses":9,"wins":17},"gpt-6-astra":{"draws":7,"losses":36,"wins":5},"gpt-6-luna":{"draws":14,"losses":15,"wins":19},"gpt-6-sol":{"draws":9,"losses":30,"wins":9},"gpt-6.1-sol":{"draws":8,"losses":35,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":6,"wins":33},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":23},"meta/muse-spark-1.2":{"draws":5,"losses":21,"wins":20},"meta/muse-spark-1.3":{"draws":14,"losses":17,"wins":17},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":19},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":15,"losses":15,"wins":16},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":9,"wins":21},"o3":{"draws":10,"losses":18,"wins":38},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":12,"losses":11,"wins":23},"qwen/qwen3.7-max":{"draws":8,"losses":0,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":20,"wins":20},"qwen/qwen3.8-27b":{"draws":8,"losses":8,"wins":18},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":12},"qwen/qwen3.8-max":{"draws":15,"losses":11,"wins":22},"qwen/qwen3.8-max-0902":{"draws":15,"losses":20,"wins":13},"stealth/ox-alpha":{"draws":50,"losses":53,"wins":55},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":9,"losses":2,"wins":23},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":8,"losses":17,"wins":21},"thinkingmachines/inkling":{"draws":18,"losses":7,"wins":39},"thinkingmachines/inkling-small":{"draws":14,"losses":3,"wins":31},"unbiased/pareto-26.10-preview":{"draws":3,"losses":10,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":16,"wins":23},"x-ai/grok-4.6":{"draws":16,"losses":17,"wins":15},"x-ai/grok-4.7":{"draws":9,"losses":20,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":8,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":12},"z-ai/glm-5.2":{"draws":29,"losses":18,"wins":49},"z-ai/glm-5.3":{"draws":6,"losses":27,"wins":13},"z-ai/glm-5.3-flash":{"draws":13,"losses":19,"wins":16},"z-ai/glm-5.3-flashx":{"draws":14,"losses":16,"wins":18}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":11,"wins":10},"claude-fable-5":{"draws":13,"losses":25,"wins":4},"claude-fable-5-1":{"draws":2,"losses":45,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":27,"wins":2},"claude-opus-4-5":{"draws":21,"losses":37,"wins":10},"claude-opus-4-8":{"draws":11,"losses":24,"wins":3},"claude-opus-5":{"draws":12,"losses":52,"wins":6},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":19,"losses":15,"wins":8},"claude-sonnet-5-5":{"draws":12,"losses":25,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":7},"deepseek/deepseek-v4-flash":{"draws":25,"losses":17,"wins":20},"deepseek/deepseek-v4-pro":{"draws":11,"losses":22,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":22,"wins":6},"fireworks/ember-1":{"draws":14,"losses":23,"wins":5},"gemini-3.1-pro-preview":{"draws":18,"losses":16,"wins":8},"google/gemini-3.1-flash-lite":{"draws":7,"losses":9,"wins":12},"google/gemini-3.5-flash":{"draws":17,"losses":26,"wins":9},"google/gemini-3.5-flash-lite":{"draws":30,"losses":27,"wins":17},"google/gemini-3.6-flash":{"draws":28,"losses":43,"wins":9},"google/gemini-3.8-flash":{"draws":11,"losses":27,"wins":4},"google/gemma-4-31b-it":{"draws":11,"losses":10,"wins":5},"gpt-4.1":{"draws":7,"losses":4,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":16,"wins":8},"gpt-5.4":{"draws":14,"losses":22,"wins":4},"gpt-5.4-mini":{"draws":10,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":9,"losses":20,"wins":11},"gpt-5.5":{"draws":14,"losses":20,"wins":4},"gpt-5.6-luna":{"draws":19,"losses":19,"wins":4},"gpt-5.6-sol":{"draws":9,"losses":31,"wins":2},"gpt-5.6-terra":{"draws":14,"losses":21,"wins":5},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":15,"losses":22,"wins":5},"gpt-6-sol":{"draws":4,"losses":35,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":7,"wins":11},"inclusionai/ling-3.0-flash":{"draws":10,"losses":8,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":16,"wins":12},"meta/muse-glimmer-30b":{"draws":18,"losses":13,"wins":5},"meta/muse-spark-1.2":{"draws":12,"losses":20,"wins":8},"meta/muse-spark-1.3":{"draws":11,"losses":28,"wins":3},"meta/muse-wonder":{"draws":8,"losses":31,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":9},"mistralai/mistral-large-4-0":{"draws":11,"losses":12,"wins":3},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":10,"wins":8},"o3":{"draws":14,"losses":33,"wins":9},"openai/gpt-oss-120b":{"draws":19,"losses":8,"wins":11},"poolside/laguna-s-2.1":{"draws":16,"losses":15,"wins":9},"qwen/qwen3.7-max":{"draws":12,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":26,"wins":2},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":3},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":3},"qwen/qwen3.8-max":{"draws":15,"losses":22,"wins":5},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":4},"stealth/ox-alpha":{"draws":38,"losses":78,"wins":26},"stealth/space-bunny-alpha":{"draws":11,"losses":16,"wins":7},"stepfun/step-3.7-flash":{"draws":11,"losses":12,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":17,"losses":19,"wins":4},"thinkingmachines/inkling":{"draws":18,"losses":21,"wins":15},"thinkingmachines/inkling-small":{"draws":19,"losses":17,"wins":6},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":1},"x-ai/grok-4.5":{"draws":12,"losses":26,"wins":4},"x-ai/grok-4.6":{"draws":14,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":31,"losses":17,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":9,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":38,"losses":34,"wins":12},"z-ai/glm-5.3":{"draws":8,"losses":31,"wins":3},"z-ai/glm-5.3-flash":{"draws":9,"losses":27,"wins":6},"z-ai/glm-5.3-flashx":{"draws":14,"losses":24,"wins":4}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":17},"claude-fable-5":{"draws":6,"losses":24,"wins":12},"claude-fable-5-1":{"draws":0,"losses":41,"wins":7},"claude-haiku-5-5":{"draws":10,"losses":16,"wins":14},"claude-opus-4-5":{"draws":19,"losses":23,"wins":26},"claude-opus-4-8":{"draws":8,"losses":17,"wins":13},"claude-opus-5":{"draws":11,"losses":53,"wins":16},"claude-opus-5-5":{"draws":2,"losses":41,"wins":3},"claude-sonnet-5":{"draws":10,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":7,"losses":20,"wins":15},"cohere/north-mini-code":{"draws":7,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":19,"losses":16,"wins":27},"deepseek/deepseek-v4-pro":{"draws":10,"losses":11,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":12,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":21,"wins":13},"fireworks/ember-1":{"draws":13,"losses":14,"wins":15},"gemini-3.1-pro-preview":{"draws":13,"losses":10,"wins":19},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":16},"google/gemini-3.5-flash":{"draws":16,"losses":14,"wins":22},"google/gemini-3.5-flash-lite":{"draws":27,"losses":11,"wins":34},"google/gemini-3.6-flash":{"draws":16,"losses":32,"wins":32},"google/gemini-3.8-flash":{"draws":8,"losses":18,"wins":16},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":10},"gpt-4.1":{"draws":3,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":5,"losses":15,"wins":18},"gpt-5.4":{"draws":9,"losses":15,"wins":16},"gpt-5.4-mini":{"draws":8,"losses":6,"wins":14},"gpt-5.4-nano":{"draws":13,"losses":11,"wins":16},"gpt-5.5":{"draws":9,"losses":14,"wins":17},"gpt-5.6-luna":{"draws":15,"losses":10,"wins":17},"gpt-5.6-sol":{"draws":4,"losses":25,"wins":13},"gpt-5.6-terra":{"draws":9,"losses":14,"wins":17},"gpt-6-astra":{"draws":5,"losses":36,"wins":1},"gpt-6-luna":{"draws":12,"losses":9,"wins":21},"gpt-6-sol":{"draws":4,"losses":33,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":3,"wins":10},"inclusionai/ling-3.0-flash":{"draws":9,"losses":7,"wins":12},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":24},"meta/muse-glimmer-30b":{"draws":11,"losses":7,"wins":22},"meta/muse-spark-1.2":{"draws":6,"losses":17,"wins":19},"meta/muse-spark-1.3":{"draws":10,"losses":17,"wins":15},"meta/muse-wonder":{"draws":6,"losses":27,"wins":9},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":12},"mistralai/mistral-large-4-0":{"draws":5,"losses":10,"wins":13},"mistralai/mistral-medium-3-5":{"draws":6,"losses":5,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":7,"wins":15},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":16,"wins":12},"o3":{"draws":9,"losses":21,"wins":24},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":21},"poolside/laguna-s-2.1":{"draws":16,"losses":8,"wins":18},"qwen/qwen3.7-max":{"draws":5,"losses":6,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":13,"wins":18},"qwen/qwen3.8-27b":{"draws":5,"losses":11,"wins":12},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":11},"qwen/qwen3.8-max":{"draws":9,"losses":17,"wins":16},"qwen/qwen3.8-max-0902":{"draws":7,"losses":24,"wins":11},"stealth/ox-alpha":{"draws":30,"losses":50,"wins":62},"stealth/space-bunny-alpha":{"draws":8,"losses":6,"wins":20},"stepfun/step-3.7-flash":{"draws":9,"losses":7,"wins":12},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":8,"losses":17,"wins":15},"thinkingmachines/inkling":{"draws":14,"losses":12,"wins":32},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":17},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":6,"losses":19,"wins":17},"x-ai/grok-4.6":{"draws":7,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":4,"losses":22,"wins":12},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":22,"losses":12,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":8,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":18,"wins":5},"z-ai/glm-5.2":{"draws":24,"losses":24,"wins":36},"z-ai/glm-5.3":{"draws":8,"losses":17,"wins":15},"z-ai/glm-5.3-flash":{"draws":11,"losses":17,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":16,"wins":15}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":12,"wins":13},"claude-fable-5":{"draws":14,"losses":39,"wins":1},"claude-fable-5-1":{"draws":4,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":16,"losses":31,"wins":7},"claude-opus-4-5":{"draws":38,"losses":42,"wins":10},"claude-opus-4-8":{"draws":15,"losses":32,"wins":7},"claude-opus-5":{"draws":15,"losses":81,"wins":2},"claude-opus-5-5":{"draws":2,"losses":60,"wins":0},"claude-sonnet-5":{"draws":25,"losses":22,"wins":7},"claude-sonnet-5-5":{"draws":12,"losses":33,"wins":9},"cohere/north-mini-code":{"draws":10,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":43,"losses":22,"wins":17},"deepseek/deepseek-v4-pro":{"draws":19,"losses":23,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":20,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":21,"wins":10},"fireworks/ember-1":{"draws":26,"losses":24,"wins":4},"gemini-3.1-pro-preview":{"draws":26,"losses":17,"wins":11},"google/gemini-3.1-flash-lite":{"draws":14,"losses":7,"wins":17},"google/gemini-3.5-flash":{"draws":25,"losses":28,"wins":15},"google/gemini-3.5-flash-lite":{"draws":41,"losses":27,"wins":26},"google/gemini-3.6-flash":{"draws":42,"losses":50,"wins":8},"google/gemini-3.8-flash":{"draws":23,"losses":29,"wins":2},"google/gemma-4-31b-it":{"draws":21,"losses":7,"wins":6},"gpt-4.1":{"draws":10,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":21,"losses":20,"wins":5},"gpt-5.4":{"draws":20,"losses":29,"wins":1},"gpt-5.4-mini":{"draws":19,"losses":11,"wins":6},"gpt-5.4-nano":{"draws":21,"losses":25,"wins":16},"gpt-5.5":{"draws":25,"losses":22,"wins":1},"gpt-5.6-luna":{"draws":27,"losses":16,"wins":11},"gpt-5.6-sol":{"draws":9,"losses":43,"wins":2},"gpt-5.6-terra":{"draws":25,"losses":22,"wins":3},"gpt-6-astra":{"draws":4,"losses":50,"wins":0},"gpt-6-luna":{"draws":19,"losses":28,"wins":7},"gpt-6-sol":{"draws":6,"losses":46,"wins":2},"gpt-6.1-sol":{"draws":5,"losses":49,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":25,"losses":8,"wins":9},"inclusionai/ling-3.0-flash":{"draws":23,"losses":5,"wins":8},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":27,"losses":11,"wins":20},"meta/muse-glimmer-30b":{"draws":28,"losses":11,"wins":7},"meta/muse-spark-1.2":{"draws":15,"losses":32,"wins":5},"meta/muse-spark-1.3":{"draws":17,"losses":36,"wins":1},"meta/muse-wonder":{"draws":20,"losses":33,"wins":1},"minimax/minimax-m3":{"draws":15,"losses":8,"wins":9},"mistralai/mistral-large-4-0":{"draws":12,"losses":17,"wins":5},"mistralai/mistral-medium-3-5":{"draws":19,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":9,"wins":1},"moonshotai/kimi-k3":{"draws":22,"losses":21,"wins":9},"nex-agi/nex-n2-pro":{"draws":11,"losses":3,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":14,"wins":4},"o3":{"draws":23,"losses":40,"wins":11},"openai/gpt-oss-120b":{"draws":25,"losses":10,"wins":13},"poolside/laguna-s-2.1":{"draws":28,"losses":17,"wins":11},"qwen/qwen3.7-max":{"draws":20,"losses":8,"wins":6},"qwen/qwen3.7-plus":{"draws":14,"losses":12,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":25,"wins":4},"qwen/qwen3.8-27b":{"draws":16,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":19,"losses":14,"wins":3},"qwen/qwen3.8-max":{"draws":27,"losses":23,"wins":4},"qwen/qwen3.8-max-0902":{"draws":28,"losses":22,"wins":4},"stealth/ox-alpha":{"draws":57,"losses":81,"wins":12},"stealth/space-bunny-alpha":{"draws":20,"losses":13,"wins":9},"stepfun/step-3.7-flash":{"draws":14,"losses":12,"wins":8},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":20,"losses":27,"wins":3},"thinkingmachines/inkling":{"draws":25,"losses":19,"wins":24},"thinkingmachines/inkling-small":{"draws":31,"losses":11,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":18,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":16,"losses":37,"wins":1},"x-ai/grok-4.6":{"draws":25,"losses":24,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":43,"wins":3},"x-ai/grok-build-0.1":{"draws":10,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":47,"losses":21,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":10,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":20,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":25,"wins":3},"z-ai/glm-5.2":{"draws":56,"losses":40,"wins":12},"z-ai/glm-5.3":{"draws":13,"losses":36,"wins":3},"z-ai/glm-5.3-flash":{"draws":20,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":17,"losses":32,"wins":5}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":35,"wins":56},"claude-fable-5":{"draws":6,"losses":90,"wins":18},"claude-fable-5-1":{"draws":0,"losses":117,"wins":7},"claude-haiku-5-5":{"draws":11,"losses":57,"wins":44},"claude-opus-4-5":{"draws":15,"losses":117,"wins":56},"claude-opus-4-8":{"draws":7,"losses":66,"wins":37},"claude-opus-5":{"draws":6,"losses":156,"wins":10},"claude-opus-5-5":{"draws":2,"losses":122,"wins":2},"claude-sonnet-5":{"draws":9,"losses":50,"wins":55},"claude-sonnet-5-5":{"draws":4,"losses":83,"wins":27},"cohere/north-mini-code":{"draws":8,"losses":10,"wins":36},"deepseek/deepseek-v4-flash":{"draws":20,"losses":50,"wins":110},"deepseek/deepseek-v4-pro":{"draws":5,"losses":54,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":63,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":53,"wins":39},"fireworks/ember-1":{"draws":10,"losses":70,"wins":34},"gemini-3.1-pro-preview":{"draws":13,"losses":44,"wins":57},"google/gemini-3.1-flash-lite":{"draws":6,"losses":9,"wins":81},"google/gemini-3.5-flash":{"draws":14,"losses":84,"wins":52},"google/gemini-3.5-flash-lite":{"draws":19,"losses":62,"wins":125},"google/gemini-3.6-flash":{"draws":15,"losses":130,"wins":77},"google/gemini-3.8-flash":{"draws":10,"losses":73,"wins":31},"google/gemma-4-31b-it":{"draws":9,"losses":13,"wins":46},"gpt-4.1":{"draws":4,"losses":18,"wins":16},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":6},"gpt-5":{"draws":10,"losses":58,"wins":38},"gpt-5.4":{"draws":4,"losses":84,"wins":26},"gpt-5.4-mini":{"draws":12,"losses":17,"wins":47},"gpt-5.4-nano":{"draws":7,"losses":64,"wins":67},"gpt-5.5":{"draws":17,"losses":61,"wins":28},"gpt-5.6-luna":{"draws":14,"losses":45,"wins":55},"gpt-5.6-sol":{"draws":5,"losses":88,"wins":21},"gpt-5.6-terra":{"draws":14,"losses":48,"wins":44},"gpt-6-astra":{"draws":4,"losses":109,"wins":1},"gpt-6-luna":{"draws":15,"losses":62,"wins":37},"gpt-6-sol":{"draws":2,"losses":100,"wins":12},"gpt-6.1-sol":{"draws":0,"losses":107,"wins":7},"inception/mercury-2.5-preview":{"draws":11,"losses":10,"wins":55},"inclusionai/ling-3.0-flash":{"draws":14,"losses":12,"wins":54},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":16,"losses":38,"wins":84},"meta/muse-glimmer-30b":{"draws":16,"losses":16,"wins":66},"meta/muse-spark-1.2":{"draws":5,"losses":46,"wins":55},"meta/muse-spark-1.3":{"draws":4,"losses":71,"wins":39},"meta/muse-wonder":{"draws":4,"losses":86,"wins":24},"minimax/minimax-m3":{"draws":5,"losses":17,"wins":44},"mistralai/mistral-large-4-0":{"draws":10,"losses":34,"wins":24},"mistralai/mistral-medium-3-5":{"draws":8,"losses":7,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":13,"wins":15},"moonshotai/kimi-k3":{"draws":11,"losses":49,"wins":46},"nex-agi/nex-n2-pro":{"draws":6,"losses":12,"wins":46},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":24,"wins":66},"o3":{"draws":14,"losses":75,"wins":81},"openai/gpt-oss-120b":{"draws":8,"losses":20,"wins":72},"poolside/laguna-s-2.1":{"draws":19,"losses":37,"wins":58},"qwen/qwen3.7-max":{"draws":10,"losses":29,"wins":35},"qwen/qwen3.7-plus":{"draws":4,"losses":16,"wins":46},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":65,"wins":38},"qwen/qwen3.8-27b":{"draws":4,"losses":42,"wins":38},"qwen/qwen3.8-flash":{"draws":12,"losses":33,"wins":31},"qwen/qwen3.8-max":{"draws":15,"losses":60,"wins":39},"qwen/qwen3.8-max-0902":{"draws":15,"losses":54,"wins":45},"stealth/ox-alpha":{"draws":33,"losses":169,"wins":142},"stealth/space-bunny-alpha":{"draws":7,"losses":36,"wins":49},"stepfun/step-3.7-flash":{"draws":12,"losses":31,"wins":55},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":23,"wins":28},"tencent/hy4-preview":{"draws":13,"losses":65,"wins":36},"thinkingmachines/inkling":{"draws":12,"losses":34,"wins":108},"thinkingmachines/inkling-small":{"draws":18,"losses":28,"wins":68},"unbiased/pareto-26.10-preview":{"draws":0,"losses":35,"wins":3},"upstage/solar-mini4":{"draws":4,"losses":9,"wins":25},"x-ai/grok-4.5":{"draws":5,"losses":73,"wins":36},"x-ai/grok-4.6":{"draws":17,"losses":67,"wins":30},"x-ai/grok-4.7":{"draws":3,"losses":76,"wins":25},"x-ai/grok-build-0.1":{"draws":6,"losses":10,"wins":22},"xiaomi/mimo-v2.5":{"draws":19,"losses":33,"wins":128},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":26,"wins":39},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":44,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":51,"wins":21},"z-ai/glm-5.2":{"draws":27,"losses":94,"wins":107},"z-ai/glm-5.3":{"draws":6,"losses":78,"wins":24},"z-ai/glm-5.3-flash":{"draws":7,"losses":54,"wins":53},"z-ai/glm-5.3-flashx":{"draws":7,"losses":68,"wins":39}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":14,"wins":11},"claude-fable-5":{"draws":10,"losses":25,"wins":7},"claude-fable-5-1":{"draws":2,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":26,"wins":4},"claude-opus-4-5":{"draws":19,"losses":31,"wins":18},"claude-opus-4-8":{"draws":13,"losses":17,"wins":8},"claude-opus-5":{"draws":13,"losses":55,"wins":2},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":11,"losses":25,"wins":6},"claude-sonnet-5-5":{"draws":8,"losses":25,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":22,"losses":17,"wins":23},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":17,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":17,"wins":13},"fireworks/ember-1":{"draws":15,"losses":19,"wins":8},"gemini-3.1-pro-preview":{"draws":14,"losses":14,"wins":14},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":14},"google/gemini-3.5-flash":{"draws":15,"losses":19,"wins":18},"google/gemini-3.5-flash-lite":{"draws":21,"losses":20,"wins":33},"google/gemini-3.6-flash":{"draws":23,"losses":45,"wins":12},"google/gemini-3.8-flash":{"draws":8,"losses":29,"wins":5},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":12},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":18,"wins":9},"gpt-5.4":{"draws":10,"losses":18,"wins":12},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":9},"gpt-5.4-nano":{"draws":8,"losses":16,"wins":16},"gpt-5.5":{"draws":14,"losses":16,"wins":8},"gpt-5.6-luna":{"draws":22,"losses":8,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":29,"wins":6},"gpt-5.6-terra":{"draws":15,"losses":18,"wins":7},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":13,"losses":18,"wins":11},"gpt-6-sol":{"draws":7,"losses":34,"wins":1},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":13,"losses":7,"wins":12},"inclusionai/ling-3.0-flash":{"draws":10,"losses":1,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":18,"wins":17},"meta/muse-glimmer-30b":{"draws":13,"losses":8,"wins":15},"meta/muse-spark-1.2":{"draws":12,"losses":19,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":29,"wins":5},"meta/muse-wonder":{"draws":9,"losses":29,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":13},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":7},"mistralai/mistral-medium-3-5":{"draws":13,"losses":3,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":22,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":7,"wins":15},"o3":{"draws":6,"losses":33,"wins":17},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":12},"poolside/laguna-s-2.1":{"draws":14,"losses":7,"wins":19},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":5},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":22,"wins":7},"qwen/qwen3.8-27b":{"draws":8,"losses":14,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":10,"wins":13},"qwen/qwen3.8-max":{"draws":10,"losses":27,"wins":5},"qwen/qwen3.8-max-0902":{"draws":11,"losses":21,"wins":10},"stealth/ox-alpha":{"draws":34,"losses":74,"wins":34},"stealth/space-bunny-alpha":{"draws":13,"losses":10,"wins":11},"stepfun/step-3.7-flash":{"draws":7,"losses":13,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":21,"wins":8},"thinkingmachines/inkling":{"draws":16,"losses":16,"wins":22},"thinkingmachines/inkling-small":{"draws":15,"losses":11,"wins":16},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":5,"wins":4},"x-ai/grok-4.5":{"draws":10,"losses":27,"wins":5},"x-ai/grok-4.6":{"draws":10,"losses":24,"wins":8},"x-ai/grok-4.7":{"draws":1,"losses":33,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":21,"losses":10,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":20,"wins":1},"z-ai/glm-5.2":{"draws":28,"losses":36,"wins":20},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":25,"wins":10},"z-ai/glm-5.3-flashx":{"draws":13,"losses":26,"wins":3}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":1,"wins":32},"claude-fable-5":{"draws":13,"losses":12,"wins":23},"claude-fable-5-1":{"draws":5,"losses":44,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":11,"wins":25},"claude-opus-4-5":{"draws":23,"losses":7,"wins":48},"claude-opus-4-8":{"draws":8,"losses":6,"wins":30},"claude-opus-5":{"draws":13,"losses":52,"wins":17},"claude-opus-5-5":{"draws":4,"losses":37,"wins":11},"claude-sonnet-5":{"draws":12,"losses":6,"wins":30},"claude-sonnet-5-5":{"draws":10,"losses":16,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":16,"losses":5,"wins":51},"deepseek/deepseek-v4-pro":{"draws":11,"losses":4,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":5,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":13,"wins":24},"fireworks/ember-1":{"draws":11,"losses":8,"wins":29},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":30},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":11,"losses":10,"wins":39},"google/gemini-3.5-flash-lite":{"draws":18,"losses":5,"wins":61},"google/gemini-3.6-flash":{"draws":22,"losses":19,"wins":51},"google/gemini-3.8-flash":{"draws":12,"losses":14,"wins":22},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":21},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":10,"losses":6,"wins":26},"gpt-5.4":{"draws":7,"losses":10,"wins":29},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":22},"gpt-5.4-nano":{"draws":8,"losses":1,"wins":39},"gpt-5.5":{"draws":11,"losses":11,"wins":22},"gpt-5.6-luna":{"draws":9,"losses":6,"wins":33},"gpt-5.6-sol":{"draws":8,"losses":17,"wins":23},"gpt-5.6-terra":{"draws":13,"losses":6,"wins":27},"gpt-6-astra":{"draws":1,"losses":42,"wins":5},"gpt-6-luna":{"draws":12,"losses":8,"wins":28},"gpt-6-sol":{"draws":7,"losses":22,"wins":19},"gpt-6.1-sol":{"draws":2,"losses":33,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":23},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":3,"wins":38},"meta/muse-glimmer-30b":{"draws":8,"losses":2,"wins":32},"meta/muse-spark-1.2":{"draws":12,"losses":11,"wins":23},"meta/muse-spark-1.3":{"draws":8,"losses":11,"wins":29},"meta/muse-wonder":{"draws":8,"losses":16,"wins":24},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":19},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":19},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":13,"losses":10,"wins":23},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":30},"o3":{"draws":3,"losses":12,"wins":51},"openai/gpt-oss-120b":{"draws":8,"losses":3,"wins":31},"poolside/laguna-s-2.1":{"draws":9,"losses":2,"wins":35},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":17},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":5,"wins":22},"qwen/qwen3.8-27b":{"draws":13,"losses":3,"wins":18},"qwen/qwen3.8-flash":{"draws":7,"losses":6,"wins":19},"qwen/qwen3.8-max":{"draws":14,"losses":9,"wins":25},"qwen/qwen3.8-max-0902":{"draws":14,"losses":10,"wins":24},"stealth/ox-alpha":{"draws":31,"losses":37,"wins":90},"stealth/space-bunny-alpha":{"draws":11,"losses":3,"wins":24},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":30},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":16},"tencent/hy4-preview":{"draws":12,"losses":11,"wins":23},"thinkingmachines/inkling":{"draws":19,"losses":2,"wins":43},"thinkingmachines/inkling-small":{"draws":14,"losses":5,"wins":29},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":13,"losses":10,"wins":25},"x-ai/grok-4.6":{"draws":8,"losses":13,"wins":27},"x-ai/grok-4.7":{"draws":2,"losses":25,"wins":15},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":25,"losses":3,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":6,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":10,"wins":15},"z-ai/glm-5.2":{"draws":28,"losses":13,"wins":55},"z-ai/glm-5.3":{"draws":11,"losses":19,"wins":16},"z-ai/glm-5.3-flash":{"draws":9,"losses":11,"wins":28},"z-ai/glm-5.3-flashx":{"draws":16,"losses":10,"wins":22}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":6,"wins":24},"claude-fable-5":{"draws":3,"losses":22,"wins":11},"claude-fable-5-1":{"draws":2,"losses":37,"wins":1},"claude-haiku-5-5":{"draws":4,"losses":14,"wins":18},"claude-opus-4-5":{"draws":8,"losses":15,"wins":37},"claude-opus-4-8":{"draws":4,"losses":14,"wins":18},"claude-opus-5":{"draws":6,"losses":46,"wins":6},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":6,"losses":11,"wins":19},"claude-sonnet-5-5":{"draws":3,"losses":18,"wins":15},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":3,"losses":13,"wins":38},"deepseek/deepseek-v4-pro":{"draws":2,"losses":11,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":10,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":20,"wins":13},"fireworks/ember-1":{"draws":3,"losses":11,"wins":22},"gemini-3.1-pro-preview":{"draws":4,"losses":9,"wins":23},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":5,"losses":12,"wins":31},"google/gemini-3.5-flash-lite":{"draws":7,"losses":8,"wins":51},"google/gemini-3.6-flash":{"draws":8,"losses":25,"wins":37},"google/gemini-3.8-flash":{"draws":4,"losses":16,"wins":16},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":16},"gpt-4.1":{"draws":2,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":8,"wins":22},"gpt-5.4":{"draws":5,"losses":20,"wins":11},"gpt-5.4-mini":{"draws":1,"losses":5,"wins":18},"gpt-5.4-nano":{"draws":3,"losses":13,"wins":24},"gpt-5.5":{"draws":3,"losses":16,"wins":15},"gpt-5.6-luna":{"draws":6,"losses":9,"wins":21},"gpt-5.6-sol":{"draws":5,"losses":20,"wins":11},"gpt-5.6-terra":{"draws":9,"losses":9,"wins":16},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":4,"losses":13,"wins":19},"gpt-6-sol":{"draws":5,"losses":23,"wins":8},"gpt-6.1-sol":{"draws":1,"losses":31,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":2,"wins":22},"inclusionai/ling-3.0-flash":{"draws":1,"losses":3,"wins":22},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":4,"losses":5,"wins":33},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":27},"meta/muse-spark-1.2":{"draws":2,"losses":12,"wins":20},"meta/muse-spark-1.3":{"draws":4,"losses":12,"wins":20},"meta/muse-wonder":{"draws":3,"losses":28,"wins":5},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":17},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":12},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":7},"moonshotai/kimi-k3":{"draws":4,"losses":16,"wins":14},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":21},"o3":{"draws":3,"losses":19,"wins":38},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":23},"poolside/laguna-s-2.1":{"draws":5,"losses":4,"wins":23},"qwen/qwen3.7-max":{"draws":1,"losses":8,"wins":13},"qwen/qwen3.7-plus":{"draws":1,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":13,"wins":15},"qwen/qwen3.8-27b":{"draws":1,"losses":7,"wins":6},"qwen/qwen3.8-flash":{"draws":4,"losses":7,"wins":13},"qwen/qwen3.8-max":{"draws":8,"losses":13,"wins":15},"qwen/qwen3.8-max-0902":{"draws":6,"losses":13,"wins":17},"stealth/ox-alpha":{"draws":16,"losses":36,"wins":50},"stealth/space-bunny-alpha":{"draws":2,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":1,"losses":7,"wins":20},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":14},"tencent/hy4-preview":{"draws":6,"losses":13,"wins":17},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":38},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":32},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":0,"losses":21,"wins":15},"x-ai/grok-4.6":{"draws":6,"losses":16,"wins":14},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":3,"losses":6,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":9,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":12,"wins":9},"z-ai/glm-5.2":{"draws":12,"losses":21,"wins":39},"z-ai/glm-5.3":{"draws":8,"losses":21,"wins":5},"z-ai/glm-5.3-flash":{"draws":5,"losses":11,"wins":20},"z-ai/glm-5.3-flashx":{"draws":5,"losses":14,"wins":17}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":19},"claude-fable-5":{"draws":9,"losses":29,"wins":10},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":23,"wins":10},"claude-opus-4-5":{"draws":25,"losses":18,"wins":35},"claude-opus-4-8":{"draws":5,"losses":22,"wins":17},"claude-opus-5":{"draws":7,"losses":64,"wins":11},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":12,"losses":15,"wins":21},"claude-sonnet-5-5":{"draws":7,"losses":23,"wins":18},"cohere/north-mini-code":{"draws":5,"losses":0,"wins":13},"deepseek/deepseek-v4-flash":{"draws":16,"losses":15,"wins":41},"deepseek/deepseek-v4-pro":{"draws":9,"losses":11,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":11,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":15,"wins":22},"fireworks/ember-1":{"draws":14,"losses":18,"wins":16},"gemini-3.1-pro-preview":{"draws":14,"losses":12,"wins":22},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":17,"losses":22,"wins":21},"google/gemini-3.5-flash-lite":{"draws":22,"losses":12,"wins":50},"google/gemini-3.6-flash":{"draws":18,"losses":38,"wins":36},"google/gemini-3.8-flash":{"draws":15,"losses":21,"wins":12},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":13,"losses":14,"wins":15},"gpt-5.4":{"draws":11,"losses":16,"wins":19},"gpt-5.4-mini":{"draws":14,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":12,"wins":27},"gpt-5.5":{"draws":13,"losses":14,"wins":17},"gpt-5.6-luna":{"draws":10,"losses":9,"wins":29},"gpt-5.6-sol":{"draws":10,"losses":30,"wins":8},"gpt-5.6-terra":{"draws":20,"losses":10,"wins":16},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":9,"losses":17,"wins":22},"gpt-6-sol":{"draws":6,"losses":35,"wins":7},"gpt-6.1-sol":{"draws":3,"losses":40,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":22},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":6,"wins":33},"meta/muse-glimmer-30b":{"draws":13,"losses":8,"wins":21},"meta/muse-spark-1.2":{"draws":11,"losses":21,"wins":14},"meta/muse-spark-1.3":{"draws":11,"losses":21,"wins":16},"meta/muse-wonder":{"draws":9,"losses":27,"wins":12},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":14},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":9},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":11,"losses":16,"wins":19},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":7,"wins":19},"o3":{"draws":10,"losses":23,"wins":33},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":29},"poolside/laguna-s-2.1":{"draws":14,"losses":9,"wins":23},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":12},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":17,"wins":15},"qwen/qwen3.8-27b":{"draws":9,"losses":8,"wins":17},"qwen/qwen3.8-flash":{"draws":9,"losses":6,"wins":17},"qwen/qwen3.8-max":{"draws":8,"losses":10,"wins":14},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":16},"stealth/ox-alpha":{"draws":39,"losses":63,"wins":56},"stealth/space-bunny-alpha":{"draws":10,"losses":9,"wins":19},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":2,"wins":12},"tencent/hy4-preview":{"draws":11,"losses":18,"wins":17},"thinkingmachines/inkling":{"draws":20,"losses":8,"wins":36},"thinkingmachines/inkling-small":{"draws":15,"losses":10,"wins":23},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":9,"losses":19,"wins":20},"x-ai/grok-4.6":{"draws":13,"losses":17,"wins":18},"x-ai/grok-4.7":{"draws":6,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":25,"losses":8,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":12,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":19,"wins":6},"z-ai/glm-5.2":{"draws":29,"losses":30,"wins":37},"z-ai/glm-5.3":{"draws":5,"losses":30,"wins":11},"z-ai/glm-5.3-flash":{"draws":14,"losses":12,"wins":22},"z-ai/glm-5.3-flashx":{"draws":17,"losses":15,"wins":16}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":4,"wins":33},"claude-fable-5":{"draws":10,"losses":16,"wins":22},"claude-fable-5-1":{"draws":3,"losses":37,"wins":14},"claude-haiku-5-5":{"draws":10,"losses":9,"wins":27},"claude-opus-4-5":{"draws":14,"losses":12,"wins":52},"claude-opus-4-8":{"draws":4,"losses":14,"wins":26},"claude-opus-5":{"draws":8,"losses":44,"wins":30},"claude-opus-5-5":{"draws":8,"losses":35,"wins":9},"claude-sonnet-5":{"draws":12,"losses":7,"wins":29},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":23},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":53},"deepseek/deepseek-v4-pro":{"draws":9,"losses":5,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":4,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":9,"wins":26},"fireworks/ember-1":{"draws":12,"losses":9,"wins":27},"gemini-3.1-pro-preview":{"draws":12,"losses":6,"wins":30},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":28},"google/gemini-3.5-flash":{"draws":12,"losses":7,"wins":41},"google/gemini-3.5-flash-lite":{"draws":12,"losses":5,"wins":67},"google/gemini-3.6-flash":{"draws":19,"losses":15,"wins":58},"google/gemini-3.8-flash":{"draws":10,"losses":8,"wins":30},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":22},"gpt-4.1":{"draws":5,"losses":1,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":4},"gpt-5":{"draws":10,"losses":4,"wins":28},"gpt-5.4":{"draws":12,"losses":13,"wins":21},"gpt-5.4-mini":{"draws":11,"losses":1,"wins":20},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":34},"gpt-5.5":{"draws":14,"losses":9,"wins":21},"gpt-5.6-luna":{"draws":12,"losses":7,"wins":29},"gpt-5.6-sol":{"draws":9,"losses":20,"wins":19},"gpt-5.6-terra":{"draws":12,"losses":8,"wins":26},"gpt-6-astra":{"draws":3,"losses":41,"wins":4},"gpt-6-luna":{"draws":9,"losses":7,"wins":32},"gpt-6-sol":{"draws":5,"losses":26,"wins":17},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inclusionai/ling-3.0-flash":{"draws":9,"losses":0,"wins":25},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":3,"wins":41},"meta/muse-glimmer-30b":{"draws":11,"losses":2,"wins":29},"meta/muse-spark-1.2":{"draws":9,"losses":8,"wins":29},"meta/muse-spark-1.3":{"draws":10,"losses":7,"wins":31},"meta/muse-wonder":{"draws":13,"losses":19,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":22},"mistralai/mistral-large-4-0":{"draws":7,"losses":3,"wins":20},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":30},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":2,"wins":31},"o3":{"draws":8,"losses":14,"wins":44},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":30},"poolside/laguna-s-2.1":{"draws":8,"losses":2,"wins":36},"qwen/qwen3.7-max":{"draws":8,"losses":2,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":7,"wins":28},"qwen/qwen3.8-27b":{"draws":6,"losses":1,"wins":27},"qwen/qwen3.8-flash":{"draws":10,"losses":7,"wins":15},"qwen/qwen3.8-max":{"draws":9,"losses":10,"wins":29},"qwen/qwen3.8-max-0902":{"draws":9,"losses":2,"wins":21},"stealth/ox-alpha":{"draws":32,"losses":40,"wins":86},"stealth/space-bunny-alpha":{"draws":8,"losses":4,"wins":26},"stepfun/step-3.7-flash":{"draws":7,"losses":5,"wins":22},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":18},"tencent/hy4-preview":{"draws":10,"losses":8,"wins":28},"thinkingmachines/inkling":{"draws":11,"losses":4,"wins":49},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":32},"unbiased/pareto-26.10-preview":{"draws":2,"losses":9,"wins":5},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":14,"wins":26},"x-ai/grok-4.6":{"draws":15,"losses":14,"wins":19},"x-ai/grok-4.7":{"draws":6,"losses":22,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":22,"losses":2,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":5,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":7,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":12,"wins":15},"z-ai/glm-5.2":{"draws":19,"losses":12,"wins":65},"z-ai/glm-5.3":{"draws":9,"losses":19,"wins":18},"z-ai/glm-5.3-flash":{"draws":13,"losses":11,"wins":24},"z-ai/glm-5.3-flashx":{"draws":12,"losses":10,"wins":26}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":19,"wins":107},"claude-fable-5":{"draws":17,"losses":78,"wins":55},"claude-fable-5-1":{"draws":18,"losses":136,"wins":18},"claude-haiku-5-5":{"draws":17,"losses":43,"wins":80},"claude-opus-4-5":{"draws":27,"losses":49,"wins":164},"claude-opus-4-8":{"draws":19,"losses":34,"wins":77},"claude-opus-5":{"draws":36,"losses":167,"wins":55},"claude-opus-5-5":{"draws":11,"losses":129,"wins":22},"claude-sonnet-5":{"draws":14,"losses":31,"wins":105},"claude-sonnet-5-5":{"draws":11,"losses":65,"wins":74},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":50},"deepseek/deepseek-v4-flash":{"draws":16,"losses":21,"wins":185},"deepseek/deepseek-v4-pro":{"draws":13,"losses":33,"wins":94},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":33,"wins":89},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":43,"wins":90},"fireworks/ember-1":{"draws":21,"losses":35,"wins":94},"gemini-3.1-pro-preview":{"draws":15,"losses":37,"wins":98},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":80},"google/gemini-3.5-flash":{"draws":20,"losses":38,"wins":128},"google/gemini-3.5-flash-lite":{"draws":19,"losses":33,"wins":212},"google/gemini-3.6-flash":{"draws":31,"losses":78,"wins":181},"google/gemini-3.8-flash":{"draws":15,"losses":57,"wins":78},"google/gemma-4-31b-it":{"draws":7,"losses":8,"wins":69},"gpt-4.1":{"draws":8,"losses":9,"wins":33},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":14},"gpt-5":{"draws":12,"losses":30,"wins":92},"gpt-5.4":{"draws":22,"losses":47,"wins":77},"gpt-5.4-mini":{"draws":15,"losses":11,"wins":74},"gpt-5.4-nano":{"draws":7,"losses":35,"wins":100},"gpt-5.5":{"draws":18,"losses":41,"wins":81},"gpt-5.6-luna":{"draws":23,"losses":22,"wins":105},"gpt-5.6-sol":{"draws":16,"losses":70,"wins":64},"gpt-5.6-terra":{"draws":21,"losses":38,"wins":85},"gpt-6-astra":{"draws":15,"losses":121,"wins":14},"gpt-6-luna":{"draws":20,"losses":29,"wins":101},"gpt-6-sol":{"draws":18,"losses":91,"wins":41},"gpt-6.1-sol":{"draws":17,"losses":116,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":17,"losses":10,"wins":73},"inclusionai/ling-3.0-flash":{"draws":9,"losses":5,"wins":92},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":16,"losses":17,"wins":131},"meta/muse-glimmer-30b":{"draws":11,"losses":9,"wins":114},"meta/muse-spark-1.2":{"draws":18,"losses":27,"wins":99},"meta/muse-spark-1.3":{"draws":17,"losses":50,"wins":83},"meta/muse-wonder":{"draws":12,"losses":76,"wins":62},"minimax/minimax-m3":{"draws":10,"losses":4,"wins":64},"mistralai/mistral-large-4-0":{"draws":15,"losses":24,"wins":55},"mistralai/mistral-medium-3-5":{"draws":12,"losses":7,"wins":69},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":7,"wins":22},"moonshotai/kimi-k3":{"draws":18,"losses":39,"wins":87},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":65},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":19,"wins":86},"o3":{"draws":10,"losses":41,"wins":153},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":112},"poolside/laguna-s-2.1":{"draws":17,"losses":17,"wins":114},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":67},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":59},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":44,"wins":87},"qwen/qwen3.8-27b":{"draws":8,"losses":22,"wins":76},"qwen/qwen3.8-flash":{"draws":10,"losses":24,"wins":66},"qwen/qwen3.8-max":{"draws":20,"losses":33,"wins":97},"qwen/qwen3.8-max-0902":{"draws":21,"losses":42,"wins":87},"stealth/ox-alpha":{"draws":53,"losses":129,"wins":306},"stealth/space-bunny-alpha":{"draws":11,"losses":16,"wins":91},"stepfun/step-3.7-flash":{"draws":2,"losses":13,"wins":93},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":13,"losses":11,"wins":54},"tencent/hy4-preview":{"draws":20,"losses":49,"wins":77},"thinkingmachines/inkling":{"draws":22,"losses":23,"wins":161},"thinkingmachines/inkling-small":{"draws":17,"losses":8,"wins":125},"unbiased/pareto-26.10-preview":{"draws":10,"losses":35,"wins":5},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":33},"x-ai/grok-4.5":{"draws":14,"losses":63,"wins":73},"x-ai/grok-4.6":{"draws":29,"losses":54,"wins":67},"x-ai/grok-4.7":{"draws":10,"losses":76,"wins":42},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":44},"xiaomi/mimo-v2.5":{"draws":21,"losses":18,"wins":177},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":13,"wins":65},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":22,"wins":64},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":39,"wins":46},"z-ai/glm-5.2":{"draws":33,"losses":48,"wins":219},"z-ai/glm-5.3":{"draws":17,"losses":63,"wins":64},"z-ai/glm-5.3-flash":{"draws":16,"losses":43,"wins":91},"z-ai/glm-5.3-flashx":{"draws":19,"losses":49,"wins":82}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":8,"wins":15},"claude-fable-5":{"draws":9,"losses":22,"wins":5},"claude-fable-5-1":{"draws":1,"losses":37,"wins":2},"claude-haiku-5-5":{"draws":7,"losses":18,"wins":11},"claude-opus-4-5":{"draws":18,"losses":27,"wins":15},"claude-opus-4-8":{"draws":8,"losses":15,"wins":13},"claude-opus-5":{"draws":11,"losses":41,"wins":6},"claude-opus-5-5":{"draws":1,"losses":38,"wins":1},"claude-sonnet-5":{"draws":6,"losses":13,"wins":17},"claude-sonnet-5-5":{"draws":3,"losses":19,"wins":14},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":17,"losses":9,"wins":28},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":15,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":14,"wins":8},"fireworks/ember-1":{"draws":8,"losses":17,"wins":11},"gemini-3.1-pro-preview":{"draws":7,"losses":11,"wins":18},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":20},"google/gemini-3.5-flash":{"draws":13,"losses":20,"wins":15},"google/gemini-3.5-flash-lite":{"draws":16,"losses":16,"wins":34},"google/gemini-3.6-flash":{"draws":14,"losses":34,"wins":22},"google/gemini-3.8-flash":{"draws":9,"losses":19,"wins":8},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":11},"gpt-4.1":{"draws":6,"losses":1,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":13,"wins":13},"gpt-5.4":{"draws":5,"losses":25,"wins":6},"gpt-5.4-mini":{"draws":6,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":20},"gpt-5.5":{"draws":11,"losses":15,"wins":8},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":15},"gpt-5.6-sol":{"draws":4,"losses":24,"wins":8},"gpt-5.6-terra":{"draws":8,"losses":13,"wins":13},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":10,"losses":14,"wins":12},"gpt-6-sol":{"draws":1,"losses":27,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":12},"inclusionai/ling-3.0-flash":{"draws":8,"losses":3,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":11,"wins":17},"meta/muse-glimmer-30b":{"draws":9,"losses":4,"wins":19},"meta/muse-spark-1.2":{"draws":5,"losses":14,"wins":15},"meta/muse-spark-1.3":{"draws":7,"losses":14,"wins":15},"meta/muse-wonder":{"draws":5,"losses":24,"wins":7},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":13},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":6},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":16,"wins":9},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":14,"wins":12},"o3":{"draws":8,"losses":27,"wins":25},"openai/gpt-oss-120b":{"draws":6,"losses":4,"wins":20},"poolside/laguna-s-2.1":{"draws":5,"losses":10,"wins":17},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":14,"wins":12},"qwen/qwen3.8-27b":{"draws":5,"losses":11,"wins":10},"qwen/qwen3.8-flash":{"draws":7,"losses":10,"wins":7},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":13},"qwen/qwen3.8-max-0902":{"draws":9,"losses":18,"wins":9},"stealth/ox-alpha":{"draws":22,"losses":45,"wins":35},"stealth/space-bunny-alpha":{"draws":6,"losses":2,"wins":10},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":15},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":8,"losses":13,"wins":15},"thinkingmachines/inkling":{"draws":11,"losses":13,"wins":24},"thinkingmachines/inkling-small":{"draws":8,"losses":6,"wins":22},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":8,"losses":21,"wins":7},"x-ai/grok-4.6":{"draws":6,"losses":20,"wins":10},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":10,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":3,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":20,"losses":24,"wins":28},"z-ai/glm-5.3":{"draws":6,"losses":21,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":21,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":18,"wins":8}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":15,"wins":9},"claude-fable-5":{"draws":2,"losses":26,"wins":2},"claude-fable-5-1":{"draws":0,"losses":32,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":22,"wins":5},"claude-opus-4-5":{"draws":4,"losses":38,"wins":8},"claude-opus-4-8":{"draws":2,"losses":24,"wins":4},"claude-opus-5":{"draws":1,"losses":44,"wins":1},"claude-opus-5-5":{"draws":0,"losses":34,"wins":0},"claude-sonnet-5":{"draws":3,"losses":20,"wins":7},"claude-sonnet-5-5":{"draws":0,"losses":24,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":11,"losses":24,"wins":13},"deepseek/deepseek-v4-pro":{"draws":2,"losses":24,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":19,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":22,"wins":2},"fireworks/ember-1":{"draws":4,"losses":24,"wins":2},"gemini-3.1-pro-preview":{"draws":4,"losses":15,"wins":11},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":5,"losses":26,"wins":9},"google/gemini-3.5-flash-lite":{"draws":8,"losses":30,"wins":16},"google/gemini-3.6-flash":{"draws":5,"losses":47,"wins":6},"google/gemini-3.8-flash":{"draws":4,"losses":25,"wins":1},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":10},"gpt-4.1":{"draws":2,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":21,"wins":1},"gpt-5.4":{"draws":2,"losses":22,"wins":6},"gpt-5.4-mini":{"draws":4,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":4,"losses":22,"wins":12},"gpt-5.5":{"draws":5,"losses":20,"wins":3},"gpt-5.6-luna":{"draws":7,"losses":14,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":27,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":17,"wins":5},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":3,"losses":20,"wins":7},"gpt-6-sol":{"draws":0,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":30,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":1,"wins":13},"inclusionai/ling-3.0-flash":{"draws":6,"losses":7,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":16,"wins":11},"meta/muse-glimmer-30b":{"draws":6,"losses":13,"wins":7},"meta/muse-spark-1.2":{"draws":1,"losses":20,"wins":7},"meta/muse-spark-1.3":{"draws":2,"losses":28,"wins":0},"meta/muse-wonder":{"draws":1,"losses":28,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":10,"wins":4},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":1},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":3,"losses":22,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":8,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":12,"wins":8},"o3":{"draws":7,"losses":38,"wins":11},"openai/gpt-oss-120b":{"draws":4,"losses":10,"wins":12},"poolside/laguna-s-2.1":{"draws":8,"losses":14,"wins":8},"qwen/qwen3.7-max":{"draws":4,"losses":13,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":10,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":22,"wins":5},"qwen/qwen3.8-27b":{"draws":1,"losses":13,"wins":8},"qwen/qwen3.8-flash":{"draws":4,"losses":11,"wins":5},"qwen/qwen3.8-max":{"draws":5,"losses":24,"wins":1},"qwen/qwen3.8-max-0902":{"draws":7,"losses":17,"wins":6},"stealth/ox-alpha":{"draws":8,"losses":62,"wins":14},"stealth/space-bunny-alpha":{"draws":4,"losses":12,"wins":8},"stepfun/step-3.7-flash":{"draws":3,"losses":10,"wins":3},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":4,"losses":24,"wins":2},"thinkingmachines/inkling":{"draws":7,"losses":12,"wins":21},"thinkingmachines/inkling-small":{"draws":7,"losses":13,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":0,"losses":28,"wins":2},"x-ai/grok-4.6":{"draws":4,"losses":23,"wins":3},"x-ai/grok-4.7":{"draws":0,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":10,"losses":26,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":13,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":19,"wins":1},"z-ai/glm-5.2":{"draws":11,"losses":36,"wins":13},"z-ai/glm-5.3":{"draws":2,"losses":26,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":22,"wins":4},"z-ai/glm-5.3-flashx":{"draws":4,"losses":21,"wins":5}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":12,"wins":14},"claude-fable-5":{"draws":13,"losses":24,"wins":5},"claude-fable-5-1":{"draws":3,"losses":42,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":18,"wins":13},"claude-opus-4-5":{"draws":23,"losses":29,"wins":18},"claude-opus-4-8":{"draws":10,"losses":22,"wins":10},"claude-opus-5":{"draws":12,"losses":56,"wins":2},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":12,"losses":17,"wins":13},"claude-sonnet-5-5":{"draws":7,"losses":30,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":17,"losses":22,"wins":25},"deepseek/deepseek-v4-pro":{"draws":11,"losses":16,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":14,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":21,"wins":11},"fireworks/ember-1":{"draws":15,"losses":21,"wins":6},"gemini-3.1-pro-preview":{"draws":11,"losses":17,"wins":14},"google/gemini-3.1-flash-lite":{"draws":8,"losses":7,"wins":17},"google/gemini-3.5-flash":{"draws":14,"losses":23,"wins":17},"google/gemini-3.5-flash-lite":{"draws":20,"losses":20,"wins":34},"google/gemini-3.6-flash":{"draws":22,"losses":42,"wins":16},"google/gemini-3.8-flash":{"draws":14,"losses":23,"wins":5},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":12},"gpt-4.1":{"draws":6,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":1},"gpt-5":{"draws":9,"losses":11,"wins":16},"gpt-5.4":{"draws":11,"losses":21,"wins":8},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":16,"wins":21},"gpt-5.5":{"draws":17,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":15,"losses":14,"wins":13},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":7},"gpt-5.6-terra":{"draws":15,"losses":16,"wins":9},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":14,"losses":16,"wins":12},"gpt-6-sol":{"draws":5,"losses":34,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":8,"wins":11},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":15,"wins":20},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":19},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":29,"wins":8},"meta/muse-wonder":{"draws":6,"losses":30,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":7,"wins":10},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":12},"nex-agi/nex-n2-pro":{"draws":6,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":8,"wins":15},"o3":{"draws":10,"losses":24,"wins":28},"openai/gpt-oss-120b":{"draws":10,"losses":10,"wins":16},"poolside/laguna-s-2.1":{"draws":12,"losses":10,"wins":16},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":17,"wins":10},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":14,"losses":20,"wins":8},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":8},"stealth/ox-alpha":{"draws":36,"losses":57,"wins":25},"stealth/space-bunny-alpha":{"draws":10,"losses":11,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":15},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":5},"tencent/hy4-preview":{"draws":11,"losses":17,"wins":12},"thinkingmachines/inkling":{"draws":15,"losses":9,"wins":30},"thinkingmachines/inkling-small":{"draws":13,"losses":11,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":10,"losses":29,"wins":3},"x-ai/grok-4.6":{"draws":9,"losses":25,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":32,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":22,"losses":20,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":13,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":22,"losses":33,"wins":29},"z-ai/glm-5.3":{"draws":7,"losses":27,"wins":6},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":8},"z-ai/glm-5.3-flashx":{"draws":6,"losses":27,"wins":9}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":2,"wins":26},"claude-fable-5":{"draws":11,"losses":19,"wins":18},"claude-fable-5-1":{"draws":4,"losses":42,"wins":8},"claude-haiku-5-5":{"draws":15,"losses":14,"wins":17},"claude-opus-4-5":{"draws":21,"losses":14,"wins":43},"claude-opus-4-8":{"draws":12,"losses":11,"wins":21},"claude-opus-5":{"draws":11,"losses":56,"wins":15},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":14,"losses":4,"wins":30},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":21},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":21,"losses":6,"wins":45},"deepseek/deepseek-v4-pro":{"draws":11,"losses":8,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":5,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":8,"wins":24},"fireworks/ember-1":{"draws":14,"losses":7,"wins":27},"gemini-3.1-pro-preview":{"draws":12,"losses":13,"wins":23},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":17,"losses":5,"wins":38},"google/gemini-3.5-flash-lite":{"draws":26,"losses":7,"wins":51},"google/gemini-3.6-flash":{"draws":24,"losses":23,"wins":45},"google/gemini-3.8-flash":{"draws":12,"losses":12,"wins":24},"google/gemma-4-31b-it":{"draws":10,"losses":1,"wins":17},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":17,"losses":7,"wins":18},"gpt-5.4":{"draws":13,"losses":16,"wins":17},"gpt-5.4-mini":{"draws":13,"losses":1,"wins":18},"gpt-5.4-nano":{"draws":9,"losses":8,"wins":31},"gpt-5.5":{"draws":14,"losses":10,"wins":20},"gpt-5.6-luna":{"draws":17,"losses":5,"wins":26},"gpt-5.6-sol":{"draws":6,"losses":21,"wins":21},"gpt-5.6-terra":{"draws":15,"losses":7,"wins":24},"gpt-6-astra":{"draws":5,"losses":40,"wins":3},"gpt-6-luna":{"draws":13,"losses":8,"wins":27},"gpt-6-sol":{"draws":7,"losses":26,"wins":15},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":1,"wins":16},"inclusionai/ling-3.0-flash":{"draws":18,"losses":0,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":7,"wins":31},"meta/muse-glimmer-30b":{"draws":16,"losses":0,"wins":26},"meta/muse-spark-1.2":{"draws":4,"losses":14,"wins":28},"meta/muse-spark-1.3":{"draws":14,"losses":17,"wins":17},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":19},"mistralai/mistral-large-4-0":{"draws":11,"losses":5,"wins":14},"mistralai/mistral-medium-3-5":{"draws":9,"losses":1,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":11,"losses":9,"wins":26},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":2,"wins":22},"o3":{"draws":14,"losses":14,"wins":38},"openai/gpt-oss-120b":{"draws":17,"losses":4,"wins":21},"poolside/laguna-s-2.1":{"draws":18,"losses":5,"wins":23},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":12,"wins":26},"qwen/qwen3.8-27b":{"draws":10,"losses":5,"wins":19},"qwen/qwen3.8-flash":{"draws":11,"losses":7,"wins":14},"qwen/qwen3.8-max":{"draws":13,"losses":10,"wins":25},"qwen/qwen3.8-max-0902":{"draws":11,"losses":11,"wins":26},"stealth/ox-alpha":{"draws":37,"losses":26,"wins":95},"stealth/space-bunny-alpha":{"draws":10,"losses":4,"wins":24},"stepfun/step-3.7-flash":{"draws":10,"losses":4,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":14},"tencent/hy4-preview":{"draws":7,"losses":5,"wins":18},"thinkingmachines/inkling":{"draws":19,"losses":9,"wins":36},"thinkingmachines/inkling-small":{"draws":14,"losses":3,"wins":31},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":5,"losses":14,"wins":29},"x-ai/grok-4.6":{"draws":18,"losses":15,"wins":15},"x-ai/grok-4.7":{"draws":4,"losses":24,"wins":14},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":28,"losses":0,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":13,"wins":12},"z-ai/glm-5.2":{"draws":24,"losses":8,"wins":64},"z-ai/glm-5.3":{"draws":9,"losses":25,"wins":12},"z-ai/glm-5.3-flash":{"draws":12,"losses":18,"wins":18},"z-ai/glm-5.3-flashx":{"draws":12,"losses":10,"wins":26}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":32,"wins":20},"claude-fable-5":{"draws":14,"losses":65,"wins":5},"claude-fable-5-1":{"draws":2,"losses":92,"wins":0},"claude-haiku-5-5":{"draws":28,"losses":43,"wins":9},"claude-opus-4-5":{"draws":44,"losses":71,"wins":21},"claude-opus-4-8":{"draws":19,"losses":46,"wins":11},"claude-opus-5":{"draws":21,"losses":119,"wins":10},"claude-opus-5-5":{"draws":7,"losses":85,"wins":0},"claude-sonnet-5":{"draws":28,"losses":45,"wins":11},"claude-sonnet-5-5":{"draws":19,"losses":47,"wins":18},"cohere/north-mini-code":{"draws":7,"losses":8,"wins":17},"deepseek/deepseek-v4-flash":{"draws":44,"losses":29,"wins":55},"deepseek/deepseek-v4-pro":{"draws":24,"losses":39,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":33,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":43,"wins":14},"fireworks/ember-1":{"draws":28,"losses":45,"wins":11},"gemini-3.1-pro-preview":{"draws":29,"losses":35,"wins":20},"google/gemini-3.1-flash-lite":{"draws":18,"losses":6,"wins":30},"google/gemini-3.5-flash":{"draws":28,"losses":49,"wins":27},"google/gemini-3.5-flash-lite":{"draws":46,"losses":48,"wins":50},"google/gemini-3.6-flash":{"draws":44,"losses":84,"wins":32},"google/gemini-3.8-flash":{"draws":28,"losses":47,"wins":9},"google/gemma-4-31b-it":{"draws":17,"losses":12,"wins":19},"gpt-4.1":{"draws":8,"losses":10,"wins":10},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":19,"losses":36,"wins":21},"gpt-5.4":{"draws":21,"losses":44,"wins":15},"gpt-5.4-mini":{"draws":23,"losses":16,"wins":17},"gpt-5.4-nano":{"draws":26,"losses":26,"wins":34},"gpt-5.5":{"draws":24,"losses":42,"wins":12},"gpt-5.6-luna":{"draws":30,"losses":34,"wins":20},"gpt-5.6-sol":{"draws":13,"losses":62,"wins":9},"gpt-5.6-terra":{"draws":24,"losses":39,"wins":17},"gpt-6-astra":{"draws":6,"losses":76,"wins":2},"gpt-6-luna":{"draws":23,"losses":41,"wins":20},"gpt-6-sol":{"draws":8,"losses":67,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":74,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":27,"losses":10,"wins":19},"inclusionai/ling-3.0-flash":{"draws":25,"losses":10,"wins":23},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":24,"losses":27,"wins":39},"meta/muse-glimmer-30b":{"draws":26,"losses":23,"wins":27},"meta/muse-spark-1.2":{"draws":22,"losses":49,"wins":11},"meta/muse-spark-1.3":{"draws":14,"losses":61,"wins":9},"meta/muse-wonder":{"draws":24,"losses":52,"wins":8},"minimax/minimax-m3":{"draws":12,"losses":15,"wins":21},"mistralai/mistral-large-4-0":{"draws":19,"losses":25,"wins":10},"mistralai/mistral-medium-3-5":{"draws":17,"losses":7,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":25,"losses":40,"wins":17},"nex-agi/nex-n2-pro":{"draws":10,"losses":13,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":21,"wins":26},"o3":{"draws":25,"losses":59,"wins":32},"openai/gpt-oss-120b":{"draws":23,"losses":19,"wins":34},"poolside/laguna-s-2.1":{"draws":29,"losses":31,"wins":26},"qwen/qwen3.7-max":{"draws":16,"losses":25,"wins":9},"qwen/qwen3.7-plus":{"draws":15,"losses":15,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":47,"wins":8},"qwen/qwen3.8-27b":{"draws":19,"losses":26,"wins":13},"qwen/qwen3.8-flash":{"draws":21,"losses":24,"wins":11},"qwen/qwen3.8-max":{"draws":27,"losses":39,"wins":18},"qwen/qwen3.8-max-0902":{"draws":26,"losses":44,"wins":14},"stealth/ox-alpha":{"draws":71,"losses":156,"wins":55},"stealth/space-bunny-alpha":{"draws":21,"losses":23,"wins":22},"stepfun/step-3.7-flash":{"draws":19,"losses":17,"wins":24},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":15,"losses":20,"wins":11},"tencent/hy4-preview":{"draws":19,"losses":45,"wins":16},"thinkingmachines/inkling":{"draws":25,"losses":29,"wins":32},"thinkingmachines/inkling-small":{"draws":33,"losses":13,"wins":38},"unbiased/pareto-26.10-preview":{"draws":0,"losses":27,"wins":1},"upstage/solar-mini4":{"draws":3,"losses":7,"wins":8},"x-ai/grok-4.5":{"draws":27,"losses":47,"wins":10},"x-ai/grok-4.6":{"draws":26,"losses":51,"wins":7},"x-ai/grok-4.7":{"draws":13,"losses":58,"wins":5},"x-ai/grok-build-0.1":{"draws":11,"losses":8,"wins":9},"xiaomi/mimo-v2.5":{"draws":46,"losses":40,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":20,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":25,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":40,"wins":7},"z-ai/glm-5.2":{"draws":45,"losses":74,"wins":49},"z-ai/glm-5.3":{"draws":18,"losses":53,"wins":9},"z-ai/glm-5.3-flash":{"draws":19,"losses":50,"wins":15},"z-ai/glm-5.3-flashx":{"draws":22,"losses":50,"wins":12}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":17,"wins":11},"claude-fable-5":{"draws":8,"losses":35,"wins":5},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":30,"wins":5},"claude-opus-4-5":{"draws":30,"losses":30,"wins":18},"claude-opus-4-8":{"draws":13,"losses":25,"wins":6},"claude-opus-5":{"draws":13,"losses":67,"wins":2},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":14,"losses":24,"wins":10},"claude-sonnet-5-5":{"draws":11,"losses":28,"wins":9},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":25,"losses":25,"wins":22},"deepseek/deepseek-v4-pro":{"draws":17,"losses":19,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":23,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":22,"wins":8},"fireworks/ember-1":{"draws":17,"losses":23,"wins":8},"gemini-3.1-pro-preview":{"draws":15,"losses":16,"wins":17},"google/gemini-3.1-flash-lite":{"draws":12,"losses":4,"wins":16},"google/gemini-3.5-flash":{"draws":18,"losses":30,"wins":12},"google/gemini-3.5-flash-lite":{"draws":27,"losses":22,"wins":35},"google/gemini-3.6-flash":{"draws":31,"losses":48,"wins":13},"google/gemini-3.8-flash":{"draws":13,"losses":29,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":10},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":16,"losses":19,"wins":7},"gpt-5.4":{"draws":11,"losses":29,"wins":6},"gpt-5.4-mini":{"draws":15,"losses":8,"wins":9},"gpt-5.4-nano":{"draws":18,"losses":13,"wins":17},"gpt-5.5":{"draws":20,"losses":19,"wins":5},"gpt-5.6-luna":{"draws":21,"losses":12,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":6},"gpt-5.6-terra":{"draws":14,"losses":21,"wins":11},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":15,"losses":19,"wins":14},"gpt-6-sol":{"draws":6,"losses":36,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":5,"wins":12},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":11,"wins":20},"meta/muse-glimmer-30b":{"draws":20,"losses":12,"wins":10},"meta/muse-spark-1.2":{"draws":13,"losses":23,"wins":10},"meta/muse-spark-1.3":{"draws":15,"losses":28,"wins":5},"meta/muse-wonder":{"draws":11,"losses":30,"wins":7},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":8},"mistralai/mistral-large-4-0":{"draws":9,"losses":16,"wins":5},"mistralai/mistral-medium-3-5":{"draws":11,"losses":2,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":21,"wins":8},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":4,"wins":18},"o3":{"draws":15,"losses":31,"wins":20},"openai/gpt-oss-120b":{"draws":18,"losses":9,"wins":15},"poolside/laguna-s-2.1":{"draws":18,"losses":18,"wins":10},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":18,"wins":9},"qwen/qwen3.8-27b":{"draws":12,"losses":16,"wins":6},"qwen/qwen3.8-flash":{"draws":16,"losses":7,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":17},"qwen/qwen3.8-max-0902":{"draws":16,"losses":26,"wins":6},"stealth/ox-alpha":{"draws":41,"losses":93,"wins":24},"stealth/space-bunny-alpha":{"draws":12,"losses":15,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":9,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":16,"losses":25,"wins":5},"thinkingmachines/inkling":{"draws":21,"losses":16,"wins":27},"thinkingmachines/inkling-small":{"draws":12,"losses":5,"wins":15},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":9,"losses":30,"wins":9},"x-ai/grok-4.6":{"draws":17,"losses":24,"wins":7},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"x-ai/grok-build-0.1":{"draws":8,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":34,"losses":17,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":11,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":18,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":23,"wins":4},"z-ai/glm-5.2":{"draws":36,"losses":35,"wins":25},"z-ai/glm-5.3":{"draws":7,"losses":35,"wins":4},"z-ai/glm-5.3-flash":{"draws":14,"losses":26,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":26,"wins":10}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":6,"wins":10},"claude-fable-5":{"draws":0,"losses":14,"wins":4},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":0,"losses":20,"wins":10},"claude-opus-4-8":{"draws":0,"losses":15,"wins":3},"claude-opus-5":{"draws":0,"losses":22,"wins":0},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":0,"losses":11,"wins":7},"claude-sonnet-5-5":{"draws":0,"losses":13,"wins":5},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":0,"losses":15,"wins":13},"deepseek/deepseek-v4-pro":{"draws":0,"losses":12,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":14,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":15,"wins":3},"fireworks/ember-1":{"draws":0,"losses":11,"wins":7},"gemini-3.1-pro-preview":{"draws":0,"losses":8,"wins":10},"google/gemini-3.1-flash-lite":{"draws":0,"losses":3,"wins":15},"google/gemini-3.5-flash":{"draws":0,"losses":15,"wins":9},"google/gemini-3.5-flash-lite":{"draws":0,"losses":12,"wins":22},"google/gemini-3.6-flash":{"draws":1,"losses":28,"wins":7},"google/gemini-3.8-flash":{"draws":0,"losses":15,"wins":3},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":9},"gpt-4.1":{"draws":0,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":13,"wins":3},"gpt-5.4":{"draws":0,"losses":16,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":5,"wins":7},"gpt-5.4-nano":{"draws":0,"losses":11,"wins":11},"gpt-5.5":{"draws":0,"losses":11,"wins":5},"gpt-5.6-luna":{"draws":1,"losses":8,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":16,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":12,"wins":4},"gpt-6-astra":{"draws":0,"losses":18,"wins":0},"gpt-6-luna":{"draws":0,"losses":9,"wins":9},"gpt-6-sol":{"draws":0,"losses":17,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":18,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":7,"wins":7},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":1,"losses":9,"wins":14},"meta/muse-glimmer-30b":{"draws":0,"losses":6,"wins":8},"meta/muse-spark-1.2":{"draws":0,"losses":13,"wins":3},"meta/muse-spark-1.3":{"draws":0,"losses":14,"wins":4},"meta/muse-wonder":{"draws":0,"losses":17,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":8},"mistralai/mistral-large-4-0":{"draws":0,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":12,"wins":4},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":10},"o3":{"draws":2,"losses":22,"wins":12},"openai/gpt-oss-120b":{"draws":0,"losses":7,"wins":9},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":0,"losses":7,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":14,"wins":4},"qwen/qwen3.8-27b":{"draws":0,"losses":9,"wins":5},"qwen/qwen3.8-flash":{"draws":0,"losses":8,"wins":4},"qwen/qwen3.8-max":{"draws":0,"losses":11,"wins":7},"qwen/qwen3.8-max-0902":{"draws":0,"losses":15,"wins":3},"stealth/ox-alpha":{"draws":0,"losses":40,"wins":12},"stealth/space-bunny-alpha":{"draws":0,"losses":9,"wins":7},"stepfun/step-3.7-flash":{"draws":0,"losses":10,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy4-preview":{"draws":0,"losses":15,"wins":3},"thinkingmachines/inkling":{"draws":0,"losses":5,"wins":19},"thinkingmachines/inkling-small":{"draws":0,"losses":3,"wins":15},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":0,"losses":13,"wins":5},"x-ai/grok-4.6":{"draws":0,"losses":14,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":13,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":0,"losses":5,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":7,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":12,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":9,"wins":3},"z-ai/glm-5.2":{"draws":0,"losses":22,"wins":14},"z-ai/glm-5.3":{"draws":0,"losses":18,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":12,"wins":6},"z-ai/glm-5.3-flashx":{"draws":0,"losses":15,"wins":3}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":1,"wins":33},"claude-fable-5":{"draws":6,"losses":17,"wins":25},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":13,"wins":23},"claude-opus-4-5":{"draws":19,"losses":19,"wins":40},"claude-opus-4-8":{"draws":11,"losses":15,"wins":18},"claude-opus-5":{"draws":10,"losses":56,"wins":16},"claude-opus-5-5":{"draws":9,"losses":38,"wins":5},"claude-sonnet-5":{"draws":9,"losses":11,"wins":28},"claude-sonnet-5-5":{"draws":7,"losses":21,"wins":20},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":9,"losses":9,"wins":54},"deepseek/deepseek-v4-pro":{"draws":14,"losses":8,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":12,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":16,"wins":26},"fireworks/ember-1":{"draws":5,"losses":12,"wins":31},"gemini-3.1-pro-preview":{"draws":8,"losses":12,"wins":28},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":6,"losses":18,"wins":36},"google/gemini-3.5-flash-lite":{"draws":16,"losses":17,"wins":51},"google/gemini-3.6-flash":{"draws":14,"losses":29,"wins":49},"google/gemini-3.8-flash":{"draws":5,"losses":16,"wins":27},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":21},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":9,"wins":24},"gpt-5.4":{"draws":10,"losses":16,"wins":20},"gpt-5.4-mini":{"draws":7,"losses":4,"wins":21},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":30},"gpt-5.5":{"draws":11,"losses":13,"wins":20},"gpt-5.6-luna":{"draws":7,"losses":13,"wins":28},"gpt-5.6-sol":{"draws":5,"losses":23,"wins":20},"gpt-5.6-terra":{"draws":10,"losses":6,"wins":30},"gpt-6-astra":{"draws":1,"losses":41,"wins":6},"gpt-6-luna":{"draws":6,"losses":15,"wins":27},"gpt-6-sol":{"draws":6,"losses":30,"wins":12},"gpt-6.1-sol":{"draws":2,"losses":38,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":25},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":2,"wins":41},"meta/muse-glimmer-30b":{"draws":7,"losses":6,"wins":29},"meta/muse-spark-1.2":{"draws":8,"losses":11,"wins":27},"meta/muse-spark-1.3":{"draws":6,"losses":19,"wins":23},"meta/muse-wonder":{"draws":11,"losses":26,"wins":11},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":7,"losses":1,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":27},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":1,"wins":31},"o3":{"draws":7,"losses":12,"wins":47},"openai/gpt-oss-120b":{"draws":8,"losses":3,"wins":31},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":32},"qwen/qwen3.7-max":{"draws":4,"losses":6,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-27b":{"draws":9,"losses":5,"wins":20},"qwen/qwen3.8-flash":{"draws":5,"losses":10,"wins":17},"qwen/qwen3.8-max":{"draws":9,"losses":12,"wins":27},"qwen/qwen3.8-max-0902":{"draws":8,"losses":16,"wins":24},"stealth/ox-alpha":{"draws":30,"losses":51,"wins":77},"stealth/space-bunny-alpha":{"draws":8,"losses":8,"wins":22},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":9,"losses":16,"wins":21},"thinkingmachines/inkling":{"draws":15,"losses":7,"wins":42},"thinkingmachines/inkling-small":{"draws":5,"losses":7,"wins":36},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":13,"losses":8,"wins":11},"x-ai/grok-4.6":{"draws":9,"losses":16,"wins":23},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":12,"losses":6,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":13},"z-ai/glm-5.2":{"draws":19,"losses":15,"wins":62},"z-ai/glm-5.3":{"draws":8,"losses":24,"wins":14},"z-ai/glm-5.3-flash":{"draws":6,"losses":20,"wins":22},"z-ai/glm-5.3-flashx":{"draws":4,"losses":20,"wins":24}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":6,"wins":28},"claude-fable-5":{"draws":10,"losses":17,"wins":21},"claude-fable-5-1":{"draws":4,"losses":36,"wins":14},"claude-haiku-5-5":{"draws":13,"losses":15,"wins":18},"claude-opus-4-5":{"draws":17,"losses":18,"wins":43},"claude-opus-4-8":{"draws":9,"losses":13,"wins":22},"claude-opus-5":{"draws":10,"losses":47,"wins":24},"claude-opus-5-5":{"draws":7,"losses":39,"wins":6},"claude-sonnet-5":{"draws":9,"losses":8,"wins":31},"claude-sonnet-5-5":{"draws":4,"losses":19,"wins":25},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":19,"losses":4,"wins":49},"deepseek/deepseek-v4-pro":{"draws":10,"losses":9,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":9,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":13,"wins":27},"fireworks/ember-1":{"draws":12,"losses":13,"wins":23},"gemini-3.1-pro-preview":{"draws":9,"losses":7,"wins":32},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":15,"losses":9,"wins":36},"google/gemini-3.5-flash-lite":{"draws":18,"losses":11,"wins":55},"google/gemini-3.6-flash":{"draws":17,"losses":30,"wins":45},"google/gemini-3.8-flash":{"draws":14,"losses":12,"wins":22},"google/gemma-4-31b-it":{"draws":9,"losses":0,"wins":19},"gpt-4.1":{"draws":6,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":13,"losses":3,"wins":26},"gpt-5.4":{"draws":13,"losses":12,"wins":21},"gpt-5.4-mini":{"draws":11,"losses":4,"wins":17},"gpt-5.4-nano":{"draws":9,"losses":7,"wins":32},"gpt-5.5":{"draws":13,"losses":6,"wins":25},"gpt-5.6-luna":{"draws":10,"losses":6,"wins":32},"gpt-5.6-sol":{"draws":8,"losses":15,"wins":25},"gpt-5.6-terra":{"draws":10,"losses":3,"wins":33},"gpt-6-astra":{"draws":4,"losses":36,"wins":8},"gpt-6-luna":{"draws":10,"losses":11,"wins":27},"gpt-6-sol":{"draws":2,"losses":36,"wins":10},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":25},"inclusionai/ling-3.0-flash":{"draws":12,"losses":1,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":12,"losses":2,"wins":38},"meta/muse-glimmer-30b":{"draws":11,"losses":5,"wins":26},"meta/muse-spark-1.2":{"draws":8,"losses":12,"wins":26},"meta/muse-spark-1.3":{"draws":10,"losses":18,"wins":20},"meta/muse-wonder":{"draws":11,"losses":20,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"mistralai/mistral-large-4-0":{"draws":11,"losses":4,"wins":15},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":6,"losses":14,"wins":26},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":4,"wins":20},"o3":{"draws":16,"losses":15,"wins":35},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":12,"losses":3,"wins":31},"qwen/qwen3.7-max":{"draws":4,"losses":7,"wins":17},"qwen/qwen3.7-plus":{"draws":8,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":20,"wins":22},"qwen/qwen3.8-27b":{"draws":7,"losses":7,"wins":20},"qwen/qwen3.8-flash":{"draws":13,"losses":2,"wins":17},"qwen/qwen3.8-max":{"draws":7,"losses":16,"wins":25},"qwen/qwen3.8-max-0902":{"draws":12,"losses":13,"wins":23},"stealth/ox-alpha":{"draws":46,"losses":44,"wins":68},"stealth/space-bunny-alpha":{"draws":10,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":8,"losses":2,"wins":24},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":18},"tencent/hy4-preview":{"draws":17,"losses":8,"wins":21},"thinkingmachines/inkling":{"draws":20,"losses":6,"wins":38},"thinkingmachines/inkling-small":{"draws":15,"losses":5,"wins":28},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":13,"losses":14,"wins":21},"x-ai/grok-4.6":{"draws":12,"losses":5,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":22,"losses":4,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":8,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":10,"wins":13},"z-ai/glm-5.2":{"draws":22,"losses":15,"wins":59},"z-ai/glm-5.3":{"draws":10,"losses":17,"wins":19},"z-ai/glm-5.3-flash":{"draws":11,"losses":16,"wins":21},"z-ai/glm-5.3-flashx":{"draws":11,"losses":13,"wins":24}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":37},"claude-fable-5":{"draws":1,"losses":12,"wins":29},"claude-fable-5-1":{"draws":1,"losses":28,"wins":17},"claude-haiku-5-5":{"draws":0,"losses":4,"wins":36},"claude-opus-4-5":{"draws":1,"losses":5,"wins":62},"claude-opus-4-8":{"draws":3,"losses":7,"wins":28},"claude-opus-5":{"draws":4,"losses":30,"wins":36},"claude-opus-5-5":{"draws":0,"losses":32,"wins":14},"claude-sonnet-5":{"draws":0,"losses":6,"wins":36},"claude-sonnet-5-5":{"draws":0,"losses":14,"wins":28},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":64},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":4,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":37},"fireworks/ember-1":{"draws":3,"losses":8,"wins":31},"gemini-3.1-pro-preview":{"draws":2,"losses":4,"wins":36},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":3,"losses":1,"wins":48},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":71},"google/gemini-3.6-flash":{"draws":2,"losses":11,"wins":67},"google/gemini-3.8-flash":{"draws":4,"losses":6,"wins":32},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":24},"gpt-4.1":{"draws":0,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":3,"wins":32},"gpt-5.4":{"draws":2,"losses":8,"wins":30},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":25},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":43},"gpt-5.5":{"draws":3,"losses":9,"wins":26},"gpt-5.6-luna":{"draws":1,"losses":4,"wins":37},"gpt-5.6-sol":{"draws":6,"losses":8,"wins":28},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":34},"gpt-6-astra":{"draws":4,"losses":30,"wins":8},"gpt-6-luna":{"draws":0,"losses":6,"wins":36},"gpt-6-sol":{"draws":1,"losses":13,"wins":28},"gpt-6.1-sol":{"draws":1,"losses":24,"wins":17},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":27},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":45},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":34},"meta/muse-spark-1.2":{"draws":0,"losses":5,"wins":35},"meta/muse-spark-1.3":{"draws":2,"losses":6,"wins":34},"meta/muse-wonder":{"draws":5,"losses":10,"wins":27},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":23},"mistralai/mistral-large-4-0":{"draws":2,"losses":3,"wins":21},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":1,"losses":4,"wins":35},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":36},"o3":{"draws":1,"losses":10,"wins":51},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":38},"poolside/laguna-s-2.1":{"draws":1,"losses":2,"wins":41},"qwen/qwen3.7-max":{"draws":1,"losses":4,"wins":21},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":6,"wins":36},"qwen/qwen3.8-27b":{"draws":1,"losses":3,"wins":26},"qwen/qwen3.8-flash":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.8-max":{"draws":1,"losses":6,"wins":35},"qwen/qwen3.8-max-0902":{"draws":5,"losses":7,"wins":30},"stealth/ox-alpha":{"draws":6,"losses":16,"wins":118},"stealth/space-bunny-alpha":{"draws":0,"losses":5,"wins":27},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":3,"losses":5,"wins":32},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":49},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":39},"unbiased/pareto-26.10-preview":{"draws":1,"losses":8,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":3,"losses":4,"wins":35},"x-ai/grok-4.6":{"draws":5,"losses":9,"wins":28},"x-ai/grok-4.7":{"draws":0,"losses":9,"wins":15},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":1,"losses":3,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":5,"wins":23},"z-ai/glm-5.2":{"draws":4,"losses":9,"wins":71},"z-ai/glm-5.3":{"draws":4,"losses":6,"wins":30},"z-ai/glm-5.3-flash":{"draws":2,"losses":5,"wins":35},"z-ai/glm-5.3-flashx":{"draws":3,"losses":6,"wins":33}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":7,"wins":6},"claude-fable-5":{"draws":10,"losses":20,"wins":0},"claude-fable-5-1":{"draws":1,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":17,"wins":1},"claude-opus-4-5":{"draws":28,"losses":19,"wins":3},"claude-opus-4-8":{"draws":11,"losses":16,"wins":3},"claude-opus-5":{"draws":9,"losses":38,"wins":3},"claude-opus-5-5":{"draws":2,"losses":32,"wins":0},"claude-sonnet-5":{"draws":15,"losses":10,"wins":5},"claude-sonnet-5-5":{"draws":11,"losses":17,"wins":2},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":25,"losses":12,"wins":9},"deepseek/deepseek-v4-pro":{"draws":15,"losses":8,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":9,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":12,"wins":1},"fireworks/ember-1":{"draws":17,"losses":10,"wins":3},"gemini-3.1-pro-preview":{"draws":15,"losses":10,"wins":5},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":19,"losses":15,"wins":4},"google/gemini-3.5-flash-lite":{"draws":30,"losses":13,"wins":9},"google/gemini-3.6-flash":{"draws":26,"losses":23,"wins":7},"google/gemini-3.8-flash":{"draws":12,"losses":17,"wins":1},"google/gemma-4-31b-it":{"draws":14,"losses":1,"wins":3},"gpt-4.1":{"draws":6,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":8,"wins":2},"gpt-5.4":{"draws":10,"losses":15,"wins":3},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":4},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":4},"gpt-5.5":{"draws":15,"losses":7,"wins":4},"gpt-5.6-luna":{"draws":18,"losses":9,"wins":3},"gpt-5.6-sol":{"draws":9,"losses":18,"wins":3},"gpt-5.6-terra":{"draws":19,"losses":9,"wins":2},"gpt-6-astra":{"draws":2,"losses":28,"wins":0},"gpt-6-luna":{"draws":18,"losses":10,"wins":2},"gpt-6-sol":{"draws":5,"losses":23,"wins":2},"gpt-6.1-sol":{"draws":5,"losses":25,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":0,"wins":7},"inclusionai/ling-3.0-flash":{"draws":17,"losses":3,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":6,"wins":6},"meta/muse-glimmer-30b":{"draws":19,"losses":3,"wins":2},"meta/muse-spark-1.2":{"draws":11,"losses":15,"wins":2},"meta/muse-spark-1.3":{"draws":11,"losses":19,"wins":0},"meta/muse-wonder":{"draws":9,"losses":17,"wins":4},"minimax/minimax-m3":{"draws":9,"losses":5,"wins":2},"mistralai/mistral-large-4-0":{"draws":12,"losses":6,"wins":0},"mistralai/mistral-medium-3-5":{"draws":13,"losses":2,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":8,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":4,"wins":4},"o3":{"draws":15,"losses":16,"wins":7},"openai/gpt-oss-120b":{"draws":13,"losses":8,"wins":3},"poolside/laguna-s-2.1":{"draws":17,"losses":7,"wins":2},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":2},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":9,"wins":3},"qwen/qwen3.8-27b":{"draws":11,"losses":8,"wins":3},"qwen/qwen3.8-flash":{"draws":16,"losses":4,"wins":0},"qwen/qwen3.8-max":{"draws":16,"losses":8,"wins":6},"qwen/qwen3.8-max-0902":{"draws":18,"losses":8,"wins":4},"stealth/ox-alpha":{"draws":37,"losses":36,"wins":9},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":2},"stepfun/step-3.7-flash":{"draws":11,"losses":6,"wins":3},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":3},"tencent/hy4-preview":{"draws":15,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":22,"losses":8,"wins":6},"thinkingmachines/inkling-small":{"draws":21,"losses":4,"wins":5},"unbiased/pareto-26.10-preview":{"draws":2,"losses":8,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":14,"losses":14,"wins":2},"x-ai/grok-4.6":{"draws":14,"losses":13,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":20,"wins":1},"x-ai/grok-build-0.1":{"draws":8,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":23,"losses":13,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":6,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":9,"wins":4},"z-ai/glm-5.2":{"draws":34,"losses":19,"wins":7},"z-ai/glm-5.3":{"draws":11,"losses":17,"wins":0},"z-ai/glm-5.3-flash":{"draws":10,"losses":17,"wins":3},"z-ai/glm-5.3-flashx":{"draws":15,"losses":14,"wins":1}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":14},"claude-fable-5":{"draws":12,"losses":28,"wins":8},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":24,"wins":9},"claude-opus-4-5":{"draws":19,"losses":34,"wins":25},"claude-opus-4-8":{"draws":12,"losses":20,"wins":12},"claude-opus-5":{"draws":19,"losses":60,"wins":3},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":8,"losses":22,"wins":18},"claude-sonnet-5-5":{"draws":8,"losses":26,"wins":14},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":27,"losses":19,"wins":26},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":18,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":20,"wins":12},"fireworks/ember-1":{"draws":13,"losses":19,"wins":16},"gemini-3.1-pro-preview":{"draws":10,"losses":16,"wins":22},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":18,"losses":26,"wins":16},"google/gemini-3.5-flash-lite":{"draws":29,"losses":18,"wins":37},"google/gemini-3.6-flash":{"draws":23,"losses":45,"wins":24},"google/gemini-3.8-flash":{"draws":14,"losses":25,"wins":9},"google/gemma-4-31b-it":{"draws":9,"losses":7,"wins":12},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":16,"losses":15,"wins":11},"gpt-5.4":{"draws":14,"losses":26,"wins":6},"gpt-5.4-mini":{"draws":13,"losses":5,"wins":14},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":21},"gpt-5.5":{"draws":13,"losses":21,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":11,"wins":22},"gpt-5.6-sol":{"draws":6,"losses":38,"wins":4},"gpt-5.6-terra":{"draws":24,"losses":18,"wins":4},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":18,"losses":21,"wins":9},"gpt-6-sol":{"draws":5,"losses":34,"wins":9},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":6,"wins":16},"inclusionai/ling-3.0-flash":{"draws":17,"losses":4,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":17,"wins":20},"meta/muse-glimmer-30b":{"draws":17,"losses":7,"wins":18},"meta/muse-spark-1.2":{"draws":9,"losses":24,"wins":13},"meta/muse-spark-1.3":{"draws":6,"losses":32,"wins":10},"meta/muse-wonder":{"draws":9,"losses":31,"wins":8},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":13},"mistralai/mistral-large-4-0":{"draws":13,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":9,"losses":5,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":20,"wins":9},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":7,"wins":13},"o3":{"draws":15,"losses":29,"wins":22},"openai/gpt-oss-120b":{"draws":14,"losses":6,"wins":22},"poolside/laguna-s-2.1":{"draws":18,"losses":7,"wins":21},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":19,"wins":14},"qwen/qwen3.8-27b":{"draws":9,"losses":10,"wins":15},"qwen/qwen3.8-flash":{"draws":11,"losses":13,"wins":8},"qwen/qwen3.8-max":{"draws":19,"losses":19,"wins":10},"qwen/qwen3.8-max-0902":{"draws":15,"losses":27,"wins":6},"stealth/ox-alpha":{"draws":49,"losses":75,"wins":34},"stealth/space-bunny-alpha":{"draws":18,"losses":9,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":9,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":15,"losses":21,"wins":10},"thinkingmachines/inkling":{"draws":18,"losses":18,"wins":28},"thinkingmachines/inkling-small":{"draws":18,"losses":10,"wins":20},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":9,"losses":27,"wins":12},"x-ai/grok-4.6":{"draws":14,"losses":25,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":32,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":34,"losses":14,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":7,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":19,"wins":4},"z-ai/glm-5.2":{"draws":29,"losses":27,"wins":24},"z-ai/glm-5.3":{"draws":11,"losses":26,"wins":9},"z-ai/glm-5.3-flash":{"draws":12,"losses":28,"wins":8},"z-ai/glm-5.3-flashx":{"draws":16,"losses":25,"wins":7}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":2,"wins":34},"claude-fable-5":{"draws":4,"losses":7,"wins":31},"claude-fable-5-1":{"draws":2,"losses":35,"wins":11},"claude-haiku-5-5":{"draws":4,"losses":4,"wins":32},"claude-opus-4-5":{"draws":5,"losses":4,"wins":59},"claude-opus-4-8":{"draws":5,"losses":5,"wins":28},"claude-opus-5":{"draws":6,"losses":25,"wins":39},"claude-opus-5-5":{"draws":2,"losses":32,"wins":12},"claude-sonnet-5":{"draws":5,"losses":2,"wins":35},"claude-sonnet-5-5":{"draws":6,"losses":14,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":57},"deepseek/deepseek-v4-pro":{"draws":1,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":2,"wins":37},"fireworks/ember-1":{"draws":3,"losses":2,"wins":37},"gemini-3.1-pro-preview":{"draws":6,"losses":5,"wins":31},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":43},"google/gemini-3.5-flash-lite":{"draws":4,"losses":1,"wins":69},"google/gemini-3.6-flash":{"draws":9,"losses":8,"wins":63},"google/gemini-3.8-flash":{"draws":7,"losses":5,"wins":30},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":21},"gpt-4.1":{"draws":1,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":3,"wins":33},"gpt-5.4":{"draws":5,"losses":2,"wins":33},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":26},"gpt-5.4-nano":{"draws":4,"losses":1,"wins":35},"gpt-5.5":{"draws":3,"losses":3,"wins":32},"gpt-5.6-luna":{"draws":6,"losses":0,"wins":36},"gpt-5.6-sol":{"draws":5,"losses":6,"wins":31},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":31},"gpt-6-astra":{"draws":8,"losses":27,"wins":7},"gpt-6-luna":{"draws":5,"losses":1,"wins":36},"gpt-6-sol":{"draws":7,"losses":17,"wins":18},"gpt-6.1-sol":{"draws":8,"losses":23,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":1,"wins":28},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":44},"meta/muse-glimmer-30b":{"draws":9,"losses":0,"wins":27},"meta/muse-spark-1.2":{"draws":5,"losses":3,"wins":32},"meta/muse-spark-1.3":{"draws":7,"losses":6,"wins":29},"meta/muse-wonder":{"draws":5,"losses":8,"wins":29},"minimax/minimax-m3":{"draws":5,"losses":0,"wins":17},"mistralai/mistral-large-4-0":{"draws":2,"losses":4,"wins":20},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":5,"losses":6,"wins":29},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":34},"o3":{"draws":1,"losses":1,"wins":54},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":33},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":36},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":21},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":3,"wins":38},"qwen/qwen3.8-27b":{"draws":3,"losses":2,"wins":23},"qwen/qwen3.8-flash":{"draws":4,"losses":1,"wins":23},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":36},"qwen/qwen3.8-max-0902":{"draws":8,"losses":5,"wins":29},"stealth/ox-alpha":{"draws":15,"losses":12,"wins":115},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":29},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":20},"tencent/hy4-preview":{"draws":3,"losses":3,"wins":34},"thinkingmachines/inkling":{"draws":6,"losses":3,"wins":45},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":38},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":4},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":6,"losses":4,"wins":32},"x-ai/grok-4.6":{"draws":5,"losses":6,"wins":31},"x-ai/grok-4.7":{"draws":5,"losses":13,"wins":18},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":5,"losses":0,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":5,"wins":17},"z-ai/glm-5.2":{"draws":11,"losses":3,"wins":70},"z-ai/glm-5.3":{"draws":6,"losses":1,"wins":21},"z-ai/glm-5.3-flash":{"draws":6,"losses":5,"wins":31},"z-ai/glm-5.3-flashx":{"draws":5,"losses":2,"wins":35}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":14,"wins":27},"claude-fable-5":{"draws":5,"losses":23,"wins":20},"claude-fable-5-1":{"draws":2,"losses":44,"wins":8},"claude-haiku-5-5":{"draws":7,"losses":17,"wins":22},"claude-opus-4-5":{"draws":11,"losses":19,"wins":48},"claude-opus-4-8":{"draws":5,"losses":17,"wins":22},"claude-opus-5":{"draws":11,"losses":53,"wins":18},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":3,"losses":15,"wins":30},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":6,"losses":20,"wins":46},"deepseek/deepseek-v4-pro":{"draws":2,"losses":15,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":12,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":21,"wins":23},"fireworks/ember-1":{"draws":7,"losses":17,"wins":24},"gemini-3.1-pro-preview":{"draws":13,"losses":13,"wins":22},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":22},"google/gemini-3.5-flash":{"draws":3,"losses":20,"wins":37},"google/gemini-3.5-flash-lite":{"draws":10,"losses":19,"wins":55},"google/gemini-3.6-flash":{"draws":6,"losses":35,"wins":51},"google/gemini-3.8-flash":{"draws":3,"losses":22,"wins":23},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":15},"gpt-4.1":{"draws":0,"losses":5,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":3},"gpt-5":{"draws":3,"losses":9,"wins":30},"gpt-5.4":{"draws":2,"losses":21,"wins":23},"gpt-5.4-mini":{"draws":7,"losses":4,"wins":21},"gpt-5.4-nano":{"draws":1,"losses":17,"wins":30},"gpt-5.5":{"draws":3,"losses":18,"wins":23},"gpt-5.6-luna":{"draws":7,"losses":9,"wins":32},"gpt-5.6-sol":{"draws":6,"losses":24,"wins":18},"gpt-5.6-terra":{"draws":5,"losses":16,"wins":25},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":9,"losses":12,"wins":27},"gpt-6-sol":{"draws":5,"losses":34,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":8,"wins":22},"inclusionai/ling-3.0-flash":{"draws":7,"losses":8,"wins":19},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":12,"wins":35},"meta/muse-glimmer-30b":{"draws":3,"losses":6,"wins":33},"meta/muse-spark-1.2":{"draws":3,"losses":20,"wins":23},"meta/muse-spark-1.3":{"draws":6,"losses":15,"wins":27},"meta/muse-wonder":{"draws":7,"losses":24,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":6,"wins":17},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":24},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":14,"wins":23},"o3":{"draws":5,"losses":30,"wins":31},"openai/gpt-oss-120b":{"draws":3,"losses":8,"wins":31},"poolside/laguna-s-2.1":{"draws":3,"losses":12,"wins":31},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":18},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":16,"wins":28},"qwen/qwen3.8-27b":{"draws":3,"losses":12,"wins":19},"qwen/qwen3.8-flash":{"draws":3,"losses":10,"wins":19},"qwen/qwen3.8-max":{"draws":8,"losses":20,"wins":20},"qwen/qwen3.8-max-0902":{"draws":10,"losses":15,"wins":23},"stealth/ox-alpha":{"draws":18,"losses":56,"wins":84},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":23},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":4,"losses":15,"wins":27},"thinkingmachines/inkling":{"draws":10,"losses":8,"wins":46},"thinkingmachines/inkling-small":{"draws":6,"losses":8,"wins":34},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":5,"losses":19,"wins":24},"x-ai/grok-4.6":{"draws":6,"losses":23,"wins":19},"x-ai/grok-4.7":{"draws":3,"losses":24,"wins":15},"x-ai/grok-build-0.1":{"draws":1,"losses":4,"wins":11},"xiaomi/mimo-v2.5":{"draws":6,"losses":20,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":12,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":18,"wins":10},"z-ai/glm-5.2":{"draws":11,"losses":27,"wins":58},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":5,"losses":15,"wins":12},"z-ai/glm-5.3-flashx":{"draws":8,"losses":15,"wins":25}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":31},"claude-fable-5":{"draws":8,"losses":16,"wins":24},"claude-fable-5-1":{"draws":8,"losses":39,"wins":7},"claude-haiku-5-5":{"draws":7,"losses":12,"wins":27},"claude-opus-4-5":{"draws":9,"losses":13,"wins":56},"claude-opus-4-8":{"draws":5,"losses":16,"wins":23},"claude-opus-5":{"draws":9,"losses":51,"wins":22},"claude-opus-5-5":{"draws":7,"losses":38,"wins":7},"claude-sonnet-5":{"draws":10,"losses":7,"wins":31},"claude-sonnet-5-5":{"draws":7,"losses":19,"wins":22},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":53},"deepseek/deepseek-v4-pro":{"draws":6,"losses":9,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":8,"wins":31},"fireworks/ember-1":{"draws":6,"losses":10,"wins":32},"gemini-3.1-pro-preview":{"draws":9,"losses":10,"wins":29},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":11,"losses":9,"wins":40},"google/gemini-3.5-flash-lite":{"draws":20,"losses":8,"wins":56},"google/gemini-3.6-flash":{"draws":20,"losses":20,"wins":52},"google/gemini-3.8-flash":{"draws":4,"losses":14,"wins":30},"google/gemma-4-31b-it":{"draws":8,"losses":1,"wins":19},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":11,"losses":5,"wins":26},"gpt-5.4":{"draws":7,"losses":10,"wins":29},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":6,"losses":9,"wins":33},"gpt-5.5":{"draws":10,"losses":12,"wins":22},"gpt-5.6-luna":{"draws":8,"losses":5,"wins":35},"gpt-5.6-sol":{"draws":5,"losses":19,"wins":24},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":28},"gpt-6-astra":{"draws":3,"losses":39,"wins":6},"gpt-6-luna":{"draws":7,"losses":10,"wins":31},"gpt-6-sol":{"draws":7,"losses":24,"wins":17},"gpt-6.1-sol":{"draws":10,"losses":32,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":5,"losses":2,"wins":27},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":4,"wins":39},"meta/muse-glimmer-30b":{"draws":11,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":29},"meta/muse-spark-1.3":{"draws":8,"losses":13,"wins":27},"meta/muse-wonder":{"draws":11,"losses":19,"wins":18},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":17},"mistralai/mistral-large-4-0":{"draws":10,"losses":4,"wins":16},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":31},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":28},"o3":{"draws":5,"losses":13,"wins":48},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":13,"losses":3,"wins":30},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":13,"wins":25},"qwen/qwen3.8-27b":{"draws":5,"losses":6,"wins":23},"qwen/qwen3.8-flash":{"draws":9,"losses":9,"wins":14},"qwen/qwen3.8-max":{"draws":10,"losses":13,"wins":25},"qwen/qwen3.8-max-0902":{"draws":10,"losses":11,"wins":27},"stealth/ox-alpha":{"draws":19,"losses":34,"wins":105},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":25},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":28},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":21},"tencent/hy4-preview":{"draws":6,"losses":14,"wins":26},"thinkingmachines/inkling":{"draws":7,"losses":9,"wins":48},"thinkingmachines/inkling-small":{"draws":10,"losses":6,"wins":32},"unbiased/pareto-26.10-preview":{"draws":2,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":4,"losses":14,"wins":30},"x-ai/grok-4.6":{"draws":7,"losses":15,"wins":26},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":15,"losses":5,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":3,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":5,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":13,"wins":14},"z-ai/glm-5.2":{"draws":20,"losses":14,"wins":62},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":17},"z-ai/glm-5.3-flash":{"draws":11,"losses":14,"wins":23},"z-ai/glm-5.3-flashx":{"draws":10,"losses":5,"wins":17}}},"medium":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":7,"wins":12},"claude-fable-5":{"draws":6,"losses":26,"wins":10},"claude-fable-5-1":{"draws":2,"losses":42,"wins":2},"claude-haiku-5-5":{"draws":6,"losses":17,"wins":17},"claude-opus-4-5":{"draws":21,"losses":22,"wins":25},"claude-opus-4-8":{"draws":9,"losses":15,"wins":14},"claude-opus-5":{"draws":11,"losses":52,"wins":11},"claude-opus-5-5":{"draws":2,"losses":39,"wins":5},"claude-sonnet-5":{"draws":14,"losses":17,"wins":11},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":19,"losses":18,"wins":25},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":16,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":16,"wins":17},"fireworks/ember-1":{"draws":10,"losses":19,"wins":13},"gemini-3.1-pro-preview":{"draws":9,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":12},"google/gemini-3.5-flash":{"draws":11,"losses":21,"wins":20},"google/gemini-3.5-flash-lite":{"draws":20,"losses":20,"wins":34},"google/gemini-3.6-flash":{"draws":17,"losses":41,"wins":22},"google/gemini-3.8-flash":{"draws":9,"losses":23,"wins":10},"google/gemma-4-31b-it":{"draws":8,"losses":8,"wins":8},"gpt-4.1":{"draws":4,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":2,"wins":1},"gpt-5":{"draws":8,"losses":10,"wins":18},"gpt-5.4":{"draws":9,"losses":19,"wins":12},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":11,"wins":22},"gpt-5.5":{"draws":12,"losses":16,"wins":10},"gpt-5.6-luna":{"draws":11,"losses":9,"wins":22},"gpt-5.6-sol":{"draws":8,"losses":28,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":18,"wins":10},"gpt-6-astra":{"draws":2,"losses":35,"wins":5},"gpt-6-luna":{"draws":11,"losses":15,"wins":16},"gpt-6-sol":{"draws":4,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":33,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":10,"wins":9},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":16},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":13,"wins":22},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":9,"losses":16,"wins":15},"meta/muse-spark-1.3":{"draws":8,"losses":23,"wins":11},"meta/muse-wonder":{"draws":13,"losses":22,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":12},"mistralai/mistral-large-4-0":{"draws":5,"losses":10,"wins":11},"mistralai/mistral-medium-3-5":{"draws":9,"losses":7,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":6},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":14},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":9,"wins":15},"o3":{"draws":9,"losses":23,"wins":22},"openai/gpt-oss-120b":{"draws":10,"losses":9,"wins":17},"poolside/laguna-s-2.1":{"draws":13,"losses":13,"wins":16},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":19,"wins":10},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":11},"qwen/qwen3.8-flash":{"draws":6,"losses":11,"wins":11},"qwen/qwen3.8-max":{"draws":14,"losses":14,"wins":14},"qwen/qwen3.8-max-0902":{"draws":8,"losses":25,"wins":9},"stealth/ox-alpha":{"draws":33,"losses":70,"wins":37},"stealth/space-bunny-alpha":{"draws":8,"losses":8,"wins":16},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":11,"losses":23,"wins":6},"thinkingmachines/inkling":{"draws":18,"losses":12,"wins":26},"thinkingmachines/inkling-small":{"draws":12,"losses":10,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":11,"losses":25,"wins":6},"x-ai/grok-4.6":{"draws":13,"losses":22,"wins":7},"x-ai/grok-4.7":{"draws":2,"losses":27,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":23,"losses":14,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":8},"z-ai/glm-5.2":{"draws":23,"losses":29,"wins":32},"z-ai/glm-5.3":{"draws":6,"losses":22,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":12},"z-ai/glm-5.3-flashx":{"draws":7,"losses":25,"wins":10}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":8,"wins":29},"claude-fable-5":{"draws":6,"losses":12,"wins":14},"claude-fable-5-1":{"draws":2,"losses":45,"wins":7},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":16,"losses":11,"wins":51},"claude-opus-4-8":{"draws":11,"losses":8,"wins":25},"claude-opus-5":{"draws":14,"losses":46,"wins":22},"claude-opus-5-5":{"draws":4,"losses":39,"wins":9},"claude-sonnet-5":{"draws":6,"losses":10,"wins":32},"claude-sonnet-5-5":{"draws":10,"losses":16,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":14,"losses":4,"wins":54},"deepseek/deepseek-v4-pro":{"draws":9,"losses":9,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":11,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":13,"wins":23},"fireworks/ember-1":{"draws":9,"losses":7,"wins":32},"gemini-3.1-pro-preview":{"draws":11,"losses":7,"wins":30},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":28},"google/gemini-3.5-flash":{"draws":12,"losses":14,"wins":34},"google/gemini-3.5-flash-lite":{"draws":16,"losses":12,"wins":56},"google/gemini-3.6-flash":{"draws":17,"losses":33,"wins":42},"google/gemini-3.8-flash":{"draws":5,"losses":15,"wins":28},"google/gemma-4-31b-it":{"draws":6,"losses":4,"wins":18},"gpt-4.1":{"draws":2,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":8,"wins":27},"gpt-5.4":{"draws":12,"losses":11,"wins":23},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":20},"gpt-5.4-nano":{"draws":6,"losses":5,"wins":37},"gpt-5.5":{"draws":11,"losses":10,"wins":23},"gpt-5.6-luna":{"draws":13,"losses":7,"wins":28},"gpt-5.6-sol":{"draws":2,"losses":22,"wins":24},"gpt-5.6-terra":{"draws":15,"losses":5,"wins":26},"gpt-6-astra":{"draws":1,"losses":37,"wins":10},"gpt-6-luna":{"draws":12,"losses":7,"wins":29},"gpt-6-sol":{"draws":8,"losses":24,"wins":16},"gpt-6.1-sol":{"draws":4,"losses":31,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":3,"wins":23},"inclusionai/ling-3.0-flash":{"draws":4,"losses":3,"wins":27},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":6,"wins":40},"meta/muse-glimmer-30b":{"draws":6,"losses":5,"wins":31},"meta/muse-spark-1.2":{"draws":11,"losses":9,"wins":26},"meta/muse-spark-1.3":{"draws":12,"losses":15,"wins":21},"meta/muse-wonder":{"draws":9,"losses":20,"wins":19},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":16},"mistralai/mistral-large-4-0":{"draws":5,"losses":11,"wins":14},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":31},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":30},"o3":{"draws":6,"losses":8,"wins":52},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":25},"poolside/laguna-s-2.1":{"draws":6,"losses":10,"wins":30},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":18},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":10,"wins":23},"qwen/qwen3.8-27b":{"draws":7,"losses":5,"wins":22},"qwen/qwen3.8-flash":{"draws":8,"losses":7,"wins":17},"qwen/qwen3.8-max":{"draws":9,"losses":14,"wins":25},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":26},"stealth/ox-alpha":{"draws":27,"losses":46,"wins":85},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":16},"tencent/hy4-preview":{"draws":11,"losses":7,"wins":28},"thinkingmachines/inkling":{"draws":17,"losses":4,"wins":43},"thinkingmachines/inkling-small":{"draws":8,"losses":8,"wins":32},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":9,"losses":17,"wins":22},"x-ai/grok-4.6":{"draws":13,"losses":19,"wins":16},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":15,"losses":2,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":12,"wins":17},"z-ai/glm-5.2":{"draws":19,"losses":15,"wins":62},"z-ai/glm-5.3":{"draws":5,"losses":23,"wins":18},"z-ai/glm-5.3-flash":{"draws":8,"losses":14,"wins":26},"z-ai/glm-5.3-flashx":{"draws":10,"losses":15,"wins":23}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":0,"wins":43},"claude-fable-5":{"draws":5,"losses":8,"wins":35},"claude-fable-5-1":{"draws":3,"losses":24,"wins":11},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":42},"claude-opus-4-5":{"draws":6,"losses":4,"wins":68},"claude-opus-4-8":{"draws":4,"losses":5,"wins":35},"claude-opus-5":{"draws":9,"losses":36,"wins":37},"claude-opus-5-5":{"draws":6,"losses":35,"wins":11},"claude-sonnet-5":{"draws":4,"losses":2,"wins":42},"claude-sonnet-5-5":{"draws":3,"losses":10,"wins":35},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":5,"losses":0,"wins":67},"deepseek/deepseek-v4-pro":{"draws":4,"losses":1,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":1,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":6,"wins":38},"fireworks/ember-1":{"draws":0,"losses":5,"wins":43},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":42},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":52},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":74},"google/gemini-3.6-flash":{"draws":9,"losses":10,"wins":73},"google/gemini-3.8-flash":{"draws":2,"losses":5,"wins":41},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":1,"losses":2,"wins":13},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":4,"losses":0,"wins":38},"gpt-5.4":{"draws":6,"losses":5,"wins":35},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":29},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":3,"losses":9,"wins":32},"gpt-5.6-luna":{"draws":3,"losses":2,"wins":43},"gpt-5.6-sol":{"draws":5,"losses":7,"wins":36},"gpt-5.6-terra":{"draws":5,"losses":3,"wins":38},"gpt-6-astra":{"draws":5,"losses":34,"wins":9},"gpt-6-luna":{"draws":5,"losses":4,"wins":39},"gpt-6-sol":{"draws":6,"losses":12,"wins":30},"gpt-6.1-sol":{"draws":6,"losses":29,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":1,"wins":47},"meta/muse-glimmer-30b":{"draws":5,"losses":1,"wins":36},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":40},"meta/muse-spark-1.3":{"draws":3,"losses":6,"wins":39},"meta/muse-wonder":{"draws":3,"losses":14,"wins":31},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":25},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":26},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":1,"losses":6,"wins":39},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":39},"o3":{"draws":3,"losses":5,"wins":58},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":41},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"wins":43},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":26},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":5,"wins":39},"qwen/qwen3.8-27b":{"draws":3,"losses":0,"wins":31},"qwen/qwen3.8-flash":{"draws":4,"losses":2,"wins":26},"qwen/qwen3.8-max":{"draws":4,"losses":1,"wins":43},"qwen/qwen3.8-max-0902":{"draws":2,"losses":7,"wins":39},"stealth/ox-alpha":{"draws":7,"losses":14,"wins":137},"stealth/space-bunny-alpha":{"draws":1,"losses":2,"wins":35},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":21},"tencent/hy4-preview":{"draws":3,"losses":5,"wins":38},"thinkingmachines/inkling":{"draws":5,"losses":0,"wins":59},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":43},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":37},"x-ai/grok-4.6":{"draws":4,"losses":9,"wins":35},"x-ai/grok-4.7":{"draws":1,"losses":17,"wins":24},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":1,"wins":26},"z-ai/glm-5.2":{"draws":9,"losses":4,"wins":83},"z-ai/glm-5.3":{"draws":4,"losses":9,"wins":33},"z-ai/glm-5.3-flash":{"draws":1,"losses":9,"wins":38},"z-ai/glm-5.3-flashx":{"draws":4,"losses":8,"wins":36}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":10,"wins":26},"claude-fable-5":{"draws":10,"losses":25,"wins":13},"claude-fable-5-1":{"draws":2,"losses":47,"wins":5},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":9},"claude-opus-4-5":{"draws":22,"losses":19,"wins":37},"claude-opus-4-8":{"draws":6,"losses":20,"wins":18},"claude-opus-5":{"draws":15,"losses":56,"wins":11},"claude-opus-5-5":{"draws":7,"losses":45,"wins":0},"claude-sonnet-5":{"draws":13,"losses":14,"wins":21},"claude-sonnet-5-5":{"draws":9,"losses":27,"wins":12},"cohere/north-mini-code":{"draws":5,"losses":3,"wins":10},"deepseek/deepseek-v4-flash":{"draws":19,"losses":8,"wins":45},"deepseek/deepseek-v4-pro":{"draws":13,"losses":14,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":6,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":11,"wins":20},"fireworks/ember-1":{"draws":14,"losses":11,"wins":23},"gemini-3.1-pro-preview":{"draws":13,"losses":14,"wins":21},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":14,"losses":23,"wins":23},"google/gemini-3.5-flash-lite":{"draws":17,"losses":13,"wins":54},"google/gemini-3.6-flash":{"draws":25,"losses":32,"wins":35},"google/gemini-3.8-flash":{"draws":13,"losses":20,"wins":15},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":11,"losses":9,"wins":22},"gpt-5.4":{"draws":11,"losses":19,"wins":16},"gpt-5.4-mini":{"draws":8,"losses":5,"wins":19},"gpt-5.4-nano":{"draws":13,"losses":11,"wins":24},"gpt-5.5":{"draws":19,"losses":10,"wins":15},"gpt-5.6-luna":{"draws":13,"losses":7,"wins":28},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":13},"gpt-5.6-terra":{"draws":18,"losses":9,"wins":19},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":17,"losses":11,"wins":20},"gpt-6-sol":{"draws":9,"losses":31,"wins":8},"gpt-6.1-sol":{"draws":8,"losses":38,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":23},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":20},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":37},"meta/muse-glimmer-30b":{"draws":11,"losses":6,"wins":25},"meta/muse-spark-1.2":{"draws":10,"losses":13,"wins":23},"meta/muse-spark-1.3":{"draws":11,"losses":19,"wins":18},"meta/muse-wonder":{"draws":10,"losses":27,"wins":11},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":20},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":12,"wins":21},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":9,"wins":23},"o3":{"draws":14,"losses":15,"wins":37},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":29},"poolside/laguna-s-2.1":{"draws":11,"losses":12,"wins":23},"qwen/qwen3.7-max":{"draws":12,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":16,"wins":17},"qwen/qwen3.8-27b":{"draws":7,"losses":8,"wins":19},"qwen/qwen3.8-flash":{"draws":10,"losses":5,"wins":17},"qwen/qwen3.8-max":{"draws":13,"losses":10,"wins":25},"qwen/qwen3.8-max-0902":{"draws":15,"losses":15,"wins":18},"stealth/ox-alpha":{"draws":36,"losses":60,"wins":62},"stealth/space-bunny-alpha":{"draws":10,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":26},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":13,"losses":16,"wins":17},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":43},"thinkingmachines/inkling-small":{"draws":9,"losses":5,"wins":34},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":21,"wins":17},"x-ai/grok-4.6":{"draws":16,"losses":22,"wins":10},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":20,"losses":9,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":6,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":7,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":24,"losses":21,"wins":51},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":12,"losses":18,"wins":18},"z-ai/glm-5.3-flashx":{"draws":12,"losses":16,"wins":20}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":8,"wins":22},"claude-fable-5":{"draws":7,"losses":34,"wins":7},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":19,"wins":15},"claude-opus-4-5":{"draws":19,"losses":15,"wins":28},"claude-opus-4-8":{"draws":12,"losses":17,"wins":15},"claude-opus-5":{"draws":14,"losses":59,"wins":9},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":13,"losses":11,"wins":24},"claude-sonnet-5-5":{"draws":10,"losses":22,"wins":16},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":17,"losses":13,"wins":42},"deepseek/deepseek-v4-pro":{"draws":9,"losses":14,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":21,"wins":16},"fireworks/ember-1":{"draws":16,"losses":19,"wins":13},"gemini-3.1-pro-preview":{"draws":12,"losses":12,"wins":24},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":17,"losses":23,"wins":20},"google/gemini-3.5-flash-lite":{"draws":26,"losses":14,"wins":44},"google/gemini-3.6-flash":{"draws":23,"losses":38,"wins":31},"google/gemini-3.8-flash":{"draws":12,"losses":23,"wins":13},"google/gemma-4-31b-it":{"draws":8,"losses":1,"wins":19},"gpt-4.1":{"draws":5,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":13,"wins":17},"gpt-5.4":{"draws":13,"losses":22,"wins":11},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":13,"losses":9,"wins":26},"gpt-5.5":{"draws":18,"losses":17,"wins":9},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":19},"gpt-5.6-sol":{"draws":7,"losses":30,"wins":11},"gpt-5.6-terra":{"draws":16,"losses":13,"wins":17},"gpt-6-astra":{"draws":6,"losses":39,"wins":3},"gpt-6-luna":{"draws":16,"losses":11,"wins":21},"gpt-6-sol":{"draws":9,"losses":31,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":34},"meta/muse-glimmer-30b":{"draws":11,"losses":8,"wins":23},"meta/muse-spark-1.2":{"draws":12,"losses":22,"wins":12},"meta/muse-spark-1.3":{"draws":7,"losses":26,"wins":15},"meta/muse-wonder":{"draws":11,"losses":25,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":16},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":11},"mistralai/mistral-medium-3-5":{"draws":10,"losses":3,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":16,"losses":15,"wins":15},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":22},"o3":{"draws":9,"losses":19,"wins":38},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":26},"poolside/laguna-s-2.1":{"draws":13,"losses":7,"wins":26},"qwen/qwen3.7-max":{"draws":9,"losses":4,"wins":15},"qwen/qwen3.7-plus":{"draws":5,"losses":5,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":18,"wins":13},"qwen/qwen3.8-27b":{"draws":10,"losses":12,"wins":12},"qwen/qwen3.8-flash":{"draws":12,"losses":8,"wins":12},"qwen/qwen3.8-max":{"draws":13,"losses":21,"wins":14},"qwen/qwen3.8-max-0902":{"draws":12,"losses":21,"wins":15},"stealth/ox-alpha":{"draws":49,"losses":59,"wins":50},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":8,"losses":23,"wins":15},"thinkingmachines/inkling":{"draws":16,"losses":12,"wins":36},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":32},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":14,"losses":19,"wins":15},"x-ai/grok-4.6":{"draws":13,"losses":25,"wins":10},"x-ai/grok-4.7":{"draws":2,"losses":30,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":23,"losses":10,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":15,"wins":6},"z-ai/glm-5.2":{"draws":27,"losses":29,"wins":40},"z-ai/glm-5.3":{"draws":12,"losses":27,"wins":7},"z-ai/glm-5.3-flash":{"draws":10,"losses":24,"wins":14},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":14}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":7,"wins":20},"claude-fable-5":{"draws":14,"losses":26,"wins":8},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":27,"losses":24,"wins":27},"claude-opus-4-8":{"draws":5,"losses":15,"wins":8},"claude-opus-5":{"draws":9,"losses":67,"wins":6},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":16,"losses":19,"wins":13},"claude-sonnet-5-5":{"draws":11,"losses":27,"wins":10},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":27,"losses":13,"wins":32},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":19,"wins":11},"fireworks/ember-1":{"draws":19,"losses":16,"wins":13},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":20,"losses":18,"wins":22},"google/gemini-3.5-flash-lite":{"draws":32,"losses":8,"wins":44},"google/gemini-3.6-flash":{"draws":26,"losses":40,"wins":26},"google/gemini-3.8-flash":{"draws":12,"losses":25,"wins":11},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":13},"gpt-4.1":{"draws":7,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":11,"wins":14},"gpt-5.4":{"draws":16,"losses":18,"wins":12},"gpt-5.4-mini":{"draws":11,"losses":10,"wins":11},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":24},"gpt-5.5":{"draws":19,"losses":14,"wins":11},"gpt-5.6-luna":{"draws":21,"losses":11,"wins":16},"gpt-5.6-sol":{"draws":9,"losses":29,"wins":10},"gpt-5.6-terra":{"draws":17,"losses":15,"wins":14},"gpt-6-astra":{"draws":1,"losses":44,"wins":3},"gpt-6-luna":{"draws":17,"losses":16,"wins":15},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":1,"losses":45,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":15},"inclusionai/ling-3.0-flash":{"draws":17,"losses":0,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":11,"wins":24},"meta/muse-glimmer-30b":{"draws":18,"losses":6,"wins":18},"meta/muse-spark-1.2":{"draws":11,"losses":22,"wins":13},"meta/muse-spark-1.3":{"draws":12,"losses":21,"wins":15},"meta/muse-wonder":{"draws":11,"losses":26,"wins":11},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":11},"mistralai/mistral-large-4-0":{"draws":9,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":12,"losses":2,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":15,"wins":15},"nex-agi/nex-n2-pro":{"draws":10,"losses":0,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":7,"wins":18},"o3":{"draws":14,"losses":20,"wins":32},"openai/gpt-oss-120b":{"draws":18,"losses":5,"wins":19},"poolside/laguna-s-2.1":{"draws":20,"losses":7,"wins":19},"qwen/qwen3.7-max":{"draws":13,"losses":5,"wins":10},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":21,"wins":10},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":11},"qwen/qwen3.8-flash":{"draws":17,"losses":6,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":19,"wins":14},"qwen/qwen3.8-max-0902":{"draws":15,"losses":18,"wins":15},"stealth/ox-alpha":{"draws":41,"losses":71,"wins":46},"stealth/space-bunny-alpha":{"draws":12,"losses":11,"wins":15},"stepfun/step-3.7-flash":{"draws":10,"losses":6,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":8,"wins":8},"tencent/hy4-preview":{"draws":17,"losses":20,"wins":9},"thinkingmachines/inkling":{"draws":24,"losses":12,"wins":28},"thinkingmachines/inkling-small":{"draws":21,"losses":3,"wins":24},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":14,"losses":19,"wins":15},"x-ai/grok-4.6":{"draws":15,"losses":22,"wins":11},"x-ai/grok-4.7":{"draws":6,"losses":27,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":29,"losses":8,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":3,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":12},"z-ai/glm-5.2":{"draws":41,"losses":20,"wins":35},"z-ai/glm-5.3":{"draws":7,"losses":33,"wins":6},"z-ai/glm-5.3-flash":{"draws":10,"losses":25,"wins":13},"z-ai/glm-5.3-flashx":{"draws":11,"losses":22,"wins":15}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":5,"wins":59},"claude-fable-5":{"draws":9,"losses":23,"wins":52},"claude-fable-5-1":{"draws":6,"losses":68,"wins":22},"claude-haiku-5-5":{"draws":15,"losses":14,"wins":51},"claude-opus-4-5":{"draws":27,"losses":7,"wins":102},"claude-opus-4-8":{"draws":13,"losses":11,"wins":52},"claude-opus-5":{"draws":18,"losses":61,"wins":53},"claude-opus-5-5":{"draws":6,"losses":60,"wins":26},"claude-sonnet-5":{"draws":13,"losses":10,"wins":61},"claude-sonnet-5-5":{"draws":7,"losses":33,"wins":44},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":28},"deepseek/deepseek-v4-flash":{"draws":15,"losses":1,"wins":108},"deepseek/deepseek-v4-pro":{"draws":9,"losses":11,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":11,"wins":57},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":16,"wins":56},"fireworks/ember-1":{"draws":9,"losses":16,"wins":59},"gemini-3.1-pro-preview":{"draws":12,"losses":11,"wins":61},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":42},"google/gemini-3.5-flash":{"draws":15,"losses":5,"wins":84},"google/gemini-3.5-flash-lite":{"draws":24,"losses":8,"wins":112},"google/gemini-3.6-flash":{"draws":18,"losses":25,"wins":117},"google/gemini-3.8-flash":{"draws":9,"losses":19,"wins":56},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":35},"gpt-4.1":{"draws":2,"losses":2,"wins":24},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":5,"wins":63},"gpt-5.4":{"draws":10,"losses":15,"wins":55},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":41},"gpt-5.4-nano":{"draws":8,"losses":5,"wins":67},"gpt-5.5":{"draws":10,"losses":21,"wins":49},"gpt-5.6-luna":{"draws":9,"losses":12,"wins":63},"gpt-5.6-sol":{"draws":16,"losses":19,"wins":49},"gpt-5.6-terra":{"draws":11,"losses":9,"wins":60},"gpt-6-astra":{"draws":4,"losses":61,"wins":19},"gpt-6-luna":{"draws":16,"losses":8,"wins":60},"gpt-6-sol":{"draws":12,"losses":31,"wins":41},"gpt-6.1-sol":{"draws":6,"losses":49,"wins":29},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":40},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":47},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":68},"meta/muse-glimmer-30b":{"draws":4,"losses":10,"wins":66},"meta/muse-spark-1.2":{"draws":12,"losses":13,"wins":59},"meta/muse-spark-1.3":{"draws":10,"losses":18,"wins":56},"meta/muse-wonder":{"draws":9,"losses":32,"wins":43},"minimax/minimax-m3":{"draws":3,"losses":5,"wins":40},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":40},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":22},"moonshotai/kimi-k3":{"draws":12,"losses":10,"wins":62},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":38},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":1,"wins":61},"o3":{"draws":9,"losses":9,"wins":90},"openai/gpt-oss-120b":{"draws":8,"losses":2,"wins":66},"poolside/laguna-s-2.1":{"draws":7,"losses":3,"wins":74},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":37},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":12,"wins":57},"qwen/qwen3.8-27b":{"draws":10,"losses":6,"wins":40},"qwen/qwen3.8-flash":{"draws":8,"losses":3,"wins":45},"qwen/qwen3.8-max":{"draws":13,"losses":5,"wins":66},"qwen/qwen3.8-max-0902":{"draws":14,"losses":14,"wins":56},"stealth/ox-alpha":{"draws":41,"losses":32,"wins":211},"stealth/space-bunny-alpha":{"draws":14,"losses":4,"wins":50},"stepfun/step-3.7-flash":{"draws":5,"losses":0,"wins":51},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":8,"losses":5,"wins":35},"tencent/hy4-preview":{"draws":5,"losses":13,"wins":62},"thinkingmachines/inkling":{"draws":20,"losses":3,"wins":93},"thinkingmachines/inkling-small":{"draws":16,"losses":3,"wins":65},"unbiased/pareto-26.10-preview":{"draws":2,"losses":18,"wins":8},"upstage/solar-mini4":{"draws":4,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":12,"losses":14,"wins":58},"x-ai/grok-4.6":{"draws":14,"losses":19,"wins":50},"x-ai/grok-4.7":{"draws":7,"losses":42,"wins":27},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":29,"losses":9,"wins":90},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":1,"wins":38},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":8,"wins":39},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":16,"wins":31},"z-ai/glm-5.2":{"draws":24,"losses":11,"wins":133},"z-ai/glm-5.3":{"draws":12,"losses":23,"wins":45},"z-ai/glm-5.3-flash":{"draws":10,"losses":18,"wins":56},"z-ai/glm-5.3-flashx":{"draws":12,"losses":13,"wins":59}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":50},"claude-fable-5":{"draws":3,"losses":3,"wins":48},"claude-fable-5-1":{"draws":5,"losses":18,"wins":37},"claude-haiku-5-5":{"draws":2,"losses":0,"wins":50},"claude-opus-4-5":{"draws":4,"losses":0,"wins":84},"claude-opus-4-8":{"draws":2,"losses":1,"wins":47},"claude-opus-5":{"draws":4,"losses":20,"wins":70},"claude-opus-5-5":{"draws":4,"losses":18,"wins":22},"claude-sonnet-5":{"draws":0,"losses":1,"wins":53},"claude-sonnet-5-5":{"draws":5,"losses":8,"wins":41},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":22},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":79},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":2,"wins":51},"fireworks/ember-1":{"draws":0,"losses":0,"wins":54},"gemini-3.1-pro-preview":{"draws":1,"losses":4,"wins":49},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":36},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":67},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":93},"google/gemini-3.6-flash":{"draws":3,"losses":8,"wins":91},"google/gemini-3.8-flash":{"draws":3,"losses":3,"wins":48},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":32},"gpt-4.1":{"draws":0,"losses":0,"wins":18},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":1,"wins":47},"gpt-5.4":{"draws":1,"losses":3,"wins":48},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":35},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":55},"gpt-5.5":{"draws":4,"losses":0,"wins":46},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":50},"gpt-5.6-sol":{"draws":1,"losses":7,"wins":46},"gpt-5.6-terra":{"draws":1,"losses":1,"wins":50},"gpt-6-astra":{"draws":5,"losses":25,"wins":24},"gpt-6-luna":{"draws":2,"losses":0,"wins":52},"gpt-6-sol":{"draws":4,"losses":12,"wins":38},"gpt-6.1-sol":{"draws":3,"losses":20,"wins":31},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":38},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":40},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":57},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":48},"meta/muse-spark-1.2":{"draws":0,"losses":1,"wins":51},"meta/muse-spark-1.3":{"draws":0,"losses":0,"wins":54},"meta/muse-wonder":{"draws":2,"losses":7,"wins":45},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":30},"mistralai/mistral-large-4-0":{"draws":2,"losses":3,"wins":29},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":14},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":51},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":50},"o3":{"draws":2,"losses":1,"wins":73},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":48},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":54},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":30},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":0,"wins":53},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":35},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":34},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":52},"qwen/qwen3.8-max-0902":{"draws":1,"losses":5,"wins":48},"stealth/ox-alpha":{"draws":8,"losses":4,"wins":162},"stealth/space-bunny-alpha":{"draws":0,"losses":1,"wins":41},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":38},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":28},"tencent/hy4-preview":{"draws":1,"losses":4,"wins":47},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":68},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":52},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":12},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":3,"losses":2,"wins":49},"x-ai/grok-4.6":{"draws":2,"losses":1,"wins":51},"x-ai/grok-4.7":{"draws":2,"losses":7,"wins":39},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":18},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":83},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":0,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":34},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":108},"z-ai/glm-5.3":{"draws":1,"losses":6,"wins":45},"z-ai/glm-5.3-flash":{"draws":4,"losses":3,"wins":47},"z-ai/glm-5.3-flashx":{"draws":3,"losses":1,"wins":50}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":5,"wins":23},"claude-fable-5":{"draws":7,"losses":36,"wins":5},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":26,"losses":29,"wins":23},"claude-opus-4-8":{"draws":13,"losses":21,"wins":10},"claude-opus-5":{"draws":11,"losses":58,"wins":13},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":10,"losses":15,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":28,"wins":10},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":24,"losses":13,"wins":35},"deepseek/deepseek-v4-pro":{"draws":18,"losses":15,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":18,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":16,"wins":13},"fireworks/ember-1":{"draws":14,"losses":21,"wins":13},"gemini-3.1-pro-preview":{"draws":17,"losses":18,"wins":13},"google/gemini-3.1-flash-lite":{"draws":11,"losses":0,"wins":21},"google/gemini-3.5-flash":{"draws":19,"losses":24,"wins":17},"google/gemini-3.5-flash-lite":{"draws":30,"losses":22,"wins":32},"google/gemini-3.6-flash":{"draws":27,"losses":48,"wins":17},"google/gemini-3.8-flash":{"draws":15,"losses":27,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":13},"gpt-4.1":{"draws":7,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":14,"losses":10,"wins":18},"gpt-5.4":{"draws":13,"losses":26,"wins":7},"gpt-5.4-mini":{"draws":16,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":12,"losses":16,"wins":20},"gpt-5.5":{"draws":21,"losses":19,"wins":4},"gpt-5.6-luna":{"draws":16,"losses":13,"wins":19},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":6},"gpt-5.6-terra":{"draws":23,"losses":14,"wins":9},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":14,"losses":17,"wins":17},"gpt-6-sol":{"draws":9,"losses":35,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":15},"inclusionai/ling-3.0-flash":{"draws":16,"losses":3,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":9,"wins":23},"meta/muse-glimmer-30b":{"draws":19,"losses":5,"wins":18},"meta/muse-spark-1.2":{"draws":13,"losses":23,"wins":10},"meta/muse-spark-1.3":{"draws":14,"losses":24,"wins":10},"meta/muse-wonder":{"draws":10,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":13},"mistralai/mistral-large-4-0":{"draws":12,"losses":11,"wins":7},"mistralai/mistral-medium-3-5":{"draws":14,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":22,"wins":9},"nex-agi/nex-n2-pro":{"draws":11,"losses":2,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":7,"wins":17},"o3":{"draws":12,"losses":32,"wins":22},"openai/gpt-oss-120b":{"draws":14,"losses":6,"wins":22},"poolside/laguna-s-2.1":{"draws":20,"losses":9,"wins":17},"qwen/qwen3.7-max":{"draws":12,"losses":5,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":22,"wins":10},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":9},"qwen/qwen3.8-flash":{"draws":13,"losses":10,"wins":9},"qwen/qwen3.8-max":{"draws":18,"losses":18,"wins":12},"qwen/qwen3.8-max-0902":{"draws":17,"losses":22,"wins":9},"stealth/ox-alpha":{"draws":36,"losses":93,"wins":29},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":10,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":18,"losses":22,"wins":6},"thinkingmachines/inkling":{"draws":22,"losses":11,"wins":31},"thinkingmachines/inkling-small":{"draws":21,"losses":7,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":12,"losses":24,"wins":12},"x-ai/grok-4.6":{"draws":13,"losses":25,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":36,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":32,"losses":13,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":8,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":15,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":33,"losses":29,"wins":34},"z-ai/glm-5.3":{"draws":9,"losses":34,"wins":3},"z-ai/glm-5.3-flash":{"draws":13,"losses":27,"wins":8},"z-ai/glm-5.3-flashx":{"draws":15,"losses":26,"wins":7}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":7,"wins":24},"claude-fable-5":{"draws":12,"losses":28,"wins":8},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":22,"losses":21,"wins":35},"claude-opus-4-8":{"draws":11,"losses":17,"wins":16},"claude-opus-5":{"draws":8,"losses":60,"wins":14},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":12,"losses":15,"wins":21},"claude-sonnet-5-5":{"draws":5,"losses":17,"wins":10},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":21,"losses":10,"wins":41},"deepseek/deepseek-v4-pro":{"draws":14,"losses":14,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":13,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":14,"wins":21},"fireworks/ember-1":{"draws":13,"losses":20,"wins":15},"gemini-3.1-pro-preview":{"draws":12,"losses":15,"wins":21},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":13,"losses":18,"wins":29},"google/gemini-3.5-flash-lite":{"draws":24,"losses":17,"wins":43},"google/gemini-3.6-flash":{"draws":23,"losses":39,"wins":30},"google/gemini-3.8-flash":{"draws":6,"losses":24,"wins":18},"google/gemma-4-31b-it":{"draws":7,"losses":6,"wins":15},"gpt-4.1":{"draws":6,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":12,"wins":16},"gpt-5.4":{"draws":15,"losses":17,"wins":14},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":13},"gpt-5.4-nano":{"draws":11,"losses":3,"wins":34},"gpt-5.5":{"draws":11,"losses":21,"wins":12},"gpt-5.6-luna":{"draws":17,"losses":12,"wins":19},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":12},"gpt-5.6-terra":{"draws":16,"losses":13,"wins":17},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":13,"losses":16,"wins":19},"gpt-6-sol":{"draws":4,"losses":33,"wins":11},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":5,"wins":17},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":20},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":12,"wins":30},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":23},"meta/muse-spark-1.2":{"draws":14,"losses":13,"wins":19},"meta/muse-spark-1.3":{"draws":10,"losses":22,"wins":16},"meta/muse-wonder":{"draws":11,"losses":21,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":17},"mistralai/mistral-large-4-0":{"draws":9,"losses":9,"wins":12},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":16},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":7,"wins":24},"o3":{"draws":7,"losses":15,"wins":44},"openai/gpt-oss-120b":{"draws":14,"losses":7,"wins":21},"poolside/laguna-s-2.1":{"draws":13,"losses":13,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":6,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":16},"qwen/qwen3.8-flash":{"draws":7,"losses":13,"wins":12},"qwen/qwen3.8-max":{"draws":9,"losses":16,"wins":23},"qwen/qwen3.8-max-0902":{"draws":10,"losses":21,"wins":17},"stealth/ox-alpha":{"draws":33,"losses":70,"wins":55},"stealth/space-bunny-alpha":{"draws":10,"losses":9,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":19,"wins":16},"thinkingmachines/inkling":{"draws":19,"losses":16,"wins":29},"thinkingmachines/inkling-small":{"draws":17,"losses":5,"wins":26},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":12,"losses":22,"wins":14},"x-ai/grok-4.6":{"draws":10,"losses":29,"wins":9},"x-ai/grok-4.7":{"draws":8,"losses":26,"wins":8},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":20,"losses":11,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":10},"z-ai/glm-5.2":{"draws":29,"losses":23,"wins":44},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":7,"losses":24,"wins":17},"z-ai/glm-5.3-flashx":{"draws":8,"losses":24,"wins":16}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":13,"wins":12},"claude-fable-5":{"draws":6,"losses":28,"wins":2},"claude-fable-5-1":{"draws":0,"losses":41,"wins":1},"claude-haiku-5-5":{"draws":7,"losses":20,"wins":7},"claude-opus-4-5":{"draws":8,"losses":43,"wins":7},"claude-opus-4-8":{"draws":7,"losses":23,"wins":2},"claude-opus-5":{"draws":6,"losses":48,"wins":4},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":6,"losses":22,"wins":8},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":16,"losses":20,"wins":16},"deepseek/deepseek-v4-pro":{"draws":7,"losses":17,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":20,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":21,"wins":6},"fireworks/ember-1":{"draws":8,"losses":21,"wins":7},"gemini-3.1-pro-preview":{"draws":8,"losses":18,"wins":10},"google/gemini-3.1-flash-lite":{"draws":8,"losses":8,"wins":10},"google/gemini-3.5-flash":{"draws":12,"losses":28,"wins":6},"google/gemini-3.5-flash-lite":{"draws":24,"losses":23,"wins":19},"google/gemini-3.6-flash":{"draws":16,"losses":45,"wins":9},"google/gemini-3.8-flash":{"draws":6,"losses":24,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":11,"wins":5},"gpt-4.1":{"draws":4,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":5,"losses":21,"wins":6},"gpt-5.4":{"draws":7,"losses":21,"wins":8},"gpt-5.4-mini":{"draws":8,"losses":10,"wins":6},"gpt-5.4-nano":{"draws":7,"losses":20,"wins":7},"gpt-5.5":{"draws":11,"losses":19,"wins":4},"gpt-5.6-luna":{"draws":13,"losses":16,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":28,"wins":5},"gpt-5.6-terra":{"draws":8,"losses":20,"wins":6},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":10,"losses":20,"wins":6},"gpt-6-sol":{"draws":6,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":7,"wins":11},"inclusionai/ling-3.0-flash":{"draws":10,"losses":8,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":23,"wins":9},"meta/muse-glimmer-30b":{"draws":16,"losses":8,"wins":8},"meta/muse-spark-1.2":{"draws":3,"losses":22,"wins":9},"meta/muse-spark-1.3":{"draws":3,"losses":31,"wins":2},"meta/muse-wonder":{"draws":3,"losses":29,"wins":4},"minimax/minimax-m3":{"draws":3,"losses":8,"wins":7},"mistralai/mistral-large-4-0":{"draws":6,"losses":11,"wins":5},"mistralai/mistral-medium-3-5":{"draws":7,"losses":8,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":19,"wins":8},"nex-agi/nex-n2-pro":{"draws":8,"losses":7,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":9},"o3":{"draws":9,"losses":33,"wins":12},"openai/gpt-oss-120b":{"draws":11,"losses":10,"wins":11},"poolside/laguna-s-2.1":{"draws":13,"losses":8,"wins":13},"qwen/qwen3.7-max":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":6,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":27,"wins":3},"qwen/qwen3.8-27b":{"draws":4,"losses":16,"wins":4},"qwen/qwen3.8-flash":{"draws":7,"losses":12,"wins":5},"qwen/qwen3.8-max":{"draws":6,"losses":26,"wins":4},"qwen/qwen3.8-max-0902":{"draws":6,"losses":25,"wins":5},"stealth/ox-alpha":{"draws":25,"losses":81,"wins":20},"stealth/space-bunny-alpha":{"draws":7,"losses":16,"wins":7},"stepfun/step-3.7-flash":{"draws":6,"losses":15,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":8,"wins":4},"tencent/hy4-preview":{"draws":11,"losses":22,"wins":3},"thinkingmachines/inkling":{"draws":15,"losses":20,"wins":13},"thinkingmachines/inkling-small":{"draws":13,"losses":13,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":8,"losses":25,"wins":3},"x-ai/grok-4.6":{"draws":8,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":17,"losses":18,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":26,"losses":33,"wins":13},"z-ai/glm-5.3":{"draws":5,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":5,"losses":25,"wins":6},"z-ai/glm-5.3-flashx":{"draws":7,"losses":26,"wins":3}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":38,"losses":47,"wins":35},"claude-fable-5":{"draws":23,"losses":102,"wins":7},"claude-fable-5-1":{"draws":4,"losses":141,"wins":1},"claude-haiku-5-5":{"draws":33,"losses":75,"wins":20},"claude-opus-4-5":{"draws":64,"losses":116,"wins":36},"claude-opus-4-8":{"draws":30,"losses":78,"wins":16},"claude-opus-5":{"draws":19,"losses":193,"wins":10},"claude-opus-5-5":{"draws":6,"losses":134,"wins":4},"claude-sonnet-5":{"draws":39,"losses":71,"wins":22},"claude-sonnet-5-5":{"draws":28,"losses":86,"wins":18},"cohere/north-mini-code":{"draws":14,"losses":17,"wins":19},"deepseek/deepseek-v4-flash":{"draws":54,"losses":55,"wins":49},"deepseek/deepseek-v4-pro":{"draws":31,"losses":68,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":60,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":74,"wins":15},"fireworks/ember-1":{"draws":41,"losses":73,"wins":18},"gemini-3.1-pro-preview":{"draws":39,"losses":64,"wins":29},"google/gemini-3.1-flash-lite":{"draws":29,"losses":20,"wins":43},"google/gemini-3.5-flash":{"draws":39,"losses":96,"wins":31},"google/gemini-3.5-flash-lite":{"draws":70,"losses":83,"wins":77},"google/gemini-3.6-flash":{"draws":61,"losses":154,"wins":37},"google/gemini-3.8-flash":{"draws":28,"losses":91,"wins":13},"google/gemma-4-31b-it":{"draws":34,"losses":17,"wins":27},"gpt-4.1":{"draws":16,"losses":21,"wins":7},"gpt-4.1-nano":{"draws":10,"losses":3,"wins":3},"gpt-5":{"draws":41,"losses":51,"wins":24},"gpt-5.4":{"draws":35,"losses":77,"wins":14},"gpt-5.4-mini":{"draws":34,"losses":33,"wins":21},"gpt-5.4-nano":{"draws":33,"losses":56,"wins":51},"gpt-5.5":{"draws":47,"losses":62,"wins":11},"gpt-5.6-luna":{"draws":52,"losses":55,"wins":25},"gpt-5.6-sol":{"draws":16,"losses":110,"wins":6},"gpt-5.6-terra":{"draws":40,"losses":71,"wins":15},"gpt-6-astra":{"draws":4,"losses":124,"wins":4},"gpt-6-luna":{"draws":35,"losses":71,"wins":26},"gpt-6-sol":{"draws":18,"losses":105,"wins":9},"gpt-6.1-sol":{"draws":6,"losses":122,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":40,"losses":20,"wins":34},"inclusionai/ling-3.0-flash":{"draws":40,"losses":21,"wins":33},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":39,"losses":52,"wins":53},"meta/muse-glimmer-30b":{"draws":49,"losses":26,"wins":39},"meta/muse-spark-1.2":{"draws":32,"losses":76,"wins":18},"meta/muse-spark-1.3":{"draws":24,"losses":93,"wins":15},"meta/muse-wonder":{"draws":23,"losses":93,"wins":16},"minimax/minimax-m3":{"draws":23,"losses":23,"wins":28},"mistralai/mistral-large-4-0":{"draws":28,"losses":43,"wins":11},"mistralai/mistral-medium-3-5":{"draws":32,"losses":19,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":17,"wins":8},"moonshotai/kimi-k3":{"draws":41,"losses":65,"wins":20},"nex-agi/nex-n2-pro":{"draws":18,"losses":21,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":47,"losses":33,"wins":40},"o3":{"draws":28,"losses":123,"wins":39},"openai/gpt-oss-120b":{"draws":41,"losses":37,"wins":38},"poolside/laguna-s-2.1":{"draws":48,"losses":43,"wins":37},"qwen/qwen3.7-max":{"draws":30,"losses":29,"wins":21},"qwen/qwen3.7-plus":{"draws":21,"losses":25,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":42,"losses":73,"wins":17},"qwen/qwen3.8-27b":{"draws":23,"losses":51,"wins":20},"qwen/qwen3.8-flash":{"draws":32,"losses":36,"wins":20},"qwen/qwen3.8-max":{"draws":44,"losses":67,"wins":21},"qwen/qwen3.8-max-0902":{"draws":38,"losses":78,"wins":16},"stealth/ox-alpha":{"draws":106,"losses":249,"wins":61},"stealth/space-bunny-alpha":{"draws":36,"losses":51,"wins":17},"stepfun/step-3.7-flash":{"draws":27,"losses":34,"wins":35},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":27,"losses":25,"wins":20},"tencent/hy4-preview":{"draws":35,"losses":74,"wins":17},"thinkingmachines/inkling":{"draws":50,"losses":67,"wins":57},"thinkingmachines/inkling-small":{"draws":54,"losses":32,"wins":46},"unbiased/pareto-26.10-preview":{"draws":0,"losses":44,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":10,"wins":18},"x-ai/grok-4.5":{"draws":21,"losses":93,"wins":18},"x-ai/grok-4.6":{"draws":36,"losses":87,"wins":9},"x-ai/grok-4.7":{"draws":12,"losses":98,"wins":8},"x-ai/grok-build-0.1":{"draws":16,"losses":11,"wins":17},"xiaomi/mimo-v2.5":{"draws":68,"losses":68,"wins":72},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":31,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":52,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":63,"wins":13},"z-ai/glm-5.2":{"draws":92,"losses":112,"wins":60},"z-ai/glm-5.3":{"draws":29,"losses":89,"wins":8},"z-ai/glm-5.3-flash":{"draws":31,"losses":77,"wins":24},"z-ai/glm-5.3-flashx":{"draws":34,"losses":78,"wins":20}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":9,"wins":27},"claude-fable-5":{"draws":8,"losses":26,"wins":14},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":9,"losses":19,"wins":18},"claude-opus-4-5":{"draws":19,"losses":21,"wins":38},"claude-opus-4-8":{"draws":10,"losses":18,"wins":16},"claude-opus-5":{"draws":9,"losses":58,"wins":15},"claude-opus-5-5":{"draws":3,"losses":45,"wins":4},"claude-sonnet-5":{"draws":14,"losses":13,"wins":21},"claude-sonnet-5-5":{"draws":12,"losses":22,"wins":14},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":14},"deepseek/deepseek-v4-flash":{"draws":14,"losses":18,"wins":40},"deepseek/deepseek-v4-pro":{"draws":7,"losses":8,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":14,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":22,"wins":17},"fireworks/ember-1":{"draws":12,"losses":19,"wins":17},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"wins":23},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":14,"losses":23,"wins":23},"google/gemini-3.5-flash-lite":{"draws":14,"losses":22,"wins":48},"google/gemini-3.6-flash":{"draws":18,"losses":32,"wins":42},"google/gemini-3.8-flash":{"draws":6,"losses":27,"wins":15},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":15},"gpt-4.1":{"draws":5,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":12,"wins":24},"gpt-5.4":{"draws":6,"losses":23,"wins":17},"gpt-5.4-mini":{"draws":11,"losses":7,"wins":14},"gpt-5.4-nano":{"draws":9,"losses":11,"wins":28},"gpt-5.5":{"draws":8,"losses":20,"wins":16},"gpt-5.6-luna":{"draws":13,"losses":11,"wins":24},"gpt-5.6-sol":{"draws":4,"losses":30,"wins":14},"gpt-5.6-terra":{"draws":10,"losses":14,"wins":22},"gpt-6-astra":{"draws":4,"losses":37,"wins":7},"gpt-6-luna":{"draws":10,"losses":20,"wins":18},"gpt-6-sol":{"draws":3,"losses":37,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":39,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inclusionai/ling-3.0-flash":{"draws":8,"losses":4,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":4,"wins":38},"meta/muse-glimmer-30b":{"draws":10,"losses":6,"wins":26},"meta/muse-spark-1.2":{"draws":10,"losses":16,"wins":20},"meta/muse-spark-1.3":{"draws":6,"losses":24,"wins":18},"meta/muse-wonder":{"draws":7,"losses":29,"wins":12},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":20},"mistralai/mistral-large-4-0":{"draws":4,"losses":14,"wins":12},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":11,"losses":18,"wins":17},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":5,"wins":25},"o3":{"draws":6,"losses":23,"wins":37},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":26},"poolside/laguna-s-2.1":{"draws":8,"losses":11,"wins":27},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":17},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":20,"wins":15},"qwen/qwen3.8-27b":{"draws":9,"losses":7,"wins":18},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":11},"qwen/qwen3.8-max":{"draws":12,"losses":20,"wins":16},"qwen/qwen3.8-max-0902":{"draws":11,"losses":23,"wins":14},"stealth/ox-alpha":{"draws":37,"losses":64,"wins":57},"stealth/space-bunny-alpha":{"draws":9,"losses":10,"wins":19},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":9,"losses":21,"wins":16},"thinkingmachines/inkling":{"draws":19,"losses":7,"wins":38},"thinkingmachines/inkling-small":{"draws":14,"losses":6,"wins":28},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":23,"wins":15},"x-ai/grok-4.6":{"draws":7,"losses":26,"wins":15},"x-ai/grok-4.7":{"draws":3,"losses":30,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":20,"losses":9,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":12},"z-ai/glm-5.2":{"draws":29,"losses":22,"wins":45},"z-ai/glm-5.3":{"draws":6,"losses":27,"wins":13},"z-ai/glm-5.3-flash":{"draws":8,"losses":23,"wins":17},"z-ai/glm-5.3-flashx":{"draws":9,"losses":22,"wins":17}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":13,"wins":19},"claude-fable-5":{"draws":5,"losses":33,"wins":10},"claude-fable-5-1":{"draws":1,"losses":51,"wins":2},"claude-haiku-5-5":{"draws":10,"losses":24,"wins":12},"claude-opus-4-5":{"draws":24,"losses":29,"wins":25},"claude-opus-4-8":{"draws":11,"losses":18,"wins":15},"claude-opus-5":{"draws":10,"losses":62,"wins":10},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":15,"losses":15,"wins":18},"claude-sonnet-5-5":{"draws":9,"losses":27,"wins":12},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":21,"losses":19,"wins":32},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":12,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":20,"wins":14},"fireworks/ember-1":{"draws":13,"losses":24,"wins":11},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":17},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":17,"losses":27,"wins":16},"google/gemini-3.5-flash-lite":{"draws":26,"losses":18,"wins":40},"google/gemini-3.6-flash":{"draws":22,"losses":46,"wins":24},"google/gemini-3.8-flash":{"draws":15,"losses":20,"wins":13},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":13},"gpt-4.1":{"draws":7,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":17,"wins":14},"gpt-5.4":{"draws":10,"losses":25,"wins":11},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":15},"gpt-5.4-nano":{"draws":11,"losses":14,"wins":23},"gpt-5.5":{"draws":13,"losses":15,"wins":16},"gpt-5.6-luna":{"draws":15,"losses":18,"wins":15},"gpt-5.6-sol":{"draws":7,"losses":32,"wins":9},"gpt-5.6-terra":{"draws":12,"losses":21,"wins":13},"gpt-6-astra":{"draws":1,"losses":47,"wins":0},"gpt-6-luna":{"draws":13,"losses":21,"wins":14},"gpt-6-sol":{"draws":3,"losses":37,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":43,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":6,"wins":17},"inclusionai/ling-3.0-flash":{"draws":15,"losses":4,"wins":15},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":18,"losses":11,"wins":23},"meta/muse-glimmer-30b":{"draws":14,"losses":6,"wins":22},"meta/muse-spark-1.2":{"draws":12,"losses":24,"wins":10},"meta/muse-spark-1.3":{"draws":11,"losses":24,"wins":13},"meta/muse-wonder":{"draws":13,"losses":27,"wins":8},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":20},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":5,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":18,"wins":15},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":19},"o3":{"draws":12,"losses":23,"wins":31},"openai/gpt-oss-120b":{"draws":12,"losses":11,"wins":19},"poolside/laguna-s-2.1":{"draws":14,"losses":14,"wins":18},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":13},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":18,"wins":14},"qwen/qwen3.8-27b":{"draws":12,"losses":13,"wins":9},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":9},"qwen/qwen3.8-max":{"draws":20,"losses":19,"wins":9},"qwen/qwen3.8-max-0902":{"draws":17,"losses":21,"wins":10},"stealth/ox-alpha":{"draws":41,"losses":64,"wins":53},"stealth/space-bunny-alpha":{"draws":11,"losses":10,"wins":17},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":20,"wins":14},"thinkingmachines/inkling":{"draws":23,"losses":15,"wins":26},"thinkingmachines/inkling-small":{"draws":12,"losses":9,"wins":27},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":22,"wins":15},"x-ai/grok-4.6":{"draws":12,"losses":26,"wins":10},"x-ai/grok-4.7":{"draws":2,"losses":35,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":26,"losses":13,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":6,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":13,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":15,"wins":9},"z-ai/glm-5.2":{"draws":35,"losses":31,"wins":30},"z-ai/glm-5.3":{"draws":13,"losses":25,"wins":8},"z-ai/glm-5.3-flash":{"draws":5,"losses":28,"wins":15},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":14}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":6,"wins":22},"claude-fable-5":{"draws":12,"losses":25,"wins":11},"claude-fable-5-1":{"draws":8,"losses":41,"wins":5},"claude-haiku-5-5":{"draws":15,"losses":18,"wins":13},"claude-opus-4-5":{"draws":18,"losses":22,"wins":38},"claude-opus-4-8":{"draws":11,"losses":11,"wins":22},"claude-opus-5":{"draws":17,"losses":52,"wins":13},"claude-opus-5-5":{"draws":4,"losses":41,"wins":7},"claude-sonnet-5":{"draws":11,"losses":15,"wins":22},"claude-sonnet-5-5":{"draws":10,"losses":20,"wins":18},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":29,"losses":6,"wins":37},"deepseek/deepseek-v4-pro":{"draws":11,"losses":14,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":10,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":11,"wins":14},"fireworks/ember-1":{"draws":17,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":16,"losses":12,"wins":20},"google/gemini-3.1-flash-lite":{"draws":13,"losses":1,"wins":18},"google/gemini-3.5-flash":{"draws":22,"losses":15,"wins":23},"google/gemini-3.5-flash-lite":{"draws":36,"losses":7,"wins":41},"google/gemini-3.6-flash":{"draws":29,"losses":33,"wins":30},"google/gemini-3.8-flash":{"draws":17,"losses":18,"wins":13},"google/gemma-4-31b-it":{"draws":14,"losses":3,"wins":11},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":16,"losses":9,"wins":17},"gpt-5.4":{"draws":15,"losses":15,"wins":16},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":18,"losses":10,"wins":20},"gpt-5.5":{"draws":14,"losses":17,"wins":13},"gpt-5.6-luna":{"draws":22,"losses":6,"wins":20},"gpt-5.6-sol":{"draws":12,"losses":23,"wins":13},"gpt-5.6-terra":{"draws":18,"losses":12,"wins":16},"gpt-6-astra":{"draws":6,"losses":39,"wins":3},"gpt-6-luna":{"draws":16,"losses":10,"wins":22},"gpt-6-sol":{"draws":9,"losses":27,"wins":12},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":15},"inclusionai/ling-3.0-flash":{"draws":19,"losses":3,"wins":12},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":13,"wins":28},"meta/muse-glimmer-30b":{"draws":18,"losses":4,"wins":20},"meta/muse-spark-1.2":{"draws":15,"losses":13,"wins":18},"meta/muse-spark-1.3":{"draws":12,"losses":18,"wins":18},"meta/muse-wonder":{"draws":16,"losses":19,"wins":13},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"mistralai/mistral-large-4-0":{"draws":14,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":9,"losses":3,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":12,"wins":18},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":9,"wins":19},"o3":{"draws":17,"losses":16,"wins":33},"openai/gpt-oss-120b":{"draws":16,"losses":5,"wins":21},"poolside/laguna-s-2.1":{"draws":22,"losses":5,"wins":19},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":12},"qwen/qwen3.7-plus":{"draws":11,"losses":1,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":23},"qwen/qwen3.8-27b":{"draws":9,"losses":7,"wins":18},"qwen/qwen3.8-flash":{"draws":11,"losses":6,"wins":15},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":19},"qwen/qwen3.8-max-0902":{"draws":20,"losses":11,"wins":17},"stealth/ox-alpha":{"draws":37,"losses":58,"wins":63},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":18},"stepfun/step-3.7-flash":{"draws":10,"losses":3,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":4,"wins":13},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":22,"losses":12,"wins":30},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":23},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":14,"losses":20,"wins":14},"x-ai/grok-4.6":{"draws":16,"losses":19,"wins":13},"x-ai/grok-4.7":{"draws":7,"losses":25,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":31,"losses":6,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":11,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":40,"losses":17,"wins":39},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":11,"losses":16,"wins":21},"z-ai/glm-5.3-flashx":{"draws":13,"losses":19,"wins":16}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":5,"wins":25},"claude-fable-5":{"draws":12,"losses":31,"wins":5},"claude-fable-5-1":{"draws":0,"losses":52,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":29,"losses":22,"wins":27},"claude-opus-4-8":{"draws":17,"losses":16,"wins":11},"claude-opus-5":{"draws":9,"losses":58,"wins":15},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":15,"losses":15,"wins":18},"claude-sonnet-5-5":{"draws":9,"losses":23,"wins":16},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":25,"losses":10,"wins":37},"deepseek/deepseek-v4-pro":{"draws":15,"losses":10,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":13,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":16,"wins":19},"fireworks/ember-1":{"draws":10,"losses":7,"wins":15},"gemini-3.1-pro-preview":{"draws":12,"losses":13,"wins":23},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":17,"losses":20,"wins":23},"google/gemini-3.5-flash-lite":{"draws":34,"losses":9,"wins":41},"google/gemini-3.6-flash":{"draws":30,"losses":27,"wins":35},"google/gemini-3.8-flash":{"draws":10,"losses":18,"wins":20},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":8,"wins":22},"gpt-5.4":{"draws":14,"losses":20,"wins":12},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":18},"gpt-5.4-nano":{"draws":15,"losses":9,"wins":24},"gpt-5.5":{"draws":19,"losses":14,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":26,"wins":12},"gpt-5.6-terra":{"draws":14,"losses":8,"wins":24},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":15,"losses":11,"wins":22},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":37,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"inclusionai/ling-3.0-flash":{"draws":13,"losses":0,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":6,"wins":33},"meta/muse-glimmer-30b":{"draws":17,"losses":6,"wins":19},"meta/muse-spark-1.2":{"draws":13,"losses":13,"wins":20},"meta/muse-spark-1.3":{"draws":21,"losses":16,"wins":11},"meta/muse-wonder":{"draws":11,"losses":27,"wins":10},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":12,"wins":17},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":5,"wins":20},"o3":{"draws":13,"losses":16,"wins":37},"openai/gpt-oss-120b":{"draws":16,"losses":3,"wins":23},"poolside/laguna-s-2.1":{"draws":18,"losses":7,"wins":21},"qwen/qwen3.7-max":{"draws":12,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":3,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":19},"qwen/qwen3.8-27b":{"draws":13,"losses":8,"wins":13},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":13},"qwen/qwen3.8-max":{"draws":15,"losses":12,"wins":21},"qwen/qwen3.8-max-0902":{"draws":19,"losses":19,"wins":10},"stealth/ox-alpha":{"draws":48,"losses":51,"wins":59},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":24,"losses":3,"wins":37},"thinkingmachines/inkling-small":{"draws":16,"losses":8,"wins":24},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":20,"wins":17},"x-ai/grok-4.6":{"draws":16,"losses":19,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":29,"losses":7,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":5,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":12,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":17,"wins":7},"z-ai/glm-5.2":{"draws":34,"losses":19,"wins":43},"z-ai/glm-5.3":{"draws":10,"losses":27,"wins":9},"z-ai/glm-5.3-flash":{"draws":12,"losses":22,"wins":14},"z-ai/glm-5.3-flashx":{"draws":12,"losses":18,"wins":18}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":13,"wins":15},"claude-fable-5":{"draws":13,"losses":25,"wins":10},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":19,"wins":13},"claude-opus-4-5":{"draws":26,"losses":35,"wins":17},"claude-opus-4-8":{"draws":16,"losses":22,"wins":6},"claude-opus-5":{"draws":10,"losses":65,"wins":7},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":19,"losses":15,"wins":14},"claude-sonnet-5-5":{"draws":8,"losses":30,"wins":10},"cohere/north-mini-code":{"draws":6,"losses":5,"wins":7},"deepseek/deepseek-v4-flash":{"draws":30,"losses":16,"wins":26},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":23,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":16,"wins":14},"fireworks/ember-1":{"draws":16,"losses":24,"wins":8},"gemini-3.1-pro-preview":{"draws":11,"losses":11,"wins":10},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":16,"losses":30,"wins":14},"google/gemini-3.5-flash-lite":{"draws":35,"losses":24,"wins":25},"google/gemini-3.6-flash":{"draws":21,"losses":46,"wins":25},"google/gemini-3.8-flash":{"draws":12,"losses":30,"wins":6},"google/gemma-4-31b-it":{"draws":14,"losses":5,"wins":9},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":12,"wins":13},"gpt-5.4":{"draws":13,"losses":21,"wins":12},"gpt-5.4-mini":{"draws":15,"losses":9,"wins":8},"gpt-5.4-nano":{"draws":14,"losses":15,"wins":19},"gpt-5.5":{"draws":15,"losses":20,"wins":9},"gpt-5.6-luna":{"draws":16,"losses":15,"wins":17},"gpt-5.6-sol":{"draws":7,"losses":36,"wins":5},"gpt-5.6-terra":{"draws":18,"losses":12,"wins":16},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":18,"losses":16,"wins":14},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":47,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":5,"wins":10},"inclusionai/ling-3.0-flash":{"draws":18,"losses":2,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":14,"wins":23},"meta/muse-glimmer-30b":{"draws":20,"losses":3,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":20,"wins":15},"meta/muse-spark-1.3":{"draws":13,"losses":23,"wins":12},"meta/muse-wonder":{"draws":9,"losses":36,"wins":3},"minimax/minimax-m3":{"draws":7,"losses":9,"wins":10},"mistralai/mistral-large-4-0":{"draws":7,"losses":14,"wins":9},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":12,"losses":24,"wins":10},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":10,"wins":8},"o3":{"draws":17,"losses":28,"wins":21},"openai/gpt-oss-120b":{"draws":17,"losses":8,"wins":17},"poolside/laguna-s-2.1":{"draws":20,"losses":11,"wins":15},"qwen/qwen3.7-max":{"draws":10,"losses":10,"wins":8},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":21,"wins":14},"qwen/qwen3.8-27b":{"draws":9,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":16,"losses":8,"wins":8},"qwen/qwen3.8-max":{"draws":14,"losses":19,"wins":15},"qwen/qwen3.8-max-0902":{"draws":15,"losses":22,"wins":11},"stealth/ox-alpha":{"draws":45,"losses":72,"wins":41},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":13},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":16,"losses":23,"wins":7},"thinkingmachines/inkling":{"draws":19,"losses":16,"wins":29},"thinkingmachines/inkling-small":{"draws":19,"losses":7,"wins":22},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":9,"losses":25,"wins":14},"x-ai/grok-4.6":{"draws":14,"losses":28,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":8,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":36,"losses":14,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":11,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":12,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":20,"wins":5},"z-ai/glm-5.2":{"draws":35,"losses":35,"wins":26},"z-ai/glm-5.3":{"draws":9,"losses":30,"wins":7},"z-ai/glm-5.3-flash":{"draws":14,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":16,"losses":25,"wins":7}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":14,"wins":8},"claude-fable-5":{"draws":3,"losses":31,"wins":2},"claude-fable-5-1":{"draws":1,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":4},"claude-opus-4-5":{"draws":14,"losses":44,"wins":2},"claude-opus-4-8":{"draws":11,"losses":23,"wins":2},"claude-opus-5":{"draws":7,"losses":46,"wins":5},"claude-opus-5-5":{"draws":4,"losses":36,"wins":0},"claude-sonnet-5":{"draws":13,"losses":21,"wins":2},"claude-sonnet-5-5":{"draws":8,"losses":22,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":18,"losses":27,"wins":9},"deepseek/deepseek-v4-pro":{"draws":11,"losses":19,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":18,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":4},"fireworks/ember-1":{"draws":8,"losses":25,"wins":3},"gemini-3.1-pro-preview":{"draws":7,"losses":19,"wins":10},"google/gemini-3.1-flash-lite":{"draws":2,"losses":8,"wins":8},"google/gemini-3.5-flash":{"draws":14,"losses":25,"wins":9},"google/gemini-3.5-flash-lite":{"draws":18,"losses":28,"wins":20},"google/gemini-3.6-flash":{"draws":16,"losses":46,"wins":8},"google/gemini-3.8-flash":{"draws":13,"losses":23,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":7},"gpt-4.1":{"draws":5,"losses":5,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":20,"wins":2},"gpt-5.4":{"draws":7,"losses":26,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":13,"wins":3},"gpt-5.4-nano":{"draws":11,"losses":20,"wins":9},"gpt-5.5":{"draws":11,"losses":20,"wins":3},"gpt-5.6-luna":{"draws":9,"losses":19,"wins":8},"gpt-5.6-sol":{"draws":2,"losses":33,"wins":1},"gpt-5.6-terra":{"draws":12,"losses":19,"wins":3},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":11,"losses":22,"wins":3},"gpt-6-sol":{"draws":6,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":11,"losses":7,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":20,"wins":13},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":7},"meta/muse-spark-1.2":{"draws":7,"losses":22,"wins":5},"meta/muse-spark-1.3":{"draws":5,"losses":30,"wins":1},"meta/muse-wonder":{"draws":5,"losses":30,"wins":1},"minimax/minimax-m3":{"draws":5,"losses":9,"wins":6},"mistralai/mistral-large-4-0":{"draws":7,"losses":15,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":9,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":22,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":13,"wins":13},"o3":{"draws":11,"losses":45,"wins":4},"openai/gpt-oss-120b":{"draws":8,"losses":17,"wins":5},"poolside/laguna-s-2.1":{"draws":8,"losses":16,"wins":8},"qwen/qwen3.7-max":{"draws":7,"losses":12,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":10,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":27,"wins":1},"qwen/qwen3.8-27b":{"draws":5,"losses":17,"wins":4},"qwen/qwen3.8-flash":{"draws":8,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":13,"losses":23,"wins":0},"qwen/qwen3.8-max-0902":{"draws":12,"losses":24,"wins":0},"stealth/ox-alpha":{"draws":19,"losses":70,"wins":13},"stealth/space-bunny-alpha":{"draws":7,"losses":18,"wins":5},"stepfun/step-3.7-flash":{"draws":6,"losses":18,"wins":4},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":5},"tencent/hy4-preview":{"draws":12,"losses":22,"wins":2},"thinkingmachines/inkling":{"draws":12,"losses":23,"wins":13},"thinkingmachines/inkling-small":{"draws":13,"losses":11,"wins":12},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":9,"losses":27,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":23,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":28,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":22,"losses":23,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":17,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":20,"wins":1},"z-ai/glm-5.2":{"draws":14,"losses":47,"wins":11},"z-ai/glm-5.3":{"draws":7,"losses":27,"wins":0},"z-ai/glm-5.3-flash":{"draws":8,"losses":24,"wins":4},"z-ai/glm-5.3-flashx":{"draws":10,"losses":23,"wins":3}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":26},"claude-fable-5":{"draws":10,"losses":26,"wins":12},"claude-fable-5-1":{"draws":5,"losses":47,"wins":2},"claude-haiku-5-5":{"draws":9,"losses":18,"wins":19},"claude-opus-4-5":{"draws":22,"losses":16,"wins":40},"claude-opus-4-8":{"draws":8,"losses":14,"wins":22},"claude-opus-5":{"draws":8,"losses":65,"wins":9},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":9,"losses":11,"wins":28},"claude-sonnet-5-5":{"draws":6,"losses":22,"wins":20},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":23,"losses":8,"wins":41},"deepseek/deepseek-v4-pro":{"draws":11,"losses":7,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":8,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":19,"wins":14},"fireworks/ember-1":{"draws":11,"losses":15,"wins":22},"gemini-3.1-pro-preview":{"draws":12,"losses":12,"wins":24},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":9,"losses":14,"wins":21},"google/gemini-3.5-flash-lite":{"draws":14,"losses":10,"wins":60},"google/gemini-3.6-flash":{"draws":19,"losses":33,"wins":40},"google/gemini-3.8-flash":{"draws":10,"losses":22,"wins":16},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":16},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":10,"losses":9,"wins":23},"gpt-5.4":{"draws":8,"losses":22,"wins":16},"gpt-5.4-mini":{"draws":9,"losses":9,"wins":14},"gpt-5.4-nano":{"draws":12,"losses":8,"wins":28},"gpt-5.5":{"draws":11,"losses":18,"wins":15},"gpt-5.6-luna":{"draws":17,"losses":8,"wins":23},"gpt-5.6-sol":{"draws":7,"losses":27,"wins":14},"gpt-5.6-terra":{"draws":14,"losses":14,"wins":18},"gpt-6-astra":{"draws":4,"losses":41,"wins":3},"gpt-6-luna":{"draws":14,"losses":13,"wins":21},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":4,"losses":39,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":1,"wins":19},"inclusionai/ling-3.0-flash":{"draws":10,"losses":2,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":9,"wins":32},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":25},"meta/muse-spark-1.2":{"draws":10,"losses":17,"wins":19},"meta/muse-spark-1.3":{"draws":9,"losses":24,"wins":15},"meta/muse-wonder":{"draws":11,"losses":27,"wins":10},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"mistralai/mistral-large-4-0":{"draws":8,"losses":6,"wins":16},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":11,"wins":18},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":8,"wins":25},"o3":{"draws":10,"losses":17,"wins":39},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":26},"poolside/laguna-s-2.1":{"draws":12,"losses":7,"wins":27},"qwen/qwen3.7-max":{"draws":7,"losses":5,"wins":16},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":23},"qwen/qwen3.8-27b":{"draws":8,"losses":6,"wins":20},"qwen/qwen3.8-flash":{"draws":10,"losses":8,"wins":14},"qwen/qwen3.8-max":{"draws":15,"losses":15,"wins":18},"qwen/qwen3.8-max-0902":{"draws":14,"losses":18,"wins":16},"stealth/ox-alpha":{"draws":32,"losses":49,"wins":77},"stealth/space-bunny-alpha":{"draws":12,"losses":3,"wins":23},"stepfun/step-3.7-flash":{"draws":6,"losses":5,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":7,"losses":22,"wins":17},"thinkingmachines/inkling":{"draws":19,"losses":6,"wins":39},"thinkingmachines/inkling-small":{"draws":13,"losses":7,"wins":28},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":9,"losses":17,"wins":22},"x-ai/grok-4.6":{"draws":15,"losses":24,"wins":9},"x-ai/grok-4.7":{"draws":6,"losses":30,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":25,"losses":10,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":6,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":8,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":9},"z-ai/glm-5.2":{"draws":25,"losses":19,"wins":52},"z-ai/glm-5.3":{"draws":10,"losses":19,"wins":17},"z-ai/glm-5.3-flash":{"draws":10,"losses":17,"wins":21},"z-ai/glm-5.3-flashx":{"draws":20,"losses":14,"wins":14}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":34,"wins":18},"claude-fable-5":{"draws":16,"losses":63,"wins":5},"claude-fable-5-1":{"draws":9,"losses":84,"wins":1},"claude-haiku-5-5":{"draws":20,"losses":48,"wins":12},"claude-opus-4-5":{"draws":49,"losses":75,"wins":12},"claude-opus-4-8":{"draws":23,"losses":52,"wins":1},"claude-opus-5":{"draws":23,"losses":113,"wins":8},"claude-opus-5-5":{"draws":6,"losses":86,"wins":0},"claude-sonnet-5":{"draws":26,"losses":48,"wins":10},"claude-sonnet-5-5":{"draws":15,"losses":57,"wins":12},"cohere/north-mini-code":{"draws":11,"losses":15,"wins":6},"deepseek/deepseek-v4-flash":{"draws":41,"losses":52,"wins":31},"deepseek/deepseek-v4-pro":{"draws":21,"losses":37,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":44,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":46,"wins":9},"fireworks/ember-1":{"draws":34,"losses":42,"wins":8},"gemini-3.1-pro-preview":{"draws":32,"losses":37,"wins":15},"google/gemini-3.1-flash-lite":{"draws":20,"losses":13,"wins":23},"google/gemini-3.5-flash":{"draws":23,"losses":60,"wins":23},"google/gemini-3.5-flash-lite":{"draws":41,"losses":45,"wins":36},"google/gemini-3.6-flash":{"draws":48,"losses":94,"wins":20},"google/gemini-3.8-flash":{"draws":17,"losses":63,"wins":4},"google/gemma-4-31b-it":{"draws":20,"losses":14,"wins":14},"gpt-4.1":{"draws":11,"losses":14,"wins":3},"gpt-4.1-nano":{"draws":6,"losses":3,"wins":1},"gpt-5":{"draws":25,"losses":33,"wins":16},"gpt-5.4":{"draws":22,"losses":51,"wins":9},"gpt-5.4-mini":{"draws":21,"losses":24,"wins":11},"gpt-5.4-nano":{"draws":20,"losses":34,"wins":30},"gpt-5.5":{"draws":32,"losses":40,"wins":6},"gpt-5.6-luna":{"draws":29,"losses":41,"wins":14},"gpt-5.6-sol":{"draws":12,"losses":68,"wins":4},"gpt-5.6-terra":{"draws":26,"losses":48,"wins":6},"gpt-6-astra":{"draws":5,"losses":79,"wins":0},"gpt-6-luna":{"draws":26,"losses":39,"wins":19},"gpt-6-sol":{"draws":14,"losses":61,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":78,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":20,"wins":16},"inclusionai/ling-3.0-flash":{"draws":21,"losses":20,"wins":19},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":28,"losses":37,"wins":27},"meta/muse-glimmer-30b":{"draws":31,"losses":20,"wins":23},"meta/muse-spark-1.2":{"draws":21,"losses":49,"wins":10},"meta/muse-spark-1.3":{"draws":15,"losses":62,"wins":7},"meta/muse-wonder":{"draws":15,"losses":63,"wins":6},"minimax/minimax-m3":{"draws":11,"losses":15,"wins":18},"mistralai/mistral-large-4-0":{"draws":18,"losses":27,"wins":7},"mistralai/mistral-medium-3-5":{"draws":20,"losses":12,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":11,"wins":4},"moonshotai/kimi-k3":{"draws":31,"losses":41,"wins":8},"nex-agi/nex-n2-pro":{"draws":12,"losses":13,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":29,"wins":17},"o3":{"draws":20,"losses":85,"wins":13},"openai/gpt-oss-120b":{"draws":24,"losses":30,"wins":18},"poolside/laguna-s-2.1":{"draws":26,"losses":41,"wins":15},"qwen/qwen3.7-max":{"draws":15,"losses":24,"wins":9},"qwen/qwen3.7-plus":{"draws":12,"losses":14,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":50,"wins":6},"qwen/qwen3.8-27b":{"draws":14,"losses":36,"wins":10},"qwen/qwen3.8-flash":{"draws":22,"losses":30,"wins":4},"qwen/qwen3.8-max":{"draws":28,"losses":46,"wins":10},"qwen/qwen3.8-max-0902":{"draws":25,"losses":53,"wins":6},"stealth/ox-alpha":{"draws":66,"losses":178,"wins":38},"stealth/space-bunny-alpha":{"draws":20,"losses":35,"wins":11},"stepfun/step-3.7-flash":{"draws":17,"losses":30,"wins":13},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":22,"wins":8},"tencent/hy4-preview":{"draws":24,"losses":46,"wins":12},"thinkingmachines/inkling":{"draws":31,"losses":49,"wins":34},"thinkingmachines/inkling-small":{"draws":26,"losses":24,"wins":34},"unbiased/pareto-26.10-preview":{"draws":0,"losses":28,"wins":0},"upstage/solar-mini4":{"draws":8,"losses":12,"wins":2},"x-ai/grok-4.5":{"draws":21,"losses":56,"wins":7},"x-ai/grok-4.6":{"draws":23,"losses":57,"wins":4},"x-ai/grok-4.7":{"draws":7,"losses":58,"wins":7},"x-ai/grok-build-0.1":{"draws":13,"losses":12,"wins":3},"xiaomi/mimo-v2.5":{"draws":37,"losses":56,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":19,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":37,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":44,"wins":6},"z-ai/glm-5.2":{"draws":59,"losses":76,"wins":33},"z-ai/glm-5.3":{"draws":18,"losses":59,"wins":3},"z-ai/glm-5.3-flash":{"draws":20,"losses":49,"wins":15},"z-ai/glm-5.3-flashx":{"draws":21,"losses":53,"wins":10}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":13,"wins":47},"claude-fable-5":{"draws":14,"losses":41,"wins":29},"claude-fable-5-1":{"draws":8,"losses":80,"wins":8},"claude-haiku-5-5":{"draws":15,"losses":29,"wins":36},"claude-opus-4-5":{"draws":40,"losses":28,"wins":68},"claude-opus-4-8":{"draws":16,"losses":23,"wins":37},"claude-opus-5":{"draws":16,"losses":91,"wins":33},"claude-opus-5-5":{"draws":6,"losses":70,"wins":12},"claude-sonnet-5":{"draws":20,"losses":24,"wins":40},"claude-sonnet-5-5":{"draws":14,"losses":32,"wins":38},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":25},"deepseek/deepseek-v4-flash":{"draws":26,"losses":14,"wins":84},"deepseek/deepseek-v4-pro":{"draws":18,"losses":25,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":19,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":24,"wins":40},"fireworks/ember-1":{"draws":21,"losses":31,"wins":32},"gemini-3.1-pro-preview":{"draws":15,"losses":27,"wins":42},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":47},"google/gemini-3.5-flash":{"draws":21,"losses":32,"wins":53},"google/gemini-3.5-flash-lite":{"draws":41,"losses":24,"wins":85},"google/gemini-3.6-flash":{"draws":26,"losses":47,"wins":63},"google/gemini-3.8-flash":{"draws":18,"losses":34,"wins":32},"google/gemma-4-31b-it":{"draws":13,"losses":7,"wins":28},"gpt-4.1":{"draws":7,"losses":4,"wins":17},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":6},"gpt-5":{"draws":15,"losses":15,"wins":44},"gpt-5.4":{"draws":17,"losses":34,"wins":31},"gpt-5.4-mini":{"draws":17,"losses":8,"wins":31},"gpt-5.4-nano":{"draws":13,"losses":10,"wins":59},"gpt-5.5":{"draws":17,"losses":31,"wins":30},"gpt-5.6-luna":{"draws":22,"losses":14,"wins":48},"gpt-5.6-sol":{"draws":11,"losses":46,"wins":27},"gpt-5.6-terra":{"draws":23,"losses":16,"wins":41},"gpt-6-astra":{"draws":7,"losses":72,"wins":5},"gpt-6-luna":{"draws":21,"losses":22,"wins":41},"gpt-6-sol":{"draws":8,"losses":51,"wins":25},"gpt-6.1-sol":{"draws":4,"losses":66,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":4,"wins":36},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":41},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":19,"losses":9,"wins":64},"meta/muse-glimmer-30b":{"draws":17,"losses":10,"wins":47},"meta/muse-spark-1.2":{"draws":17,"losses":26,"wins":37},"meta/muse-spark-1.3":{"draws":9,"losses":42,"wins":33},"meta/muse-wonder":{"draws":13,"losses":43,"wins":28},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":32},"mistralai/mistral-large-4-0":{"draws":10,"losses":19,"wins":23},"mistralai/mistral-medium-3-5":{"draws":12,"losses":4,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":2,"wins":11},"moonshotai/kimi-k3":{"draws":19,"losses":27,"wins":34},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":31},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":8,"wins":42},"o3":{"draws":14,"losses":25,"wins":81},"openai/gpt-oss-120b":{"draws":21,"losses":6,"wins":45},"poolside/laguna-s-2.1":{"draws":18,"losses":12,"wins":48},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":29},"qwen/qwen3.7-plus":{"draws":11,"losses":3,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":25,"wins":38},"qwen/qwen3.8-27b":{"draws":10,"losses":18,"wins":34},"qwen/qwen3.8-flash":{"draws":15,"losses":14,"wins":27},"qwen/qwen3.8-max":{"draws":20,"losses":27,"wins":37},"qwen/qwen3.8-max-0902":{"draws":16,"losses":31,"wins":37},"stealth/ox-alpha":{"draws":56,"losses":102,"wins":126},"stealth/space-bunny-alpha":{"draws":19,"losses":10,"wins":39},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":43},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":13,"losses":9,"wins":22},"tencent/hy4-preview":{"draws":17,"losses":29,"wins":36},"thinkingmachines/inkling":{"draws":27,"losses":16,"wins":73},"thinkingmachines/inkling-small":{"draws":19,"losses":11,"wins":54},"unbiased/pareto-26.10-preview":{"draws":3,"losses":22,"wins":3},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":21},"x-ai/grok-4.5":{"draws":18,"losses":31,"wins":35},"x-ai/grok-4.6":{"draws":21,"losses":35,"wins":28},"x-ai/grok-4.7":{"draws":4,"losses":47,"wins":21},"x-ai/grok-build-0.1":{"draws":8,"losses":0,"wins":20},"xiaomi/mimo-v2.5":{"draws":36,"losses":9,"wins":83},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":32},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":17,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":18,"wins":25},"z-ai/glm-5.2":{"draws":38,"losses":47,"wins":83},"z-ai/glm-5.3":{"draws":13,"losses":46,"wins":21},"z-ai/glm-5.3-flash":{"draws":7,"losses":44,"wins":33},"z-ai/glm-5.3-flashx":{"draws":14,"losses":31,"wins":39}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":7,"wins":25},"claude-fable-5":{"draws":9,"losses":14,"wins":25},"claude-fable-5-1":{"draws":1,"losses":47,"wins":6},"claude-haiku-5-5":{"draws":10,"losses":13,"wins":23},"claude-opus-4-5":{"draws":31,"losses":9,"wins":38},"claude-opus-4-8":{"draws":12,"losses":12,"wins":20},"claude-opus-5":{"draws":11,"losses":50,"wins":21},"claude-opus-5-5":{"draws":7,"losses":41,"wins":4},"claude-sonnet-5":{"draws":15,"losses":10,"wins":23},"claude-sonnet-5-5":{"draws":10,"losses":20,"wins":18},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":18,"losses":8,"wins":46},"deepseek/deepseek-v4-pro":{"draws":13,"losses":12,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":9,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":12,"wins":20},"fireworks/ember-1":{"draws":17,"losses":13,"wins":18},"gemini-3.1-pro-preview":{"draws":14,"losses":9,"wins":25},"google/gemini-3.1-flash-lite":{"draws":11,"losses":0,"wins":21},"google/gemini-3.5-flash":{"draws":16,"losses":14,"wins":30},"google/gemini-3.5-flash-lite":{"draws":25,"losses":2,"wins":57},"google/gemini-3.6-flash":{"draws":26,"losses":25,"wins":41},"google/gemini-3.8-flash":{"draws":9,"losses":9,"wins":14},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":6,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":13,"losses":11,"wins":18},"gpt-5.4":{"draws":12,"losses":17,"wins":17},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":16},"gpt-5.4-nano":{"draws":13,"losses":9,"wins":26},"gpt-5.5":{"draws":23,"losses":12,"wins":9},"gpt-5.6-luna":{"draws":12,"losses":6,"wins":30},"gpt-5.6-sol":{"draws":9,"losses":24,"wins":15},"gpt-5.6-terra":{"draws":14,"losses":10,"wins":22},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":14,"losses":12,"wins":22},"gpt-6-sol":{"draws":9,"losses":30,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":0,"wins":20},"inclusionai/ling-3.0-flash":{"draws":12,"losses":0,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":4,"wins":33},"meta/muse-glimmer-30b":{"draws":17,"losses":3,"wins":22},"meta/muse-spark-1.2":{"draws":11,"losses":24,"wins":11},"meta/muse-spark-1.3":{"draws":15,"losses":15,"wins":18},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":8,"losses":0,"wins":18},"mistralai/mistral-large-4-0":{"draws":11,"losses":6,"wins":13},"mistralai/mistral-medium-3-5":{"draws":11,"losses":0,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":10,"wins":21},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":0,"wins":25},"o3":{"draws":12,"losses":18,"wins":36},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":17,"losses":6,"wins":23},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":12,"wins":21},"qwen/qwen3.8-27b":{"draws":5,"losses":7,"wins":22},"qwen/qwen3.8-flash":{"draws":11,"losses":6,"wins":15},"qwen/qwen3.8-max":{"draws":14,"losses":13,"wins":21},"qwen/qwen3.8-max-0902":{"draws":18,"losses":11,"wins":19},"stealth/ox-alpha":{"draws":42,"losses":40,"wins":76},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":8,"losses":3,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":12},"tencent/hy4-preview":{"draws":15,"losses":14,"wins":17},"thinkingmachines/inkling":{"draws":23,"losses":4,"wins":37},"thinkingmachines/inkling-small":{"draws":17,"losses":2,"wins":29},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":11,"losses":21,"wins":16},"x-ai/grok-4.6":{"draws":21,"losses":16,"wins":11},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":25,"losses":3,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":9,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":32,"losses":15,"wins":49},"z-ai/glm-5.3":{"draws":9,"losses":21,"wins":16},"z-ai/glm-5.3-flash":{"draws":8,"losses":17,"wins":23},"z-ai/glm-5.3-flashx":{"draws":12,"losses":14,"wins":22}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":13,"wins":17},"claude-fable-5":{"draws":11,"losses":30,"wins":7},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":28,"wins":6},"claude-opus-4-5":{"draws":28,"losses":37,"wins":13},"claude-opus-4-8":{"draws":12,"losses":24,"wins":8},"claude-opus-5":{"draws":13,"losses":62,"wins":7},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":13,"losses":25,"wins":10},"claude-sonnet-5-5":{"draws":9,"losses":31,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":34,"losses":24,"wins":14},"deepseek/deepseek-v4-pro":{"draws":18,"losses":15,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":22,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":19,"wins":9},"fireworks/ember-1":{"draws":19,"losses":21,"wins":8},"gemini-3.1-pro-preview":{"draws":17,"losses":20,"wins":11},"google/gemini-3.1-flash-lite":{"draws":12,"losses":5,"wins":15},"google/gemini-3.5-flash":{"draws":14,"losses":29,"wins":17},"google/gemini-3.5-flash-lite":{"draws":29,"losses":31,"wins":24},"google/gemini-3.6-flash":{"draws":28,"losses":49,"wins":15},"google/gemini-3.8-flash":{"draws":10,"losses":31,"wins":7},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":6},"gpt-4.1":{"draws":5,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":17,"losses":17,"wins":8},"gpt-5.4":{"draws":17,"losses":22,"wins":7},"gpt-5.4-mini":{"draws":13,"losses":13,"wins":6},"gpt-5.4-nano":{"draws":17,"losses":20,"wins":11},"gpt-5.5":{"draws":19,"losses":20,"wins":5},"gpt-5.6-luna":{"draws":20,"losses":14,"wins":14},"gpt-5.6-sol":{"draws":5,"losses":38,"wins":5},"gpt-5.6-terra":{"draws":18,"losses":19,"wins":9},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":5,"losses":41,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":44,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":9,"wins":10},"inclusionai/ling-3.0-flash":{"draws":18,"losses":7,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":15,"wins":16},"meta/muse-glimmer-30b":{"draws":22,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":12,"losses":19,"wins":15},"meta/muse-spark-1.3":{"draws":12,"losses":30,"wins":6},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":11,"losses":7,"wins":8},"mistralai/mistral-large-4-0":{"draws":11,"losses":12,"wins":7},"mistralai/mistral-medium-3-5":{"draws":12,"losses":1,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":15,"losses":19,"wins":12},"nex-agi/nex-n2-pro":{"draws":10,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":8,"wins":10},"o3":{"draws":15,"losses":34,"wins":17},"openai/gpt-oss-120b":{"draws":17,"losses":17,"wins":8},"poolside/laguna-s-2.1":{"draws":18,"losses":14,"wins":14},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":23,"wins":7},"qwen/qwen3.8-27b":{"draws":11,"losses":14,"wins":9},"qwen/qwen3.8-flash":{"draws":16,"losses":11,"wins":5},"qwen/qwen3.8-max":{"draws":21,"losses":22,"wins":5},"qwen/qwen3.8-max-0902":{"draws":16,"losses":26,"wins":6},"stealth/ox-alpha":{"draws":32,"losses":91,"wins":35},"stealth/space-bunny-alpha":{"draws":14,"losses":13,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":12,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":6},"tencent/hy4-preview":{"draws":16,"losses":21,"wins":9},"thinkingmachines/inkling":{"draws":25,"losses":17,"wins":22},"thinkingmachines/inkling-small":{"draws":19,"losses":13,"wins":16},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":10,"losses":29,"wins":9},"x-ai/grok-4.6":{"draws":15,"losses":29,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":34,"losses":19,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":10,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":16,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":43,"losses":31,"wins":22},"z-ai/glm-5.3":{"draws":13,"losses":27,"wins":6},"z-ai/glm-5.3-flash":{"draws":13,"losses":24,"wins":11},"z-ai/glm-5.3-flashx":{"draws":15,"losses":24,"wins":9}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":15,"wins":16},"claude-fable-5":{"draws":7,"losses":27,"wins":8},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":22,"wins":6},"claude-opus-4-5":{"draws":15,"losses":31,"wins":22},"claude-opus-4-8":{"draws":8,"losses":21,"wins":9},"claude-opus-5":{"draws":8,"losses":57,"wins":5},"claude-opus-5-5":{"draws":3,"losses":42,"wins":1},"claude-sonnet-5":{"draws":13,"losses":16,"wins":13},"claude-sonnet-5-5":{"draws":7,"losses":26,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":16,"losses":18,"wins":28},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":23,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":25,"wins":8},"fireworks/ember-1":{"draws":11,"losses":22,"wins":9},"gemini-3.1-pro-preview":{"draws":12,"losses":18,"wins":12},"google/gemini-3.1-flash-lite":{"draws":11,"losses":0,"wins":19},"google/gemini-3.5-flash":{"draws":13,"losses":27,"wins":14},"google/gemini-3.5-flash-lite":{"draws":21,"losses":26,"wins":29},"google/gemini-3.6-flash":{"draws":10,"losses":45,"wins":27},"google/gemini-3.8-flash":{"draws":8,"losses":27,"wins":7},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":11},"gpt-4.1":{"draws":3,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":13,"wins":4},"gpt-5.4":{"draws":9,"losses":24,"wins":9},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":9},"gpt-5.4-nano":{"draws":6,"losses":21,"wins":15},"gpt-5.5":{"draws":12,"losses":15,"wins":13},"gpt-5.6-luna":{"draws":11,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":4,"losses":32,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":17,"wins":11},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":10,"losses":19,"wins":13},"gpt-6-sol":{"draws":2,"losses":34,"wins":6},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":15},"inclusionai/ling-3.0-flash":{"draws":11,"losses":10,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":9,"wins":24},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":13},"meta/muse-spark-1.2":{"draws":7,"losses":22,"wins":11},"meta/muse-spark-1.3":{"draws":7,"losses":26,"wins":9},"meta/muse-wonder":{"draws":7,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":10},"mistralai/mistral-large-4-0":{"draws":8,"losses":15,"wins":3},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":8,"losses":18,"wins":14},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":13,"wins":14},"o3":{"draws":11,"losses":24,"wins":29},"openai/gpt-oss-120b":{"draws":8,"losses":9,"wins":19},"poolside/laguna-s-2.1":{"draws":12,"losses":12,"wins":16},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":22,"wins":8},"qwen/qwen3.8-27b":{"draws":5,"losses":16,"wins":9},"qwen/qwen3.8-flash":{"draws":10,"losses":11,"wins":7},"qwen/qwen3.8-max":{"draws":7,"losses":27,"wins":8},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":8},"stealth/ox-alpha":{"draws":35,"losses":61,"wins":46},"stealth/space-bunny-alpha":{"draws":7,"losses":16,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":17},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":6},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":11},"thinkingmachines/inkling":{"draws":13,"losses":14,"wins":31},"thinkingmachines/inkling-small":{"draws":16,"losses":6,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":9,"losses":19,"wins":14},"x-ai/grok-4.6":{"draws":10,"losses":26,"wins":6},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":7},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":7},"xiaomi/mimo-v2.5":{"draws":20,"losses":16,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":8,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":29,"losses":28,"wins":27},"z-ai/glm-5.3":{"draws":7,"losses":25,"wins":8},"z-ai/glm-5.3-flash":{"draws":9,"losses":27,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":8}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":9,"wins":24},"claude-fable-5":{"draws":13,"losses":22,"wins":13},"claude-fable-5-1":{"draws":2,"losses":46,"wins":6},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":15},"claude-opus-4-5":{"draws":28,"losses":11,"wins":39},"claude-opus-4-8":{"draws":11,"losses":16,"wins":17},"claude-opus-5":{"draws":6,"losses":63,"wins":13},"claude-opus-5-5":{"draws":4,"losses":43,"wins":5},"claude-sonnet-5":{"draws":19,"losses":9,"wins":20},"claude-sonnet-5-5":{"draws":17,"losses":20,"wins":11},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":25,"losses":9,"wins":38},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":14,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":15,"wins":14},"fireworks/ember-1":{"draws":16,"losses":14,"wins":18},"gemini-3.1-pro-preview":{"draws":14,"losses":14,"wins":20},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":14,"losses":19,"wins":27},"google/gemini-3.5-flash-lite":{"draws":26,"losses":12,"wins":46},"google/gemini-3.6-flash":{"draws":25,"losses":36,"wins":31},"google/gemini-3.8-flash":{"draws":17,"losses":15,"wins":16},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":12},"gpt-4.1":{"draws":6,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":10,"wins":19},"gpt-5.4":{"draws":8,"losses":10,"wins":12},"gpt-5.4-mini":{"draws":12,"losses":2,"wins":18},"gpt-5.4-nano":{"draws":10,"losses":11,"wins":27},"gpt-5.5":{"draws":16,"losses":16,"wins":12},"gpt-5.6-luna":{"draws":19,"losses":6,"wins":23},"gpt-5.6-sol":{"draws":7,"losses":27,"wins":14},"gpt-5.6-terra":{"draws":17,"losses":10,"wins":19},"gpt-6-astra":{"draws":3,"losses":38,"wins":7},"gpt-6-luna":{"draws":15,"losses":12,"wins":21},"gpt-6-sol":{"draws":5,"losses":37,"wins":6},"gpt-6.1-sol":{"draws":6,"losses":36,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":1,"wins":15},"inclusionai/ling-3.0-flash":{"draws":13,"losses":6,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":6,"wins":30},"meta/muse-glimmer-30b":{"draws":16,"losses":3,"wins":23},"meta/muse-spark-1.2":{"draws":13,"losses":13,"wins":20},"meta/muse-spark-1.3":{"draws":16,"losses":16,"wins":16},"meta/muse-wonder":{"draws":15,"losses":20,"wins":13},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":15},"mistralai/mistral-large-4-0":{"draws":12,"losses":5,"wins":13},"mistralai/mistral-medium-3-5":{"draws":11,"losses":4,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":13,"wins":23},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":2,"wins":22},"o3":{"draws":11,"losses":11,"wins":44},"openai/gpt-oss-120b":{"draws":17,"losses":7,"wins":18},"poolside/laguna-s-2.1":{"draws":14,"losses":6,"wins":26},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":12},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":21,"wins":17},"qwen/qwen3.8-27b":{"draws":8,"losses":6,"wins":20},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":15},"qwen/qwen3.8-max":{"draws":16,"losses":16,"wins":16},"qwen/qwen3.8-max-0902":{"draws":16,"losses":15,"wins":17},"stealth/ox-alpha":{"draws":52,"losses":47,"wins":59},"stealth/space-bunny-alpha":{"draws":15,"losses":6,"wins":17},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":3,"wins":11},"tencent/hy4-preview":{"draws":15,"losses":14,"wins":17},"thinkingmachines/inkling":{"draws":19,"losses":10,"wins":35},"thinkingmachines/inkling-small":{"draws":19,"losses":3,"wins":26},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":13,"losses":16,"wins":19},"x-ai/grok-4.6":{"draws":19,"losses":14,"wins":15},"x-ai/grok-4.7":{"draws":6,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":26,"losses":7,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":8,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":13},"z-ai/glm-5.2":{"draws":35,"losses":19,"wins":42},"z-ai/glm-5.3":{"draws":11,"losses":24,"wins":11},"z-ai/glm-5.3-flash":{"draws":11,"losses":19,"wins":18},"z-ai/glm-5.3-flashx":{"draws":13,"losses":20,"wins":15}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":10,"wins":20},"claude-fable-5":{"draws":11,"losses":27,"wins":10},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":23,"wins":10},"claude-opus-4-5":{"draws":21,"losses":29,"wins":28},"claude-opus-4-8":{"draws":12,"losses":14,"wins":18},"claude-opus-5":{"draws":10,"losses":63,"wins":9},"claude-opus-5-5":{"draws":2,"losses":48,"wins":2},"claude-sonnet-5":{"draws":17,"losses":11,"wins":20},"claude-sonnet-5-5":{"draws":8,"losses":27,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":24,"losses":11,"wins":37},"deepseek/deepseek-v4-pro":{"draws":16,"losses":12,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":15,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":18,"wins":15},"fireworks/ember-1":{"draws":14,"losses":22,"wins":12},"gemini-3.1-pro-preview":{"draws":16,"losses":14,"wins":18},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":17,"losses":18,"wins":25},"google/gemini-3.5-flash-lite":{"draws":28,"losses":14,"wins":42},"google/gemini-3.6-flash":{"draws":21,"losses":46,"wins":25},"google/gemini-3.8-flash":{"draws":8,"losses":28,"wins":12},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":17},"gpt-4.1":{"draws":5,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":9,"wins":24},"gpt-5.4":{"draws":12,"losses":28,"wins":6},"gpt-5.4-mini":{"draws":7,"losses":2,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":21},"gpt-5.5":{"draws":22,"losses":14,"wins":8},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":19},"gpt-5.6-sol":{"draws":9,"losses":28,"wins":11},"gpt-5.6-terra":{"draws":18,"losses":12,"wins":16},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":21,"losses":17,"wins":10},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":5,"wins":16},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":7,"wins":28},"meta/muse-glimmer-30b":{"draws":19,"losses":0,"wins":23},"meta/muse-spark-1.2":{"draws":11,"losses":19,"wins":16},"meta/muse-spark-1.3":{"draws":9,"losses":29,"wins":10},"meta/muse-wonder":{"draws":10,"losses":30,"wins":8},"minimax/minimax-m3":{"draws":9,"losses":4,"wins":13},"mistralai/mistral-large-4-0":{"draws":12,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":14,"losses":13,"wins":19},"nex-agi/nex-n2-pro":{"draws":10,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":20},"o3":{"draws":11,"losses":28,"wins":27},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":25},"poolside/laguna-s-2.1":{"draws":14,"losses":6,"wins":26},"qwen/qwen3.7-max":{"draws":9,"losses":9,"wins":10},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":23,"wins":11},"qwen/qwen3.8-27b":{"draws":7,"losses":14,"wins":13},"qwen/qwen3.8-flash":{"draws":9,"losses":12,"wins":11},"qwen/qwen3.8-max":{"draws":15,"losses":21,"wins":12},"qwen/qwen3.8-max-0902":{"draws":14,"losses":21,"wins":13},"stealth/ox-alpha":{"draws":35,"losses":75,"wins":48},"stealth/space-bunny-alpha":{"draws":12,"losses":11,"wins":15},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":15,"losses":20,"wins":11},"thinkingmachines/inkling":{"draws":23,"losses":11,"wins":30},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":23},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":24,"wins":11},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":7,"losses":31,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":25,"losses":13,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":8},"z-ai/glm-5.2":{"draws":37,"losses":29,"wins":30},"z-ai/glm-5.3":{"draws":6,"losses":32,"wins":8},"z-ai/glm-5.3-flash":{"draws":12,"losses":25,"wins":11},"z-ai/glm-5.3-flashx":{"draws":11,"losses":25,"wins":12}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":26,"wins":26},"claude-fable-5":{"draws":8,"losses":54,"wins":10},"claude-fable-5-1":{"draws":0,"losses":78,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":38,"wins":24},"claude-opus-4-5":{"draws":32,"losses":47,"wins":41},"claude-opus-4-8":{"draws":11,"losses":42,"wins":19},"claude-opus-5":{"draws":10,"losses":92,"wins":14},"claude-opus-5-5":{"draws":2,"losses":76,"wins":2},"claude-sonnet-5":{"draws":11,"losses":38,"wins":23},"claude-sonnet-5-5":{"draws":9,"losses":52,"wins":11},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":20},"deepseek/deepseek-v4-flash":{"draws":26,"losses":39,"wins":47},"deepseek/deepseek-v4-pro":{"draws":7,"losses":37,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":31,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":37,"wins":21},"fireworks/ember-1":{"draws":16,"losses":35,"wins":21},"gemini-3.1-pro-preview":{"draws":14,"losses":33,"wins":25},"google/gemini-3.1-flash-lite":{"draws":12,"losses":9,"wins":37},"google/gemini-3.5-flash":{"draws":14,"losses":48,"wins":32},"google/gemini-3.5-flash-lite":{"draws":19,"losses":58,"wins":51},"google/gemini-3.6-flash":{"draws":22,"losses":83,"wins":33},"google/gemini-3.8-flash":{"draws":13,"losses":44,"wins":15},"google/gemma-4-31b-it":{"draws":11,"losses":7,"wins":26},"gpt-4.1":{"draws":4,"losses":11,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":10,"losses":29,"wins":25},"gpt-5.4":{"draws":10,"losses":41,"wins":19},"gpt-5.4-mini":{"draws":9,"losses":14,"wins":25},"gpt-5.4-nano":{"draws":6,"losses":26,"wins":28},"gpt-5.5":{"draws":15,"losses":32,"wins":19},"gpt-5.6-luna":{"draws":13,"losses":30,"wins":29},"gpt-5.6-sol":{"draws":6,"losses":56,"wins":10},"gpt-5.6-terra":{"draws":10,"losses":36,"wins":22},"gpt-6-astra":{"draws":0,"losses":70,"wins":2},"gpt-6-luna":{"draws":14,"losses":30,"wins":28},"gpt-6-sol":{"draws":12,"losses":56,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":67,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":14,"losses":5,"wins":33},"inclusionai/ling-3.0-flash":{"draws":13,"losses":18,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":23,"wins":50},"meta/muse-glimmer-30b":{"draws":13,"losses":23,"wins":26},"meta/muse-spark-1.2":{"draws":10,"losses":32,"wins":26},"meta/muse-spark-1.3":{"draws":15,"losses":38,"wins":19},"meta/muse-wonder":{"draws":7,"losses":55,"wins":10},"minimax/minimax-m3":{"draws":8,"losses":15,"wins":19},"mistralai/mistral-large-4-0":{"draws":8,"losses":23,"wins":13},"mistralai/mistral-medium-3-5":{"draws":8,"losses":7,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":9,"wins":8},"moonshotai/kimi-k3":{"draws":17,"losses":32,"wins":19},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":26,"wins":30},"o3":{"draws":8,"losses":47,"wins":63},"openai/gpt-oss-120b":{"draws":11,"losses":23,"wins":28},"poolside/laguna-s-2.1":{"draws":10,"losses":28,"wins":30},"qwen/qwen3.7-max":{"draws":9,"losses":17,"wins":20},"qwen/qwen3.7-plus":{"draws":8,"losses":15,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":39,"wins":16},"qwen/qwen3.8-27b":{"draws":7,"losses":24,"wins":21},"qwen/qwen3.8-flash":{"draws":12,"losses":20,"wins":16},"qwen/qwen3.8-max":{"draws":18,"losses":37,"wins":17},"qwen/qwen3.8-max-0902":{"draws":16,"losses":36,"wins":20},"stealth/ox-alpha":{"draws":34,"losses":102,"wins":66},"stealth/space-bunny-alpha":{"draws":13,"losses":20,"wins":25},"stepfun/step-3.7-flash":{"draws":9,"losses":15,"wins":32},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":16,"wins":16},"tencent/hy4-preview":{"draws":9,"losses":40,"wins":21},"thinkingmachines/inkling":{"draws":17,"losses":29,"wins":48},"thinkingmachines/inkling-small":{"draws":23,"losses":18,"wins":31},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":13},"x-ai/grok-4.5":{"draws":14,"losses":37,"wins":21},"x-ai/grok-4.6":{"draws":9,"losses":51,"wins":12},"x-ai/grok-4.7":{"draws":7,"losses":50,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":6,"wins":13},"xiaomi/mimo-v2.5":{"draws":25,"losses":35,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":18,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":25,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":31,"wins":11},"z-ai/glm-5.2":{"draws":29,"losses":54,"wins":61},"z-ai/glm-5.3":{"draws":7,"losses":48,"wins":13},"z-ai/glm-5.3-flash":{"draws":12,"losses":37,"wins":23},"z-ai/glm-5.3-flashx":{"draws":12,"losses":41,"wins":19}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":9,"wins":16},"claude-fable-5":{"draws":11,"losses":24,"wins":13},"claude-fable-5-1":{"draws":3,"losses":47,"wins":4},"claude-haiku-5-5":{"draws":20,"losses":19,"wins":7},"claude-opus-4-5":{"draws":37,"losses":17,"wins":24},"claude-opus-4-8":{"draws":13,"losses":12,"wins":19},"claude-opus-5":{"draws":12,"losses":57,"wins":13},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":22,"losses":7,"wins":19},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":15},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":27,"losses":11,"wins":34},"deepseek/deepseek-v4-pro":{"draws":9,"losses":12,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":19,"wins":12},"fireworks/ember-1":{"draws":17,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":14,"losses":12,"wins":22},"google/gemini-3.1-flash-lite":{"draws":7,"losses":5,"wins":20},"google/gemini-3.5-flash":{"draws":18,"losses":17,"wins":25},"google/gemini-3.5-flash-lite":{"draws":35,"losses":13,"wins":36},"google/gemini-3.6-flash":{"draws":26,"losses":34,"wins":32},"google/gemini-3.8-flash":{"draws":16,"losses":20,"wins":12},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":15,"losses":9,"wins":18},"gpt-5.4":{"draws":15,"losses":16,"wins":15},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":18,"wins":17},"gpt-5.5":{"draws":11,"losses":8,"wins":9},"gpt-5.6-luna":{"draws":19,"losses":9,"wins":20},"gpt-5.6-sol":{"draws":11,"losses":21,"wins":16},"gpt-5.6-terra":{"draws":16,"losses":12,"wins":18},"gpt-6-astra":{"draws":2,"losses":41,"wins":5},"gpt-6-luna":{"draws":21,"losses":9,"wins":18},"gpt-6-sol":{"draws":6,"losses":30,"wins":12},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":13,"losses":7,"wins":14},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":20,"losses":8,"wins":24},"meta/muse-glimmer-30b":{"draws":19,"losses":5,"wins":18},"meta/muse-spark-1.2":{"draws":13,"losses":15,"wins":18},"meta/muse-spark-1.3":{"draws":12,"losses":18,"wins":18},"meta/muse-wonder":{"draws":12,"losses":26,"wins":10},"minimax/minimax-m3":{"draws":9,"losses":2,"wins":15},"mistralai/mistral-large-4-0":{"draws":11,"losses":7,"wins":12},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":12,"losses":17,"wins":17},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":4,"wins":22},"o3":{"draws":15,"losses":20,"wins":31},"openai/gpt-oss-120b":{"draws":18,"losses":5,"wins":19},"poolside/laguna-s-2.1":{"draws":20,"losses":8,"wins":18},"qwen/qwen3.7-max":{"draws":10,"losses":4,"wins":14},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-27b":{"draws":12,"losses":9,"wins":13},"qwen/qwen3.8-flash":{"draws":13,"losses":9,"wins":10},"qwen/qwen3.8-max":{"draws":16,"losses":16,"wins":16},"qwen/qwen3.8-max-0902":{"draws":19,"losses":14,"wins":15},"stealth/ox-alpha":{"draws":45,"losses":65,"wins":48},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":11,"losses":2,"wins":13},"tencent/hy4-preview":{"draws":15,"losses":16,"wins":15},"thinkingmachines/inkling":{"draws":20,"losses":15,"wins":29},"thinkingmachines/inkling-small":{"draws":19,"losses":9,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":5,"wins":6},"x-ai/grok-4.5":{"draws":8,"losses":20,"wins":20},"x-ai/grok-4.6":{"draws":14,"losses":21,"wins":13},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":14},"x-ai/grok-build-0.1":{"draws":9,"losses":4,"wins":3},"xiaomi/mimo-v2.5":{"draws":30,"losses":12,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":7,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":13},"z-ai/glm-5.2":{"draws":40,"losses":18,"wins":38},"z-ai/glm-5.3":{"draws":15,"losses":24,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":18,"wins":21},"z-ai/glm-5.3-flashx":{"draws":14,"losses":19,"wins":15}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":14,"wins":15},"claude-fable-5":{"draws":11,"losses":34,"wins":3},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":28,"losses":29,"wins":21},"claude-opus-4-8":{"draws":14,"losses":23,"wins":7},"claude-opus-5":{"draws":9,"losses":62,"wins":11},"claude-opus-5-5":{"draws":6,"losses":46,"wins":0},"claude-sonnet-5":{"draws":19,"losses":18,"wins":11},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":26,"losses":17,"wins":29},"deepseek/deepseek-v4-pro":{"draws":16,"losses":17,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":22,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":22,"wins":7},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":16,"losses":16,"wins":16},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":18,"losses":28,"wins":14},"google/gemini-3.5-flash-lite":{"draws":30,"losses":18,"wins":36},"google/gemini-3.6-flash":{"draws":30,"losses":43,"wins":19},"google/gemini-3.8-flash":{"draws":12,"losses":32,"wins":4},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":13},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":17,"wins":10},"gpt-5.4":{"draws":14,"losses":24,"wins":8},"gpt-5.4-mini":{"draws":14,"losses":4,"wins":14},"gpt-5.4-nano":{"draws":13,"losses":13,"wins":22},"gpt-5.5":{"draws":18,"losses":18,"wins":8},"gpt-5.6-luna":{"draws":14,"losses":8,"wins":10},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":15},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":18,"losses":18,"wins":12},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":44,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":2,"wins":13},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":10,"wins":25},"meta/muse-glimmer-30b":{"draws":19,"losses":6,"wins":17},"meta/muse-spark-1.2":{"draws":13,"losses":21,"wins":12},"meta/muse-spark-1.3":{"draws":12,"losses":26,"wins":10},"meta/muse-wonder":{"draws":9,"losses":34,"wins":5},"minimax/minimax-m3":{"draws":9,"losses":3,"wins":14},"mistralai/mistral-large-4-0":{"draws":13,"losses":15,"wins":2},"mistralai/mistral-medium-3-5":{"draws":11,"losses":1,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":22,"wins":9},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":8,"wins":14},"o3":{"draws":15,"losses":22,"wins":29},"openai/gpt-oss-120b":{"draws":19,"losses":8,"wins":15},"poolside/laguna-s-2.1":{"draws":18,"losses":10,"wins":18},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":24,"wins":7},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":9},"qwen/qwen3.8-flash":{"draws":9,"losses":11,"wins":12},"qwen/qwen3.8-max":{"draws":18,"losses":21,"wins":9},"qwen/qwen3.8-max-0902":{"draws":19,"losses":21,"wins":8},"stealth/ox-alpha":{"draws":53,"losses":71,"wins":34},"stealth/space-bunny-alpha":{"draws":12,"losses":15,"wins":11},"stepfun/step-3.7-flash":{"draws":10,"losses":9,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":13,"losses":27,"wins":6},"thinkingmachines/inkling":{"draws":20,"losses":13,"wins":31},"thinkingmachines/inkling-small":{"draws":21,"losses":8,"wins":19},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":25,"wins":10},"x-ai/grok-4.6":{"draws":15,"losses":28,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":34,"losses":9,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":7,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":17,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":21,"wins":6},"z-ai/glm-5.2":{"draws":34,"losses":34,"wins":28},"z-ai/glm-5.3":{"draws":9,"losses":32,"wins":5},"z-ai/glm-5.3-flash":{"draws":13,"losses":27,"wins":8},"z-ai/glm-5.3-flashx":{"draws":16,"losses":22,"wins":10}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":8,"wins":30},"claude-fable-5":{"draws":6,"losses":24,"wins":18},"claude-fable-5-1":{"draws":5,"losses":48,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":14,"wins":22},"claude-opus-4-5":{"draws":17,"losses":15,"wins":46},"claude-opus-4-8":{"draws":3,"losses":17,"wins":24},"claude-opus-5":{"draws":12,"losses":53,"wins":17},"claude-opus-5-5":{"draws":3,"losses":43,"wins":6},"claude-sonnet-5":{"draws":6,"losses":7,"wins":35},"claude-sonnet-5-5":{"draws":5,"losses":21,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":12,"losses":6,"wins":54},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":9,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":18,"wins":23},"fireworks/ember-1":{"draws":7,"losses":12,"wins":29},"gemini-3.1-pro-preview":{"draws":3,"losses":17,"wins":28},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":29},"google/gemini-3.5-flash":{"draws":6,"losses":15,"wins":39},"google/gemini-3.5-flash-lite":{"draws":11,"losses":10,"wins":63},"google/gemini-3.6-flash":{"draws":11,"losses":27,"wins":54},"google/gemini-3.8-flash":{"draws":5,"losses":22,"wins":21},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":25},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":8,"losses":2,"wins":32},"gpt-5.4":{"draws":10,"losses":14,"wins":22},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":25},"gpt-5.4-nano":{"draws":3,"losses":7,"wins":38},"gpt-5.5":{"draws":10,"losses":13,"wins":21},"gpt-5.6-luna":{"draws":4,"losses":9,"wins":35},"gpt-5.6-sol":{"draws":6,"losses":20,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":7,"wins":27},"gpt-6-astra":{"draws":6,"losses":40,"wins":2},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":4,"losses":31,"wins":13},"gpt-6.1-sol":{"draws":6,"losses":36,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":29},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":5,"wins":38},"meta/muse-glimmer-30b":{"draws":4,"losses":3,"wins":35},"meta/muse-spark-1.2":{"draws":5,"losses":16,"wins":25},"meta/muse-spark-1.3":{"draws":9,"losses":17,"wins":22},"meta/muse-wonder":{"draws":10,"losses":22,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":22},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":1,"losses":3,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":11,"losses":11,"wins":24},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":4,"wins":33},"o3":{"draws":7,"losses":10,"wins":49},"openai/gpt-oss-120b":{"draws":1,"losses":4,"wins":37},"poolside/laguna-s-2.1":{"draws":7,"losses":3,"wins":36},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":20},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":11,"wins":29},"qwen/qwen3.8-27b":{"draws":5,"losses":7,"wins":22},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":20},"qwen/qwen3.8-max":{"draws":12,"losses":12,"wins":24},"qwen/qwen3.8-max-0902":{"draws":8,"losses":11,"wins":29},"stealth/ox-alpha":{"draws":25,"losses":38,"wins":95},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":25},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":29},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":13,"wins":27},"thinkingmachines/inkling":{"draws":8,"losses":8,"wins":48},"thinkingmachines/inkling-small":{"draws":7,"losses":8,"wins":33},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":7,"losses":16,"wins":25},"x-ai/grok-4.6":{"draws":9,"losses":21,"wins":18},"x-ai/grok-4.7":{"draws":5,"losses":25,"wins":12},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":11,"losses":7,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":6,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":12,"wins":10},"z-ai/glm-5.2":{"draws":11,"losses":15,"wins":70},"z-ai/glm-5.3":{"draws":10,"losses":15,"wins":21},"z-ai/glm-5.3-flash":{"draws":11,"losses":16,"wins":21},"z-ai/glm-5.3-flashx":{"draws":7,"losses":15,"wins":26}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":11,"wins":21},"claude-fable-5":{"draws":10,"losses":29,"wins":9},"claude-fable-5-1":{"draws":5,"losses":47,"wins":2},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":24,"losses":24,"wins":30},"claude-opus-4-8":{"draws":10,"losses":21,"wins":13},"claude-opus-5":{"draws":5,"losses":72,"wins":5},"claude-opus-5-5":{"draws":2,"losses":49,"wins":1},"claude-sonnet-5":{"draws":15,"losses":14,"wins":19},"claude-sonnet-5-5":{"draws":9,"losses":28,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":25,"losses":11,"wins":36},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":14,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":13,"wins":16},"fireworks/ember-1":{"draws":13,"losses":20,"wins":15},"gemini-3.1-pro-preview":{"draws":14,"losses":16,"wins":18},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":21},"google/gemini-3.5-flash":{"draws":14,"losses":19,"wins":27},"google/gemini-3.5-flash-lite":{"draws":24,"losses":15,"wins":45},"google/gemini-3.6-flash":{"draws":21,"losses":42,"wins":29},"google/gemini-3.8-flash":{"draws":14,"losses":16,"wins":18},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":9,"losses":3,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":10,"wins":24},"gpt-5.4":{"draws":13,"losses":21,"wins":12},"gpt-5.4-mini":{"draws":13,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":10,"losses":14,"wins":24},"gpt-5.5":{"draws":14,"losses":18,"wins":12},"gpt-5.6-luna":{"draws":15,"losses":15,"wins":18},"gpt-5.6-sol":{"draws":11,"losses":28,"wins":9},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":10},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":10,"losses":22,"wins":16},"gpt-6-sol":{"draws":6,"losses":37,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":43,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":1,"wins":19},"inclusionai/ling-3.0-flash":{"draws":12,"losses":1,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":11,"wins":29},"meta/muse-glimmer-30b":{"draws":14,"losses":5,"wins":23},"meta/muse-spark-1.2":{"draws":13,"losses":16,"wins":17},"meta/muse-spark-1.3":{"draws":8,"losses":25,"wins":15},"meta/muse-wonder":{"draws":13,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":16},"mistralai/mistral-large-4-0":{"draws":10,"losses":11,"wins":9},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":8,"losses":22,"wins":16},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":7,"wins":19},"o3":{"draws":12,"losses":24,"wins":30},"openai/gpt-oss-120b":{"draws":14,"losses":6,"wins":22},"poolside/laguna-s-2.1":{"draws":14,"losses":4,"wins":28},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":13},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":22,"wins":10},"qwen/qwen3.8-27b":{"draws":10,"losses":9,"wins":15},"qwen/qwen3.8-flash":{"draws":11,"losses":13,"wins":8},"qwen/qwen3.8-max":{"draws":19,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":19,"losses":16,"wins":13},"stealth/ox-alpha":{"draws":43,"losses":66,"wins":49},"stealth/space-bunny-alpha":{"draws":11,"losses":10,"wins":17},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":17},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":11,"losses":4,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":23,"wins":12},"thinkingmachines/inkling":{"draws":20,"losses":12,"wins":32},"thinkingmachines/inkling-small":{"draws":14,"losses":9,"wins":25},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":13,"losses":23,"wins":12},"x-ai/grok-4.6":{"draws":16,"losses":22,"wins":10},"x-ai/grok-4.7":{"draws":6,"losses":28,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":24,"losses":4,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":3,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":14,"wins":9},"z-ai/glm-5.2":{"draws":36,"losses":22,"wins":38},"z-ai/glm-5.3":{"draws":10,"losses":30,"wins":6},"z-ai/glm-5.3-flash":{"draws":11,"losses":22,"wins":15},"z-ai/glm-5.3-flashx":{"draws":12,"losses":19,"wins":17}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":2,"wins":41},"claude-fable-5":{"draws":5,"losses":8,"wins":35},"claude-fable-5-1":{"draws":6,"losses":19,"wins":29},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":41},"claude-opus-4-5":{"draws":6,"losses":2,"wins":70},"claude-opus-4-8":{"draws":2,"losses":2,"wins":40},"claude-opus-5":{"draws":9,"losses":24,"wins":49},"claude-opus-5-5":{"draws":4,"losses":24,"wins":24},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":6,"losses":9,"wins":33},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":5,"losses":3,"wins":64},"deepseek/deepseek-v4-pro":{"draws":0,"losses":3,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":3,"wins":41},"fireworks/ember-1":{"draws":1,"losses":3,"wins":44},"gemini-3.1-pro-preview":{"draws":5,"losses":2,"wins":41},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":53},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":82},"google/gemini-3.6-flash":{"draws":5,"losses":7,"wins":80},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":42},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":1,"losses":0,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":4,"losses":1,"wins":37},"gpt-5.4":{"draws":1,"losses":6,"wins":39},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":30},"gpt-5.4-nano":{"draws":0,"losses":1,"wins":47},"gpt-5.5":{"draws":1,"losses":3,"wins":40},"gpt-5.6-luna":{"draws":5,"losses":1,"wins":42},"gpt-5.6-sol":{"draws":4,"losses":7,"wins":37},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":42},"gpt-6-astra":{"draws":4,"losses":21,"wins":7},"gpt-6-luna":{"draws":4,"losses":5,"wins":39},"gpt-6-sol":{"draws":6,"losses":7,"wins":35},"gpt-6.1-sol":{"draws":7,"losses":19,"wins":22},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":33},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":0,"wins":49},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":39},"meta/muse-spark-1.2":{"draws":3,"losses":1,"wins":42},"meta/muse-spark-1.3":{"draws":7,"losses":4,"wins":37},"meta/muse-wonder":{"draws":3,"losses":6,"wins":39},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"mistralai/mistral-large-4-0":{"draws":3,"losses":0,"wins":27},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":39},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":39},"o3":{"draws":3,"losses":1,"wins":62},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":38},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":45},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":26},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":2,"wins":45},"qwen/qwen3.8-27b":{"draws":1,"losses":0,"wins":33},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":28},"qwen/qwen3.8-max":{"draws":5,"losses":0,"wins":43},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":46},"stealth/ox-alpha":{"draws":11,"losses":8,"wins":139},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":2,"losses":1,"wins":43},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":60},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":44},"unbiased/pareto-26.10-preview":{"draws":3,"losses":8,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":3,"losses":5,"wins":40},"x-ai/grok-4.6":{"draws":4,"losses":6,"wins":38},"x-ai/grok-4.7":{"draws":3,"losses":10,"wins":29},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":15},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":71},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":1,"wins":26},"z-ai/glm-5.2":{"draws":5,"losses":3,"wins":88},"z-ai/glm-5.3":{"draws":5,"losses":3,"wins":38},"z-ai/glm-5.3-flash":{"draws":3,"losses":2,"wins":43},"z-ai/glm-5.3-flashx":{"draws":4,"losses":3,"wins":41}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":14,"wins":14},"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":23,"wins":9},"claude-opus-4-5":{"draws":31,"losses":33,"wins":14},"claude-opus-4-8":{"draws":11,"losses":22,"wins":11},"claude-opus-5":{"draws":19,"losses":57,"wins":6},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":14,"losses":22,"wins":12},"claude-sonnet-5-5":{"draws":14,"losses":21,"wins":13},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":11},"deepseek/deepseek-v4-flash":{"draws":32,"losses":13,"wins":27},"deepseek/deepseek-v4-pro":{"draws":13,"losses":11,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":20,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":20,"wins":11},"fireworks/ember-1":{"draws":17,"losses":21,"wins":10},"gemini-3.1-pro-preview":{"draws":15,"losses":19,"wins":14},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":18,"losses":26,"wins":16},"google/gemini-3.5-flash-lite":{"draws":29,"losses":23,"wins":32},"google/gemini-3.6-flash":{"draws":28,"losses":52,"wins":12},"google/gemini-3.8-flash":{"draws":19,"losses":22,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":10},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":3,"losses":2,"wins":1},"gpt-5":{"draws":17,"losses":15,"wins":10},"gpt-5.4":{"draws":15,"losses":22,"wins":9},"gpt-5.4-mini":{"draws":17,"losses":5,"wins":10},"gpt-5.4-nano":{"draws":14,"losses":14,"wins":20},"gpt-5.5":{"draws":22,"losses":17,"wins":5},"gpt-5.6-luna":{"draws":22,"losses":13,"wins":13},"gpt-5.6-sol":{"draws":7,"losses":36,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":14,"wins":18},"gpt-6-astra":{"draws":4,"losses":43,"wins":1},"gpt-6-luna":{"draws":9,"losses":13,"wins":10},"gpt-6-sol":{"draws":9,"losses":35,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":18,"losses":5,"wins":11},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":13,"wins":25},"meta/muse-glimmer-30b":{"draws":20,"losses":5,"wins":17},"meta/muse-spark-1.2":{"draws":16,"losses":21,"wins":9},"meta/muse-spark-1.3":{"draws":6,"losses":31,"wins":11},"meta/muse-wonder":{"draws":12,"losses":26,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":13,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":20,"losses":16,"wins":10},"nex-agi/nex-n2-pro":{"draws":8,"losses":1,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":11,"wins":14},"o3":{"draws":15,"losses":20,"wins":31},"openai/gpt-oss-120b":{"draws":14,"losses":12,"wins":16},"poolside/laguna-s-2.1":{"draws":18,"losses":11,"wins":17},"qwen/qwen3.7-max":{"draws":10,"losses":12,"wins":6},"qwen/qwen3.7-plus":{"draws":11,"losses":5,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":23,"wins":11},"qwen/qwen3.8-27b":{"draws":11,"losses":15,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-max-0902":{"draws":16,"losses":20,"wins":12},"stealth/ox-alpha":{"draws":38,"losses":76,"wins":44},"stealth/space-bunny-alpha":{"draws":15,"losses":10,"wins":13},"stepfun/step-3.7-flash":{"draws":10,"losses":10,"wins":14},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":18,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":27,"losses":10,"wins":27},"thinkingmachines/inkling-small":{"draws":15,"losses":10,"wins":23},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":6,"wins":6},"x-ai/grok-4.5":{"draws":12,"losses":21,"wins":15},"x-ai/grok-4.6":{"draws":14,"losses":31,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":32,"wins":6},"x-ai/grok-build-0.1":{"draws":9,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":31,"losses":10,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":12,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":17,"wins":8},"z-ai/glm-5.2":{"draws":44,"losses":23,"wins":29},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":6},"z-ai/glm-5.3-flash":{"draws":14,"losses":27,"wins":7},"z-ai/glm-5.3-flashx":{"draws":11,"losses":28,"wins":9}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":2,"wins":34},"claude-fable-5":{"draws":7,"losses":13,"wins":28},"claude-fable-5-1":{"draws":8,"losses":36,"wins":10},"claude-haiku-5-5":{"draws":13,"losses":5,"wins":28},"claude-opus-4-5":{"draws":18,"losses":5,"wins":55},"claude-opus-4-8":{"draws":10,"losses":7,"wins":27},"claude-opus-5":{"draws":10,"losses":36,"wins":36},"claude-opus-5-5":{"draws":6,"losses":34,"wins":12},"claude-sonnet-5":{"draws":11,"losses":7,"wins":30},"claude-sonnet-5-5":{"draws":5,"losses":17,"wins":26},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":15,"losses":3,"wins":54},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":7,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":7,"wins":29},"fireworks/ember-1":{"draws":7,"losses":5,"wins":36},"gemini-3.1-pro-preview":{"draws":3,"losses":5,"wins":40},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":11,"losses":3,"wins":46},"google/gemini-3.5-flash-lite":{"draws":23,"losses":4,"wins":57},"google/gemini-3.6-flash":{"draws":12,"losses":16,"wins":64},"google/gemini-3.8-flash":{"draws":9,"losses":7,"wins":32},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":24},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":2,"wins":32},"gpt-5.4":{"draws":7,"losses":7,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":24},"gpt-5.4-nano":{"draws":11,"losses":5,"wins":32},"gpt-5.5":{"draws":7,"losses":9,"wins":28},"gpt-5.6-luna":{"draws":11,"losses":3,"wins":34},"gpt-5.6-sol":{"draws":5,"losses":16,"wins":27},"gpt-5.6-terra":{"draws":10,"losses":4,"wins":32},"gpt-6-astra":{"draws":8,"losses":30,"wins":10},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":6,"losses":13,"wins":13},"gpt-6.1-sol":{"draws":7,"losses":31,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":28},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":45},"meta/muse-glimmer-30b":{"draws":8,"losses":2,"wins":32},"meta/muse-spark-1.2":{"draws":6,"losses":9,"wins":31},"meta/muse-spark-1.3":{"draws":11,"losses":6,"wins":31},"meta/muse-wonder":{"draws":4,"losses":16,"wins":28},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":8,"losses":7,"wins":31},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":34},"o3":{"draws":6,"losses":4,"wins":56},"openai/gpt-oss-120b":{"draws":7,"losses":0,"wins":35},"poolside/laguna-s-2.1":{"draws":11,"losses":2,"wins":33},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":19},"qwen/qwen3.7-plus":{"draws":3,"losses":2,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":9,"wins":34},"qwen/qwen3.8-27b":{"draws":9,"losses":4,"wins":21},"qwen/qwen3.8-flash":{"draws":3,"losses":4,"wins":25},"qwen/qwen3.8-max":{"draws":5,"losses":8,"wins":35},"qwen/qwen3.8-max-0902":{"draws":5,"losses":8,"wins":35},"stealth/ox-alpha":{"draws":23,"losses":20,"wins":115},"stealth/space-bunny-alpha":{"draws":7,"losses":3,"wins":28},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":28},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":19},"tencent/hy4-preview":{"draws":7,"losses":6,"wins":33},"thinkingmachines/inkling":{"draws":9,"losses":4,"wins":51},"thinkingmachines/inkling-small":{"draws":7,"losses":1,"wins":40},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":6,"losses":9,"wins":33},"x-ai/grok-4.6":{"draws":7,"losses":9,"wins":32},"x-ai/grok-4.7":{"draws":4,"losses":23,"wins":15},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":14,"losses":4,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":6,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":10,"wins":14},"z-ai/glm-5.2":{"draws":16,"losses":6,"wins":74},"z-ai/glm-5.3":{"draws":7,"losses":14,"wins":25},"z-ai/glm-5.3-flash":{"draws":8,"losses":8,"wins":32},"z-ai/glm-5.3-flashx":{"draws":7,"losses":10,"wins":31}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":5,"wins":38},"claude-fable-5":{"draws":4,"losses":9,"wins":35},"claude-fable-5-1":{"draws":3,"losses":21,"wins":30},"claude-haiku-5-5":{"draws":5,"losses":4,"wins":37},"claude-opus-4-5":{"draws":2,"losses":5,"wins":71},"claude-opus-4-8":{"draws":2,"losses":5,"wins":37},"claude-opus-5":{"draws":11,"losses":26,"wins":45},"claude-opus-5-5":{"draws":3,"losses":28,"wins":21},"claude-sonnet-5":{"draws":1,"losses":2,"wins":45},"claude-sonnet-5-5":{"draws":1,"losses":12,"wins":35},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":65},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":6,"wins":38},"fireworks/ember-1":{"draws":0,"losses":8,"wins":40},"gemini-3.1-pro-preview":{"draws":4,"losses":3,"wins":41},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":51},"google/gemini-3.5-flash-lite":{"draws":6,"losses":1,"wins":77},"google/gemini-3.6-flash":{"draws":6,"losses":7,"wins":79},"google/gemini-3.8-flash":{"draws":3,"losses":7,"wins":38},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":1,"losses":0,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":0,"wins":41},"gpt-5.4":{"draws":2,"losses":4,"wins":40},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":29},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":45},"gpt-5.5":{"draws":1,"losses":6,"wins":37},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":42},"gpt-5.6-sol":{"draws":3,"losses":4,"wins":41},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":41},"gpt-6-astra":{"draws":5,"losses":26,"wins":17},"gpt-6-luna":{"draws":1,"losses":1,"wins":46},"gpt-6-sol":{"draws":5,"losses":10,"wins":33},"gpt-6.1-sol":{"draws":2,"losses":16,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":33},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":6,"wins":45},"meta/muse-glimmer-30b":{"draws":1,"losses":0,"wins":41},"meta/muse-spark-1.2":{"draws":2,"losses":6,"wins":38},"meta/muse-spark-1.3":{"draws":5,"losses":5,"wins":38},"meta/muse-wonder":{"draws":7,"losses":11,"wins":30},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"mistralai/mistral-large-4-0":{"draws":3,"losses":4,"wins":23},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":4,"losses":4,"wins":38},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":42},"o3":{"draws":1,"losses":0,"wins":65},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":41},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":45},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":24},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":7,"wins":38},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":33},"qwen/qwen3.8-flash":{"draws":0,"losses":3,"wins":29},"qwen/qwen3.8-max":{"draws":5,"losses":4,"wins":39},"qwen/qwen3.8-max-0902":{"draws":2,"losses":1,"wins":45},"stealth/ox-alpha":{"draws":14,"losses":8,"wins":136},"stealth/space-bunny-alpha":{"draws":1,"losses":1,"wins":36},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":0,"losses":2,"wins":44},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":61},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":46},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":42},"x-ai/grok-4.6":{"draws":3,"losses":5,"wins":40},"x-ai/grok-4.7":{"draws":2,"losses":13,"wins":27},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":7,"wins":21},"z-ai/glm-5.2":{"draws":11,"losses":5,"wins":80},"z-ai/glm-5.3":{"draws":8,"losses":7,"wins":31},"z-ai/glm-5.3-flash":{"draws":5,"losses":5,"wins":38},"z-ai/glm-5.3-flashx":{"draws":4,"losses":6,"wins":38}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":4,"losses":2,"wins":0},"claude-fable-5-1":{"draws":3,"losses":4,"wins":1},"claude-haiku-5-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-5":{"draws":9,"losses":1,"wins":0},"claude-opus-4-8":{"draws":6,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":6,"wins":2},"claude-opus-5-5":{"draws":1,"losses":5,"wins":0},"claude-sonnet-5":{"draws":3,"losses":3,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":3,"wins":0},"google/gemini-3.6-flash":{"draws":11,"losses":1,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":0},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":1},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":1,"losses":5,"wins":0},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":4,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":1,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":0,"wins":1},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":1,"wins":2},"meta/muse-wonder":{"draws":4,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":0},"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":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":0},"o3":{"draws":4,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":1},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.8-max-0902":{"draws":1,"losses":4,"wins":1},"stealth/ox-alpha":{"draws":9,"losses":8,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":1,"wins":0},"x-ai/grok-4.6":{"draws":5,"losses":1,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":12,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":0},"z-ai/glm-5.3":{"draws":3,"losses":3,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":2,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":2,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":7},"claude-fable-5":{"draws":8,"losses":28,"wins":0},"claude-fable-5-1":{"draws":4,"losses":36,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":25,"wins":1},"claude-opus-4-5":{"draws":21,"losses":38,"wins":1},"claude-opus-4-8":{"draws":11,"losses":24,"wins":1},"claude-opus-5":{"draws":7,"losses":49,"wins":2},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":14,"losses":20,"wins":2},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":25,"losses":21,"wins":8},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":4},"fireworks/ember-1":{"draws":16,"losses":20,"wins":0},"gemini-3.1-pro-preview":{"draws":15,"losses":17,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":8,"wins":10},"google/gemini-3.5-flash":{"draws":15,"losses":26,"wins":5},"google/gemini-3.5-flash-lite":{"draws":27,"losses":29,"wins":8},"google/gemini-3.6-flash":{"draws":24,"losses":42,"wins":2},"google/gemini-3.8-flash":{"draws":12,"losses":22,"wins":2},"google/gemma-4-31b-it":{"draws":12,"losses":10,"wins":2},"gpt-4.1":{"draws":6,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":12,"losses":16,"wins":2},"gpt-5.4":{"draws":14,"losses":20,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":11,"losses":24,"wins":3},"gpt-5.5":{"draws":14,"losses":16,"wins":2},"gpt-5.6-luna":{"draws":17,"losses":14,"wins":5},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":0},"gpt-5.6-terra":{"draws":17,"losses":17,"wins":0},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":13,"losses":20,"wins":3},"gpt-6-sol":{"draws":5,"losses":30,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":14,"losses":6,"wins":4},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":16,"wins":11},"meta/muse-glimmer-30b":{"draws":16,"losses":10,"wins":4},"meta/muse-spark-1.2":{"draws":11,"losses":20,"wins":3},"meta/muse-spark-1.3":{"draws":10,"losses":25,"wins":1},"meta/muse-wonder":{"draws":10,"losses":25,"wins":1},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":3},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":1},"mistralai/mistral-medium-3-5":{"draws":12,"losses":7,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":16,"losses":18,"wins":0},"nex-agi/nex-n2-pro":{"draws":8,"losses":7,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":11,"wins":6},"o3":{"draws":15,"losses":33,"wins":4},"openai/gpt-oss-120b":{"draws":15,"losses":14,"wins":3},"poolside/laguna-s-2.1":{"draws":16,"losses":9,"wins":7},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":3},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":21,"wins":3},"qwen/qwen3.8-27b":{"draws":7,"losses":16,"wins":1},"qwen/qwen3.8-flash":{"draws":12,"losses":10,"wins":2},"qwen/qwen3.8-max":{"draws":14,"losses":20,"wins":2},"qwen/qwen3.8-max-0902":{"draws":15,"losses":16,"wins":5},"stealth/ox-alpha":{"draws":33,"losses":65,"wins":4},"stealth/space-bunny-alpha":{"draws":13,"losses":13,"wins":4},"stepfun/step-3.7-flash":{"draws":8,"losses":16,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":4},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":3},"thinkingmachines/inkling":{"draws":18,"losses":19,"wins":7},"thinkingmachines/inkling-small":{"draws":17,"losses":12,"wins":7},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":11,"losses":24,"wins":1},"x-ai/grok-4.6":{"draws":8,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":1},"xiaomi/mimo-v2.5":{"draws":29,"losses":25,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":15,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":0},"z-ai/glm-5.2":{"draws":27,"losses":41,"wins":4},"z-ai/glm-5.3":{"draws":12,"losses":24,"wins":0},"z-ai/glm-5.3-flash":{"draws":8,"losses":25,"wins":3},"z-ai/glm-5.3-flashx":{"draws":11,"losses":23,"wins":2}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":12,"wins":6},"claude-fable-5":{"draws":4,"losses":31,"wins":1},"claude-fable-5-1":{"draws":2,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":24,"wins":1},"claude-opus-4-5":{"draws":24,"losses":24,"wins":12},"claude-opus-4-8":{"draws":10,"losses":26,"wins":0},"claude-opus-5":{"draws":9,"losses":43,"wins":2},"claude-opus-5-5":{"draws":3,"losses":33,"wins":0},"claude-sonnet-5":{"draws":12,"losses":20,"wins":4},"claude-sonnet-5-5":{"draws":10,"losses":22,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":18,"losses":20,"wins":18},"deepseek/deepseek-v4-pro":{"draws":10,"losses":20,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":15,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":21,"wins":3},"fireworks/ember-1":{"draws":12,"losses":20,"wins":4},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":5},"google/gemini-3.1-flash-lite":{"draws":7,"losses":7,"wins":14},"google/gemini-3.5-flash":{"draws":11,"losses":28,"wins":7},"google/gemini-3.5-flash-lite":{"draws":17,"losses":32,"wins":13},"google/gemini-3.6-flash":{"draws":22,"losses":40,"wins":8},"google/gemini-3.8-flash":{"draws":9,"losses":26,"wins":1},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":8},"gpt-4.1":{"draws":4,"losses":7,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":16,"wins":4},"gpt-5.4":{"draws":7,"losses":21,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":8,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":14,"wins":14},"gpt-5.5":{"draws":10,"losses":18,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":13,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":29,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":23,"wins":4},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":9,"losses":21,"wins":6},"gpt-6-sol":{"draws":5,"losses":29,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":5,"wins":11},"inclusionai/ling-3.0-flash":{"draws":4,"losses":7,"wins":5},"meituan/longcat-2.0":{"draws":12,"losses":14,"wins":12},"meta/muse-glimmer-30b":{"draws":14,"losses":10,"wins":6},"meta/muse-spark-1.2":{"draws":11,"losses":17,"wins":6},"meta/muse-spark-1.3":{"draws":1,"losses":30,"wins":5},"meta/muse-wonder":{"draws":9,"losses":27,"wins":0},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":6},"mistralai/mistral-large-4-0":{"draws":7,"losses":11,"wins":4},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":20,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":9,"wins":11},"o3":{"draws":4,"losses":37,"wins":11},"openai/gpt-oss-120b":{"draws":9,"losses":15,"wins":6},"poolside/laguna-s-2.1":{"draws":7,"losses":15,"wins":4},"qwen/qwen3.7-max":{"draws":7,"losses":13,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":18,"wins":3},"qwen/qwen3.8-27b":{"draws":5,"losses":19,"wins":4},"qwen/qwen3.8-flash":{"draws":7,"losses":13,"wins":4},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":7},"qwen/qwen3.8-max-0902":{"draws":10,"losses":20,"wins":6},"stealth/ox-alpha":{"draws":21,"losses":66,"wins":15},"stealth/space-bunny-alpha":{"draws":10,"losses":15,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":16,"wins":7},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":3},"tencent/hy4-preview":{"draws":8,"losses":23,"wins":3},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":10},"thinkingmachines/inkling-small":{"draws":13,"losses":15,"wins":8},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":9,"losses":24,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":23,"wins":2},"x-ai/grok-4.7":{"draws":5,"losses":25,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":7,"wins":3},"xiaomi/mimo-v2.5":{"draws":26,"losses":20,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":12,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":18,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":15,"wins":2},"z-ai/glm-5.2":{"draws":22,"losses":35,"wins":15},"z-ai/glm-5.3":{"draws":5,"losses":29,"wins":0},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":2},"z-ai/glm-5.3-flashx":{"draws":9,"losses":25,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":27,"wins":19},"claude-fable-5":{"draws":12,"losses":49,"wins":11},"claude-fable-5-1":{"draws":5,"losses":74,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":44,"wins":11},"claude-opus-4-5":{"draws":29,"losses":71,"wins":18},"claude-opus-4-8":{"draws":17,"losses":40,"wins":11},"claude-opus-5":{"draws":14,"losses":91,"wins":11},"claude-opus-5-5":{"draws":6,"losses":69,"wins":5},"claude-sonnet-5":{"draws":19,"losses":43,"wins":10},"claude-sonnet-5-5":{"draws":9,"losses":46,"wins":17},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":19},"deepseek/deepseek-v4-flash":{"draws":33,"losses":41,"wins":32},"deepseek/deepseek-v4-pro":{"draws":16,"losses":38,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":34,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":41,"wins":14},"fireworks/ember-1":{"draws":17,"losses":41,"wins":14},"gemini-3.1-pro-preview":{"draws":13,"losses":36,"wins":23},"google/gemini-3.1-flash-lite":{"draws":12,"losses":13,"wins":29},"google/gemini-3.5-flash":{"draws":19,"losses":57,"wins":16},"google/gemini-3.5-flash-lite":{"draws":29,"losses":52,"wins":49},"google/gemini-3.6-flash":{"draws":33,"losses":86,"wins":19},"google/gemini-3.8-flash":{"draws":18,"losses":44,"wins":10},"google/gemma-4-31b-it":{"draws":13,"losses":15,"wins":18},"gpt-4.1":{"draws":10,"losses":10,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":22,"losses":30,"wins":10},"gpt-5.4":{"draws":16,"losses":42,"wins":12},"gpt-5.4-mini":{"draws":16,"losses":17,"wins":15},"gpt-5.4-nano":{"draws":12,"losses":39,"wins":21},"gpt-5.5":{"draws":15,"losses":41,"wins":10},"gpt-5.6-luna":{"draws":22,"losses":29,"wins":21},"gpt-5.6-sol":{"draws":12,"losses":52,"wins":8},"gpt-5.6-terra":{"draws":20,"losses":32,"wins":16},"gpt-6-astra":{"draws":3,"losses":67,"wins":2},"gpt-6-luna":{"draws":15,"losses":40,"wins":17},"gpt-6-sol":{"draws":4,"losses":63,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":64,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":21,"losses":12,"wins":23},"inclusionai/ling-3.0-flash":{"draws":23,"losses":7,"wins":18},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":18,"wins":24},"meta/muse-glimmer-30b":{"draws":19,"losses":21,"wins":22},"meta/muse-spark-1.2":{"draws":14,"losses":39,"wins":15},"meta/muse-spark-1.3":{"draws":17,"losses":45,"wins":10},"meta/muse-wonder":{"draws":11,"losses":51,"wins":10},"minimax/minimax-m3":{"draws":8,"losses":12,"wins":18},"mistralai/mistral-large-4-0":{"draws":16,"losses":19,"wins":9},"mistralai/mistral-medium-3-5":{"draws":17,"losses":8,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":9,"wins":5},"moonshotai/kimi-k3":{"draws":19,"losses":40,"wins":9},"nex-agi/nex-n2-pro":{"draws":9,"losses":13,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":20,"wins":25},"o3":{"draws":14,"losses":62,"wins":30},"openai/gpt-oss-120b":{"draws":20,"losses":13,"wins":31},"poolside/laguna-s-2.1":{"draws":20,"losses":21,"wins":25},"qwen/qwen3.7-max":{"draws":13,"losses":23,"wins":6},"qwen/qwen3.7-plus":{"draws":8,"losses":12,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":42,"wins":12},"qwen/qwen3.8-27b":{"draws":9,"losses":31,"wins":8},"qwen/qwen3.8-flash":{"draws":15,"losses":22,"wins":11},"qwen/qwen3.8-max":{"draws":22,"losses":41,"wins":9},"qwen/qwen3.8-max-0902":{"draws":11,"losses":52,"wins":9},"stealth/ox-alpha":{"draws":55,"losses":141,"wins":32},"stealth/space-bunny-alpha":{"draws":18,"losses":24,"wins":18},"stepfun/step-3.7-flash":{"draws":14,"losses":26,"wins":10},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":15,"losses":11,"wins":12},"tencent/hy4-preview":{"draws":21,"losses":40,"wins":9},"thinkingmachines/inkling":{"draws":26,"losses":34,"wins":32},"thinkingmachines/inkling-small":{"draws":21,"losses":22,"wins":29},"unbiased/pareto-26.10-preview":{"draws":0,"losses":23,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":8,"wins":7},"x-ai/grok-4.5":{"draws":15,"losses":47,"wins":10},"x-ai/grok-4.6":{"draws":16,"losses":45,"wins":11},"x-ai/grok-4.7":{"draws":3,"losses":56,"wins":3},"x-ai/grok-build-0.1":{"draws":9,"losses":8,"wins":7},"xiaomi/mimo-v2.5":{"draws":43,"losses":35,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":14,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":24,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":38,"wins":5},"z-ai/glm-5.2":{"draws":37,"losses":72,"wins":35},"z-ai/glm-5.3":{"draws":16,"losses":50,"wins":6},"z-ai/glm-5.3-flash":{"draws":14,"losses":46,"wins":12},"z-ai/glm-5.3-flashx":{"draws":20,"losses":45,"wins":7}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":15,"wins":12},"claude-fable-5":{"draws":11,"losses":35,"wins":2},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":28,"wins":4},"claude-opus-4-5":{"draws":28,"losses":39,"wins":11},"claude-opus-4-8":{"draws":13,"losses":26,"wins":5},"claude-opus-5":{"draws":5,"losses":68,"wins":9},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":18,"losses":24,"wins":6},"claude-sonnet-5-5":{"draws":11,"losses":32,"wins":5},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":35,"losses":27,"wins":10},"deepseek/deepseek-v4-pro":{"draws":14,"losses":23,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":25,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":31,"wins":3},"fireworks/ember-1":{"draws":16,"losses":28,"wins":4},"gemini-3.1-pro-preview":{"draws":20,"losses":24,"wins":4},"google/gemini-3.1-flash-lite":{"draws":12,"losses":11,"wins":9},"google/gemini-3.5-flash":{"draws":20,"losses":33,"wins":7},"google/gemini-3.5-flash-lite":{"draws":39,"losses":31,"wins":14},"google/gemini-3.6-flash":{"draws":29,"losses":56,"wins":7},"google/gemini-3.8-flash":{"draws":12,"losses":32,"wins":4},"google/gemma-4-31b-it":{"draws":15,"losses":8,"wins":5},"gpt-4.1":{"draws":7,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":19,"wins":9},"gpt-5.4":{"draws":11,"losses":29,"wins":6},"gpt-5.4-mini":{"draws":15,"losses":12,"wins":5},"gpt-5.4-nano":{"draws":11,"losses":21,"wins":16},"gpt-5.5":{"draws":12,"losses":23,"wins":9},"gpt-5.6-luna":{"draws":19,"losses":20,"wins":9},"gpt-5.6-sol":{"draws":8,"losses":38,"wins":2},"gpt-5.6-terra":{"draws":15,"losses":24,"wins":7},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":16,"losses":27,"wins":5},"gpt-6-sol":{"draws":10,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":9,"wins":8},"inclusionai/ling-3.0-flash":{"draws":20,"losses":6,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":17,"wins":16},"meta/muse-glimmer-30b":{"draws":14,"losses":6,"wins":6},"meta/muse-spark-1.2":{"draws":13,"losses":25,"wins":8},"meta/muse-spark-1.3":{"draws":14,"losses":29,"wins":5},"meta/muse-wonder":{"draws":8,"losses":34,"wins":6},"minimax/minimax-m3":{"draws":9,"losses":10,"wins":7},"mistralai/mistral-large-4-0":{"draws":9,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":27,"wins":6},"nex-agi/nex-n2-pro":{"draws":10,"losses":4,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":14,"wins":7},"o3":{"draws":17,"losses":44,"wins":5},"openai/gpt-oss-120b":{"draws":21,"losses":14,"wins":7},"poolside/laguna-s-2.1":{"draws":21,"losses":14,"wins":11},"qwen/qwen3.7-max":{"draws":11,"losses":13,"wins":4},"qwen/qwen3.7-plus":{"draws":11,"losses":8,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":32,"wins":2},"qwen/qwen3.8-27b":{"draws":11,"losses":19,"wins":4},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":25,"wins":8},"qwen/qwen3.8-max-0902":{"draws":17,"losses":28,"wins":3},"stealth/ox-alpha":{"draws":41,"losses":103,"wins":14},"stealth/space-bunny-alpha":{"draws":14,"losses":15,"wins":9},"stepfun/step-3.7-flash":{"draws":10,"losses":16,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":6},"tencent/hy4-preview":{"draws":13,"losses":31,"wins":2},"thinkingmachines/inkling":{"draws":23,"losses":23,"wins":18},"thinkingmachines/inkling-small":{"draws":21,"losses":13,"wins":14},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":10,"losses":34,"wins":4},"x-ai/grok-4.6":{"draws":14,"losses":30,"wins":4},"x-ai/grok-4.7":{"draws":1,"losses":38,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":31,"losses":23,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":13,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":16,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":25,"wins":3},"z-ai/glm-5.2":{"draws":41,"losses":40,"wins":15},"z-ai/glm-5.3":{"draws":9,"losses":33,"wins":4},"z-ai/glm-5.3-flash":{"draws":12,"losses":30,"wins":6},"z-ai/glm-5.3-flashx":{"draws":15,"losses":29,"wins":4}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":9,"wins":19},"claude-fable-5":{"draws":7,"losses":23,"wins":12},"claude-fable-5-1":{"draws":2,"losses":41,"wins":5},"claude-haiku-5-5":{"draws":8,"losses":16,"wins":16},"claude-opus-4-5":{"draws":20,"losses":11,"wins":37},"claude-opus-4-8":{"draws":10,"losses":12,"wins":16},"claude-opus-5":{"draws":11,"losses":54,"wins":15},"claude-opus-5-5":{"draws":5,"losses":36,"wins":5},"claude-sonnet-5":{"draws":14,"losses":10,"wins":18},"claude-sonnet-5-5":{"draws":14,"losses":18,"wins":10},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":18,"losses":4,"wins":40},"deepseek/deepseek-v4-pro":{"draws":7,"losses":14,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":9,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":11,"wins":18},"fireworks/ember-1":{"draws":11,"losses":13,"wins":18},"gemini-3.1-pro-preview":{"draws":10,"losses":12,"wins":20},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":19},"google/gemini-3.5-flash":{"draws":11,"losses":11,"wins":30},"google/gemini-3.5-flash-lite":{"draws":19,"losses":7,"wins":46},"google/gemini-3.6-flash":{"draws":14,"losses":23,"wins":43},"google/gemini-3.8-flash":{"draws":7,"losses":13,"wins":22},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":12},"gpt-4.1":{"draws":6,"losses":1,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":11,"losses":8,"wins":19},"gpt-5.4":{"draws":10,"losses":14,"wins":16},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":16},"gpt-5.4-nano":{"draws":7,"losses":8,"wins":25},"gpt-5.5":{"draws":9,"losses":15,"wins":16},"gpt-5.6-luna":{"draws":13,"losses":6,"wins":23},"gpt-5.6-sol":{"draws":5,"losses":24,"wins":13},"gpt-5.6-terra":{"draws":17,"losses":8,"wins":15},"gpt-6-astra":{"draws":4,"losses":37,"wins":1},"gpt-6-luna":{"draws":15,"losses":7,"wins":20},"gpt-6-sol":{"draws":5,"losses":27,"wins":10},"gpt-6.1-sol":{"draws":4,"losses":31,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":14},"inclusionai/ling-3.0-flash":{"draws":9,"losses":4,"wins":15},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":11,"losses":5,"wins":28},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":28},"meta/muse-spark-1.2":{"draws":7,"losses":8,"wins":13},"meta/muse-spark-1.3":{"draws":9,"losses":13,"wins":20},"meta/muse-wonder":{"draws":8,"losses":18,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":20},"mistralai/mistral-large-4-0":{"draws":6,"losses":6,"wins":16},"mistralai/mistral-medium-3-5":{"draws":5,"losses":4,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":15,"wins":19},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":2,"wins":23},"o3":{"draws":10,"losses":14,"wins":30},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":26},"poolside/laguna-s-2.1":{"draws":12,"losses":5,"wins":25},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":16},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":14,"wins":16},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":9},"qwen/qwen3.8-flash":{"draws":9,"losses":7,"wins":12},"qwen/qwen3.8-max":{"draws":13,"losses":13,"wins":16},"qwen/qwen3.8-max-0902":{"draws":13,"losses":13,"wins":16},"stealth/ox-alpha":{"draws":39,"losses":60,"wins":43},"stealth/space-bunny-alpha":{"draws":10,"losses":6,"wins":18},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":20},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":16,"wins":16},"thinkingmachines/inkling":{"draws":13,"losses":8,"wins":37},"thinkingmachines/inkling-small":{"draws":14,"losses":4,"wins":24},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":18,"wins":13},"x-ai/grok-4.6":{"draws":11,"losses":19,"wins":12},"x-ai/grok-4.7":{"draws":2,"losses":21,"wins":15},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":16,"losses":3,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":6,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":19,"wins":8},"z-ai/glm-5.2":{"draws":16,"losses":19,"wins":49},"z-ai/glm-5.3":{"draws":7,"losses":20,"wins":13},"z-ai/glm-5.3-flash":{"draws":7,"losses":15,"wins":20},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":15}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":6,"wins":31},"claude-fable-5":{"draws":9,"losses":22,"wins":17},"claude-fable-5-1":{"draws":5,"losses":43,"wins":6},"claude-haiku-5-5":{"draws":4,"losses":19,"wins":23},"claude-opus-4-5":{"draws":13,"losses":13,"wins":52},"claude-opus-4-8":{"draws":8,"losses":14,"wins":22},"claude-opus-5":{"draws":11,"losses":48,"wins":23},"claude-opus-5-5":{"draws":5,"losses":42,"wins":5},"claude-sonnet-5":{"draws":13,"losses":8,"wins":27},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":23},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":10,"losses":5,"wins":57},"deepseek/deepseek-v4-pro":{"draws":6,"losses":7,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":9,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":18,"wins":23},"fireworks/ember-1":{"draws":11,"losses":14,"wins":23},"gemini-3.1-pro-preview":{"draws":7,"losses":9,"wins":32},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":7,"losses":9,"wins":44},"google/gemini-3.5-flash-lite":{"draws":13,"losses":9,"wins":62},"google/gemini-3.6-flash":{"draws":20,"losses":24,"wins":48},"google/gemini-3.8-flash":{"draws":10,"losses":13,"wins":25},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":19},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":7,"losses":5,"wins":30},"gpt-5.4":{"draws":9,"losses":16,"wins":21},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":24},"gpt-5.4-nano":{"draws":5,"losses":8,"wins":35},"gpt-5.5":{"draws":9,"losses":16,"wins":19},"gpt-5.6-luna":{"draws":9,"losses":6,"wins":33},"gpt-5.6-sol":{"draws":9,"losses":20,"wins":19},"gpt-5.6-terra":{"draws":13,"losses":8,"wins":25},"gpt-6-astra":{"draws":6,"losses":38,"wins":4},"gpt-6-luna":{"draws":5,"losses":10,"wins":33},"gpt-6-sol":{"draws":8,"losses":33,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":34,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":3,"wins":23},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":3,"wins":43},"meta/muse-glimmer-30b":{"draws":9,"losses":1,"wins":32},"meta/muse-spark-1.2":{"draws":8,"losses":15,"wins":23},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":14},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":7,"losses":1,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":9,"wins":29},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":31},"o3":{"draws":5,"losses":11,"wins":50},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":30},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":34},"qwen/qwen3.7-max":{"draws":4,"losses":6,"wins":18},"qwen/qwen3.7-plus":{"draws":2,"losses":7,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":20,"wins":21},"qwen/qwen3.8-27b":{"draws":6,"losses":5,"wins":23},"qwen/qwen3.8-flash":{"draws":8,"losses":6,"wins":18},"qwen/qwen3.8-max":{"draws":8,"losses":12,"wins":28},"qwen/qwen3.8-max-0902":{"draws":9,"losses":14,"wins":25},"stealth/ox-alpha":{"draws":29,"losses":46,"wins":83},"stealth/space-bunny-alpha":{"draws":6,"losses":6,"wins":26},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":29},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":19},"tencent/hy4-preview":{"draws":8,"losses":12,"wins":26},"thinkingmachines/inkling":{"draws":8,"losses":4,"wins":52},"thinkingmachines/inkling-small":{"draws":8,"losses":4,"wins":36},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":5,"losses":15,"wins":28},"x-ai/grok-4.6":{"draws":10,"losses":19,"wins":19},"x-ai/grok-4.7":{"draws":2,"losses":29,"wins":11},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":12,"losses":1,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":14,"wins":12},"z-ai/glm-5.2":{"draws":18,"losses":16,"wins":62},"z-ai/glm-5.3":{"draws":6,"losses":22,"wins":18},"z-ai/glm-5.3-flash":{"draws":9,"losses":18,"wins":21},"z-ai/glm-5.3-flashx":{"draws":10,"losses":16,"wins":22}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":5,"wins":28},"claude-fable-5":{"draws":9,"losses":16,"wins":23},"claude-fable-5-1":{"draws":4,"losses":44,"wins":6},"claude-haiku-5-5":{"draws":8,"losses":11,"wins":27},"claude-opus-4-5":{"draws":11,"losses":22,"wins":45},"claude-opus-4-8":{"draws":5,"losses":17,"wins":22},"claude-opus-5":{"draws":7,"losses":53,"wins":22},"claude-opus-5-5":{"draws":5,"losses":37,"wins":10},"claude-sonnet-5":{"draws":8,"losses":13,"wins":27},"claude-sonnet-5-5":{"draws":6,"losses":23,"wins":19},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":14,"losses":10,"wins":48},"deepseek/deepseek-v4-pro":{"draws":7,"losses":12,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":10,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":24},"fireworks/ember-1":{"draws":8,"losses":15,"wins":25},"gemini-3.1-pro-preview":{"draws":6,"losses":6,"wins":36},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":27},"google/gemini-3.5-flash":{"draws":11,"losses":9,"wins":40},"google/gemini-3.5-flash-lite":{"draws":15,"losses":10,"wins":59},"google/gemini-3.6-flash":{"draws":16,"losses":29,"wins":47},"google/gemini-3.8-flash":{"draws":10,"losses":10,"wins":28},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":20},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":10,"wins":24},"gpt-5.4":{"draws":7,"losses":19,"wins":20},"gpt-5.4-mini":{"draws":6,"losses":7,"wins":19},"gpt-5.4-nano":{"draws":3,"losses":9,"wins":36},"gpt-5.5":{"draws":11,"losses":14,"wins":19},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":30},"gpt-5.6-sol":{"draws":8,"losses":19,"wins":21},"gpt-5.6-terra":{"draws":3,"losses":16,"wins":27},"gpt-6-astra":{"draws":3,"losses":40,"wins":5},"gpt-6-luna":{"draws":9,"losses":14,"wins":25},"gpt-6-sol":{"draws":8,"losses":26,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":33,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":24},"inclusionai/ling-3.0-flash":{"draws":7,"losses":2,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":33},"meta/muse-glimmer-30b":{"draws":5,"losses":9,"wins":28},"meta/muse-spark-1.2":{"draws":11,"losses":15,"wins":20},"meta/muse-spark-1.3":{"draws":9,"losses":15,"wins":24},"meta/muse-wonder":{"draws":5,"losses":13,"wins":14},"minimax/minimax-m3":{"draws":3,"losses":5,"wins":18},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":13,"wins":26},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":28},"o3":{"draws":2,"losses":14,"wins":50},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":30},"poolside/laguna-s-2.1":{"draws":5,"losses":5,"wins":36},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":21},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":18,"wins":22},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":21},"qwen/qwen3.8-flash":{"draws":8,"losses":6,"wins":18},"qwen/qwen3.8-max":{"draws":13,"losses":12,"wins":23},"qwen/qwen3.8-max-0902":{"draws":7,"losses":14,"wins":27},"stealth/ox-alpha":{"draws":29,"losses":47,"wins":82},"stealth/space-bunny-alpha":{"draws":8,"losses":10,"wins":20},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":8,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":18,"wins":22},"thinkingmachines/inkling":{"draws":10,"losses":12,"wins":42},"thinkingmachines/inkling-small":{"draws":11,"losses":6,"wins":31},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":28},"x-ai/grok-4.6":{"draws":11,"losses":15,"wins":22},"x-ai/grok-4.7":{"draws":7,"losses":24,"wins":11},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":12,"losses":9,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":10,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":15,"wins":14},"z-ai/glm-5.2":{"draws":23,"losses":15,"wins":58},"z-ai/glm-5.3":{"draws":9,"losses":17,"wins":20},"z-ai/glm-5.3-flash":{"draws":8,"losses":12,"wins":28},"z-ai/glm-5.3-flashx":{"draws":11,"losses":13,"wins":24}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":15,"wins":7},"claude-fable-5":{"draws":10,"losses":31,"wins":1},"claude-fable-5-1":{"draws":1,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":31,"wins":5},"claude-opus-4-5":{"draws":21,"losses":46,"wins":3},"claude-opus-4-8":{"draws":12,"losses":28,"wins":2},"claude-opus-5":{"draws":6,"losses":61,"wins":3},"claude-opus-5-5":{"draws":0,"losses":46,"wins":0},"claude-sonnet-5":{"draws":13,"losses":25,"wins":4},"claude-sonnet-5-5":{"draws":7,"losses":33,"wins":2},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":25,"losses":24,"wins":15},"deepseek/deepseek-v4-pro":{"draws":9,"losses":28,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":26,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":7},"fireworks/ember-1":{"draws":12,"losses":29,"wins":1},"gemini-3.1-pro-preview":{"draws":13,"losses":22,"wins":7},"google/gemini-3.1-flash-lite":{"draws":9,"losses":15,"wins":8},"google/gemini-3.5-flash":{"draws":17,"losses":30,"wins":7},"google/gemini-3.5-flash-lite":{"draws":23,"losses":35,"wins":16},"google/gemini-3.6-flash":{"draws":21,"losses":49,"wins":10},"google/gemini-3.8-flash":{"draws":13,"losses":26,"wins":3},"google/gemma-4-31b-it":{"draws":12,"losses":7,"wins":7},"gpt-4.1":{"draws":6,"losses":7,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":12,"losses":18,"wins":6},"gpt-5.4":{"draws":11,"losses":26,"wins":3},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":7},"gpt-5.4-nano":{"draws":11,"losses":27,"wins":8},"gpt-5.5":{"draws":16,"losses":19,"wins":3},"gpt-5.6-luna":{"draws":15,"losses":18,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":34,"wins":2},"gpt-5.6-terra":{"draws":13,"losses":24,"wins":3},"gpt-6-astra":{"draws":1,"losses":41,"wins":0},"gpt-6-luna":{"draws":13,"losses":24,"wins":5},"gpt-6-sol":{"draws":7,"losses":33,"wins":2},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":8,"wins":8},"inclusionai/ling-3.0-flash":{"draws":15,"losses":7,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":24,"wins":12},"meta/muse-glimmer-30b":{"draws":16,"losses":14,"wins":6},"meta/muse-spark-1.2":{"draws":10,"losses":26,"wins":4},"meta/muse-spark-1.3":{"draws":9,"losses":31,"wins":2},"meta/muse-wonder":{"draws":8,"losses":30,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":2},"mistralai/mistral-large-4-0":{"draws":8,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":10,"losses":9,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":8,"losses":24,"wins":8},"nex-agi/nex-n2-pro":{"draws":5,"losses":7,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":16,"wins":6},"o3":{"draws":11,"losses":41,"wins":10},"openai/gpt-oss-120b":{"draws":14,"losses":16,"wins":6},"poolside/laguna-s-2.1":{"draws":16,"losses":18,"wins":4},"qwen/qwen3.7-max":{"draws":9,"losses":13,"wins":4},"qwen/qwen3.7-plus":{"draws":6,"losses":11,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":27,"wins":2},"qwen/qwen3.8-27b":{"draws":7,"losses":20,"wins":3},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":15,"losses":20,"wins":7},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":4},"stealth/ox-alpha":{"draws":26,"losses":83,"wins":9},"stealth/space-bunny-alpha":{"draws":11,"losses":19,"wins":4},"stepfun/step-3.7-flash":{"draws":9,"losses":12,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":12,"wins":1},"tencent/hy4-preview":{"draws":11,"losses":27,"wins":2},"thinkingmachines/inkling":{"draws":14,"losses":31,"wins":9},"thinkingmachines/inkling-small":{"draws":17,"losses":12,"wins":13},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":9,"losses":31,"wins":2},"x-ai/grok-4.6":{"draws":13,"losses":27,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":32,"wins":5},"x-ai/grok-build-0.1":{"draws":5,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":25,"losses":30,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":13,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":17,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":23,"wins":1},"z-ai/glm-5.2":{"draws":30,"losses":47,"wins":7},"z-ai/glm-5.3":{"draws":11,"losses":28,"wins":1},"z-ai/glm-5.3-flash":{"draws":10,"losses":26,"wins":6},"z-ai/glm-5.3-flashx":{"draws":14,"losses":26,"wins":2}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":8,"wins":15},"claude-fable-5":{"draws":8,"losses":21,"wins":7},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":15},"claude-opus-4-5":{"draws":16,"losses":30,"wins":14},"claude-opus-4-8":{"draws":10,"losses":19,"wins":7},"claude-opus-5":{"draws":4,"losses":58,"wins":6},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":10,"losses":9,"wins":17},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":13,"losses":11,"wins":30},"deepseek/deepseek-v4-pro":{"draws":8,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":14,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":11},"fireworks/ember-1":{"draws":11,"losses":14,"wins":11},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":11},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":11,"losses":19,"wins":16},"google/gemini-3.5-flash-lite":{"draws":15,"losses":14,"wins":33},"google/gemini-3.6-flash":{"draws":19,"losses":33,"wins":16},"google/gemini-3.8-flash":{"draws":8,"losses":13,"wins":15},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":11},"gpt-4.1":{"draws":4,"losses":3,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":11,"wins":15},"gpt-5.4":{"draws":8,"losses":20,"wins":6},"gpt-5.4-mini":{"draws":7,"losses":5,"wins":12},"gpt-5.4-nano":{"draws":8,"losses":14,"wins":16},"gpt-5.5":{"draws":13,"losses":11,"wins":10},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":23,"wins":7},"gpt-5.6-terra":{"draws":10,"losses":13,"wins":11},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":12,"losses":14,"wins":10},"gpt-6-sol":{"draws":7,"losses":27,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":31,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":14},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":13},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":24},"meta/muse-glimmer-30b":{"draws":7,"losses":10,"wins":17},"meta/muse-spark-1.2":{"draws":9,"losses":15,"wins":12},"meta/muse-spark-1.3":{"draws":9,"losses":12,"wins":15},"meta/muse-wonder":{"draws":7,"losses":21,"wins":8},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":13},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":15},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":19},"o3":{"draws":5,"losses":21,"wins":24},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":7,"losses":12,"wins":15},"qwen/qwen3.7-max":{"draws":4,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":16,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.8-max":{"draws":9,"losses":16,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":24,"losses":49,"wins":29},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":14},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":15},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":9,"losses":17,"wins":8},"thinkingmachines/inkling":{"draws":10,"losses":10,"wins":28},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":9,"losses":22,"wins":4},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":24,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":11,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":3},"z-ai/glm-5.2":{"draws":16,"losses":26,"wins":30},"z-ai/glm-5.3":{"draws":9,"losses":21,"wins":4},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":13},"z-ai/glm-5.3-flashx":{"draws":12,"losses":12,"wins":12}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":10,"wins":21},"claude-fable-5":{"draws":15,"losses":31,"wins":2},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":12,"losses":23,"wins":11},"claude-opus-4-5":{"draws":29,"losses":25,"wins":24},"claude-opus-4-8":{"draws":13,"losses":18,"wins":13},"claude-opus-5":{"draws":15,"losses":59,"wins":8},"claude-opus-5-5":{"draws":2,"losses":44,"wins":6},"claude-sonnet-5":{"draws":17,"losses":13,"wins":18},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":15},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":20,"losses":13,"wins":39},"deepseek/deepseek-v4-pro":{"draws":10,"losses":16,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":17,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":15,"wins":13},"fireworks/ember-1":{"draws":19,"losses":19,"wins":10},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":20},"google/gemini-3.1-flash-lite":{"draws":8,"losses":4,"wins":20},"google/gemini-3.5-flash":{"draws":20,"losses":22,"wins":18},"google/gemini-3.5-flash-lite":{"draws":26,"losses":16,"wins":42},"google/gemini-3.6-flash":{"draws":27,"losses":38,"wins":27},"google/gemini-3.8-flash":{"draws":17,"losses":25,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":13},"gpt-4.1":{"draws":6,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":15,"losses":13,"wins":14},"gpt-5.4":{"draws":13,"losses":27,"wins":6},"gpt-5.4-mini":{"draws":12,"losses":6,"wins":14},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":25},"gpt-5.5":{"draws":18,"losses":15,"wins":11},"gpt-5.6-luna":{"draws":17,"losses":12,"wins":19},"gpt-5.6-sol":{"draws":8,"losses":32,"wins":8},"gpt-5.6-terra":{"draws":17,"losses":14,"wins":15},"gpt-6-astra":{"draws":1,"losses":43,"wins":4},"gpt-6-luna":{"draws":18,"losses":15,"wins":15},"gpt-6-sol":{"draws":7,"losses":33,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":38,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":16,"losses":2,"wins":16},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":7,"wins":26},"meta/muse-glimmer-30b":{"draws":15,"losses":7,"wins":20},"meta/muse-spark-1.2":{"draws":10,"losses":19,"wins":17},"meta/muse-spark-1.3":{"draws":13,"losses":24,"wins":11},"meta/muse-wonder":{"draws":12,"losses":29,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"mistralai/mistral-large-4-0":{"draws":14,"losses":9,"wins":7},"mistralai/mistral-medium-3-5":{"draws":13,"losses":2,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":12,"wins":7},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":7,"wins":18},"o3":{"draws":13,"losses":24,"wins":29},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":15,"losses":7,"wins":24},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":20,"wins":12},"qwen/qwen3.8-27b":{"draws":11,"losses":6,"wins":17},"qwen/qwen3.8-flash":{"draws":13,"losses":6,"wins":13},"qwen/qwen3.8-max":{"draws":19,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":19,"wins":11},"stealth/ox-alpha":{"draws":41,"losses":65,"wins":52},"stealth/space-bunny-alpha":{"draws":16,"losses":7,"wins":15},"stepfun/step-3.7-flash":{"draws":8,"losses":7,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":14,"losses":19,"wins":13},"thinkingmachines/inkling":{"draws":18,"losses":14,"wins":32},"thinkingmachines/inkling-small":{"draws":16,"losses":4,"wins":28},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":12,"losses":24,"wins":12},"x-ai/grok-4.6":{"draws":21,"losses":20,"wins":7},"x-ai/grok-4.7":{"draws":7,"losses":29,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":26,"losses":9,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":8,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":10,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":9},"z-ai/glm-5.2":{"draws":34,"losses":27,"wins":35},"z-ai/glm-5.3":{"draws":10,"losses":26,"wins":10},"z-ai/glm-5.3-flash":{"draws":12,"losses":19,"wins":17},"z-ai/glm-5.3-flashx":{"draws":17,"losses":22,"wins":9}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":21,"wins":3},"claude-fable-5":{"draws":3,"losses":27,"wins":0},"claude-fable-5-1":{"draws":1,"losses":33,"wins":0},"claude-haiku-5-5":{"draws":1,"losses":24,"wins":3},"claude-opus-4-5":{"draws":4,"losses":41,"wins":3},"claude-opus-4-8":{"draws":3,"losses":23,"wins":0},"claude-opus-5":{"draws":0,"losses":45,"wins":1},"claude-opus-5-5":{"draws":3,"losses":31,"wins":0},"claude-sonnet-5":{"draws":6,"losses":22,"wins":2},"claude-sonnet-5-5":{"draws":3,"losses":25,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":7,"wins":5},"deepseek/deepseek-v4-flash":{"draws":5,"losses":26,"wins":15},"deepseek/deepseek-v4-pro":{"draws":2,"losses":24,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":23,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":27,"wins":2},"fireworks/ember-1":{"draws":2,"losses":26,"wins":2},"gemini-3.1-pro-preview":{"draws":4,"losses":21,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":10,"wins":12},"google/gemini-3.5-flash":{"draws":5,"losses":28,"wins":5},"google/gemini-3.5-flash-lite":{"draws":7,"losses":38,"wins":9},"google/gemini-3.6-flash":{"draws":2,"losses":54,"wins":2},"google/gemini-3.8-flash":{"draws":1,"losses":28,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":10,"wins":4},"gpt-4.1":{"draws":0,"losses":10,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":21,"wins":5},"gpt-5.4":{"draws":4,"losses":21,"wins":5},"gpt-5.4-mini":{"draws":3,"losses":11,"wins":6},"gpt-5.4-nano":{"draws":3,"losses":18,"wins":11},"gpt-5.5":{"draws":1,"losses":26,"wins":1},"gpt-5.6-luna":{"draws":6,"losses":20,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":29,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":26,"wins":1},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":2,"losses":23,"wins":5},"gpt-6-sol":{"draws":0,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":30,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":10,"wins":7},"inclusionai/ling-3.0-flash":{"draws":3,"losses":11,"wins":6},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":25,"wins":11},"meta/muse-glimmer-30b":{"draws":5,"losses":18,"wins":3},"meta/muse-spark-1.2":{"draws":1,"losses":25,"wins":2},"meta/muse-spark-1.3":{"draws":0,"losses":30,"wins":0},"meta/muse-wonder":{"draws":1,"losses":26,"wins":3},"minimax/minimax-m3":{"draws":1,"losses":11,"wins":4},"mistralai/mistral-large-4-0":{"draws":1,"losses":14,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":12,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":24,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":19,"wins":4},"o3":{"draws":2,"losses":46,"wins":2},"openai/gpt-oss-120b":{"draws":4,"losses":15,"wins":9},"poolside/laguna-s-2.1":{"draws":10,"losses":20,"wins":2},"qwen/qwen3.7-max":{"draws":3,"losses":13,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":23,"wins":2},"qwen/qwen3.8-27b":{"draws":2,"losses":14,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":16,"wins":2},"qwen/qwen3.8-max":{"draws":4,"losses":22,"wins":4},"qwen/qwen3.8-max-0902":{"draws":4,"losses":24,"wins":2},"stealth/ox-alpha":{"draws":14,"losses":83,"wins":11},"stealth/space-bunny-alpha":{"draws":3,"losses":17,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":13,"wins":9},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":1,"losses":8,"wins":5},"tencent/hy4-preview":{"draws":2,"losses":25,"wins":3},"thinkingmachines/inkling":{"draws":6,"losses":23,"wins":11},"thinkingmachines/inkling-small":{"draws":4,"losses":19,"wins":7},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":6,"wins":1},"x-ai/grok-4.5":{"draws":3,"losses":23,"wins":4},"x-ai/grok-4.6":{"draws":4,"losses":26,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":25,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":2,"losses":29,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":14,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":17,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":18,"wins":1},"z-ai/glm-5.2":{"draws":15,"losses":40,"wins":5},"z-ai/glm-5.3":{"draws":2,"losses":27,"wins":1},"z-ai/glm-5.3-flash":{"draws":3,"losses":25,"wins":2},"z-ai/glm-5.3-flashx":{"draws":2,"losses":27,"wins":1}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":8},"claude-fable-5":{"draws":5,"losses":22,"wins":3},"claude-fable-5-1":{"draws":1,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":16,"wins":7},"claude-opus-4-5":{"draws":22,"losses":19,"wins":9},"claude-opus-4-8":{"draws":6,"losses":23,"wins":1},"claude-opus-5":{"draws":4,"losses":41,"wins":1},"claude-opus-5-5":{"draws":0,"losses":34,"wins":0},"claude-sonnet-5":{"draws":9,"losses":12,"wins":9},"claude-sonnet-5-5":{"draws":5,"losses":18,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":18,"losses":15,"wins":17},"deepseek/deepseek-v4-pro":{"draws":6,"losses":17,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":14,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":13,"wins":6},"fireworks/ember-1":{"draws":11,"losses":14,"wins":5},"gemini-3.1-pro-preview":{"draws":12,"losses":12,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":13},"google/gemini-3.5-flash":{"draws":10,"losses":22,"wins":6},"google/gemini-3.5-flash-lite":{"draws":18,"losses":17,"wins":15},"google/gemini-3.6-flash":{"draws":14,"losses":31,"wins":11},"google/gemini-3.8-flash":{"draws":9,"losses":19,"wins":2},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":4},"gpt-4.1":{"draws":4,"losses":5,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":11,"wins":6},"gpt-5.4":{"draws":7,"losses":17,"wins":4},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":6},"gpt-5.4-nano":{"draws":10,"losses":12,"wins":14},"gpt-5.5":{"draws":10,"losses":12,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":21,"wins":5},"gpt-5.6-terra":{"draws":7,"losses":13,"wins":10},"gpt-6-astra":{"draws":3,"losses":26,"wins":1},"gpt-6-luna":{"draws":13,"losses":11,"wins":6},"gpt-6-sol":{"draws":2,"losses":26,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":24,"wins":4},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":10},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":8,"wins":13},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":7},"meta/muse-spark-1.2":{"draws":8,"losses":16,"wins":4},"meta/muse-spark-1.3":{"draws":7,"losses":16,"wins":7},"meta/muse-wonder":{"draws":7,"losses":19,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":7,"wins":4},"mistralai/mistral-large-4-0":{"draws":6,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":8,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":11,"losses":7,"wins":10},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":2,"wins":6},"o3":{"draws":10,"losses":26,"wins":10},"openai/gpt-oss-120b":{"draws":9,"losses":13,"wins":4},"poolside/laguna-s-2.1":{"draws":15,"losses":7,"wins":6},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":4},"qwen/qwen3.7-plus":{"draws":6,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":5},"qwen/qwen3.8-27b":{"draws":6,"losses":9,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":7,"wins":5},"qwen/qwen3.8-max":{"draws":9,"losses":11,"wins":10},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":2},"stealth/ox-alpha":{"draws":22,"losses":40,"wins":20},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":12},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":11,"losses":12,"wins":5},"thinkingmachines/inkling":{"draws":10,"losses":13,"wins":13},"thinkingmachines/inkling-small":{"draws":13,"losses":7,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":6,"losses":18,"wins":6},"x-ai/grok-4.6":{"draws":9,"losses":17,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":22,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":4},"xiaomi/mimo-v2.5":{"draws":20,"losses":14,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":9,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":10,"wins":4},"z-ai/glm-5.2":{"draws":27,"losses":19,"wins":14},"z-ai/glm-5.3":{"draws":5,"losses":17,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":10,"wins":12},"z-ai/glm-5.3-flashx":{"draws":8,"losses":13,"wins":9}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":9,"wins":17},"claude-fable-5":{"draws":4,"losses":28,"wins":4},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":4,"losses":25,"wins":7},"claude-opus-4-5":{"draws":16,"losses":27,"wins":17},"claude-opus-4-8":{"draws":6,"losses":20,"wins":10},"claude-opus-5":{"draws":7,"losses":45,"wins":6},"claude-opus-5-5":{"draws":2,"losses":37,"wins":1},"claude-sonnet-5":{"draws":6,"losses":17,"wins":13},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":9},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":6,"losses":13,"wins":35},"deepseek/deepseek-v4-pro":{"draws":5,"losses":18,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":15,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":16,"wins":10},"fireworks/ember-1":{"draws":13,"losses":16,"wins":7},"gemini-3.1-pro-preview":{"draws":7,"losses":12,"wins":17},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":21},"google/gemini-3.5-flash":{"draws":9,"losses":23,"wins":16},"google/gemini-3.5-flash-lite":{"draws":17,"losses":12,"wins":37},"google/gemini-3.6-flash":{"draws":16,"losses":30,"wins":24},"google/gemini-3.8-flash":{"draws":2,"losses":24,"wins":10},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":13},"gpt-4.1":{"draws":2,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":15,"wins":13},"gpt-5.4":{"draws":6,"losses":21,"wins":9},"gpt-5.4-mini":{"draws":5,"losses":10,"wins":9},"gpt-5.4-nano":{"draws":3,"losses":16,"wins":21},"gpt-5.5":{"draws":10,"losses":19,"wins":5},"gpt-5.6-luna":{"draws":7,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":2,"losses":28,"wins":6},"gpt-5.6-terra":{"draws":7,"losses":19,"wins":8},"gpt-6-astra":{"draws":1,"losses":34,"wins":1},"gpt-6-luna":{"draws":6,"losses":16,"wins":14},"gpt-6-sol":{"draws":6,"losses":27,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":17},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":11,"wins":25},"meta/muse-glimmer-30b":{"draws":9,"losses":3,"wins":20},"meta/muse-spark-1.2":{"draws":6,"losses":19,"wins":9},"meta/muse-spark-1.3":{"draws":6,"losses":23,"wins":7},"meta/muse-wonder":{"draws":2,"losses":29,"wins":5},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":16},"mistralai/mistral-large-4-0":{"draws":9,"losses":8,"wins":5},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":12},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":7,"wins":15},"o3":{"draws":6,"losses":22,"wins":20},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":25},"poolside/laguna-s-2.1":{"draws":3,"losses":9,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":18,"wins":9},"qwen/qwen3.8-27b":{"draws":3,"losses":15,"wins":8},"qwen/qwen3.8-flash":{"draws":4,"losses":12,"wins":8},"qwen/qwen3.8-max":{"draws":9,"losses":14,"wins":13},"qwen/qwen3.8-max-0902":{"draws":11,"losses":18,"wins":7},"stealth/ox-alpha":{"draws":15,"losses":61,"wins":26},"stealth/space-bunny-alpha":{"draws":6,"losses":8,"wins":16},"stepfun/step-3.7-flash":{"draws":7,"losses":7,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":7,"losses":20,"wins":9},"thinkingmachines/inkling":{"draws":10,"losses":9,"wins":29},"thinkingmachines/inkling-small":{"draws":9,"losses":3,"wins":24},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":6,"losses":21,"wins":9},"x-ai/grok-4.6":{"draws":8,"losses":22,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":22,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":16,"losses":10,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":16,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":17,"wins":4},"z-ai/glm-5.2":{"draws":16,"losses":27,"wins":29},"z-ai/glm-5.3":{"draws":4,"losses":27,"wins":3},"z-ai/glm-5.3-flash":{"draws":7,"losses":17,"wins":12},"z-ai/glm-5.3-flashx":{"draws":3,"losses":23,"wins":10}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":14,"wins":13},"claude-fable-5":{"draws":13,"losses":34,"wins":1},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":31,"wins":3},"claude-opus-4-5":{"draws":28,"losses":41,"wins":9},"claude-opus-4-8":{"draws":14,"losses":29,"wins":1},"claude-opus-5":{"draws":12,"losses":65,"wins":5},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":15,"losses":26,"wins":7},"claude-sonnet-5-5":{"draws":12,"losses":31,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":7,"wins":4},"deepseek/deepseek-v4-flash":{"draws":29,"losses":23,"wins":20},"deepseek/deepseek-v4-pro":{"draws":14,"losses":23,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":19,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":27,"wins":7},"fireworks/ember-1":{"draws":19,"losses":25,"wins":4},"gemini-3.1-pro-preview":{"draws":16,"losses":23,"wins":9},"google/gemini-3.1-flash-lite":{"draws":10,"losses":7,"wins":15},"google/gemini-3.5-flash":{"draws":17,"losses":34,"wins":9},"google/gemini-3.5-flash-lite":{"draws":30,"losses":31,"wins":23},"google/gemini-3.6-flash":{"draws":29,"losses":52,"wins":11},"google/gemini-3.8-flash":{"draws":11,"losses":36,"wins":1},"google/gemma-4-31b-it":{"draws":12,"losses":4,"wins":12},"gpt-4.1":{"draws":7,"losses":6,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":22,"wins":5},"gpt-5.4":{"draws":16,"losses":28,"wins":2},"gpt-5.4-mini":{"draws":14,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":18},"gpt-5.5":{"draws":19,"losses":22,"wins":3},"gpt-5.6-luna":{"draws":20,"losses":20,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":41,"wins":1},"gpt-5.6-terra":{"draws":17,"losses":27,"wins":2},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":16,"losses":23,"wins":9},"gpt-6-sol":{"draws":6,"losses":39,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":17,"losses":7,"wins":10},"inclusionai/ling-3.0-flash":{"draws":17,"losses":4,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":24,"wins":11},"meta/muse-glimmer-30b":{"draws":19,"losses":11,"wins":12},"meta/muse-spark-1.2":{"draws":13,"losses":29,"wins":4},"meta/muse-spark-1.3":{"draws":13,"losses":32,"wins":3},"meta/muse-wonder":{"draws":10,"losses":36,"wins":2},"minimax/minimax-m3":{"draws":10,"losses":10,"wins":6},"mistralai/mistral-large-4-0":{"draws":10,"losses":18,"wins":2},"mistralai/mistral-medium-3-5":{"draws":13,"losses":7,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":14,"losses":26,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":10,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":13,"wins":12},"o3":{"draws":11,"losses":51,"wins":4},"openai/gpt-oss-120b":{"draws":9,"losses":12,"wins":5},"poolside/laguna-s-2.1":{"draws":18,"losses":19,"wins":9},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":31,"wins":2},"qwen/qwen3.8-27b":{"draws":9,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":13,"losses":14,"wins":5},"qwen/qwen3.8-max":{"draws":19,"losses":27,"wins":2},"qwen/qwen3.8-max-0902":{"draws":16,"losses":31,"wins":1},"stealth/ox-alpha":{"draws":42,"losses":102,"wins":14},"stealth/space-bunny-alpha":{"draws":14,"losses":17,"wins":7},"stepfun/step-3.7-flash":{"draws":13,"losses":15,"wins":6},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":12,"wins":6},"tencent/hy4-preview":{"draws":16,"losses":24,"wins":6},"thinkingmachines/inkling":{"draws":20,"losses":24,"wins":20},"thinkingmachines/inkling-small":{"draws":19,"losses":14,"wins":15},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":14,"losses":31,"wins":3},"x-ai/grok-4.6":{"draws":18,"losses":29,"wins":1},"x-ai/grok-4.7":{"draws":5,"losses":36,"wins":1},"x-ai/grok-build-0.1":{"draws":8,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":26,"losses":25,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":11,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":21,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":24,"wins":2},"z-ai/glm-5.2":{"draws":35,"losses":44,"wins":17},"z-ai/glm-5.3":{"draws":10,"losses":34,"wins":2},"z-ai/glm-5.3-flash":{"draws":9,"losses":34,"wins":5},"z-ai/glm-5.3-flashx":{"draws":11,"losses":29,"wins":8}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":21,"wins":14},"claude-fable-5":{"draws":17,"losses":42,"wins":7},"claude-fable-5-1":{"draws":5,"losses":66,"wins":1},"claude-haiku-5-5":{"draws":19,"losses":31,"wins":12},"claude-opus-4-5":{"draws":43,"losses":50,"wins":13},"claude-opus-4-8":{"draws":23,"losses":31,"wins":4},"claude-opus-5":{"draws":16,"losses":99,"wins":7},"claude-opus-5-5":{"draws":5,"losses":69,"wins":0},"claude-sonnet-5":{"draws":24,"losses":36,"wins":6},"claude-sonnet-5-5":{"draws":15,"losses":40,"wins":11},"cohere/north-mini-code":{"draws":12,"losses":8,"wins":4},"deepseek/deepseek-v4-flash":{"draws":48,"losses":28,"wins":22},"deepseek/deepseek-v4-pro":{"draws":23,"losses":22,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":25,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":25,"wins":8},"fireworks/ember-1":{"draws":30,"losses":27,"wins":9},"gemini-3.1-pro-preview":{"draws":27,"losses":28,"wins":11},"google/gemini-3.1-flash-lite":{"draws":15,"losses":7,"wins":16},"google/gemini-3.5-flash":{"draws":27,"losses":41,"wins":12},"google/gemini-3.5-flash-lite":{"draws":52,"losses":29,"wins":33},"google/gemini-3.6-flash":{"draws":45,"losses":67,"wins":12},"google/gemini-3.8-flash":{"draws":18,"losses":44,"wins":4},"google/gemma-4-31b-it":{"draws":20,"losses":10,"wins":8},"gpt-4.1":{"draws":11,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":1},"gpt-5":{"draws":30,"losses":22,"wins":6},"gpt-5.4":{"draws":18,"losses":37,"wins":7},"gpt-5.4-mini":{"draws":21,"losses":16,"wins":7},"gpt-5.4-nano":{"draws":24,"losses":22,"wins":20},"gpt-5.5":{"draws":27,"losses":25,"wins":8},"gpt-5.6-luna":{"draws":30,"losses":23,"wins":13},"gpt-5.6-sol":{"draws":11,"losses":54,"wins":1},"gpt-5.6-terra":{"draws":29,"losses":29,"wins":4},"gpt-6-astra":{"draws":5,"losses":61,"wins":0},"gpt-6-luna":{"draws":25,"losses":34,"wins":7},"gpt-6-sol":{"draws":12,"losses":51,"wins":3},"gpt-6.1-sol":{"draws":5,"losses":61,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":10,"wins":10},"inclusionai/ling-3.0-flash":{"draws":27,"losses":5,"wins":12},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":28,"losses":23,"wins":19},"meta/muse-glimmer-30b":{"draws":31,"losses":10,"wins":17},"meta/muse-spark-1.2":{"draws":18,"losses":43,"wins":3},"meta/muse-spark-1.3":{"draws":22,"losses":37,"wins":7},"meta/muse-wonder":{"draws":12,"losses":48,"wins":6},"minimax/minimax-m3":{"draws":16,"losses":9,"wins":11},"mistralai/mistral-large-4-0":{"draws":19,"losses":19,"wins":4},"mistralai/mistral-medium-3-5":{"draws":22,"losses":7,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":28,"losses":34,"wins":2},"nex-agi/nex-n2-pro":{"draws":15,"losses":7,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":17,"wins":9},"o3":{"draws":23,"losses":41,"wins":18},"openai/gpt-oss-120b":{"draws":30,"losses":22,"wins":8},"poolside/laguna-s-2.1":{"draws":26,"losses":15,"wins":9},"qwen/qwen3.7-max":{"draws":19,"losses":11,"wins":8},"qwen/qwen3.7-plus":{"draws":15,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":36,"wins":5},"qwen/qwen3.8-27b":{"draws":16,"losses":22,"wins":6},"qwen/qwen3.8-flash":{"draws":23,"losses":16,"wins":5},"qwen/qwen3.8-max":{"draws":26,"losses":30,"wins":10},"qwen/qwen3.8-max-0902":{"draws":26,"losses":35,"wins":5},"stealth/ox-alpha":{"draws":75,"losses":131,"wins":24},"stealth/space-bunny-alpha":{"draws":20,"losses":18,"wins":12},"stepfun/step-3.7-flash":{"draws":20,"losses":14,"wins":8},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":12,"wins":8},"tencent/hy4-preview":{"draws":22,"losses":31,"wins":9},"thinkingmachines/inkling":{"draws":36,"losses":26,"wins":26},"thinkingmachines/inkling-small":{"draws":33,"losses":10,"wins":23},"unbiased/pareto-26.10-preview":{"draws":0,"losses":22,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":5,"wins":4},"x-ai/grok-4.5":{"draws":22,"losses":38,"wins":6},"x-ai/grok-4.6":{"draws":19,"losses":42,"wins":5},"x-ai/grok-4.7":{"draws":7,"losses":46,"wins":5},"x-ai/grok-build-0.1":{"draws":13,"losses":6,"wins":3},"xiaomi/mimo-v2.5":{"draws":43,"losses":27,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":9,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":26,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":31,"wins":5},"z-ai/glm-5.2":{"draws":67,"losses":44,"wins":21},"z-ai/glm-5.3":{"draws":18,"losses":40,"wins":6},"z-ai/glm-5.3-flash":{"draws":20,"losses":35,"wins":11},"z-ai/glm-5.3-flashx":{"draws":27,"losses":31,"wins":8}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":6,"wins":17},"claude-fable-5":{"draws":7,"losses":27,"wins":8},"claude-fable-5-1":{"draws":3,"losses":42,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":16,"wins":12},"claude-opus-4-5":{"draws":23,"losses":28,"wins":19},"claude-opus-4-8":{"draws":13,"losses":17,"wins":12},"claude-opus-5":{"draws":9,"losses":52,"wins":9},"claude-opus-5-5":{"draws":1,"losses":45,"wins":0},"claude-sonnet-5":{"draws":12,"losses":20,"wins":10},"claude-sonnet-5-5":{"draws":5,"losses":26,"wins":11},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":33,"losses":9,"wins":22},"deepseek/deepseek-v4-pro":{"draws":14,"losses":19,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":13,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":12,"wins":12},"fireworks/ember-1":{"draws":13,"losses":17,"wins":12},"gemini-3.1-pro-preview":{"draws":14,"losses":12,"wins":16},"google/gemini-3.1-flash-lite":{"draws":13,"losses":2,"wins":17},"google/gemini-3.5-flash":{"draws":19,"losses":18,"wins":17},"google/gemini-3.5-flash-lite":{"draws":25,"losses":20,"wins":29},"google/gemini-3.6-flash":{"draws":25,"losses":33,"wins":22},"google/gemini-3.8-flash":{"draws":13,"losses":18,"wins":11},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":10},"gpt-4.1":{"draws":8,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":16,"losses":14,"wins":6},"gpt-5.4":{"draws":7,"losses":23,"wins":10},"gpt-5.4-mini":{"draws":10,"losses":8,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":13,"wins":20},"gpt-5.5":{"draws":13,"losses":18,"wins":7},"gpt-5.6-luna":{"draws":16,"losses":12,"wins":14},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":8},"gpt-5.6-terra":{"draws":11,"losses":18,"wins":11},"gpt-6-astra":{"draws":4,"losses":37,"wins":1},"gpt-6-luna":{"draws":11,"losses":19,"wins":12},"gpt-6-sol":{"draws":7,"losses":30,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":13},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":6,"wins":24},"meta/muse-glimmer-30b":{"draws":15,"losses":9,"wins":12},"meta/muse-spark-1.2":{"draws":5,"losses":25,"wins":10},"meta/muse-spark-1.3":{"draws":10,"losses":21,"wins":11},"meta/muse-wonder":{"draws":6,"losses":33,"wins":3},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":11},"mistralai/mistral-large-4-0":{"draws":9,"losses":14,"wins":3},"mistralai/mistral-medium-3-5":{"draws":12,"losses":1,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":19,"wins":11},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":8,"wins":13},"o3":{"draws":16,"losses":22,"wins":24},"openai/gpt-oss-120b":{"draws":15,"losses":5,"wins":16},"poolside/laguna-s-2.1":{"draws":16,"losses":8,"wins":14},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":4},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":17,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":14,"wins":8},"qwen/qwen3.8-flash":{"draws":12,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":13,"losses":13,"wins":16},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":8},"stealth/ox-alpha":{"draws":31,"losses":56,"wins":31},"stealth/space-bunny-alpha":{"draws":11,"losses":10,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":8,"losses":21,"wins":11},"thinkingmachines/inkling":{"draws":17,"losses":6,"wins":31},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":10,"losses":21,"wins":11},"x-ai/grok-4.6":{"draws":8,"losses":26,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":25,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":32,"losses":13,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":25,"losses":33,"wins":26},"z-ai/glm-5.3":{"draws":11,"losses":20,"wins":9},"z-ai/glm-5.3-flash":{"draws":15,"losses":15,"wins":12},"z-ai/glm-5.3-flashx":{"draws":13,"losses":17,"wins":12}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":9,"wins":13},"claude-fable-5":{"draws":7,"losses":24,"wins":5},"claude-fable-5-1":{"draws":0,"losses":37,"wins":1},"claude-haiku-5-5":{"draws":7,"losses":22,"wins":7},"claude-opus-4-5":{"draws":15,"losses":24,"wins":21},"claude-opus-4-8":{"draws":8,"losses":19,"wins":9},"claude-opus-5":{"draws":10,"losses":47,"wins":1},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":9,"losses":15,"wins":12},"claude-sonnet-5-5":{"draws":9,"losses":19,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":18,"losses":17,"wins":23},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":8,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":18,"wins":5},"fireworks/ember-1":{"draws":11,"losses":16,"wins":9},"gemini-3.1-pro-preview":{"draws":11,"losses":13,"wins":12},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":11,"losses":21,"wins":14},"google/gemini-3.5-flash-lite":{"draws":19,"losses":13,"wins":30},"google/gemini-3.6-flash":{"draws":16,"losses":33,"wins":19},"google/gemini-3.8-flash":{"draws":10,"losses":22,"wins":4},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":9},"gpt-4.1":{"draws":4,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":15,"wins":7},"gpt-5.4":{"draws":6,"losses":22,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":13},"gpt-5.4-nano":{"draws":10,"losses":11,"wins":23},"gpt-5.5":{"draws":15,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":12,"wins":12},"gpt-5.6-sol":{"draws":8,"losses":23,"wins":5},"gpt-5.6-terra":{"draws":16,"losses":9,"wins":9},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":11,"losses":15,"wins":10},"gpt-6-sol":{"draws":3,"losses":27,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":30,"wins":4},"inception/mercury-2.5-preview":{"draws":10,"losses":1,"wins":15},"inclusionai/ling-3.0-flash":{"draws":11,"losses":2,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":10,"wins":21},"meta/muse-glimmer-30b":{"draws":12,"losses":8,"wins":10},"meta/muse-spark-1.2":{"draws":6,"losses":23,"wins":5},"meta/muse-spark-1.3":{"draws":10,"losses":17,"wins":9},"meta/muse-wonder":{"draws":11,"losses":25,"wins":0},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":11},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":1},"mistralai/mistral-medium-3-5":{"draws":8,"losses":1,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":11,"wins":11},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":6,"wins":16},"o3":{"draws":9,"losses":26,"wins":23},"openai/gpt-oss-120b":{"draws":12,"losses":3,"wins":17},"poolside/laguna-s-2.1":{"draws":16,"losses":10,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":9,"wins":8},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":7},"qwen/qwen3.8-27b":{"draws":5,"losses":10,"wins":11},"qwen/qwen3.8-flash":{"draws":9,"losses":4,"wins":11},"qwen/qwen3.8-max":{"draws":11,"losses":11,"wins":14},"qwen/qwen3.8-max-0902":{"draws":13,"losses":16,"wins":7},"stealth/ox-alpha":{"draws":21,"losses":59,"wins":20},"stealth/space-bunny-alpha":{"draws":10,"losses":12,"wins":6},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":8},"tencent/hy4-preview":{"draws":7,"losses":21,"wins":6},"thinkingmachines/inkling":{"draws":11,"losses":6,"wins":29},"thinkingmachines/inkling-small":{"draws":13,"losses":6,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":6,"losses":23,"wins":7},"x-ai/grok-4.6":{"draws":13,"losses":19,"wins":4},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":18,"losses":8,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":13,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":18,"wins":4},"z-ai/glm-5.2":{"draws":23,"losses":28,"wins":21},"z-ai/glm-5.3":{"draws":7,"losses":22,"wins":5},"z-ai/glm-5.3-flash":{"draws":11,"losses":17,"wins":8},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":9}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":12,"wins":14},"claude-fable-5":{"draws":13,"losses":31,"wins":4},"claude-fable-5-1":{"draws":6,"losses":47,"wins":1},"claude-haiku-5-5":{"draws":16,"losses":22,"wins":8},"claude-opus-4-5":{"draws":37,"losses":27,"wins":14},"claude-opus-4-8":{"draws":16,"losses":20,"wins":8},"claude-opus-5":{"draws":9,"losses":61,"wins":12},"claude-opus-5-5":{"draws":2,"losses":47,"wins":3},"claude-sonnet-5":{"draws":18,"losses":21,"wins":9},"claude-sonnet-5-5":{"draws":14,"losses":24,"wins":10},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":32,"losses":16,"wins":24},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":22,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":22,"wins":10},"fireworks/ember-1":{"draws":27,"losses":19,"wins":2},"gemini-3.1-pro-preview":{"draws":15,"losses":19,"wins":14},"google/gemini-3.1-flash-lite":{"draws":12,"losses":2,"wins":18},"google/gemini-3.5-flash":{"draws":19,"losses":27,"wins":14},"google/gemini-3.5-flash-lite":{"draws":36,"losses":21,"wins":27},"google/gemini-3.6-flash":{"draws":29,"losses":45,"wins":18},"google/gemini-3.8-flash":{"draws":13,"losses":27,"wins":8},"google/gemma-4-31b-it":{"draws":14,"losses":6,"wins":8},"gpt-4.1":{"draws":8,"losses":2,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":19,"losses":14,"wins":9},"gpt-5.4":{"draws":12,"losses":26,"wins":8},"gpt-5.4-mini":{"draws":14,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":17,"losses":16,"wins":15},"gpt-5.5":{"draws":17,"losses":18,"wins":9},"gpt-5.6-luna":{"draws":25,"losses":10,"wins":13},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":22,"losses":12,"wins":12},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":7,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":6,"losses":37,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":15},"inclusionai/ling-3.0-flash":{"draws":20,"losses":2,"wins":12},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":11,"wins":23},"meta/muse-glimmer-30b":{"draws":25,"losses":2,"wins":15},"meta/muse-spark-1.2":{"draws":15,"losses":22,"wins":9},"meta/muse-spark-1.3":{"draws":14,"losses":28,"wins":6},"meta/muse-wonder":{"draws":9,"losses":33,"wins":6},"minimax/minimax-m3":{"draws":9,"losses":4,"wins":13},"mistralai/mistral-large-4-0":{"draws":14,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":13,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":22,"wins":9},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":8,"wins":10},"o3":{"draws":16,"losses":28,"wins":22},"openai/gpt-oss-120b":{"draws":20,"losses":4,"wins":18},"poolside/laguna-s-2.1":{"draws":21,"losses":6,"wins":19},"qwen/qwen3.7-max":{"draws":14,"losses":7,"wins":7},"qwen/qwen3.7-plus":{"draws":12,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":16,"wins":6},"qwen/qwen3.8-27b":{"draws":15,"losses":11,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":11,"wins":7},"qwen/qwen3.8-max":{"draws":20,"losses":15,"wins":13},"qwen/qwen3.8-max-0902":{"draws":20,"losses":24,"wins":4},"stealth/ox-alpha":{"draws":54,"losses":72,"wins":32},"stealth/space-bunny-alpha":{"draws":18,"losses":10,"wins":10},"stepfun/step-3.7-flash":{"draws":12,"losses":7,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":5,"wins":8},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":21,"losses":11,"wins":32},"thinkingmachines/inkling-small":{"draws":20,"losses":6,"wins":22},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":29,"wins":8},"x-ai/grok-4.6":{"draws":14,"losses":26,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":8},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":36,"losses":16,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":6,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":17,"wins":6},"z-ai/glm-5.2":{"draws":47,"losses":31,"wins":18},"z-ai/glm-5.3":{"draws":8,"losses":33,"wins":5},"z-ai/glm-5.3-flash":{"draws":11,"losses":31,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":26,"wins":12}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":10,"wins":16},"claude-fable-5":{"draws":12,"losses":27,"wins":3},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":9},"claude-opus-4-5":{"draws":26,"losses":14,"wins":28},"claude-opus-4-8":{"draws":11,"losses":17,"wins":10},"claude-opus-5":{"draws":14,"losses":51,"wins":5},"claude-opus-5-5":{"draws":2,"losses":39,"wins":1},"claude-sonnet-5":{"draws":14,"losses":14,"wins":14},"claude-sonnet-5-5":{"draws":6,"losses":28,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":21,"losses":11,"wins":30},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":12,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":19,"wins":14},"fireworks/ember-1":{"draws":14,"losses":13,"wins":15},"gemini-3.1-pro-preview":{"draws":11,"losses":14,"wins":17},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":13,"losses":25,"wins":14},"google/gemini-3.5-flash-lite":{"draws":20,"losses":17,"wins":37},"google/gemini-3.6-flash":{"draws":22,"losses":39,"wins":21},"google/gemini-3.8-flash":{"draws":6,"losses":30,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":10},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":14,"wins":13},"gpt-5.4":{"draws":10,"losses":24,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":12},"gpt-5.4-nano":{"draws":11,"losses":9,"wins":20},"gpt-5.5":{"draws":17,"losses":13,"wins":8},"gpt-5.6-luna":{"draws":14,"losses":10,"wins":18},"gpt-5.6-sol":{"draws":6,"losses":31,"wins":5},"gpt-5.6-terra":{"draws":19,"losses":15,"wins":6},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":13,"losses":17,"wins":12},"gpt-6-sol":{"draws":5,"losses":32,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":4,"wins":13},"inclusionai/ling-3.0-flash":{"draws":9,"losses":4,"wins":15},"meituan/longcat-2.0":{"draws":10,"losses":8,"wins":26},"meta/muse-glimmer-30b":{"draws":11,"losses":9,"wins":16},"meta/muse-spark-1.2":{"draws":13,"losses":14,"wins":13},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":10},"meta/muse-wonder":{"draws":10,"losses":27,"wins":5},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":13},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":7},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":14,"wins":11},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":6,"wins":16},"o3":{"draws":7,"losses":20,"wins":29},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":16},"poolside/laguna-s-2.1":{"draws":14,"losses":9,"wins":15},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":15,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":3,"wins":11},"qwen/qwen3.8-flash":{"draws":8,"losses":12,"wins":8},"qwen/qwen3.8-max":{"draws":15,"losses":14,"wins":13},"qwen/qwen3.8-max-0902":{"draws":10,"losses":24,"wins":8},"stealth/ox-alpha":{"draws":40,"losses":61,"wins":41},"stealth/space-bunny-alpha":{"draws":12,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":8,"losses":10,"wins":12},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":10},"tencent/hy4-preview":{"draws":15,"losses":17,"wins":8},"thinkingmachines/inkling":{"draws":21,"losses":8,"wins":29},"thinkingmachines/inkling-small":{"draws":15,"losses":8,"wins":19},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":16,"losses":17,"wins":9},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":6},"x-ai/grok-4.7":{"draws":7,"losses":23,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":26,"losses":9,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":7},"z-ai/glm-5.2":{"draws":34,"losses":27,"wins":23},"z-ai/glm-5.3":{"draws":10,"losses":24,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":26,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":24,"wins":6}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":4,"wins":27},"claude-fable-5":{"draws":16,"losses":16,"wins":16},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":15,"losses":14,"wins":17},"claude-opus-4-5":{"draws":26,"losses":13,"wins":39},"claude-opus-4-8":{"draws":19,"losses":11,"wins":14},"claude-opus-5":{"draws":11,"losses":61,"wins":10},"claude-opus-5-5":{"draws":6,"losses":44,"wins":2},"claude-sonnet-5":{"draws":14,"losses":9,"wins":25},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":24},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":26,"losses":6,"wins":40},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":7,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":15,"wins":15},"fireworks/ember-1":{"draws":17,"losses":9,"wins":22},"gemini-3.1-pro-preview":{"draws":19,"losses":11,"wins":18},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":21,"losses":12,"wins":27},"google/gemini-3.5-flash-lite":{"draws":28,"losses":5,"wins":51},"google/gemini-3.6-flash":{"draws":27,"losses":26,"wins":39},"google/gemini-3.8-flash":{"draws":14,"losses":9,"wins":25},"google/gemma-4-31b-it":{"draws":14,"losses":1,"wins":13},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":16,"losses":5,"wins":21},"gpt-5.4":{"draws":11,"losses":16,"wins":19},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":14,"losses":8,"wins":26},"gpt-5.5":{"draws":16,"losses":15,"wins":13},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":28},"gpt-5.6-sol":{"draws":13,"losses":22,"wins":13},"gpt-5.6-terra":{"draws":19,"losses":8,"wins":19},"gpt-6-astra":{"draws":7,"losses":38,"wins":3},"gpt-6-luna":{"draws":14,"losses":10,"wins":24},"gpt-6-sol":{"draws":7,"losses":28,"wins":13},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":15,"losses":0,"wins":19},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":20},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":7,"wins":30},"meta/muse-glimmer-30b":{"draws":16,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":11,"losses":15,"wins":20},"meta/muse-spark-1.3":{"draws":13,"losses":15,"wins":20},"meta/muse-wonder":{"draws":13,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"mistralai/mistral-large-4-0":{"draws":11,"losses":3,"wins":16},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":13,"losses":8,"wins":25},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":3,"wins":19},"o3":{"draws":11,"losses":12,"wins":43},"openai/gpt-oss-120b":{"draws":15,"losses":6,"wins":21},"poolside/laguna-s-2.1":{"draws":20,"losses":2,"wins":24},"qwen/qwen3.7-max":{"draws":9,"losses":2,"wins":17},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":11,"wins":26},"qwen/qwen3.8-27b":{"draws":11,"losses":6,"wins":17},"qwen/qwen3.8-flash":{"draws":9,"losses":0,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":13,"wins":20},"qwen/qwen3.8-max-0902":{"draws":17,"losses":10,"wins":21},"stealth/ox-alpha":{"draws":48,"losses":37,"wins":73},"stealth/space-bunny-alpha":{"draws":13,"losses":4,"wins":21},"stepfun/step-3.7-flash":{"draws":9,"losses":0,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":16},"tencent/hy4-preview":{"draws":16,"losses":9,"wins":21},"thinkingmachines/inkling":{"draws":20,"losses":7,"wins":37},"thinkingmachines/inkling-small":{"draws":21,"losses":6,"wins":21},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":4},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":14,"losses":17,"wins":17},"x-ai/grok-4.6":{"draws":19,"losses":16,"wins":13},"x-ai/grok-4.7":{"draws":6,"losses":26,"wins":10},"x-ai/grok-build-0.1":{"draws":7,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":30,"losses":4,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":3,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":5,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":13,"wins":12},"z-ai/glm-5.2":{"draws":34,"losses":11,"wins":51},"z-ai/glm-5.3":{"draws":14,"losses":21,"wins":11},"z-ai/glm-5.3-flash":{"draws":8,"losses":14,"wins":26},"z-ai/glm-5.3-flashx":{"draws":13,"losses":16,"wins":19}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":8,"wins":19},"claude-fable-5":{"draws":6,"losses":30,"wins":12},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":27,"wins":12},"claude-opus-4-5":{"draws":25,"losses":16,"wins":37},"claude-opus-4-8":{"draws":11,"losses":20,"wins":13},"claude-opus-5":{"draws":15,"losses":60,"wins":7},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"claude-sonnet-5":{"draws":15,"losses":13,"wins":20},"claude-sonnet-5-5":{"draws":9,"losses":28,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":22,"losses":10,"wins":40},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":13,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":18,"wins":13},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":17},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":16,"losses":24,"wins":20},"google/gemini-3.5-flash-lite":{"draws":30,"losses":14,"wins":40},"google/gemini-3.6-flash":{"draws":30,"losses":41,"wins":21},"google/gemini-3.8-flash":{"draws":13,"losses":19,"wins":16},"google/gemma-4-31b-it":{"draws":10,"losses":1,"wins":17},"gpt-4.1":{"draws":7,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":8,"wins":20},"gpt-5.4":{"draws":12,"losses":20,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":11,"losses":10,"wins":27},"gpt-5.5":{"draws":16,"losses":17,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":10,"wins":19},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":13},"gpt-5.6-terra":{"draws":20,"losses":14,"wins":12},"gpt-6-astra":{"draws":6,"losses":41,"wins":1},"gpt-6-luna":{"draws":15,"losses":14,"wins":19},"gpt-6-sol":{"draws":6,"losses":35,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":40,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":15},"inclusionai/ling-3.0-flash":{"draws":16,"losses":5,"wins":13},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":14,"wins":26},"meta/muse-glimmer-30b":{"draws":15,"losses":8,"wins":19},"meta/muse-spark-1.2":{"draws":13,"losses":12,"wins":21},"meta/muse-spark-1.3":{"draws":11,"losses":29,"wins":8},"meta/muse-wonder":{"draws":11,"losses":29,"wins":8},"minimax/minimax-m3":{"draws":8,"losses":1,"wins":17},"mistralai/mistral-large-4-0":{"draws":10,"losses":10,"wins":10},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":15,"losses":15,"wins":16},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":6,"wins":22},"o3":{"draws":13,"losses":19,"wins":34},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":17,"losses":11,"wins":18},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":13,"wins":19},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":10},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":10,"losses":8,"wins":14},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":14},"stealth/ox-alpha":{"draws":39,"losses":61,"wins":58},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":5,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":12,"losses":20,"wins":14},"thinkingmachines/inkling":{"draws":19,"losses":13,"wins":32},"thinkingmachines/inkling-small":{"draws":12,"losses":15,"wins":21},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":26,"wins":11},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":2,"losses":34,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":26,"losses":15,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":14,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":17,"wins":5},"z-ai/glm-5.2":{"draws":33,"losses":23,"wins":40},"z-ai/glm-5.3":{"draws":13,"losses":24,"wins":9},"z-ai/glm-5.3-flash":{"draws":11,"losses":22,"wins":15},"z-ai/glm-5.3-flashx":{"draws":9,"losses":24,"wins":15}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":12,"wins":22},"claude-fable-5":{"draws":7,"losses":36,"wins":5},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":20,"wins":11},"claude-opus-4-5":{"draws":23,"losses":39,"wins":16},"claude-opus-4-8":{"draws":13,"losses":24,"wins":7},"claude-opus-5":{"draws":16,"losses":57,"wins":9},"claude-opus-5-5":{"draws":6,"losses":45,"wins":1},"claude-sonnet-5":{"draws":13,"losses":15,"wins":20},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":16},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":24,"losses":14,"wins":34},"deepseek/deepseek-v4-pro":{"draws":12,"losses":16,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":21,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":23,"wins":10},"fireworks/ember-1":{"draws":14,"losses":21,"wins":13},"gemini-3.1-pro-preview":{"draws":12,"losses":17,"wins":19},"google/gemini-3.1-flash-lite":{"draws":12,"losses":1,"wins":19},"google/gemini-3.5-flash":{"draws":16,"losses":25,"wins":19},"google/gemini-3.5-flash-lite":{"draws":30,"losses":21,"wins":33},"google/gemini-3.6-flash":{"draws":20,"losses":50,"wins":22},"google/gemini-3.8-flash":{"draws":13,"losses":29,"wins":6},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":12},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":15,"wins":14},"gpt-5.4":{"draws":7,"losses":28,"wins":11},"gpt-5.4-mini":{"draws":14,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":15,"losses":19,"wins":14},"gpt-5.5":{"draws":11,"losses":21,"wins":12},"gpt-5.6-luna":{"draws":17,"losses":13,"wins":18},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":19,"losses":12,"wins":15},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":13,"losses":25,"wins":10},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":42,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":15},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":12,"wins":31},"meta/muse-glimmer-30b":{"draws":17,"losses":7,"wins":18},"meta/muse-spark-1.2":{"draws":13,"losses":24,"wins":9},"meta/muse-spark-1.3":{"draws":15,"losses":23,"wins":10},"meta/muse-wonder":{"draws":7,"losses":30,"wins":11},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":12},"mistralai/mistral-large-4-0":{"draws":12,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":12,"losses":17,"wins":17},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":8,"wins":18},"o3":{"draws":13,"losses":28,"wins":25},"openai/gpt-oss-120b":{"draws":12,"losses":9,"wins":21},"poolside/laguna-s-2.1":{"draws":18,"losses":13,"wins":15},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.7-plus":{"draws":11,"losses":4,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":21,"wins":11},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":11},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":13,"losses":19,"wins":16},"qwen/qwen3.8-max-0902":{"draws":8,"losses":19,"wins":5},"stealth/ox-alpha":{"draws":37,"losses":75,"wins":46},"stealth/space-bunny-alpha":{"draws":15,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":10,"losses":8,"wins":16},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":11,"losses":5,"wins":10},"tencent/hy4-preview":{"draws":10,"losses":24,"wins":12},"thinkingmachines/inkling":{"draws":22,"losses":15,"wins":27},"thinkingmachines/inkling-small":{"draws":16,"losses":9,"wins":23},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.6":{"draws":13,"losses":25,"wins":10},"x-ai/grok-4.7":{"draws":8,"losses":28,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":28,"losses":17,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":10,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":22,"wins":7},"z-ai/glm-5.2":{"draws":34,"losses":29,"wins":33},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":6},"z-ai/glm-5.3-flash":{"draws":14,"losses":22,"wins":12},"z-ai/glm-5.3-flashx":{"draws":12,"losses":23,"wins":13}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":33,"wins":77},"claude-fable-5":{"draws":35,"losses":88,"wins":33},"claude-fable-5-1":{"draws":9,"losses":167,"wins":6},"claude-haiku-5-5":{"draws":31,"losses":59,"wins":52},"claude-opus-4-5":{"draws":75,"losses":76,"wins":95},"claude-opus-4-8":{"draws":32,"losses":49,"wins":47},"claude-opus-5":{"draws":49,"losses":187,"wins":44},"claude-opus-5-5":{"draws":21,"losses":140,"wins":7},"claude-sonnet-5":{"draws":41,"losses":43,"wins":72},"claude-sonnet-5-5":{"draws":37,"losses":70,"wins":49},"cohere/north-mini-code":{"draws":9,"losses":6,"wins":45},"deepseek/deepseek-v4-flash":{"draws":57,"losses":46,"wins":125},"deepseek/deepseek-v4-pro":{"draws":34,"losses":46,"wins":66},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":52,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":62,"wins":52},"fireworks/ember-1":{"draws":41,"losses":61,"wins":54},"gemini-3.1-pro-preview":{"draws":37,"losses":47,"wins":72},"google/gemini-3.1-flash-lite":{"draws":18,"losses":14,"wins":54},"google/gemini-3.5-flash":{"draws":44,"losses":65,"wins":79},"google/gemini-3.5-flash-lite":{"draws":62,"losses":53,"wins":155},"google/gemini-3.6-flash":{"draws":76,"losses":124,"wins":100},"google/gemini-3.8-flash":{"draws":39,"losses":74,"wins":43},"google/gemma-4-31b-it":{"draws":18,"losses":17,"wins":51},"gpt-4.1":{"draws":12,"losses":9,"wins":31},"gpt-4.1-nano":{"draws":13,"losses":1,"wins":10},"gpt-5":{"draws":31,"losses":44,"wins":65},"gpt-5.4":{"draws":40,"losses":59,"wins":51},"gpt-5.4-mini":{"draws":29,"losses":18,"wins":57},"gpt-5.4-nano":{"draws":30,"losses":35,"wins":71},"gpt-5.5":{"draws":42,"losses":56,"wins":48},"gpt-5.6-luna":{"draws":51,"losses":31,"wins":74},"gpt-5.6-sol":{"draws":24,"losses":105,"wins":27},"gpt-5.6-terra":{"draws":42,"losses":39,"wins":69},"gpt-6-astra":{"draws":9,"losses":142,"wins":5},"gpt-6-luna":{"draws":38,"losses":56,"wins":62},"gpt-6-sol":{"draws":23,"losses":116,"wins":17},"gpt-6.1-sol":{"draws":16,"losses":133,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":35,"losses":12,"wins":55},"inclusionai/ling-3.0-flash":{"draws":26,"losses":8,"wins":72},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":34,"losses":25,"wins":109},"meta/muse-glimmer-30b":{"draws":31,"losses":21,"wins":90},"meta/muse-spark-1.2":{"draws":35,"losses":59,"wins":58},"meta/muse-spark-1.3":{"draws":35,"losses":69,"wins":52},"meta/muse-wonder":{"draws":37,"losses":76,"wins":43},"minimax/minimax-m3":{"draws":19,"losses":17,"wins":44},"mistralai/mistral-large-4-0":{"draws":33,"losses":24,"wins":43},"mistralai/mistral-medium-3-5":{"draws":19,"losses":18,"wins":57},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":10,"wins":16},"moonshotai/kimi-k3":{"draws":40,"losses":64,"wins":48},"nex-agi/nex-n2-pro":{"draws":19,"losses":13,"wins":52},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":17,"wins":68},"o3":{"draws":28,"losses":71,"wins":93},"openai/gpt-oss-120b":{"draws":31,"losses":24,"wins":87},"poolside/laguna-s-2.1":{"draws":37,"losses":30,"wins":93},"qwen/qwen3.7-max":{"draws":23,"losses":22,"wins":39},"qwen/qwen3.7-plus":{"draws":15,"losses":10,"wins":39},"qwen/qwen3.8-2.4t-a95b":{"draws":44,"losses":62,"wins":50},"qwen/qwen3.8-27b":{"draws":23,"losses":41,"wins":42},"qwen/qwen3.8-flash":{"draws":31,"losses":35,"wins":38},"qwen/qwen3.8-max":{"draws":52,"losses":48,"wins":56},"qwen/qwen3.8-max-0902":{"draws":35,"losses":72,"wins":49},"stealth/ox-alpha":{"draws":101,"losses":246,"wins":203},"stealth/space-bunny-alpha":{"draws":33,"losses":30,"wins":59},"stepfun/step-3.7-flash":{"draws":15,"losses":22,"wins":69},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":25,"losses":13,"wins":42},"tencent/hy4-preview":{"draws":32,"losses":68,"wins":50},"thinkingmachines/inkling":{"draws":53,"losses":45,"wins":118},"thinkingmachines/inkling-small":{"draws":41,"losses":34,"wins":81},"unbiased/pareto-26.10-preview":{"draws":0,"losses":50,"wins":2},"upstage/solar-mini4":{"draws":5,"losses":7,"wins":18},"x-ai/grok-4.5":{"draws":38,"losses":69,"wins":49},"x-ai/grok-4.6":{"draws":43,"losses":65,"wins":48},"x-ai/grok-4.7":{"draws":17,"losses":98,"wins":17},"x-ai/grok-build-0.1":{"draws":13,"losses":5,"wins":34},"xiaomi/mimo-v2.5":{"draws":61,"losses":30,"wins":117},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":18,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":35,"wins":42},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":51,"wins":37},"z-ai/glm-5.2":{"draws":83,"losses":79,"wins":150},"z-ai/glm-5.3":{"draws":30,"losses":89,"wins":33},"z-ai/glm-5.3-flash":{"draws":31,"losses":76,"wins":49},"z-ai/glm-5.3-flashx":{"draws":24,"losses":78,"wins":54}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":11,"wins":14},"claude-fable-5":{"draws":9,"losses":27,"wins":6},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":18,"wins":8},"claude-opus-4-5":{"draws":21,"losses":23,"wins":24},"claude-opus-4-8":{"draws":11,"losses":22,"wins":5},"claude-opus-5":{"draws":9,"losses":56,"wins":5},"claude-opus-5-5":{"draws":1,"losses":41,"wins":0},"claude-sonnet-5":{"draws":12,"losses":17,"wins":13},"claude-sonnet-5-5":{"draws":9,"losses":29,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":17,"losses":17,"wins":28},"deepseek/deepseek-v4-pro":{"draws":9,"losses":18,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":17,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":23,"wins":10},"fireworks/ember-1":{"draws":14,"losses":20,"wins":8},"gemini-3.1-pro-preview":{"draws":13,"losses":19,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":15},"google/gemini-3.5-flash":{"draws":13,"losses":29,"wins":10},"google/gemini-3.5-flash-lite":{"draws":16,"losses":28,"wins":30},"google/gemini-3.6-flash":{"draws":24,"losses":42,"wins":16},"google/gemini-3.8-flash":{"draws":11,"losses":28,"wins":3},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":10},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":14,"wins":15},"gpt-5.4":{"draws":11,"losses":23,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":7,"losses":18,"wins":15},"gpt-5.5":{"draws":10,"losses":18,"wins":10},"gpt-5.6-luna":{"draws":14,"losses":15,"wins":13},"gpt-5.6-sol":{"draws":9,"losses":27,"wins":6},"gpt-5.6-terra":{"draws":16,"losses":14,"wins":10},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":17,"losses":20,"wins":5},"gpt-6-sol":{"draws":9,"losses":30,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":5,"wins":15},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":14},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":25},"meta/muse-glimmer-30b":{"draws":11,"losses":15,"wins":10},"meta/muse-spark-1.2":{"draws":14,"losses":18,"wins":8},"meta/muse-spark-1.3":{"draws":7,"losses":31,"wins":4},"meta/muse-wonder":{"draws":14,"losses":21,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":12},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":19,"wins":8},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":11,"wins":8},"o3":{"draws":6,"losses":26,"wins":24},"openai/gpt-oss-120b":{"draws":11,"losses":12,"wins":13},"poolside/laguna-s-2.1":{"draws":8,"losses":15,"wins":15},"qwen/qwen3.7-max":{"draws":5,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":15,"wins":9},"qwen/qwen3.8-27b":{"draws":6,"losses":17,"wins":9},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":13},"qwen/qwen3.8-max-0902":{"draws":12,"losses":22,"wins":8},"stealth/ox-alpha":{"draws":31,"losses":76,"wins":35},"stealth/space-bunny-alpha":{"draws":8,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":9,"wins":16},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":8},"tencent/hy4-preview":{"draws":10,"losses":22,"wins":8},"thinkingmachines/inkling":{"draws":19,"losses":18,"wins":21},"thinkingmachines/inkling-small":{"draws":12,"losses":13,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":12,"losses":20,"wins":10},"x-ai/grok-4.6":{"draws":14,"losses":23,"wins":5},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":23,"losses":18,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":11},"z-ai/glm-5.2":{"draws":33,"losses":28,"wins":23},"z-ai/glm-5.3":{"draws":11,"losses":28,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":27,"wins":8},"z-ai/glm-5.3-flashx":{"draws":9,"losses":25,"wins":8}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":13},"claude-fable-5":{"draws":2,"losses":30,"wins":4},"claude-fable-5-1":{"draws":0,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":4,"losses":23,"wins":7},"claude-opus-4-5":{"draws":10,"losses":32,"wins":16},"claude-opus-4-8":{"draws":3,"losses":19,"wins":10},"claude-opus-5":{"draws":2,"losses":54,"wins":2},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":7,"losses":21,"wins":8},"claude-sonnet-5-5":{"draws":3,"losses":23,"wins":10},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":13,"losses":24,"wins":19},"deepseek/deepseek-v4-pro":{"draws":6,"losses":18,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":21,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":19,"wins":9},"fireworks/ember-1":{"draws":5,"losses":22,"wins":9},"gemini-3.1-pro-preview":{"draws":4,"losses":19,"wins":13},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":7,"losses":29,"wins":10},"google/gemini-3.5-flash-lite":{"draws":13,"losses":23,"wins":28},"google/gemini-3.6-flash":{"draws":9,"losses":45,"wins":16},"google/gemini-3.8-flash":{"draws":4,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":9},"gpt-4.1":{"draws":1,"losses":8,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":15,"wins":8},"gpt-5.4":{"draws":6,"losses":25,"wins":5},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":6,"losses":22,"wins":12},"gpt-5.5":{"draws":8,"losses":21,"wins":5},"gpt-5.6-luna":{"draws":9,"losses":14,"wins":13},"gpt-5.6-sol":{"draws":2,"losses":31,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":19,"wins":7},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":6,"losses":21,"wins":9},"gpt-6-sol":{"draws":4,"losses":32,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":7,"wins":11},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":14,"wins":19},"meta/muse-glimmer-30b":{"draws":7,"losses":11,"wins":14},"meta/muse-spark-1.2":{"draws":0,"losses":27,"wins":7},"meta/muse-spark-1.3":{"draws":3,"losses":24,"wins":9},"meta/muse-wonder":{"draws":1,"losses":32,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":8},"mistralai/mistral-large-4-0":{"draws":6,"losses":12,"wins":4},"mistralai/mistral-medium-3-5":{"draws":5,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":20,"wins":5},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":13,"wins":9},"o3":{"draws":10,"losses":32,"wins":18},"openai/gpt-oss-120b":{"draws":10,"losses":9,"wins":13},"poolside/laguna-s-2.1":{"draws":14,"losses":12,"wins":12},"qwen/qwen3.7-max":{"draws":6,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":24,"wins":8},"qwen/qwen3.8-27b":{"draws":4,"losses":14,"wins":8},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":8,"losses":20,"wins":8},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":4},"stealth/ox-alpha":{"draws":17,"losses":88,"wins":19},"stealth/space-bunny-alpha":{"draws":4,"losses":15,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":8,"wins":5},"tencent/hy4-preview":{"draws":7,"losses":22,"wins":7},"thinkingmachines/inkling":{"draws":11,"losses":19,"wins":20},"thinkingmachines/inkling-small":{"draws":10,"losses":11,"wins":15},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":0,"losses":27,"wins":9},"x-ai/grok-4.6":{"draws":8,"losses":22,"wins":6},"x-ai/grok-4.7":{"draws":1,"losses":27,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":12,"losses":16,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":10,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":20,"wins":4},"z-ai/glm-5.2":{"draws":18,"losses":37,"wins":17},"z-ai/glm-5.3":{"draws":3,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":6},"z-ai/glm-5.3-flashx":{"draws":6,"losses":24,"wins":6}},"stepfun/step-5-preview":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":4},"claude-fable-5":{"draws":0,"losses":1,"wins":5},"claude-fable-5-1":{"draws":0,"losses":4,"wins":2},"claude-haiku-5-5":{"draws":0,"losses":2,"wins":4},"claude-opus-4-5":{"draws":0,"losses":0,"wins":10},"claude-opus-4-8":{"draws":0,"losses":2,"wins":4},"claude-opus-5":{"draws":0,"losses":5,"wins":7},"claude-opus-5-5":{"draws":0,"losses":6,"wins":4},"claude-sonnet-5":{"draws":0,"losses":0,"wins":6},"claude-sonnet-5-5":{"draws":0,"losses":4,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":1,"wins":5},"fireworks/ember-1":{"draws":0,"losses":2,"wins":4},"gemini-3.1-pro-preview":{"draws":0,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":10},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":9},"google/gemini-3.8-flash":{"draws":0,"losses":2,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":0,"losses":0,"wins":6},"gpt-5.4":{"draws":0,"losses":0,"wins":6},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":8},"gpt-5.5":{"draws":0,"losses":3,"wins":3},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":6},"gpt-6-astra":{"draws":0,"losses":2,"wins":4},"gpt-6-luna":{"draws":0,"losses":1,"wins":5},"gpt-6-sol":{"draws":1,"losses":2,"wins":3},"gpt-6.1-sol":{"draws":0,"losses":4,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":6},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":8},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":6},"meta/muse-spark-1.3":{"draws":0,"losses":1,"wins":5},"meta/muse-wonder":{"draws":0,"losses":0,"wins":6},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-large-4-0":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":8},"o3":{"draws":0,"losses":0,"wins":10},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-flash":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-max":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.8-max-0902":{"draws":0,"losses":1,"wins":5},"stealth/ox-alpha":{"draws":0,"losses":1,"wins":15},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":4},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":0,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":6},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":6},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.6":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":5,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":11},"z-ai/glm-5.3":{"draws":0,"losses":2,"wins":4},"z-ai/glm-5.3-flash":{"draws":0,"losses":0,"wins":6},"z-ai/glm-5.3-flashx":{"draws":0,"losses":0,"wins":6}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":6,"wins":25},"claude-fable-5":{"draws":3,"losses":28,"wins":11},"claude-fable-5-1":{"draws":1,"losses":44,"wins":3},"claude-haiku-5-5":{"draws":5,"losses":13,"wins":22},"claude-opus-4-5":{"draws":13,"losses":14,"wins":41},"claude-opus-4-8":{"draws":7,"losses":13,"wins":18},"claude-opus-5":{"draws":2,"losses":57,"wins":11},"claude-opus-5-5":{"draws":4,"losses":35,"wins":7},"claude-sonnet-5":{"draws":11,"losses":12,"wins":19},"claude-sonnet-5-5":{"draws":8,"losses":18,"wins":16},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":11,"losses":11,"wins":40},"deepseek/deepseek-v4-pro":{"draws":8,"losses":9,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":19,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":16,"wins":17},"fireworks/ember-1":{"draws":8,"losses":15,"wins":19},"gemini-3.1-pro-preview":{"draws":7,"losses":10,"wins":25},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":7,"losses":15,"wins":32},"google/gemini-3.5-flash-lite":{"draws":10,"losses":17,"wins":49},"google/gemini-3.6-flash":{"draws":9,"losses":37,"wins":36},"google/gemini-3.8-flash":{"draws":9,"losses":13,"wins":20},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":16},"gpt-4.1":{"draws":3,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":13,"wins":19},"gpt-5.4":{"draws":4,"losses":18,"wins":20},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":2,"losses":6,"wins":34},"gpt-5.5":{"draws":10,"losses":14,"wins":16},"gpt-5.6-luna":{"draws":7,"losses":10,"wins":25},"gpt-5.6-sol":{"draws":5,"losses":17,"wins":20},"gpt-5.6-terra":{"draws":9,"losses":11,"wins":20},"gpt-6-astra":{"draws":2,"losses":38,"wins":2},"gpt-6-luna":{"draws":8,"losses":10,"wins":24},"gpt-6-sol":{"draws":3,"losses":31,"wins":8},"gpt-6.1-sol":{"draws":1,"losses":37,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":3,"wins":18},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":34},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":6,"losses":14,"wins":20},"meta/muse-spark-1.3":{"draws":3,"losses":17,"wins":22},"meta/muse-wonder":{"draws":6,"losses":19,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":17},"mistralai/mistral-large-4-0":{"draws":2,"losses":12,"wins":12},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":6,"losses":18,"wins":16},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":5,"wins":27},"o3":{"draws":5,"losses":13,"wins":46},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":8,"losses":8,"wins":24},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":1,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":17},"qwen/qwen3.8-27b":{"draws":6,"losses":9,"wins":15},"qwen/qwen3.8-flash":{"draws":5,"losses":8,"wins":15},"qwen/qwen3.8-max":{"draws":6,"losses":18,"wins":18},"qwen/qwen3.8-max-0902":{"draws":6,"losses":18,"wins":18},"stealth/ox-alpha":{"draws":31,"losses":56,"wins":55},"stealth/space-bunny-alpha":{"draws":9,"losses":8,"wins":17},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":25},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":6,"losses":11,"wins":11},"thinkingmachines/inkling":{"draws":13,"losses":5,"wins":40},"thinkingmachines/inkling-small":{"draws":10,"losses":3,"wins":29},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":9,"losses":17,"wins":16},"x-ai/grok-4.6":{"draws":8,"losses":22,"wins":12},"x-ai/grok-4.7":{"draws":4,"losses":19,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":11,"losses":7,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":13,"wins":12},"z-ai/glm-5.2":{"draws":18,"losses":20,"wins":46},"z-ai/glm-5.3":{"draws":4,"losses":29,"wins":7},"z-ai/glm-5.3-flash":{"draws":2,"losses":20,"wins":20},"z-ai/glm-5.3-flashx":{"draws":5,"losses":18,"wins":19}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":17,"wins":7},"claude-fable-5":{"draws":9,"losses":27,"wins":0},"claude-fable-5-1":{"draws":2,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":24,"wins":2},"claude-opus-4-5":{"draws":18,"losses":37,"wins":3},"claude-opus-4-8":{"draws":6,"losses":25,"wins":1},"claude-opus-5":{"draws":10,"losses":43,"wins":5},"claude-opus-5-5":{"draws":5,"losses":31,"wins":0},"claude-sonnet-5":{"draws":10,"losses":23,"wins":3},"claude-sonnet-5-5":{"draws":7,"losses":21,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":13,"losses":26,"wins":13},"deepseek/deepseek-v4-pro":{"draws":13,"losses":21,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":25,"wins":1},"fireworks/ember-1":{"draws":8,"losses":27,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":21,"wins":7},"google/gemini-3.1-flash-lite":{"draws":6,"losses":11,"wins":9},"google/gemini-3.5-flash":{"draws":7,"losses":36,"wins":3},"google/gemini-3.5-flash-lite":{"draws":16,"losses":32,"wins":18},"google/gemini-3.6-flash":{"draws":14,"losses":54,"wins":4},"google/gemini-3.8-flash":{"draws":9,"losses":27,"wins":0},"google/gemma-4-31b-it":{"draws":5,"losses":8,"wins":7},"gpt-4.1":{"draws":4,"losses":7,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":23,"wins":2},"gpt-5.4":{"draws":9,"losses":24,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":11,"wins":5},"gpt-5.4-nano":{"draws":4,"losses":20,"wins":10},"gpt-5.5":{"draws":13,"losses":18,"wins":3},"gpt-5.6-luna":{"draws":9,"losses":21,"wins":6},"gpt-5.6-sol":{"draws":3,"losses":32,"wins":1},"gpt-5.6-terra":{"draws":9,"losses":22,"wins":3},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":10,"losses":24,"wins":2},"gpt-6-sol":{"draws":4,"losses":31,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":8,"wins":10},"inclusionai/ling-3.0-flash":{"draws":9,"losses":5,"wins":10},"meituan/longcat-2.0":{"draws":10,"losses":23,"wins":7},"meta/muse-glimmer-30b":{"draws":9,"losses":17,"wins":6},"meta/muse-spark-1.2":{"draws":9,"losses":21,"wins":4},"meta/muse-spark-1.3":{"draws":4,"losses":31,"wins":1},"meta/muse-wonder":{"draws":8,"losses":27,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":8},"mistralai/mistral-large-4-0":{"draws":7,"losses":13,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":5,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":22,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":16,"wins":6},"o3":{"draws":5,"losses":46,"wins":3},"openai/gpt-oss-120b":{"draws":8,"losses":14,"wins":8},"poolside/laguna-s-2.1":{"draws":10,"losses":16,"wins":6},"qwen/qwen3.7-max":{"draws":3,"losses":15,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":9,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":28,"wins":1},"qwen/qwen3.8-27b":{"draws":6,"losses":19,"wins":3},"qwen/qwen3.8-flash":{"draws":8,"losses":12,"wins":4},"qwen/qwen3.8-max":{"draws":8,"losses":28,"wins":0},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":4},"stealth/ox-alpha":{"draws":34,"losses":77,"wins":15},"stealth/space-bunny-alpha":{"draws":10,"losses":15,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":17,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":4},"tencent/hy4-preview":{"draws":7,"losses":25,"wins":4},"thinkingmachines/inkling":{"draws":13,"losses":19,"wins":8},"thinkingmachines/inkling-small":{"draws":11,"losses":13,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":27,"wins":1},"x-ai/grok-4.6":{"draws":11,"losses":22,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":14,"losses":29,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":15,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":18,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":20,"wins":2},"z-ai/glm-5.2":{"draws":22,"losses":43,"wins":7},"z-ai/glm-5.3":{"draws":2,"losses":30,"wins":2},"z-ai/glm-5.3-flash":{"draws":2,"losses":31,"wins":3},"z-ai/glm-5.3-flashx":{"draws":6,"losses":29,"wins":1}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":16,"wins":12},"claude-fable-5":{"draws":12,"losses":32,"wins":4},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":33,"wins":3},"claude-opus-4-5":{"draws":23,"losses":47,"wins":8},"claude-opus-4-8":{"draws":14,"losses":26,"wins":4},"claude-opus-5":{"draws":13,"losses":63,"wins":6},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":16,"losses":25,"wins":7},"claude-sonnet-5-5":{"draws":11,"losses":31,"wins":6},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":33,"losses":25,"wins":14},"deepseek/deepseek-v4-pro":{"draws":11,"losses":27,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":22,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":25,"wins":9},"fireworks/ember-1":{"draws":17,"losses":26,"wins":5},"gemini-3.1-pro-preview":{"draws":14,"losses":28,"wins":6},"google/gemini-3.1-flash-lite":{"draws":10,"losses":11,"wins":11},"google/gemini-3.5-flash":{"draws":16,"losses":32,"wins":12},"google/gemini-3.5-flash-lite":{"draws":32,"losses":37,"wins":15},"google/gemini-3.6-flash":{"draws":25,"losses":52,"wins":15},"google/gemini-3.8-flash":{"draws":15,"losses":25,"wins":8},"google/gemma-4-31b-it":{"draws":13,"losses":10,"wins":5},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":15,"losses":19,"wins":8},"gpt-5.4":{"draws":16,"losses":27,"wins":3},"gpt-5.4-mini":{"draws":14,"losses":10,"wins":8},"gpt-5.4-nano":{"draws":13,"losses":25,"wins":10},"gpt-5.5":{"draws":14,"losses":20,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":18,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":37,"wins":5},"gpt-5.6-terra":{"draws":15,"losses":22,"wins":9},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":12,"losses":28,"wins":8},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":47,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":9,"wins":10},"inclusionai/ling-3.0-flash":{"draws":17,"losses":6,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":21,"wins":16},"meta/muse-glimmer-30b":{"draws":18,"losses":16,"wins":8},"meta/muse-spark-1.2":{"draws":10,"losses":26,"wins":10},"meta/muse-spark-1.3":{"draws":8,"losses":35,"wins":5},"meta/muse-wonder":{"draws":10,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":14,"wins":4},"mistralai/mistral-large-4-0":{"draws":10,"losses":15,"wins":5},"mistralai/mistral-medium-3-5":{"draws":12,"losses":7,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":14,"losses":25,"wins":7},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":17,"wins":6},"o3":{"draws":14,"losses":42,"wins":10},"openai/gpt-oss-120b":{"draws":14,"losses":20,"wins":8},"poolside/laguna-s-2.1":{"draws":18,"losses":22,"wins":6},"qwen/qwen3.7-max":{"draws":12,"losses":11,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":31,"wins":4},"qwen/qwen3.8-27b":{"draws":9,"losses":21,"wins":4},"qwen/qwen3.8-flash":{"draws":12,"losses":14,"wins":6},"qwen/qwen3.8-max":{"draws":14,"losses":26,"wins":8},"qwen/qwen3.8-max-0902":{"draws":16,"losses":26,"wins":6},"stealth/ox-alpha":{"draws":48,"losses":89,"wins":21},"stealth/space-bunny-alpha":{"draws":13,"losses":15,"wins":10},"stepfun/step-3.7-flash":{"draws":12,"losses":15,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":14,"wins":2},"tencent/hy4-preview":{"draws":14,"losses":29,"wins":3},"thinkingmachines/inkling":{"draws":21,"losses":32,"wins":11},"thinkingmachines/inkling-small":{"draws":12,"losses":12,"wins":8},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":13,"losses":30,"wins":5},"x-ai/grok-4.6":{"draws":13,"losses":30,"wins":5},"x-ai/grok-4.7":{"draws":3,"losses":39,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":6,"wins":5},"xiaomi/mimo-v2.5":{"draws":29,"losses":26,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":13,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":24,"wins":4},"z-ai/glm-5.2":{"draws":35,"losses":44,"wins":17},"z-ai/glm-5.3":{"draws":9,"losses":32,"wins":5},"z-ai/glm-5.3-flash":{"draws":10,"losses":32,"wins":6},"z-ai/glm-5.3-flashx":{"draws":11,"losses":30,"wins":7}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":7,"wins":5},"claude-fable-5":{"draws":0,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":12,"wins":0},"claude-haiku-5-5":{"draws":0,"losses":10,"wins":2},"claude-opus-4-5":{"draws":1,"losses":18,"wins":1},"claude-opus-4-8":{"draws":0,"losses":12,"wins":0},"claude-opus-5":{"draws":0,"losses":13,"wins":1},"claude-opus-5-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":1,"losses":10,"wins":1},"claude-sonnet-5-5":{"draws":0,"losses":11,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":6,"losses":11,"wins":3},"deepseek/deepseek-v4-pro":{"draws":1,"losses":9,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":12,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":10,"wins":1},"fireworks/ember-1":{"draws":0,"losses":11,"wins":1},"gemini-3.1-pro-preview":{"draws":2,"losses":7,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":12,"wins":3},"google/gemini-3.5-flash-lite":{"draws":9,"losses":10,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":20,"wins":2},"google/gemini-3.8-flash":{"draws":1,"losses":11,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":2},"gpt-4.1":{"draws":0,"losses":4,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":0,"losses":10,"wins":0},"gpt-5.4":{"draws":0,"losses":12,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":6,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":11,"wins":3},"gpt-5.5":{"draws":0,"losses":9,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":8,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":12,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":12,"wins":0},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"gpt-6-luna":{"draws":0,"losses":11,"wins":1},"gpt-6-sol":{"draws":1,"losses":9,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":12,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":2},"meta/muse-glimmer-30b":{"draws":1,"losses":3,"wins":4},"meta/muse-spark-1.2":{"draws":0,"losses":7,"wins":3},"meta/muse-spark-1.3":{"draws":2,"losses":9,"wins":1},"meta/muse-wonder":{"draws":0,"losses":12,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":2},"mistralai/mistral-large-4-0":{"draws":0,"losses":6,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":8,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":7,"wins":3},"o3":{"draws":5,"losses":16,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":2},"poolside/laguna-s-2.1":{"draws":5,"losses":1,"wins":4},"qwen/qwen3.7-max":{"draws":0,"losses":7,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":5,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":12,"wins":0},"qwen/qwen3.8-27b":{"draws":4,"losses":7,"wins":1},"qwen/qwen3.8-flash":{"draws":0,"losses":7,"wins":1},"qwen/qwen3.8-max":{"draws":1,"losses":9,"wins":2},"qwen/qwen3.8-max-0902":{"draws":0,"losses":12,"wins":0},"stealth/ox-alpha":{"draws":3,"losses":26,"wins":3},"stealth/space-bunny-alpha":{"draws":0,"losses":7,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":9,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":5,"wins":1},"tencent/hy4-preview":{"draws":2,"losses":10,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":10,"wins":3},"thinkingmachines/inkling-small":{"draws":0,"losses":7,"wins":5},"unbiased/pareto-26.10-preview":{"draws":0,"losses":4,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":0,"losses":12,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":10,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":7,"wins":1},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":0},"xiaomi/mimo-v2.5":{"draws":5,"losses":10,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":6,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":7,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":7,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":22,"wins":2},"z-ai/glm-5.3":{"draws":0,"losses":10,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":9,"wins":2},"z-ai/glm-5.3-flashx":{"draws":0,"losses":11,"wins":1}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":31},"claude-fable-5":{"draws":5,"losses":26,"wins":17},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":9,"losses":16,"wins":21},"claude-opus-4-5":{"draws":20,"losses":19,"wins":39},"claude-opus-4-8":{"draws":7,"losses":15,"wins":22},"claude-opus-5":{"draws":11,"losses":56,"wins":15},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"claude-sonnet-5":{"draws":12,"losses":11,"wins":25},"claude-sonnet-5-5":{"draws":9,"losses":22,"wins":17},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":14,"losses":8,"wins":50},"deepseek/deepseek-v4-pro":{"draws":8,"losses":12,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":13,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":14,"wins":21},"fireworks/ember-1":{"draws":12,"losses":15,"wins":21},"gemini-3.1-pro-preview":{"draws":10,"losses":11,"wins":27},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":23},"google/gemini-3.5-flash":{"draws":10,"losses":21,"wins":29},"google/gemini-3.5-flash-lite":{"draws":18,"losses":11,"wins":55},"google/gemini-3.6-flash":{"draws":24,"losses":27,"wins":41},"google/gemini-3.8-flash":{"draws":8,"losses":15,"wins":25},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":18},"gpt-4.1":{"draws":5,"losses":2,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":7,"wins":27},"gpt-5.4":{"draws":14,"losses":17,"wins":15},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":18},"gpt-5.4-nano":{"draws":10,"losses":11,"wins":27},"gpt-5.5":{"draws":13,"losses":11,"wins":20},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":24},"gpt-5.6-sol":{"draws":9,"losses":27,"wins":12},"gpt-5.6-terra":{"draws":14,"losses":7,"wins":25},"gpt-6-astra":{"draws":4,"losses":40,"wins":4},"gpt-6-luna":{"draws":11,"losses":13,"wins":24},"gpt-6-sol":{"draws":8,"losses":32,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":40,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":21},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":8,"wins":36},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":30},"meta/muse-spark-1.2":{"draws":11,"losses":10,"wins":25},"meta/muse-spark-1.3":{"draws":10,"losses":17,"wins":21},"meta/muse-wonder":{"draws":9,"losses":25,"wins":14},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":23},"mistralai/mistral-large-4-0":{"draws":6,"losses":9,"wins":15},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":14,"losses":11,"wins":21},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":2,"wins":33},"o3":{"draws":7,"losses":16,"wins":43},"openai/gpt-oss-120b":{"draws":11,"losses":3,"wins":28},"poolside/laguna-s-2.1":{"draws":11,"losses":6,"wins":29},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":13},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":17,"wins":21},"qwen/qwen3.8-27b":{"draws":4,"losses":7,"wins":23},"qwen/qwen3.8-flash":{"draws":12,"losses":6,"wins":14},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":25},"qwen/qwen3.8-max-0902":{"draws":10,"losses":15,"wins":23},"stealth/ox-alpha":{"draws":31,"losses":46,"wins":81},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":3,"losses":7,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":18},"tencent/hy4-preview":{"draws":11,"losses":13,"wins":22},"thinkingmachines/inkling":{"draws":19,"losses":5,"wins":40},"thinkingmachines/inkling-small":{"draws":15,"losses":5,"wins":28},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":9,"losses":8,"wins":15},"x-ai/grok-4.6":{"draws":16,"losses":16,"wins":16},"x-ai/grok-4.7":{"draws":7,"losses":24,"wins":11},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":21,"losses":5,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":12,"wins":14},"z-ai/glm-5.2":{"draws":26,"losses":14,"wins":56},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":8,"losses":16,"wins":24},"z-ai/glm-5.3-flashx":{"draws":9,"losses":16,"wins":23}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":2,"wins":37},"claude-fable-5":{"draws":8,"losses":16,"wins":24},"claude-fable-5-1":{"draws":4,"losses":44,"wins":6},"claude-haiku-5-5":{"draws":7,"losses":10,"wins":29},"claude-opus-4-5":{"draws":15,"losses":10,"wins":53},"claude-opus-4-8":{"draws":11,"losses":9,"wins":24},"claude-opus-5":{"draws":11,"losses":49,"wins":22},"claude-opus-5-5":{"draws":8,"losses":37,"wins":7},"claude-sonnet-5":{"draws":10,"losses":7,"wins":31},"claude-sonnet-5-5":{"draws":7,"losses":15,"wins":26},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":11,"losses":4,"wins":57},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":3,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":11,"wins":25},"fireworks/ember-1":{"draws":8,"losses":7,"wins":33},"gemini-3.1-pro-preview":{"draws":11,"losses":7,"wins":30},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":11,"losses":7,"wins":42},"google/gemini-3.5-flash-lite":{"draws":11,"losses":5,"wins":68},"google/gemini-3.6-flash":{"draws":20,"losses":16,"wins":56},"google/gemini-3.8-flash":{"draws":11,"losses":13,"wins":24},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":24},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":3,"wins":29},"gpt-5.4":{"draws":12,"losses":11,"wins":23},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":23},"gpt-5.4-nano":{"draws":4,"losses":0,"wins":44},"gpt-5.5":{"draws":8,"losses":13,"wins":23},"gpt-5.6-luna":{"draws":8,"losses":5,"wins":35},"gpt-5.6-sol":{"draws":10,"losses":16,"wins":22},"gpt-5.6-terra":{"draws":13,"losses":6,"wins":27},"gpt-6-astra":{"draws":2,"losses":40,"wins":6},"gpt-6-luna":{"draws":8,"losses":2,"wins":38},"gpt-6-sol":{"draws":9,"losses":25,"wins":14},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":26},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":27},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":4,"wins":40},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":35},"meta/muse-spark-1.2":{"draws":7,"losses":6,"wins":33},"meta/muse-spark-1.3":{"draws":8,"losses":12,"wins":28},"meta/muse-wonder":{"draws":10,"losses":16,"wins":22},"minimax/minimax-m3":{"draws":7,"losses":0,"wins":19},"mistralai/mistral-large-4-0":{"draws":6,"losses":6,"wins":18},"mistralai/mistral-medium-3-5":{"draws":7,"losses":1,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":10,"losses":10,"wins":26},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":0,"wins":32},"o3":{"draws":9,"losses":3,"wins":54},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":34},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":40},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":20},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":9,"wins":29},"qwen/qwen3.8-27b":{"draws":7,"losses":3,"wins":24},"qwen/qwen3.8-flash":{"draws":9,"losses":4,"wins":19},"qwen/qwen3.8-max":{"draws":12,"losses":6,"wins":30},"qwen/qwen3.8-max-0902":{"draws":11,"losses":8,"wins":29},"stealth/ox-alpha":{"draws":30,"losses":29,"wins":99},"stealth/space-bunny-alpha":{"draws":11,"losses":3,"wins":24},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":28},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":7,"losses":1,"wins":18},"tencent/hy4-preview":{"draws":8,"losses":7,"wins":31},"thinkingmachines/inkling":{"draws":19,"losses":3,"wins":42},"thinkingmachines/inkling-small":{"draws":9,"losses":1,"wins":38},"unbiased/pareto-26.10-preview":{"draws":2,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":14,"losses":9,"wins":25},"x-ai/grok-4.6":{"draws":12,"losses":7,"wins":13},"x-ai/grok-4.7":{"draws":6,"losses":19,"wins":17},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":21,"losses":1,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":1,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":9,"wins":16},"z-ai/glm-5.2":{"draws":20,"losses":8,"wins":68},"z-ai/glm-5.3":{"draws":8,"losses":20,"wins":18},"z-ai/glm-5.3-flash":{"draws":12,"losses":11,"wins":25},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":30}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":36},"claude-fable-5":{"draws":1,"losses":5,"wins":36},"claude-fable-5-1":{"draws":2,"losses":30,"wins":16},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":36},"claude-opus-4-5":{"draws":3,"losses":3,"wins":62},"claude-opus-4-8":{"draws":2,"losses":5,"wins":31},"claude-opus-5":{"draws":9,"losses":26,"wins":45},"claude-opus-5-5":{"draws":6,"losses":28,"wins":12},"claude-sonnet-5":{"draws":3,"losses":4,"wins":35},"claude-sonnet-5-5":{"draws":3,"losses":15,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":55},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":3,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":10,"wins":29},"fireworks/ember-1":{"draws":2,"losses":5,"wins":35},"gemini-3.1-pro-preview":{"draws":5,"losses":5,"wins":32},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":1,"losses":7,"wins":44},"google/gemini-3.5-flash-lite":{"draws":6,"losses":7,"wins":59},"google/gemini-3.6-flash":{"draws":3,"losses":6,"wins":71},"google/gemini-3.8-flash":{"draws":0,"losses":4,"wins":38},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":22},"gpt-4.1":{"draws":1,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":1,"losses":0,"wins":37},"gpt-5.4":{"draws":2,"losses":5,"wins":33},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":24},"gpt-5.4-nano":{"draws":5,"losses":1,"wins":34},"gpt-5.5":{"draws":0,"losses":8,"wins":32},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":36},"gpt-5.6-sol":{"draws":5,"losses":8,"wins":29},"gpt-5.6-terra":{"draws":1,"losses":4,"wins":35},"gpt-6-astra":{"draws":5,"losses":28,"wins":9},"gpt-6-luna":{"draws":3,"losses":1,"wins":38},"gpt-6-sol":{"draws":3,"losses":15,"wins":24},"gpt-6.1-sol":{"draws":2,"losses":25,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":1,"wins":25},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":4,"wins":40},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":40},"meta/muse-spark-1.2":{"draws":1,"losses":5,"wins":36},"meta/muse-spark-1.3":{"draws":2,"losses":7,"wins":33},"meta/muse-wonder":{"draws":1,"losses":10,"wins":31},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":23},"mistralai/mistral-large-4-0":{"draws":4,"losses":3,"wins":21},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":1,"losses":6,"wins":35},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":34},"o3":{"draws":3,"losses":2,"wins":49},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":36},"poolside/laguna-s-2.1":{"draws":1,"losses":2,"wins":39},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":19},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":6,"wins":36},"qwen/qwen3.8-27b":{"draws":2,"losses":4,"wins":22},"qwen/qwen3.8-flash":{"draws":1,"losses":3,"wins":24},"qwen/qwen3.8-max":{"draws":2,"losses":5,"wins":35},"qwen/qwen3.8-max-0902":{"draws":3,"losses":4,"wins":35},"stealth/ox-alpha":{"draws":14,"losses":13,"wins":115},"stealth/space-bunny-alpha":{"draws":2,"losses":2,"wins":30},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":22},"tencent/hy4-preview":{"draws":1,"losses":8,"wins":31},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":51},"thinkingmachines/inkling-small":{"draws":2,"losses":1,"wins":39},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":7},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":34},"x-ai/grok-4.6":{"draws":2,"losses":6,"wins":34},"x-ai/grok-4.7":{"draws":1,"losses":10,"wins":13},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":5,"wins":21},"z-ai/glm-5.2":{"draws":3,"losses":6,"wins":75},"z-ai/glm-5.3":{"draws":2,"losses":9,"wins":29},"z-ai/glm-5.3-flash":{"draws":4,"losses":10,"wins":28},"z-ai/glm-5.3-flashx":{"draws":5,"losses":4,"wins":33}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":18,"wins":10},"claude-fable-5":{"draws":11,"losses":31,"wins":6},"claude-fable-5-1":{"draws":0,"losses":53,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":29,"wins":4},"claude-opus-4-5":{"draws":27,"losses":40,"wins":11},"claude-opus-4-8":{"draws":10,"losses":28,"wins":6},"claude-opus-5":{"draws":13,"losses":65,"wins":4},"claude-opus-5-5":{"draws":1,"losses":51,"wins":0},"claude-sonnet-5":{"draws":19,"losses":26,"wins":3},"claude-sonnet-5-5":{"draws":9,"losses":33,"wins":6},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":27,"losses":27,"wins":18},"deepseek/deepseek-v4-pro":{"draws":18,"losses":17,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":21,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":27,"wins":5},"fireworks/ember-1":{"draws":18,"losses":24,"wins":6},"gemini-3.1-pro-preview":{"draws":17,"losses":19,"wins":12},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":19,"losses":31,"wins":10},"google/gemini-3.5-flash-lite":{"draws":34,"losses":26,"wins":24},"google/gemini-3.6-flash":{"draws":30,"losses":57,"wins":5},"google/gemini-3.8-flash":{"draws":13,"losses":32,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":8,"wins":9},"gpt-4.1":{"draws":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":18,"wins":9},"gpt-5.4":{"draws":12,"losses":28,"wins":6},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":11,"losses":23,"wins":14},"gpt-5.5":{"draws":23,"losses":14,"wins":7},"gpt-5.6-luna":{"draws":19,"losses":18,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":4},"gpt-5.6-terra":{"draws":17,"losses":24,"wins":5},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":20,"losses":24,"wins":4},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":8,"wins":8},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":16,"wins":17},"meta/muse-glimmer-30b":{"draws":18,"losses":10,"wins":14},"meta/muse-spark-1.2":{"draws":10,"losses":28,"wins":8},"meta/muse-spark-1.3":{"draws":12,"losses":28,"wins":8},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":8,"wins":10},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":14,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":17,"losses":25,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":9,"wins":12},"o3":{"draws":16,"losses":37,"wins":13},"openai/gpt-oss-120b":{"draws":17,"losses":9,"wins":16},"poolside/laguna-s-2.1":{"draws":21,"losses":11,"wins":14},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":7,"losses":9,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":25,"wins":6},"qwen/qwen3.8-27b":{"draws":13,"losses":20,"wins":1},"qwen/qwen3.8-flash":{"draws":17,"losses":11,"wins":4},"qwen/qwen3.8-max":{"draws":19,"losses":20,"wins":9},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"stealth/ox-alpha":{"draws":40,"losses":101,"wins":17},"stealth/space-bunny-alpha":{"draws":12,"losses":16,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":15,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":12,"wins":5},"tencent/hy4-preview":{"draws":17,"losses":24,"wins":5},"thinkingmachines/inkling":{"draws":22,"losses":16,"wins":26},"thinkingmachines/inkling-small":{"draws":20,"losses":14,"wins":14},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":30,"wins":5},"x-ai/grok-4.6":{"draws":15,"losses":27,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"xiaomi/mimo-v2.5":{"draws":31,"losses":20,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":12,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":21,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":42,"losses":36,"wins":18},"z-ai/glm-5.3":{"draws":11,"losses":34,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":28,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":30,"wins":6}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":35,"wins":13},"claude-fable-5":{"draws":19,"losses":68,"wins":3},"claude-fable-5-1":{"draws":6,"losses":91,"wins":3},"claude-haiku-5-5":{"draws":28,"losses":52,"wins":10},"claude-opus-4-5":{"draws":57,"losses":73,"wins":20},"claude-opus-4-8":{"draws":33,"losses":51,"wins":6},"claude-opus-5":{"draws":24,"losses":122,"wins":16},"claude-opus-5-5":{"draws":5,"losses":89,"wins":4},"claude-sonnet-5":{"draws":37,"losses":38,"wins":15},"claude-sonnet-5-5":{"draws":23,"losses":55,"wins":12},"cohere/north-mini-code":{"draws":9,"losses":13,"wins":10},"deepseek/deepseek-v4-flash":{"draws":53,"losses":38,"wins":43},"deepseek/deepseek-v4-pro":{"draws":30,"losses":40,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":40,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":49,"wins":10},"fireworks/ember-1":{"draws":34,"losses":48,"wins":8},"gemini-3.1-pro-preview":{"draws":35,"losses":37,"wins":18},"google/gemini-3.1-flash-lite":{"draws":21,"losses":13,"wins":30},"google/gemini-3.5-flash":{"draws":37,"losses":58,"wins":19},"google/gemini-3.5-flash-lite":{"draws":55,"losses":48,"wins":53},"google/gemini-3.6-flash":{"draws":59,"losses":100,"wins":11},"google/gemini-3.8-flash":{"draws":25,"losses":58,"wins":7},"google/gemma-4-31b-it":{"draws":28,"losses":15,"wins":13},"gpt-4.1":{"draws":14,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":25,"losses":35,"wins":16},"gpt-5.4":{"draws":26,"losses":48,"wins":10},"gpt-5.4-mini":{"draws":25,"losses":23,"wins":12},"gpt-5.4-nano":{"draws":24,"losses":38,"wins":30},"gpt-5.5":{"draws":32,"losses":45,"wins":5},"gpt-5.6-luna":{"draws":39,"losses":33,"wins":18},"gpt-5.6-sol":{"draws":17,"losses":72,"wins":1},"gpt-5.6-terra":{"draws":32,"losses":48,"wins":6},"gpt-6-astra":{"draws":4,"losses":85,"wins":1},"gpt-6-luna":{"draws":36,"losses":41,"wins":13},"gpt-6-sol":{"draws":16,"losses":69,"wins":5},"gpt-6.1-sol":{"draws":8,"losses":80,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":36,"losses":10,"wins":24},"inclusionai/ling-3.0-flash":{"draws":29,"losses":13,"wins":20},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":32,"losses":30,"wins":32},"meta/muse-glimmer-30b":{"draws":31,"losses":27,"wins":22},"meta/muse-spark-1.2":{"draws":29,"losses":51,"wins":8},"meta/muse-spark-1.3":{"draws":26,"losses":56,"wins":8},"meta/muse-wonder":{"draws":26,"losses":60,"wins":4},"minimax/minimax-m3":{"draws":21,"losses":16,"wins":15},"mistralai/mistral-large-4-0":{"draws":24,"losses":27,"wins":7},"mistralai/mistral-medium-3-5":{"draws":27,"losses":8,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":16,"wins":2},"moonshotai/kimi-k3":{"draws":32,"losses":43,"wins":13},"nex-agi/nex-n2-pro":{"draws":11,"losses":14,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":32,"wins":16},"o3":{"draws":22,"losses":79,"wins":17},"openai/gpt-oss-120b":{"draws":31,"losses":24,"wins":23},"poolside/laguna-s-2.1":{"draws":23,"losses":30,"wins":27},"qwen/qwen3.7-max":{"draws":22,"losses":25,"wins":7},"qwen/qwen3.7-plus":{"draws":21,"losses":17,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":44,"wins":7},"qwen/qwen3.8-27b":{"draws":21,"losses":34,"wins":7},"qwen/qwen3.8-flash":{"draws":24,"losses":22,"wins":14},"qwen/qwen3.8-max":{"draws":36,"losses":44,"wins":10},"qwen/qwen3.8-max-0902":{"draws":31,"losses":46,"wins":13},"stealth/ox-alpha":{"draws":75,"losses":144,"wins":35},"stealth/space-bunny-alpha":{"draws":32,"losses":29,"wins":13},"stepfun/step-3.7-flash":{"draws":17,"losses":22,"wins":19},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":24,"losses":17,"wins":13},"tencent/hy4-preview":{"draws":27,"losses":47,"wins":10},"thinkingmachines/inkling":{"draws":43,"losses":31,"wins":42},"thinkingmachines/inkling-small":{"draws":37,"losses":29,"wins":24},"unbiased/pareto-26.10-preview":{"draws":0,"losses":30,"wins":0},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":3},"x-ai/grok-4.5":{"draws":28,"losses":58,"wins":4},"x-ai/grok-4.6":{"draws":26,"losses":57,"wins":7},"x-ai/grok-4.7":{"draws":10,"losses":66,"wins":6},"x-ai/grok-build-0.1":{"draws":15,"losses":8,"wins":7},"xiaomi/mimo-v2.5":{"draws":59,"losses":35,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":20,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":33,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":38,"wins":4},"z-ai/glm-5.2":{"draws":68,"losses":78,"wins":34},"z-ai/glm-5.3":{"draws":24,"losses":61,"wins":1},"z-ai/glm-5.3-flash":{"draws":27,"losses":52,"wins":11},"z-ai/glm-5.3-flashx":{"draws":35,"losses":50,"wins":5}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":10,"wins":16},"claude-fable-5":{"draws":3,"losses":31,"wins":2},"claude-fable-5-1":{"draws":2,"losses":38,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":19,"wins":10},"claude-opus-4-5":{"draws":14,"losses":24,"wins":22},"claude-opus-4-8":{"draws":7,"losses":20,"wins":9},"claude-opus-5":{"draws":8,"losses":46,"wins":4},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":3,"losses":18,"wins":15},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":15,"losses":12,"wins":27},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":15,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":12,"wins":15},"fireworks/ember-1":{"draws":10,"losses":14,"wins":12},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":15},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":23},"google/gemini-3.5-flash":{"draws":9,"losses":23,"wins":16},"google/gemini-3.5-flash-lite":{"draws":20,"losses":16,"wins":30},"google/gemini-3.6-flash":{"draws":16,"losses":37,"wins":17},"google/gemini-3.8-flash":{"draws":6,"losses":23,"wins":7},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":12},"gpt-4.1":{"draws":3,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":14,"wins":9},"gpt-5.4":{"draws":5,"losses":23,"wins":8},"gpt-5.4-mini":{"draws":5,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":5,"losses":13,"wins":22},"gpt-5.5":{"draws":8,"losses":19,"wins":7},"gpt-5.6-luna":{"draws":9,"losses":12,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":8},"gpt-5.6-terra":{"draws":9,"losses":17,"wins":8},"gpt-6-astra":{"draws":1,"losses":34,"wins":1},"gpt-6-luna":{"draws":8,"losses":16,"wins":12},"gpt-6-sol":{"draws":4,"losses":29,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":32,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":4,"wins":15},"inclusionai/ling-3.0-flash":{"draws":9,"losses":2,"wins":15},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":24},"meta/muse-glimmer-30b":{"draws":11,"losses":7,"wins":14},"meta/muse-spark-1.2":{"draws":2,"losses":18,"wins":14},"meta/muse-spark-1.3":{"draws":5,"losses":20,"wins":11},"meta/muse-wonder":{"draws":3,"losses":25,"wins":8},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":10},"mistralai/mistral-large-4-0":{"draws":4,"losses":12,"wins":6},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":13,"wins":14},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":6,"wins":19},"o3":{"draws":7,"losses":22,"wins":31},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":9,"losses":7,"wins":16},"qwen/qwen3.7-max":{"draws":6,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":17,"wins":13},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":14},"qwen/qwen3.8-flash":{"draws":5,"losses":11,"wins":8},"qwen/qwen3.8-max":{"draws":1,"losses":21,"wins":14},"qwen/qwen3.8-max-0902":{"draws":5,"losses":19,"wins":12},"stealth/ox-alpha":{"draws":15,"losses":52,"wins":35},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":11},"stepfun/step-3.7-flash":{"draws":3,"losses":5,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":7},"tencent/hy4-preview":{"draws":7,"losses":20,"wins":9},"thinkingmachines/inkling":{"draws":8,"losses":10,"wins":30},"thinkingmachines/inkling-small":{"draws":10,"losses":9,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":5,"losses":15,"wins":16},"x-ai/grok-4.6":{"draws":7,"losses":21,"wins":8},"x-ai/grok-4.7":{"draws":0,"losses":26,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":18,"losses":6,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":11,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":12,"wins":11},"z-ai/glm-5.2":{"draws":20,"losses":23,"wins":29},"z-ai/glm-5.3":{"draws":6,"losses":24,"wins":4},"z-ai/glm-5.3-flash":{"draws":3,"losses":23,"wins":10},"z-ai/glm-5.3-flashx":{"draws":12,"losses":13,"wins":11}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":9,"wins":32},"claude-fable-5":{"draws":6,"losses":24,"wins":18},"claude-fable-5-1":{"draws":4,"losses":42,"wins":8},"claude-haiku-5-5":{"draws":9,"losses":20,"wins":17},"claude-opus-4-5":{"draws":11,"losses":18,"wins":49},"claude-opus-4-8":{"draws":6,"losses":12,"wins":26},"claude-opus-5":{"draws":8,"losses":63,"wins":11},"claude-opus-5-5":{"draws":5,"losses":45,"wins":2},"claude-sonnet-5":{"draws":6,"losses":10,"wins":32},"claude-sonnet-5-5":{"draws":2,"losses":23,"wins":23},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":12,"losses":12,"wins":48},"deepseek/deepseek-v4-pro":{"draws":9,"losses":10,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":22,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":18,"wins":21},"fireworks/ember-1":{"draws":5,"losses":18,"wins":25},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":27},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":9,"losses":18,"wins":33},"google/gemini-3.5-flash-lite":{"draws":14,"losses":10,"wins":60},"google/gemini-3.6-flash":{"draws":9,"losses":35,"wins":48},"google/gemini-3.8-flash":{"draws":8,"losses":19,"wins":21},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":20},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":6,"losses":11,"wins":25},"gpt-5.4":{"draws":7,"losses":19,"wins":20},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":22},"gpt-5.4-nano":{"draws":9,"losses":10,"wins":29},"gpt-5.5":{"draws":6,"losses":19,"wins":19},"gpt-5.6-luna":{"draws":10,"losses":10,"wins":28},"gpt-5.6-sol":{"draws":2,"losses":31,"wins":15},"gpt-5.6-terra":{"draws":7,"losses":16,"wins":23},"gpt-6-astra":{"draws":2,"losses":42,"wins":4},"gpt-6-luna":{"draws":8,"losses":13,"wins":27},"gpt-6-sol":{"draws":6,"losses":31,"wins":11},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":7,"losses":2,"wins":25},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":25},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":10,"wins":31},"meta/muse-glimmer-30b":{"draws":9,"losses":7,"wins":26},"meta/muse-spark-1.2":{"draws":6,"losses":22,"wins":18},"meta/muse-spark-1.3":{"draws":8,"losses":21,"wins":19},"meta/muse-wonder":{"draws":1,"losses":31,"wins":16},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":17},"mistralai/mistral-large-4-0":{"draws":9,"losses":7,"wins":14},"mistralai/mistral-medium-3-5":{"draws":5,"losses":5,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":13,"wins":24},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":7,"wins":26},"o3":{"draws":9,"losses":15,"wins":42},"openai/gpt-oss-120b":{"draws":8,"losses":3,"wins":31},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":32},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":16,"wins":24},"qwen/qwen3.8-27b":{"draws":3,"losses":11,"wins":20},"qwen/qwen3.8-flash":{"draws":9,"losses":10,"wins":13},"qwen/qwen3.8-max":{"draws":6,"losses":17,"wins":25},"qwen/qwen3.8-max-0902":{"draws":8,"losses":15,"wins":25},"stealth/ox-alpha":{"draws":22,"losses":61,"wins":75},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":30},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":6,"wins":18},"tencent/hy4-preview":{"draws":6,"losses":18,"wins":22},"thinkingmachines/inkling":{"draws":13,"losses":9,"wins":42},"thinkingmachines/inkling-small":{"draws":13,"losses":1,"wins":34},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":3,"losses":19,"wins":26},"x-ai/grok-4.6":{"draws":8,"losses":19,"wins":21},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":12,"losses":11,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":14,"wins":12},"z-ai/glm-5.2":{"draws":12,"losses":20,"wins":64},"z-ai/glm-5.3":{"draws":7,"losses":28,"wins":11},"z-ai/glm-5.3-flash":{"draws":8,"losses":17,"wins":23},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":24}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":6,"wins":38},"claude-fable-5":{"draws":2,"losses":15,"wins":31},"claude-fable-5-1":{"draws":9,"losses":38,"wins":7},"claude-haiku-5-5":{"draws":4,"losses":11,"wins":31},"claude-opus-4-5":{"draws":11,"losses":8,"wins":59},"claude-opus-4-8":{"draws":2,"losses":13,"wins":29},"claude-opus-5":{"draws":16,"losses":39,"wins":27},"claude-opus-5-5":{"draws":4,"losses":39,"wins":9},"claude-sonnet-5":{"draws":0,"losses":9,"wins":39},"claude-sonnet-5-5":{"draws":4,"losses":18,"wins":26},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":16},"deepseek/deepseek-v4-flash":{"draws":3,"losses":9,"wins":60},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":15,"wins":26},"fireworks/ember-1":{"draws":7,"losses":11,"wins":30},"gemini-3.1-pro-preview":{"draws":2,"losses":9,"wins":37},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":30},"google/gemini-3.5-flash":{"draws":9,"losses":11,"wins":40},"google/gemini-3.5-flash-lite":{"draws":0,"losses":12,"wins":72},"google/gemini-3.6-flash":{"draws":10,"losses":18,"wins":64},"google/gemini-3.8-flash":{"draws":7,"losses":8,"wins":33},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":26},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":8,"wins":32},"gpt-5.4":{"draws":5,"losses":14,"wins":27},"gpt-5.4-mini":{"draws":2,"losses":5,"wins":25},"gpt-5.4-nano":{"draws":0,"losses":8,"wins":40},"gpt-5.5":{"draws":8,"losses":10,"wins":26},"gpt-5.6-luna":{"draws":3,"losses":5,"wins":40},"gpt-5.6-sol":{"draws":9,"losses":14,"wins":25},"gpt-5.6-terra":{"draws":9,"losses":7,"wins":30},"gpt-6-astra":{"draws":5,"losses":37,"wins":6},"gpt-6-luna":{"draws":9,"losses":10,"wins":29},"gpt-6-sol":{"draws":8,"losses":21,"wins":19},"gpt-6.1-sol":{"draws":8,"losses":27,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":30},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":7,"wins":43},"meta/muse-glimmer-30b":{"draws":0,"losses":7,"wins":35},"meta/muse-spark-1.2":{"draws":2,"losses":9,"wins":35},"meta/muse-spark-1.3":{"draws":5,"losses":9,"wins":34},"meta/muse-wonder":{"draws":9,"losses":15,"wins":24},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":22},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":19},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":31},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":5,"wins":32},"o3":{"draws":1,"losses":8,"wins":57},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":38},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":40},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":13,"wins":27},"qwen/qwen3.8-27b":{"draws":2,"losses":9,"wins":23},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":24},"qwen/qwen3.8-max":{"draws":6,"losses":6,"wins":36},"qwen/qwen3.8-max-0902":{"draws":4,"losses":11,"wins":33},"stealth/ox-alpha":{"draws":14,"losses":37,"wins":107},"stealth/space-bunny-alpha":{"draws":4,"losses":7,"wins":27},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":30},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":7,"wins":18},"tencent/hy4-preview":{"draws":6,"losses":10,"wins":30},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":56},"thinkingmachines/inkling-small":{"draws":0,"losses":5,"wins":43},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":6,"losses":13,"wins":29},"x-ai/grok-4.6":{"draws":9,"losses":11,"wins":28},"x-ai/grok-4.7":{"draws":1,"losses":25,"wins":16},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":7,"losses":9,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":7,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":13},"z-ai/glm-5.2":{"draws":9,"losses":15,"wins":72},"z-ai/glm-5.3":{"draws":5,"losses":15,"wins":26},"z-ai/glm-5.3-flash":{"draws":6,"losses":10,"wins":32},"z-ai/glm-5.3-flashx":{"draws":6,"losses":12,"wins":30}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":16,"wins":44},"claude-fable-5":{"draws":20,"losses":61,"wins":15},"claude-fable-5-1":{"draws":9,"losses":96,"wins":3},"claude-haiku-5-5":{"draws":23,"losses":40,"wins":29},"claude-opus-4-5":{"draws":55,"losses":46,"wins":55},"claude-opus-4-8":{"draws":27,"losses":38,"wins":23},"claude-opus-5":{"draws":25,"losses":130,"wins":9},"claude-opus-5-5":{"draws":5,"losses":95,"wins":4},"claude-sonnet-5":{"draws":25,"losses":35,"wins":36},"claude-sonnet-5-5":{"draws":19,"losses":52,"wins":25},"cohere/north-mini-code":{"draws":14,"losses":6,"wins":16},"deepseek/deepseek-v4-flash":{"draws":56,"losses":29,"wins":59},"deepseek/deepseek-v4-pro":{"draws":34,"losses":29,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":33,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":36,"wins":23},"fireworks/ember-1":{"draws":33,"losses":40,"wins":23},"gemini-3.1-pro-preview":{"draws":32,"losses":29,"wins":35},"google/gemini-3.1-flash-lite":{"draws":19,"losses":5,"wins":40},"google/gemini-3.5-flash":{"draws":41,"losses":37,"wins":42},"google/gemini-3.5-flash-lite":{"draws":66,"losses":30,"wins":72},"google/gemini-3.6-flash":{"draws":45,"losses":75,"wins":64},"google/gemini-3.8-flash":{"draws":24,"losses":48,"wins":24},"google/gemma-4-31b-it":{"draws":25,"losses":8,"wins":23},"gpt-4.1":{"draws":13,"losses":5,"wins":14},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":4},"gpt-5":{"draws":33,"losses":24,"wins":27},"gpt-5.4":{"draws":30,"losses":37,"wins":25},"gpt-5.4-mini":{"draws":31,"losses":9,"wins":24},"gpt-5.4-nano":{"draws":29,"losses":27,"wins":40},"gpt-5.5":{"draws":37,"losses":37,"wins":14},"gpt-5.6-luna":{"draws":44,"losses":18,"wins":34},"gpt-5.6-sol":{"draws":12,"losses":60,"wins":24},"gpt-5.6-terra":{"draws":41,"losses":28,"wins":23},"gpt-6-astra":{"draws":8,"losses":82,"wins":6},"gpt-6-luna":{"draws":31,"losses":35,"wins":30},"gpt-6-sol":{"draws":12,"losses":72,"wins":12},"gpt-6.1-sol":{"draws":15,"losses":78,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":32,"losses":3,"wins":33},"inclusionai/ling-3.0-flash":{"draws":37,"losses":5,"wins":26},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":23,"wins":48},"meta/muse-glimmer-30b":{"draws":38,"losses":14,"wins":32},"meta/muse-spark-1.2":{"draws":24,"losses":45,"wins":23},"meta/muse-spark-1.3":{"draws":23,"losses":44,"wins":29},"meta/muse-wonder":{"draws":26,"losses":52,"wins":18},"minimax/minimax-m3":{"draws":14,"losses":11,"wins":27},"mistralai/mistral-large-4-0":{"draws":29,"losses":19,"wins":12},"mistralai/mistral-medium-3-5":{"draws":24,"losses":6,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":7,"wins":12},"moonshotai/kimi-k3":{"draws":35,"losses":30,"wins":27},"nex-agi/nex-n2-pro":{"draws":20,"losses":2,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":17,"wins":33},"o3":{"draws":28,"losses":47,"wins":57},"openai/gpt-oss-120b":{"draws":39,"losses":10,"wins":35},"poolside/laguna-s-2.1":{"draws":49,"losses":12,"wins":31},"qwen/qwen3.7-max":{"draws":21,"losses":11,"wins":24},"qwen/qwen3.7-plus":{"draws":16,"losses":7,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":38,"wins":26},"qwen/qwen3.8-27b":{"draws":22,"losses":19,"wins":27},"qwen/qwen3.8-flash":{"draws":21,"losses":24,"wins":19},"qwen/qwen3.8-max":{"draws":28,"losses":38,"wins":30},"qwen/qwen3.8-max-0902":{"draws":32,"losses":42,"wins":22},"stealth/ox-alpha":{"draws":85,"losses":144,"wins":87},"stealth/space-bunny-alpha":{"draws":31,"losses":19,"wins":26},"stepfun/step-3.7-flash":{"draws":22,"losses":7,"wins":39},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":17,"losses":15,"wins":20},"tencent/hy4-preview":{"draws":24,"losses":47,"wins":21},"thinkingmachines/inkling":{"draws":41,"losses":27,"wins":60},"thinkingmachines/inkling-small":{"draws":38,"losses":11,"wins":47},"unbiased/pareto-26.10-preview":{"draws":1,"losses":29,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":20},"x-ai/grok-4.5":{"draws":28,"losses":41,"wins":27},"x-ai/grok-4.6":{"draws":27,"losses":51,"wins":18},"x-ai/grok-4.7":{"draws":9,"losses":60,"wins":15},"x-ai/grok-build-0.1":{"draws":16,"losses":3,"wins":13},"xiaomi/mimo-v2.5":{"draws":57,"losses":18,"wins":73},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":10,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":22,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":31,"wins":15},"z-ai/glm-5.2":{"draws":66,"losses":38,"wins":56},"z-ai/glm-5.3":{"draws":20,"losses":54,"wins":18},"z-ai/glm-5.3-flash":{"draws":30,"losses":42,"wins":24},"z-ai/glm-5.3-flashx":{"draws":31,"losses":41,"wins":24}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":5,"wins":29},"claude-fable-5":{"draws":9,"losses":17,"wins":22},"claude-fable-5-1":{"draws":4,"losses":41,"wins":9},"claude-haiku-5-5":{"draws":9,"losses":9,"wins":28},"claude-opus-4-5":{"draws":15,"losses":7,"wins":56},"claude-opus-4-8":{"draws":6,"losses":12,"wins":26},"claude-opus-5":{"draws":15,"losses":51,"wins":16},"claude-opus-5-5":{"draws":3,"losses":36,"wins":13},"claude-sonnet-5":{"draws":6,"losses":6,"wins":36},"claude-sonnet-5-5":{"draws":7,"losses":14,"wins":27},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":15,"losses":3,"wins":54},"deepseek/deepseek-v4-pro":{"draws":5,"losses":8,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":5,"wins":35},"fireworks/ember-1":{"draws":5,"losses":11,"wins":32},"gemini-3.1-pro-preview":{"draws":8,"losses":9,"wins":31},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":6,"losses":11,"wins":43},"google/gemini-3.5-flash-lite":{"draws":11,"losses":3,"wins":70},"google/gemini-3.6-flash":{"draws":19,"losses":18,"wins":55},"google/gemini-3.8-flash":{"draws":11,"losses":9,"wins":28},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":21},"gpt-4.1":{"draws":3,"losses":2,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":8,"wins":28},"gpt-5.4":{"draws":5,"losses":12,"wins":29},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":24},"gpt-5.4-nano":{"draws":5,"losses":6,"wins":37},"gpt-5.5":{"draws":13,"losses":10,"wins":21},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":40},"gpt-5.6-sol":{"draws":9,"losses":22,"wins":17},"gpt-5.6-terra":{"draws":14,"losses":4,"wins":28},"gpt-6-astra":{"draws":7,"losses":39,"wins":2},"gpt-6-luna":{"draws":10,"losses":7,"wins":31},"gpt-6-sol":{"draws":6,"losses":23,"wins":19},"gpt-6.1-sol":{"draws":11,"losses":29,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":25},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":2,"wins":40},"meta/muse-glimmer-30b":{"draws":6,"losses":2,"wins":34},"meta/muse-spark-1.2":{"draws":6,"losses":14,"wins":26},"meta/muse-spark-1.3":{"draws":9,"losses":14,"wins":25},"meta/muse-wonder":{"draws":4,"losses":23,"wins":21},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":20},"mistralai/mistral-large-4-0":{"draws":4,"losses":6,"wins":20},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":4,"losses":17,"wins":25},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":31},"o3":{"draws":8,"losses":8,"wins":50},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":32},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":34},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":11,"wins":29},"qwen/qwen3.8-27b":{"draws":10,"losses":6,"wins":18},"qwen/qwen3.8-flash":{"draws":7,"losses":4,"wins":21},"qwen/qwen3.8-max":{"draws":10,"losses":8,"wins":30},"qwen/qwen3.8-max-0902":{"draws":9,"losses":7,"wins":32},"stealth/ox-alpha":{"draws":21,"losses":38,"wins":99},"stealth/space-bunny-alpha":{"draws":5,"losses":2,"wins":31},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":19},"tencent/hy4-preview":{"draws":5,"losses":10,"wins":31},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":47},"thinkingmachines/inkling-small":{"draws":7,"losses":0,"wins":41},"unbiased/pareto-26.10-preview":{"draws":2,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":6,"losses":13,"wins":29},"x-ai/grok-4.6":{"draws":11,"losses":14,"wins":23},"x-ai/grok-4.7":{"draws":6,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":15,"losses":1,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":6,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":15},"z-ai/glm-5.2":{"draws":17,"losses":14,"wins":65},"z-ai/glm-5.3":{"draws":9,"losses":8,"wins":13},"z-ai/glm-5.3-flash":{"draws":13,"losses":9,"wins":26},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":30}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":6,"wins":27},"claude-fable-5":{"draws":8,"losses":23,"wins":17},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":20,"losses":12,"wins":46},"claude-opus-4-8":{"draws":8,"losses":13,"wins":23},"claude-opus-5":{"draws":8,"losses":55,"wins":19},"claude-opus-5-5":{"draws":5,"losses":42,"wins":5},"claude-sonnet-5":{"draws":9,"losses":7,"wins":32},"claude-sonnet-5-5":{"draws":5,"losses":24,"wins":19},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":20,"losses":5,"wins":47},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":13,"wins":22},"fireworks/ember-1":{"draws":10,"losses":13,"wins":25},"gemini-3.1-pro-preview":{"draws":12,"losses":10,"wins":26},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":11,"losses":15,"wins":34},"google/gemini-3.5-flash-lite":{"draws":19,"losses":4,"wins":61},"google/gemini-3.6-flash":{"draws":15,"losses":21,"wins":56},"google/gemini-3.8-flash":{"draws":11,"losses":18,"wins":19},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":17},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":9,"wins":23},"gpt-5.4":{"draws":10,"losses":19,"wins":17},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":22},"gpt-5.4-nano":{"draws":9,"losses":6,"wins":33},"gpt-5.5":{"draws":9,"losses":14,"wins":21},"gpt-5.6-luna":{"draws":11,"losses":8,"wins":29},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":20},"gpt-5.6-terra":{"draws":13,"losses":11,"wins":22},"gpt-6-astra":{"draws":7,"losses":36,"wins":5},"gpt-6-luna":{"draws":14,"losses":10,"wins":24},"gpt-6-sol":{"draws":7,"losses":27,"wins":14},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":0,"wins":24},"inclusionai/ling-3.0-flash":{"draws":12,"losses":1,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":4,"wins":36},"meta/muse-glimmer-30b":{"draws":10,"losses":3,"wins":29},"meta/muse-spark-1.2":{"draws":7,"losses":17,"wins":22},"meta/muse-spark-1.3":{"draws":11,"losses":14,"wins":23},"meta/muse-wonder":{"draws":7,"losses":23,"wins":18},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":16},"mistralai/mistral-large-4-0":{"draws":8,"losses":7,"wins":15},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":9,"losses":15,"wins":22},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":4,"wins":23},"o3":{"draws":12,"losses":16,"wins":38},"openai/gpt-oss-120b":{"draws":12,"losses":2,"wins":28},"poolside/laguna-s-2.1":{"draws":14,"losses":6,"wins":26},"qwen/qwen3.7-max":{"draws":11,"losses":4,"wins":13},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":14,"wins":21},"qwen/qwen3.8-27b":{"draws":6,"losses":8,"wins":20},"qwen/qwen3.8-flash":{"draws":8,"losses":10,"wins":14},"qwen/qwen3.8-max":{"draws":9,"losses":14,"wins":25},"qwen/qwen3.8-max-0902":{"draws":16,"losses":14,"wins":18},"stealth/ox-alpha":{"draws":30,"losses":46,"wins":82},"stealth/space-bunny-alpha":{"draws":9,"losses":1,"wins":28},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":26},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":15,"wins":25},"thinkingmachines/inkling":{"draws":11,"losses":5,"wins":48},"thinkingmachines/inkling-small":{"draws":13,"losses":2,"wins":33},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":6,"losses":19,"wins":23},"x-ai/grok-4.6":{"draws":11,"losses":16,"wins":21},"x-ai/grok-4.7":{"draws":6,"losses":23,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":18,"losses":3,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":1,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":15},"z-ai/glm-5.2":{"draws":25,"losses":10,"wins":61},"z-ai/glm-5.3":{"draws":10,"losses":21,"wins":15},"z-ai/glm-5.3-flash":{"draws":5,"losses":6,"wins":21},"z-ai/glm-5.3-flashx":{"draws":12,"losses":13,"wins":23}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":11,"wins":27},"claude-fable-5":{"draws":12,"losses":27,"wins":9},"claude-fable-5-1":{"draws":4,"losses":45,"wins":5},"claude-haiku-5-5":{"draws":7,"losses":26,"wins":13},"claude-opus-4-5":{"draws":22,"losses":18,"wins":38},"claude-opus-4-8":{"draws":9,"losses":22,"wins":13},"claude-opus-5":{"draws":14,"losses":57,"wins":11},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":10,"losses":15,"wins":23},"claude-sonnet-5-5":{"draws":4,"losses":25,"wins":19},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":23,"losses":11,"wins":38},"deepseek/deepseek-v4-pro":{"draws":11,"losses":18,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":16,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":16},"fireworks/ember-1":{"draws":12,"losses":21,"wins":15},"gemini-3.1-pro-preview":{"draws":7,"losses":14,"wins":27},"google/gemini-3.1-flash-lite":{"draws":5,"losses":5,"wins":22},"google/gemini-3.5-flash":{"draws":16,"losses":18,"wins":26},"google/gemini-3.5-flash-lite":{"draws":15,"losses":26,"wins":43},"google/gemini-3.6-flash":{"draws":17,"losses":41,"wins":34},"google/gemini-3.8-flash":{"draws":11,"losses":24,"wins":13},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":12},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":17,"wins":15},"gpt-5.4":{"draws":10,"losses":23,"wins":13},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":12,"losses":13,"wins":23},"gpt-5.5":{"draws":13,"losses":16,"wins":15},"gpt-5.6-luna":{"draws":16,"losses":11,"wins":21},"gpt-5.6-sol":{"draws":9,"losses":30,"wins":9},"gpt-5.6-terra":{"draws":15,"losses":13,"wins":18},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":12,"losses":16,"wins":20},"gpt-6-sol":{"draws":4,"losses":34,"wins":10},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":22},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":34},"meta/muse-glimmer-30b":{"draws":9,"losses":11,"wins":22},"meta/muse-spark-1.2":{"draws":12,"losses":21,"wins":13},"meta/muse-spark-1.3":{"draws":10,"losses":23,"wins":15},"meta/muse-wonder":{"draws":12,"losses":24,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"mistralai/mistral-large-4-0":{"draws":6,"losses":13,"wins":11},"mistralai/mistral-medium-3-5":{"draws":5,"losses":4,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":15,"wins":16},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":11,"wins":26},"o3":{"draws":4,"losses":31,"wins":31},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":24},"poolside/laguna-s-2.1":{"draws":8,"losses":14,"wins":24},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":13},"qwen/qwen3.7-plus":{"draws":6,"losses":4,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":19,"wins":18},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":16},"qwen/qwen3.8-flash":{"draws":10,"losses":5,"wins":17},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":17},"qwen/qwen3.8-max-0902":{"draws":11,"losses":22,"wins":15},"stealth/ox-alpha":{"draws":31,"losses":64,"wins":63},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":5,"losses":8,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":17},"tencent/hy4-preview":{"draws":13,"losses":22,"wins":11},"thinkingmachines/inkling":{"draws":18,"losses":8,"wins":38},"thinkingmachines/inkling-small":{"draws":10,"losses":10,"wins":28},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":8,"losses":23,"wins":17},"x-ai/grok-4.6":{"draws":14,"losses":22,"wins":12},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":10},"xiaomi/mimo-v2.5":{"draws":26,"losses":10,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":17,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":15,"wins":10},"z-ai/glm-5.2":{"draws":27,"losses":26,"wins":43},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":12,"losses":18,"wins":18},"z-ai/glm-5.3-flashx":{"draws":12,"losses":15,"wins":5}}},"none":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":5},"claude-fable-5":{"draws":5,"losses":34,"wins":3},"claude-fable-5-1":{"draws":0,"losses":48,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":30,"wins":3},"claude-opus-4-5":{"draws":20,"losses":38,"wins":10},"claude-opus-4-8":{"draws":7,"losses":31,"wins":0},"claude-opus-5":{"draws":7,"losses":62,"wins":1},"claude-opus-5-5":{"draws":0,"losses":46,"wins":0},"claude-sonnet-5":{"draws":10,"losses":28,"wins":4},"claude-sonnet-5-5":{"draws":7,"losses":30,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":21,"losses":25,"wins":16},"deepseek/deepseek-v4-pro":{"draws":11,"losses":26,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":22,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":7},"fireworks/ember-1":{"draws":13,"losses":25,"wins":4},"gemini-3.1-pro-preview":{"draws":11,"losses":24,"wins":7},"google/gemini-3.1-flash-lite":{"draws":10,"losses":9,"wins":11},"google/gemini-3.5-flash":{"draws":10,"losses":33,"wins":11},"google/gemini-3.5-flash-lite":{"draws":22,"losses":35,"wins":19},"google/gemini-3.6-flash":{"draws":19,"losses":54,"wins":9},"google/gemini-3.8-flash":{"draws":9,"losses":29,"wins":4},"google/gemma-4-31b-it":{"draws":9,"losses":8,"wins":7},"gpt-4.1":{"draws":5,"losses":6,"wins":3},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":2},"gpt-5":{"draws":11,"losses":18,"wins":9},"gpt-5.4":{"draws":10,"losses":26,"wins":6},"gpt-5.4-mini":{"draws":9,"losses":13,"wins":6},"gpt-5.4-nano":{"draws":7,"losses":20,"wins":15},"gpt-5.5":{"draws":14,"losses":24,"wins":2},"gpt-5.6-luna":{"draws":10,"losses":20,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":37,"wins":1},"gpt-5.6-terra":{"draws":10,"losses":26,"wins":4},"gpt-6-astra":{"draws":1,"losses":40,"wins":1},"gpt-6-luna":{"draws":13,"losses":22,"wins":7},"gpt-6-sol":{"draws":4,"losses":35,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":7,"wins":11},"inclusionai/ling-3.0-flash":{"draws":14,"losses":7,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":18,"wins":14},"meta/muse-glimmer-30b":{"draws":16,"losses":15,"wins":7},"meta/muse-spark-1.2":{"draws":10,"losses":26,"wins":4},"meta/muse-spark-1.3":{"draws":5,"losses":33,"wins":4},"meta/muse-wonder":{"draws":5,"losses":35,"wins":2},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":9},"mistralai/mistral-large-4-0":{"draws":8,"losses":14,"wins":4},"mistralai/mistral-medium-3-5":{"draws":11,"losses":7,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":21,"wins":8},"nex-agi/nex-n2-pro":{"draws":7,"losses":7,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":14,"wins":8},"o3":{"draws":15,"losses":37,"wins":12},"openai/gpt-oss-120b":{"draws":11,"losses":16,"wins":9},"poolside/laguna-s-2.1":{"draws":13,"losses":18,"wins":9},"qwen/qwen3.7-max":{"draws":7,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":5,"losses":11,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":28,"wins":3},"qwen/qwen3.8-27b":{"draws":7,"losses":17,"wins":6},"qwen/qwen3.8-flash":{"draws":11,"losses":15,"wins":2},"qwen/qwen3.8-max":{"draws":15,"losses":22,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":26,"wins":4},"stealth/ox-alpha":{"draws":26,"losses":97,"wins":19},"stealth/space-bunny-alpha":{"draws":9,"losses":19,"wins":6},"stepfun/step-3.7-flash":{"draws":10,"losses":14,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":10,"wins":7},"tencent/hy4-preview":{"draws":14,"losses":25,"wins":3},"thinkingmachines/inkling":{"draws":16,"losses":24,"wins":18},"thinkingmachines/inkling-small":{"draws":16,"losses":11,"wins":15},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":5,"losses":32,"wins":5},"x-ai/grok-4.6":{"draws":11,"losses":27,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":33,"wins":1},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":23,"losses":24,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":11,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":18,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":22,"wins":2},"z-ai/glm-5.2":{"draws":35,"losses":37,"wins":12},"z-ai/glm-5.3":{"draws":8,"losses":30,"wins":2},"z-ai/glm-5.3-flash":{"draws":10,"losses":26,"wins":6},"z-ai/glm-5.3-flashx":{"draws":7,"losses":29,"wins":6}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":5,"wins":30},"claude-fable-5":{"draws":5,"losses":18,"wins":9},"claude-fable-5-1":{"draws":2,"losses":49,"wins":3},"claude-haiku-5-5":{"draws":7,"losses":15,"wins":24},"claude-opus-4-5":{"draws":19,"losses":16,"wins":43},"claude-opus-4-8":{"draws":10,"losses":15,"wins":19},"claude-opus-5":{"draws":14,"losses":56,"wins":12},"claude-opus-5-5":{"draws":1,"losses":46,"wins":5},"claude-sonnet-5":{"draws":13,"losses":11,"wins":24},"claude-sonnet-5-5":{"draws":14,"losses":22,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":17,"losses":7,"wins":48},"deepseek/deepseek-v4-pro":{"draws":14,"losses":10,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":9,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":17},"fireworks/ember-1":{"draws":14,"losses":10,"wins":24},"gemini-3.1-pro-preview":{"draws":11,"losses":14,"wins":23},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":14,"losses":16,"wins":30},"google/gemini-3.5-flash-lite":{"draws":22,"losses":11,"wins":51},"google/gemini-3.6-flash":{"draws":21,"losses":32,"wins":39},"google/gemini-3.8-flash":{"draws":11,"losses":19,"wins":18},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":16},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":4,"wins":25},"gpt-5.4":{"draws":14,"losses":14,"wins":18},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":10,"losses":3,"wins":35},"gpt-5.5":{"draws":15,"losses":11,"wins":18},"gpt-5.6-luna":{"draws":15,"losses":6,"wins":27},"gpt-5.6-sol":{"draws":9,"losses":23,"wins":16},"gpt-5.6-terra":{"draws":13,"losses":9,"wins":24},"gpt-6-astra":{"draws":3,"losses":37,"wins":8},"gpt-6-luna":{"draws":11,"losses":10,"wins":27},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":18},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":9,"wins":34},"meta/muse-glimmer-30b":{"draws":12,"losses":1,"wins":29},"meta/muse-spark-1.2":{"draws":10,"losses":14,"wins":22},"meta/muse-spark-1.3":{"draws":8,"losses":18,"wins":22},"meta/muse-wonder":{"draws":11,"losses":22,"wins":15},"minimax/minimax-m3":{"draws":8,"losses":0,"wins":18},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":9,"losses":1,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":14,"losses":9,"wins":23},"nex-agi/nex-n2-pro":{"draws":7,"losses":1,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":4,"wins":31},"o3":{"draws":7,"losses":10,"wins":49},"openai/gpt-oss-120b":{"draws":13,"losses":3,"wins":26},"poolside/laguna-s-2.1":{"draws":12,"losses":8,"wins":26},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":18},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":14,"wins":18},"qwen/qwen3.8-27b":{"draws":11,"losses":8,"wins":15},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":15},"qwen/qwen3.8-max":{"draws":11,"losses":14,"wins":23},"qwen/qwen3.8-max-0902":{"draws":13,"losses":12,"wins":23},"stealth/ox-alpha":{"draws":37,"losses":48,"wins":73},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":18},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":25},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":11,"losses":4,"wins":11},"tencent/hy4-preview":{"draws":7,"losses":17,"wins":22},"thinkingmachines/inkling":{"draws":17,"losses":4,"wins":43},"thinkingmachines/inkling-small":{"draws":13,"losses":5,"wins":30},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":10,"losses":21,"wins":17},"x-ai/grok-4.6":{"draws":10,"losses":17,"wins":21},"x-ai/grok-4.7":{"draws":1,"losses":28,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":20,"losses":2,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":9,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":20,"wins":10},"z-ai/glm-5.2":{"draws":30,"losses":17,"wins":49},"z-ai/glm-5.3":{"draws":7,"losses":29,"wins":10},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":18},"z-ai/glm-5.3-flashx":{"draws":8,"losses":19,"wins":21}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":2,"wins":39},"claude-fable-5":{"draws":5,"losses":8,"wins":35},"claude-fable-5-1":{"draws":2,"losses":26,"wins":10},"claude-haiku-5-5":{"draws":2,"losses":6,"wins":38},"claude-opus-4-5":{"draws":7,"losses":2,"wins":69},"claude-opus-4-8":{"draws":4,"losses":3,"wins":37},"claude-opus-5":{"draws":12,"losses":24,"wins":46},"claude-opus-5-5":{"draws":2,"losses":28,"wins":22},"claude-sonnet-5":{"draws":5,"losses":1,"wins":42},"claude-sonnet-5-5":{"draws":5,"losses":12,"wins":31},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":70},"deepseek/deepseek-v4-pro":{"draws":4,"losses":1,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":1,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":2,"wins":36},"fireworks/ember-1":{"draws":4,"losses":2,"wins":42},"gemini-3.1-pro-preview":{"draws":2,"losses":1,"wins":45},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":6,"losses":3,"wins":51},"google/gemini-3.5-flash-lite":{"draws":11,"losses":0,"wins":73},"google/gemini-3.6-flash":{"draws":13,"losses":3,"wins":76},"google/gemini-3.8-flash":{"draws":2,"losses":6,"wins":40},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":25},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":1,"wins":38},"gpt-5.4":{"draws":3,"losses":8,"wins":35},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":47},"gpt-5.5":{"draws":2,"losses":6,"wins":36},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":42},"gpt-5.6-sol":{"draws":5,"losses":7,"wins":36},"gpt-5.6-terra":{"draws":7,"losses":0,"wins":39},"gpt-6-astra":{"draws":5,"losses":32,"wins":11},"gpt-6-luna":{"draws":4,"losses":1,"wins":43},"gpt-6-sol":{"draws":7,"losses":14,"wins":27},"gpt-6.1-sol":{"draws":5,"losses":25,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":28},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":49},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":37},"meta/muse-spark-1.2":{"draws":4,"losses":1,"wins":41},"meta/muse-spark-1.3":{"draws":6,"losses":5,"wins":37},"meta/muse-wonder":{"draws":6,"losses":10,"wins":32},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":25},"mistralai/mistral-large-4-0":{"draws":1,"losses":1,"wins":28},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":38},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":40},"o3":{"draws":2,"losses":3,"wins":61},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":39},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":44},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":27},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":1,"wins":38},"qwen/qwen3.8-27b":{"draws":3,"losses":1,"wins":30},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":28},"qwen/qwen3.8-max":{"draws":4,"losses":1,"wins":43},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":41},"stealth/ox-alpha":{"draws":15,"losses":9,"wins":134},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":33},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":22},"tencent/hy4-preview":{"draws":4,"losses":5,"wins":37},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":60},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":5},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":5,"losses":3,"wins":40},"x-ai/grok-4.6":{"draws":3,"losses":6,"wins":39},"x-ai/grok-4.7":{"draws":4,"losses":16,"wins":22},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":6,"wins":21},"z-ai/glm-5.2":{"draws":8,"losses":3,"wins":85},"z-ai/glm-5.3":{"draws":4,"losses":10,"wins":32},"z-ai/glm-5.3-flash":{"draws":6,"losses":2,"wins":40},"z-ai/glm-5.3-flashx":{"draws":5,"losses":4,"wins":39}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":12,"wins":14},"claude-fable-5":{"draws":9,"losses":36,"wins":3},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":18,"wins":7},"claude-opus-4-5":{"draws":30,"losses":32,"wins":16},"claude-opus-4-8":{"draws":15,"losses":27,"wins":2},"claude-opus-5":{"draws":10,"losses":66,"wins":6},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":17,"losses":22,"wins":9},"claude-sonnet-5-5":{"draws":11,"losses":30,"wins":7},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":30,"losses":18,"wins":24},"deepseek/deepseek-v4-pro":{"draws":16,"losses":22,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":19,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":20,"wins":11},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":15,"losses":23,"wins":10},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":20,"losses":26,"wins":14},"google/gemini-3.5-flash-lite":{"draws":30,"losses":22,"wins":32},"google/gemini-3.6-flash":{"draws":30,"losses":49,"wins":13},"google/gemini-3.8-flash":{"draws":13,"losses":33,"wins":2},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":11},"gpt-4.1":{"draws":8,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":14,"wins":11},"gpt-5.4":{"draws":18,"losses":22,"wins":6},"gpt-5.4-mini":{"draws":15,"losses":5,"wins":12},"gpt-5.4-nano":{"draws":11,"losses":24,"wins":13},"gpt-5.5":{"draws":22,"losses":15,"wins":7},"gpt-5.6-luna":{"draws":22,"losses":15,"wins":11},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":17,"losses":18,"wins":11},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":13,"losses":22,"wins":13},"gpt-6-sol":{"draws":6,"losses":38,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.0-flash":{"draws":15,"losses":3,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":10,"wins":20},"meta/muse-glimmer-30b":{"draws":22,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":23,"wins":12},"meta/muse-spark-1.3":{"draws":11,"losses":28,"wins":9},"meta/muse-wonder":{"draws":11,"losses":36,"wins":1},"minimax/minimax-m3":{"draws":5,"losses":9,"wins":12},"mistralai/mistral-large-4-0":{"draws":16,"losses":11,"wins":3},"mistralai/mistral-medium-3-5":{"draws":13,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":19,"losses":19,"wins":8},"nex-agi/nex-n2-pro":{"draws":9,"losses":5,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":11,"wins":11},"o3":{"draws":16,"losses":35,"wins":15},"openai/gpt-oss-120b":{"draws":17,"losses":7,"wins":18},"poolside/laguna-s-2.1":{"draws":21,"losses":17,"wins":8},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":23,"wins":10},"qwen/qwen3.8-27b":{"draws":12,"losses":15,"wins":7},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":18,"losses":19,"wins":11},"qwen/qwen3.8-max-0902":{"draws":19,"losses":23,"wins":6},"stealth/ox-alpha":{"draws":43,"losses":84,"wins":31},"stealth/space-bunny-alpha":{"draws":17,"losses":11,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":10,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":13,"losses":29,"wins":4},"thinkingmachines/inkling":{"draws":28,"losses":14,"wins":22},"thinkingmachines/inkling-small":{"draws":22,"losses":8,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":16,"losses":26,"wins":6},"x-ai/grok-4.6":{"draws":16,"losses":27,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":38,"wins":0},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":30,"losses":16,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":8,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":13,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":21,"wins":5},"z-ai/glm-5.2":{"draws":35,"losses":34,"wins":27},"z-ai/glm-5.3":{"draws":10,"losses":34,"wins":2},"z-ai/glm-5.3-flash":{"draws":12,"losses":29,"wins":7},"z-ai/glm-5.3-flashx":{"draws":12,"losses":26,"wins":10}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":17,"wins":13},"claude-fable-5":{"draws":9,"losses":29,"wins":10},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":19,"wins":12},"claude-opus-4-5":{"draws":24,"losses":18,"wins":20},"claude-opus-4-8":{"draws":11,"losses":23,"wins":10},"claude-opus-5":{"draws":16,"losses":59,"wins":7},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":17,"losses":21,"wins":10},"claude-sonnet-5-5":{"draws":10,"losses":28,"wins":10},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":16},"deepseek/deepseek-v4-flash":{"draws":22,"losses":18,"wins":32},"deepseek/deepseek-v4-pro":{"draws":13,"losses":20,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":22,"wins":15},"fireworks/ember-1":{"draws":18,"losses":21,"wins":9},"gemini-3.1-pro-preview":{"draws":12,"losses":19,"wins":17},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":17,"losses":24,"wins":19},"google/gemini-3.5-flash-lite":{"draws":28,"losses":19,"wins":37},"google/gemini-3.6-flash":{"draws":30,"losses":40,"wins":22},"google/gemini-3.8-flash":{"draws":17,"losses":22,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":13},"gpt-4.1":{"draws":8,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":13,"wins":15},"gpt-5.4":{"draws":13,"losses":21,"wins":12},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":11},"gpt-5.4-nano":{"draws":13,"losses":13,"wins":22},"gpt-5.5":{"draws":22,"losses":17,"wins":5},"gpt-5.6-luna":{"draws":19,"losses":10,"wins":19},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":22,"losses":15,"wins":9},"gpt-6-astra":{"draws":2,"losses":40,"wins":6},"gpt-6-luna":{"draws":15,"losses":19,"wins":14},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":5,"losses":39,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":18},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":19,"losses":5,"wins":28},"meta/muse-glimmer-30b":{"draws":16,"losses":7,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":19,"wins":16},"meta/muse-spark-1.3":{"draws":11,"losses":28,"wins":9},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":17},"mistralai/mistral-large-4-0":{"draws":10,"losses":6,"wins":14},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":19,"losses":15,"wins":12},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":5,"wins":22},"o3":{"draws":10,"losses":17,"wins":39},"openai/gpt-oss-120b":{"draws":15,"losses":13,"wins":14},"poolside/laguna-s-2.1":{"draws":20,"losses":8,"wins":18},"qwen/qwen3.7-max":{"draws":5,"losses":10,"wins":13},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":19,"wins":11},"qwen/qwen3.8-27b":{"draws":13,"losses":12,"wins":9},"qwen/qwen3.8-flash":{"draws":13,"losses":10,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":19,"wins":15},"qwen/qwen3.8-max-0902":{"draws":10,"losses":17,"wins":21},"stealth/ox-alpha":{"draws":46,"losses":76,"wins":36},"stealth/space-bunny-alpha":{"draws":13,"losses":11,"wins":14},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":5,"wins":13},"tencent/hy4-preview":{"draws":13,"losses":19,"wins":14},"thinkingmachines/inkling":{"draws":24,"losses":11,"wins":29},"thinkingmachines/inkling-small":{"draws":17,"losses":6,"wins":25},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":14,"losses":19,"wins":15},"x-ai/grok-4.6":{"draws":10,"losses":24,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":31,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":23,"losses":10,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":10,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":32,"losses":26,"wins":38},"z-ai/glm-5.3":{"draws":12,"losses":27,"wins":7},"z-ai/glm-5.3-flash":{"draws":13,"losses":24,"wins":11},"z-ai/glm-5.3-flashx":{"draws":10,"losses":31,"wins":7}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":8,"wins":19},"claude-fable-5":{"draws":5,"losses":31,"wins":6},"claude-fable-5-1":{"draws":3,"losses":43,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":18,"wins":15},"claude-opus-4-5":{"draws":24,"losses":19,"wins":27},"claude-opus-4-8":{"draws":6,"losses":16,"wins":6},"claude-opus-5":{"draws":13,"losses":49,"wins":8},"claude-opus-5-5":{"draws":1,"losses":40,"wins":5},"claude-sonnet-5":{"draws":12,"losses":14,"wins":16},"claude-sonnet-5-5":{"draws":7,"losses":24,"wins":11},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":16,"losses":10,"wins":38},"deepseek/deepseek-v4-pro":{"draws":9,"losses":16,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":17,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":21,"wins":12},"fireworks/ember-1":{"draws":15,"losses":15,"wins":12},"gemini-3.1-pro-preview":{"draws":12,"losses":11,"wins":19},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":11,"losses":23,"wins":20},"google/gemini-3.5-flash-lite":{"draws":24,"losses":10,"wins":40},"google/gemini-3.6-flash":{"draws":18,"losses":40,"wins":22},"google/gemini-3.8-flash":{"draws":8,"losses":24,"wins":10},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":13},"gpt-4.1":{"draws":3,"losses":2,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":14,"wins":12},"gpt-5.4":{"draws":9,"losses":22,"wins":9},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":12},"gpt-5.4-nano":{"draws":8,"losses":15,"wins":23},"gpt-5.5":{"draws":11,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":13,"wins":17},"gpt-5.6-sol":{"draws":5,"losses":31,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":15,"wins":13},"gpt-6-astra":{"draws":2,"losses":36,"wins":4},"gpt-6-luna":{"draws":9,"losses":16,"wins":17},"gpt-6-sol":{"draws":5,"losses":27,"wins":10},"gpt-6.1-sol":{"draws":1,"losses":37,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":5,"wins":16},"inclusionai/ling-3.0-flash":{"draws":11,"losses":0,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":29},"meta/muse-glimmer-30b":{"draws":11,"losses":9,"wins":16},"meta/muse-spark-1.2":{"draws":13,"losses":15,"wins":12},"meta/muse-spark-1.3":{"draws":8,"losses":22,"wins":12},"meta/muse-wonder":{"draws":8,"losses":22,"wins":12},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":17},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":9},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":17,"wins":13},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":7,"wins":25},"o3":{"draws":7,"losses":28,"wins":27},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":19},"poolside/laguna-s-2.1":{"draws":14,"losses":7,"wins":17},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":9},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":16,"wins":12},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":11},"qwen/qwen3.8-flash":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.8-max":{"draws":10,"losses":17,"wins":15},"qwen/qwen3.8-max-0902":{"draws":9,"losses":18,"wins":15},"stealth/ox-alpha":{"draws":19,"losses":64,"wins":35},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":15},"stepfun/step-3.7-flash":{"draws":5,"losses":7,"wins":18},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":13},"tencent/hy4-preview":{"draws":9,"losses":21,"wins":10},"thinkingmachines/inkling":{"draws":13,"losses":7,"wins":34},"thinkingmachines/inkling-small":{"draws":14,"losses":6,"wins":22},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":12,"losses":23,"wins":7},"x-ai/grok-4.6":{"draws":9,"losses":23,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":22,"losses":12,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":10,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":17,"wins":6},"z-ai/glm-5.2":{"draws":23,"losses":29,"wins":32},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":6},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":12},"z-ai/glm-5.3-flashx":{"draws":6,"losses":22,"wins":14}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":8,"wins":57},"claude-fable-5":{"draws":24,"losses":23,"wins":37},"claude-fable-5-1":{"draws":12,"losses":63,"wins":19},"claude-haiku-5-5":{"draws":19,"losses":14,"wins":47},"claude-opus-4-5":{"draws":35,"losses":22,"wins":79},"claude-opus-4-8":{"draws":18,"losses":11,"wins":47},"claude-opus-5":{"draws":22,"losses":68,"wins":36},"claude-opus-5-5":{"draws":14,"losses":62,"wins":16},"claude-sonnet-5":{"draws":17,"losses":18,"wins":49},"claude-sonnet-5-5":{"draws":15,"losses":32,"wins":37},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":26},"deepseek/deepseek-v4-flash":{"draws":22,"losses":12,"wins":90},"deepseek/deepseek-v4-pro":{"draws":14,"losses":15,"wins":49},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":12,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":13,"wins":53},"fireworks/ember-1":{"draws":15,"losses":14,"wins":55},"gemini-3.1-pro-preview":{"draws":8,"losses":21,"wins":55},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":42},"google/gemini-3.5-flash":{"draws":13,"losses":20,"wins":71},"google/gemini-3.5-flash-lite":{"draws":25,"losses":16,"wins":105},"google/gemini-3.6-flash":{"draws":37,"losses":38,"wins":85},"google/gemini-3.8-flash":{"draws":16,"losses":23,"wins":45},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":34},"gpt-4.1":{"draws":7,"losses":2,"wins":19},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":6},"gpt-5":{"draws":15,"losses":9,"wins":50},"gpt-5.4":{"draws":16,"losses":13,"wins":51},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":34},"gpt-5.4-nano":{"draws":12,"losses":6,"wins":64},"gpt-5.5":{"draws":18,"losses":15,"wins":45},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":60},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":49},"gpt-5.6-terra":{"draws":13,"losses":9,"wins":58},"gpt-6-astra":{"draws":11,"losses":58,"wins":15},"gpt-6-luna":{"draws":20,"losses":9,"wins":55},"gpt-6-sol":{"draws":14,"losses":37,"wins":33},"gpt-6.1-sol":{"draws":13,"losses":53,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":42},"inclusionai/ling-3.0-flash":{"draws":17,"losses":2,"wins":39},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":14,"losses":5,"wins":69},"meta/muse-glimmer-30b":{"draws":7,"losses":11,"wins":58},"meta/muse-spark-1.2":{"draws":17,"losses":16,"wins":49},"meta/muse-spark-1.3":{"draws":18,"losses":23,"wins":43},"meta/muse-wonder":{"draws":15,"losses":27,"wins":42},"minimax/minimax-m3":{"draws":11,"losses":0,"wins":35},"mistralai/mistral-large-4-0":{"draws":12,"losses":7,"wins":35},"mistralai/mistral-medium-3-5":{"draws":10,"losses":5,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":17},"moonshotai/kimi-k3":{"draws":19,"losses":22,"wins":41},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":33},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":1,"wins":57},"o3":{"draws":15,"losses":5,"wins":88},"openai/gpt-oss-120b":{"draws":17,"losses":5,"wins":52},"poolside/laguna-s-2.1":{"draws":16,"losses":6,"wins":62},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":35},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":22,"wins":50},"qwen/qwen3.8-27b":{"draws":15,"losses":4,"wins":39},"qwen/qwen3.8-flash":{"draws":14,"losses":9,"wins":33},"qwen/qwen3.8-max":{"draws":21,"losses":19,"wins":44},"qwen/qwen3.8-max-0902":{"draws":17,"losses":19,"wins":48},"stealth/ox-alpha":{"draws":69,"losses":68,"wins":145},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":46},"stepfun/step-3.7-flash":{"draws":8,"losses":4,"wins":44},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":13,"losses":2,"wins":33},"tencent/hy4-preview":{"draws":15,"losses":15,"wins":50},"thinkingmachines/inkling":{"draws":22,"losses":18,"wins":74},"thinkingmachines/inkling-small":{"draws":18,"losses":3,"wins":63},"unbiased/pareto-26.10-preview":{"draws":1,"losses":20,"wins":7},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":15},"x-ai/grok-4.5":{"draws":16,"losses":16,"wins":52},"x-ai/grok-4.6":{"draws":17,"losses":23,"wins":44},"x-ai/grok-4.7":{"draws":9,"losses":38,"wins":27},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":19},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":96},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":1,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":7,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":16,"wins":27},"z-ai/glm-5.2":{"draws":41,"losses":13,"wins":114},"z-ai/glm-5.3":{"draws":15,"losses":32,"wins":33},"z-ai/glm-5.3-flash":{"draws":18,"losses":20,"wins":46},"z-ai/glm-5.3-flashx":{"draws":17,"losses":24,"wins":43}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":38},"claude-fable-5":{"draws":8,"losses":15,"wins":31},"claude-fable-5-1":{"draws":7,"losses":37,"wins":16},"claude-haiku-5-5":{"draws":12,"losses":7,"wins":33},"claude-opus-4-5":{"draws":16,"losses":15,"wins":57},"claude-opus-4-8":{"draws":9,"losses":14,"wins":27},"claude-opus-5":{"draws":16,"losses":49,"wins":29},"claude-opus-5-5":{"draws":1,"losses":33,"wins":10},"claude-sonnet-5":{"draws":11,"losses":10,"wins":33},"claude-sonnet-5-5":{"draws":7,"losses":16,"wins":31},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":20},"deepseek/deepseek-v4-flash":{"draws":11,"losses":5,"wins":66},"deepseek/deepseek-v4-pro":{"draws":8,"losses":4,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":4,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":10,"wins":36},"fireworks/ember-1":{"draws":8,"losses":11,"wins":35},"gemini-3.1-pro-preview":{"draws":7,"losses":5,"wins":42},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":11,"losses":7,"wins":50},"google/gemini-3.5-flash-lite":{"draws":16,"losses":1,"wins":77},"google/gemini-3.6-flash":{"draws":20,"losses":9,"wins":73},"google/gemini-3.8-flash":{"draws":12,"losses":15,"wins":27},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":27},"gpt-4.1":{"draws":5,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":4,"wins":35},"gpt-5.4":{"draws":10,"losses":4,"wins":38},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":32},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":48},"gpt-5.5":{"draws":11,"losses":11,"wins":28},"gpt-5.6-luna":{"draws":14,"losses":1,"wins":39},"gpt-5.6-sol":{"draws":10,"losses":12,"wins":32},"gpt-5.6-terra":{"draws":8,"losses":2,"wins":42},"gpt-6-astra":{"draws":8,"losses":34,"wins":12},"gpt-6-luna":{"draws":13,"losses":1,"wins":40},"gpt-6-sol":{"draws":8,"losses":26,"wins":20},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":30},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":33},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":9,"losses":6,"wins":45},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":41},"meta/muse-spark-1.2":{"draws":11,"losses":6,"wins":35},"meta/muse-spark-1.3":{"draws":7,"losses":11,"wins":36},"meta/muse-wonder":{"draws":6,"losses":20,"wins":28},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":27},"mistralai/mistral-large-4-0":{"draws":11,"losses":2,"wins":21},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":5,"losses":9,"wins":38},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":45},"o3":{"draws":8,"losses":1,"wins":67},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":40},"poolside/laguna-s-2.1":{"draws":9,"losses":0,"wins":45},"qwen/qwen3.7-max":{"draws":3,"losses":0,"wins":29},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":13,"wins":31},"qwen/qwen3.8-27b":{"draws":5,"losses":1,"wins":30},"qwen/qwen3.8-flash":{"draws":7,"losses":2,"wins":27},"qwen/qwen3.8-max":{"draws":11,"losses":10,"wins":33},"qwen/qwen3.8-max-0902":{"draws":12,"losses":5,"wins":37},"stealth/ox-alpha":{"draws":39,"losses":25,"wins":110},"stealth/space-bunny-alpha":{"draws":5,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":6,"losses":0,"wins":24},"tencent/hy4-preview":{"draws":11,"losses":8,"wins":33},"thinkingmachines/inkling":{"draws":15,"losses":0,"wins":55},"thinkingmachines/inkling-small":{"draws":8,"losses":0,"wins":46},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":12,"losses":12,"wins":30},"x-ai/grok-4.6":{"draws":13,"losses":13,"wins":28},"x-ai/grok-4.7":{"draws":8,"losses":22,"wins":18},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":17},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":2,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":17,"losses":10,"wins":81},"z-ai/glm-5.3":{"draws":6,"losses":17,"wins":29},"z-ai/glm-5.3-flash":{"draws":7,"losses":6,"wins":41},"z-ai/glm-5.3-flashx":{"draws":10,"losses":6,"wins":38}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":14,"wins":16},"claude-fable-5":{"draws":11,"losses":31,"wins":6},"claude-fable-5-1":{"draws":4,"losses":48,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":21,"wins":10},"claude-opus-4-5":{"draws":28,"losses":31,"wins":19},"claude-opus-4-8":{"draws":13,"losses":23,"wins":8},"claude-opus-5":{"draws":12,"losses":61,"wins":9},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":9,"losses":15,"wins":8},"claude-sonnet-5-5":{"draws":9,"losses":31,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":22,"losses":19,"wins":31},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":15,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":19,"wins":14},"fireworks/ember-1":{"draws":19,"losses":22,"wins":7},"gemini-3.1-pro-preview":{"draws":15,"losses":20,"wins":13},"google/gemini-3.1-flash-lite":{"draws":10,"losses":5,"wins":17},"google/gemini-3.5-flash":{"draws":16,"losses":29,"wins":15},"google/gemini-3.5-flash-lite":{"draws":25,"losses":20,"wins":39},"google/gemini-3.6-flash":{"draws":24,"losses":42,"wins":26},"google/gemini-3.8-flash":{"draws":10,"losses":28,"wins":10},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":18,"wins":11},"gpt-5.4":{"draws":13,"losses":25,"wins":8},"gpt-5.4-mini":{"draws":14,"losses":12,"wins":6},"gpt-5.4-nano":{"draws":13,"losses":14,"wins":21},"gpt-5.5":{"draws":18,"losses":20,"wins":6},"gpt-5.6-luna":{"draws":17,"losses":11,"wins":20},"gpt-5.6-sol":{"draws":7,"losses":37,"wins":4},"gpt-5.6-terra":{"draws":18,"losses":19,"wins":9},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":7,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":0,"losses":45,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":12,"wins":22},"meta/muse-glimmer-30b":{"draws":16,"losses":8,"wins":18},"meta/muse-spark-1.2":{"draws":13,"losses":24,"wins":9},"meta/muse-spark-1.3":{"draws":15,"losses":26,"wins":7},"meta/muse-wonder":{"draws":10,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":10},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":10,"losses":2,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":19,"wins":13},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":11,"wins":14},"o3":{"draws":11,"losses":27,"wins":28},"openai/gpt-oss-120b":{"draws":14,"losses":7,"wins":21},"poolside/laguna-s-2.1":{"draws":14,"losses":14,"wins":18},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":22,"wins":9},"qwen/qwen3.8-27b":{"draws":7,"losses":15,"wins":12},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":11},"qwen/qwen3.8-max":{"draws":18,"losses":22,"wins":8},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":10},"stealth/ox-alpha":{"draws":38,"losses":81,"wins":39},"stealth/space-bunny-alpha":{"draws":12,"losses":15,"wins":11},"stepfun/step-3.7-flash":{"draws":10,"losses":11,"wins":13},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":10},"tencent/hy4-preview":{"draws":14,"losses":23,"wins":9},"thinkingmachines/inkling":{"draws":21,"losses":9,"wins":34},"thinkingmachines/inkling-small":{"draws":15,"losses":10,"wins":23},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":11,"losses":27,"wins":10},"x-ai/grok-4.6":{"draws":15,"losses":26,"wins":7},"x-ai/grok-4.7":{"draws":4,"losses":33,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":30,"losses":18,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":8,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":19,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":20,"wins":9},"z-ai/glm-5.2":{"draws":26,"losses":33,"wins":37},"z-ai/glm-5.3":{"draws":10,"losses":31,"wins":5},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":14},"z-ai/glm-5.3-flashx":{"draws":14,"losses":27,"wins":7}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":18,"wins":18},"claude-fable-5":{"draws":8,"losses":32,"wins":8},"claude-fable-5-1":{"draws":0,"losses":54,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":22,"wins":15},"claude-opus-4-5":{"draws":18,"losses":34,"wins":26},"claude-opus-4-8":{"draws":12,"losses":24,"wins":8},"claude-opus-5":{"draws":11,"losses":63,"wins":8},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":12,"losses":21,"wins":15},"claude-sonnet-5-5":{"draws":4,"losses":25,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":22,"losses":21,"wins":29},"deepseek/deepseek-v4-pro":{"draws":16,"losses":19,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":20,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":25,"wins":10},"fireworks/ember-1":{"draws":12,"losses":22,"wins":14},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":17},"google/gemini-3.1-flash-lite":{"draws":8,"losses":10,"wins":14},"google/gemini-3.5-flash":{"draws":13,"losses":27,"wins":20},"google/gemini-3.5-flash-lite":{"draws":21,"losses":21,"wins":42},"google/gemini-3.6-flash":{"draws":21,"losses":52,"wins":19},"google/gemini-3.8-flash":{"draws":9,"losses":28,"wins":11},"google/gemma-4-31b-it":{"draws":7,"losses":10,"wins":11},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":14,"wins":18},"gpt-5.4":{"draws":13,"losses":24,"wins":9},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":16},"gpt-5.4-nano":{"draws":10,"losses":15,"wins":23},"gpt-5.5":{"draws":14,"losses":20,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":16,"wins":17},"gpt-5.6-sol":{"draws":6,"losses":37,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":17,"wins":15},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":11,"losses":27,"wins":10},"gpt-6-sol":{"draws":4,"losses":42,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":7,"wins":17},"inclusionai/ling-3.0-flash":{"draws":11,"losses":4,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":18,"wins":25},"meta/muse-glimmer-30b":{"draws":11,"losses":12,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":27,"wins":8},"meta/muse-spark-1.3":{"draws":9,"losses":31,"wins":8},"meta/muse-wonder":{"draws":5,"losses":32,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":15,"wins":4},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":12,"losses":27,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":7,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":14,"wins":19},"o3":{"draws":8,"losses":29,"wins":29},"openai/gpt-oss-120b":{"draws":11,"losses":10,"wins":21},"poolside/laguna-s-2.1":{"draws":10,"losses":11,"wins":25},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":7},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":29,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":14,"wins":14},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":11},"qwen/qwen3.8-max":{"draws":12,"losses":25,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":28,"wins":9},"stealth/ox-alpha":{"draws":42,"losses":90,"wins":26},"stealth/space-bunny-alpha":{"draws":9,"losses":15,"wins":14},"stepfun/step-3.7-flash":{"draws":2,"losses":19,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":15},"tencent/hy4-preview":{"draws":10,"losses":28,"wins":8},"thinkingmachines/inkling":{"draws":16,"losses":24,"wins":24},"thinkingmachines/inkling-small":{"draws":14,"losses":16,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":27,"wins":8},"x-ai/grok-4.6":{"draws":9,"losses":30,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":21,"losses":16,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":19,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":9},"z-ai/glm-5.2":{"draws":21,"losses":42,"wins":33},"z-ai/glm-5.3":{"draws":9,"losses":31,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":27,"wins":13},"z-ai/glm-5.3-flashx":{"draws":11,"losses":27,"wins":10}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":10,"wins":2},"claude-fable-5":{"draws":2,"losses":16,"wins":0},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":13,"wins":2},"claude-opus-4-5":{"draws":3,"losses":27,"wins":0},"claude-opus-4-8":{"draws":2,"losses":15,"wins":1},"claude-opus-5":{"draws":0,"losses":32,"wins":0},"claude-opus-5-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":3,"losses":15,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":14,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":9,"losses":14,"wins":5},"deepseek/deepseek-v4-pro":{"draws":4,"losses":12,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":12,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":11,"wins":1},"fireworks/ember-1":{"draws":3,"losses":13,"wins":2},"gemini-3.1-pro-preview":{"draws":4,"losses":10,"wins":4},"google/gemini-3.1-flash-lite":{"draws":3,"losses":7,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":15,"wins":3},"google/gemini-3.5-flash-lite":{"draws":10,"losses":11,"wins":11},"google/gemini-3.6-flash":{"draws":6,"losses":28,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":14,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":7,"wins":1},"gpt-4.1":{"draws":2,"losses":3,"wins":1},"gpt-5":{"draws":6,"losses":12,"wins":0},"gpt-5.4":{"draws":4,"losses":14,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":7,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":16,"wins":2},"gpt-5.5":{"draws":4,"losses":14,"wins":0},"gpt-5.6-luna":{"draws":5,"losses":11,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":18,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":12,"wins":0},"gpt-6-astra":{"draws":0,"losses":18,"wins":0},"gpt-6-luna":{"draws":4,"losses":12,"wins":2},"gpt-6-sol":{"draws":0,"losses":18,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":18,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":6,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":4,"wins":0},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":14,"wins":4},"meta/muse-glimmer-30b":{"draws":6,"losses":9,"wins":3},"meta/muse-spark-1.2":{"draws":0,"losses":18,"wins":0},"meta/muse-spark-1.3":{"draws":2,"losses":16,"wins":0},"meta/muse-wonder":{"draws":0,"losses":18,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":8,"wins":2},"mistralai/mistral-large-4-0":{"draws":3,"losses":9,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":14,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":7,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":8,"wins":2},"o3":{"draws":8,"losses":25,"wins":1},"openai/gpt-oss-120b":{"draws":6,"losses":8,"wins":4},"poolside/laguna-s-2.1":{"draws":8,"losses":10,"wins":2},"qwen/qwen3.7-max":{"draws":3,"losses":8,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":6,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":16,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":9,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":6,"wins":2},"qwen/qwen3.8-max":{"draws":4,"losses":14,"wins":0},"qwen/qwen3.8-max-0902":{"draws":4,"losses":14,"wins":0},"stealth/ox-alpha":{"draws":5,"losses":46,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":12,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":10,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":4,"losses":14,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":13,"wins":8},"thinkingmachines/inkling-small":{"draws":6,"losses":9,"wins":3},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":18,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":15,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":18,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":8,"losses":13,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":12,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":25,"wins":1},"z-ai/glm-5.3":{"draws":3,"losses":15,"wins":0},"z-ai/glm-5.3-flash":{"draws":5,"losses":11,"wins":2},"z-ai/glm-5.3-flashx":{"draws":4,"losses":13,"wins":1}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":13,"wins":15},"claude-fable-5":{"draws":8,"losses":34,"wins":0},"claude-fable-5-1":{"draws":2,"losses":44,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":24,"wins":4},"claude-opus-4-5":{"draws":22,"losses":35,"wins":11},"claude-opus-4-8":{"draws":8,"losses":26,"wins":4},"claude-opus-5":{"draws":7,"losses":61,"wins":2},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":9,"losses":24,"wins":9},"claude-sonnet-5-5":{"draws":7,"losses":27,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":16,"losses":18,"wins":18},"deepseek/deepseek-v4-pro":{"draws":8,"losses":18,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":17,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":24,"wins":4},"fireworks/ember-1":{"draws":14,"losses":17,"wins":11},"gemini-3.1-pro-preview":{"draws":14,"losses":18,"wins":10},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":18},"google/gemini-3.5-flash":{"draws":12,"losses":26,"wins":14},"google/gemini-3.5-flash-lite":{"draws":22,"losses":25,"wins":25},"google/gemini-3.6-flash":{"draws":14,"losses":58,"wins":8},"google/gemini-3.8-flash":{"draws":6,"losses":32,"wins":4},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":10},"gpt-4.1":{"draws":2,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":24,"wins":8},"gpt-5.4":{"draws":7,"losses":28,"wins":5},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":8},"gpt-5.4-nano":{"draws":10,"losses":18,"wins":18},"gpt-5.5":{"draws":10,"losses":22,"wins":6},"gpt-5.6-luna":{"draws":11,"losses":19,"wins":12},"gpt-5.6-sol":{"draws":5,"losses":29,"wins":8},"gpt-5.6-terra":{"draws":12,"losses":22,"wins":6},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":12,"losses":21,"wins":9},"gpt-6-sol":{"draws":5,"losses":35,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":3,"wins":15},"inclusionai/ling-3.0-flash":{"draws":12,"losses":8,"wins":10},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":11,"losses":17,"wins":18},"meta/muse-glimmer-30b":{"draws":16,"losses":12,"wins":8},"meta/muse-spark-1.2":{"draws":7,"losses":24,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":33,"wins":4},"meta/muse-wonder":{"draws":6,"losses":30,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":12,"wins":6},"mistralai/mistral-large-4-0":{"draws":6,"losses":16,"wins":4},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":21,"wins":12},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":11,"wins":14},"o3":{"draws":10,"losses":33,"wins":19},"openai/gpt-oss-120b":{"draws":15,"losses":13,"wins":10},"poolside/laguna-s-2.1":{"draws":16,"losses":16,"wins":12},"qwen/qwen3.7-max":{"draws":11,"losses":13,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":25,"wins":4},"qwen/qwen3.8-27b":{"draws":8,"losses":17,"wins":5},"qwen/qwen3.8-flash":{"draws":9,"losses":15,"wins":4},"qwen/qwen3.8-max":{"draws":11,"losses":23,"wins":8},"qwen/qwen3.8-max-0902":{"draws":7,"losses":30,"wins":5},"stealth/ox-alpha":{"draws":29,"losses":79,"wins":32},"stealth/space-bunny-alpha":{"draws":7,"losses":12,"wins":13},"stepfun/step-3.7-flash":{"draws":6,"losses":14,"wins":12},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":4,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":9,"losses":24,"wins":7},"thinkingmachines/inkling":{"draws":16,"losses":20,"wins":20},"thinkingmachines/inkling-small":{"draws":17,"losses":8,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":8,"losses":27,"wins":7},"x-ai/grok-4.6":{"draws":8,"losses":28,"wins":6},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":22,"losses":20,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":20,"wins":3},"z-ai/glm-5.2":{"draws":27,"losses":38,"wins":19},"z-ai/glm-5.3":{"draws":9,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":13,"losses":22,"wins":7},"z-ai/glm-5.3-flashx":{"draws":8,"losses":29,"wins":5}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":13,"wins":9},"claude-fable-5":{"draws":7,"losses":25,"wins":4},"claude-fable-5-1":{"draws":3,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":14,"wins":7},"claude-opus-4-5":{"draws":18,"losses":33,"wins":7},"claude-opus-4-8":{"draws":8,"losses":18,"wins":6},"claude-opus-5":{"draws":8,"losses":53,"wins":7},"claude-opus-5-5":{"draws":4,"losses":36,"wins":0},"claude-sonnet-5":{"draws":13,"losses":13,"wins":10},"claude-sonnet-5-5":{"draws":7,"losses":22,"wins":7},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":20,"losses":8,"wins":24},"deepseek/deepseek-v4-pro":{"draws":5,"losses":13,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":15,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":6},"fireworks/ember-1":{"draws":12,"losses":18,"wins":6},"gemini-3.1-pro-preview":{"draws":10,"losses":17,"wins":9},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":12},"google/gemini-3.5-flash":{"draws":11,"losses":23,"wins":12},"google/gemini-3.5-flash-lite":{"draws":24,"losses":19,"wins":21},"google/gemini-3.6-flash":{"draws":24,"losses":35,"wins":11},"google/gemini-3.8-flash":{"draws":10,"losses":18,"wins":8},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":6},"gpt-4.1":{"draws":2,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":15,"losses":11,"wins":8},"gpt-5.4":{"draws":8,"losses":17,"wins":11},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":8},"gpt-5.4-nano":{"draws":4,"losses":19,"wins":11},"gpt-5.5":{"draws":13,"losses":17,"wins":6},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":29,"wins":3},"gpt-5.6-terra":{"draws":16,"losses":11,"wins":7},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":12,"losses":16,"wins":8},"gpt-6-sol":{"draws":3,"losses":29,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":5,"wins":7},"inclusionai/ling-3.0-flash":{"draws":15,"losses":3,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":7,"wins":19},"meta/muse-glimmer-30b":{"draws":15,"losses":10,"wins":11},"meta/muse-spark-1.2":{"draws":4,"losses":21,"wins":11},"meta/muse-spark-1.3":{"draws":5,"losses":25,"wins":6},"meta/muse-wonder":{"draws":2,"losses":27,"wins":7},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":11},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":8,"losses":5,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":15,"wins":10},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":8},"o3":{"draws":10,"losses":23,"wins":19},"openai/gpt-oss-120b":{"draws":11,"losses":10,"wins":11},"poolside/laguna-s-2.1":{"draws":16,"losses":14,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":7},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":6},"qwen/qwen3.8-flash":{"draws":9,"losses":9,"wins":6},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":17,"wins":7},"stealth/ox-alpha":{"draws":35,"losses":60,"wins":31},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"wins":10},"stepfun/step-3.7-flash":{"draws":8,"losses":8,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":13,"losses":18,"wins":5},"thinkingmachines/inkling":{"draws":18,"losses":14,"wins":20},"thinkingmachines/inkling-small":{"draws":17,"losses":9,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":12,"losses":17,"wins":7},"x-ai/grok-4.6":{"draws":15,"losses":20,"wins":1},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":3},"xiaomi/mimo-v2.5":{"draws":23,"losses":12,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":12,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":30,"losses":24,"wins":18},"z-ai/glm-5.3":{"draws":6,"losses":24,"wins":4},"z-ai/glm-5.3-flash":{"draws":7,"losses":24,"wins":5},"z-ai/glm-5.3-flashx":{"draws":12,"losses":20,"wins":4}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":9},"claude-fable-5":{"draws":8,"losses":24,"wins":4},"claude-fable-5-1":{"draws":2,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":3},"claude-opus-4-5":{"draws":21,"losses":28,"wins":9},"claude-opus-4-8":{"draws":5,"losses":23,"wins":4},"claude-opus-5":{"draws":6,"losses":45,"wins":7},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":13,"losses":16,"wins":7},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":8,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":24,"losses":14,"wins":16},"deepseek/deepseek-v4-pro":{"draws":15,"losses":11,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":13,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":3},"fireworks/ember-1":{"draws":11,"losses":19,"wins":6},"gemini-3.1-pro-preview":{"draws":13,"losses":13,"wins":10},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":11},"google/gemini-3.5-flash":{"draws":14,"losses":25,"wins":7},"google/gemini-3.5-flash-lite":{"draws":26,"losses":23,"wins":15},"google/gemini-3.6-flash":{"draws":20,"losses":36,"wins":14},"google/gemini-3.8-flash":{"draws":10,"losses":24,"wins":2},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":9},"gpt-4.1":{"draws":5,"losses":4,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":15,"wins":5},"gpt-5.4":{"draws":9,"losses":20,"wins":7},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":5},"gpt-5.4-nano":{"draws":7,"losses":15,"wins":12},"gpt-5.5":{"draws":14,"losses":14,"wins":6},"gpt-5.6-luna":{"draws":12,"losses":12,"wins":12},"gpt-5.6-sol":{"draws":5,"losses":25,"wins":6},"gpt-5.6-terra":{"draws":14,"losses":16,"wins":6},"gpt-6-astra":{"draws":2,"losses":33,"wins":1},"gpt-6-luna":{"draws":11,"losses":16,"wins":9},"gpt-6-sol":{"draws":3,"losses":30,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":34,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":10},"inclusionai/ling-3.0-flash":{"draws":14,"losses":8,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":10,"wins":12},"meta/muse-glimmer-30b":{"draws":15,"losses":7,"wins":10},"meta/muse-spark-1.2":{"draws":8,"losses":19,"wins":7},"meta/muse-spark-1.3":{"draws":5,"losses":25,"wins":6},"meta/muse-wonder":{"draws":7,"losses":22,"wins":7},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":5},"mistralai/mistral-large-4-0":{"draws":9,"losses":8,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":13,"losses":11,"wins":10},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":2,"wins":14},"o3":{"draws":11,"losses":19,"wins":22},"openai/gpt-oss-120b":{"draws":12,"losses":9,"wins":9},"poolside/laguna-s-2.1":{"draws":17,"losses":11,"wins":4},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":20,"wins":7},"qwen/qwen3.8-27b":{"draws":8,"losses":11,"wins":7},"qwen/qwen3.8-flash":{"draws":13,"losses":5,"wins":6},"qwen/qwen3.8-max":{"draws":10,"losses":19,"wins":7},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":39,"losses":62,"wins":23},"stealth/space-bunny-alpha":{"draws":11,"losses":11,"wins":6},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":5,"wins":5},"tencent/hy4-preview":{"draws":13,"losses":16,"wins":7},"thinkingmachines/inkling":{"draws":23,"losses":15,"wins":10},"thinkingmachines/inkling-small":{"draws":17,"losses":7,"wins":12},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":9,"losses":19,"wins":8},"x-ai/grok-4.6":{"draws":18,"losses":13,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":20,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":23,"losses":13,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":11,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":32,"losses":22,"wins":18},"z-ai/glm-5.3":{"draws":5,"losses":26,"wins":3},"z-ai/glm-5.3-flash":{"draws":10,"losses":19,"wins":7},"z-ai/glm-5.3-flashx":{"draws":8,"losses":22,"wins":6}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":21,"wins":7},"claude-fable-5":{"draws":11,"losses":32,"wins":5},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":27,"wins":5},"claude-opus-4-5":{"draws":29,"losses":34,"wins":15},"claude-opus-4-8":{"draws":14,"losses":25,"wins":5},"claude-opus-5":{"draws":14,"losses":63,"wins":5},"claude-opus-5-5":{"draws":1,"losses":50,"wins":1},"claude-sonnet-5":{"draws":20,"losses":25,"wins":3},"claude-sonnet-5-5":{"draws":14,"losses":32,"wins":2},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":31,"losses":18,"wins":23},"deepseek/deepseek-v4-pro":{"draws":16,"losses":20,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":16,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":8},"fireworks/ember-1":{"draws":18,"losses":27,"wins":3},"gemini-3.1-pro-preview":{"draws":14,"losses":27,"wins":7},"google/gemini-3.1-flash-lite":{"draws":16,"losses":7,"wins":9},"google/gemini-3.5-flash":{"draws":17,"losses":31,"wins":12},"google/gemini-3.5-flash-lite":{"draws":33,"losses":35,"wins":16},"google/gemini-3.6-flash":{"draws":28,"losses":53,"wins":11},"google/gemini-3.8-flash":{"draws":12,"losses":33,"wins":3},"google/gemma-4-31b-it":{"draws":13,"losses":8,"wins":7},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":14,"losses":15,"wins":13},"gpt-5.4":{"draws":17,"losses":27,"wins":2},"gpt-5.4-mini":{"draws":14,"losses":14,"wins":4},"gpt-5.4-nano":{"draws":13,"losses":20,"wins":15},"gpt-5.5":{"draws":20,"losses":17,"wins":7},"gpt-5.6-luna":{"draws":20,"losses":17,"wins":11},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":21,"losses":18,"wins":7},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":17,"losses":23,"wins":8},"gpt-6-sol":{"draws":9,"losses":32,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":42,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":4,"wins":12},"inclusionai/ling-3.0-flash":{"draws":19,"losses":5,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":18,"wins":19},"meta/muse-glimmer-30b":{"draws":22,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":26,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":31,"wins":9},"meta/muse-wonder":{"draws":9,"losses":35,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":10,"wins":9},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":13,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":21,"wins":8},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":10,"wins":12},"o3":{"draws":18,"losses":33,"wins":15},"openai/gpt-oss-120b":{"draws":18,"losses":17,"wins":7},"poolside/laguna-s-2.1":{"draws":24,"losses":14,"wins":8},"qwen/qwen3.7-max":{"draws":11,"losses":9,"wins":8},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":26,"wins":7},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":8},"qwen/qwen3.8-flash":{"draws":16,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":16,"losses":22,"wins":10},"qwen/qwen3.8-max-0902":{"draws":17,"losses":23,"wins":8},"stealth/ox-alpha":{"draws":42,"losses":82,"wins":33},"stealth/space-bunny-alpha":{"draws":16,"losses":13,"wins":9},"stepfun/step-3.7-flash":{"draws":9,"losses":9,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":18,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":24,"losses":14,"wins":26},"thinkingmachines/inkling-small":{"draws":18,"losses":15,"wins":15},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":32,"wins":5},"x-ai/grok-4.6":{"draws":14,"losses":30,"wins":4},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":29,"losses":19,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":12,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":20,"wins":4},"z-ai/glm-5.2":{"draws":40,"losses":36,"wins":20},"z-ai/glm-5.3":{"draws":11,"losses":30,"wins":5},"z-ai/glm-5.3-flash":{"draws":12,"losses":30,"wins":6},"z-ai/glm-5.3-flashx":{"draws":14,"losses":30,"wins":4}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":15,"wins":12},"claude-fable-5":{"draws":12,"losses":35,"wins":1},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":34,"losses":28,"wins":16},"claude-opus-4-8":{"draws":17,"losses":24,"wins":3},"claude-opus-5":{"draws":10,"losses":68,"wins":4},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":19,"losses":17,"wins":12},"claude-sonnet-5-5":{"draws":13,"losses":29,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":29,"losses":21,"wins":22},"deepseek/deepseek-v4-pro":{"draws":16,"losses":20,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":20,"wins":7},"fireworks/ember-1":{"draws":11,"losses":21,"wins":0},"gemini-3.1-pro-preview":{"draws":20,"losses":17,"wins":11},"google/gemini-3.1-flash-lite":{"draws":11,"losses":3,"wins":18},"google/gemini-3.5-flash":{"draws":23,"losses":27,"wins":10},"google/gemini-3.5-flash-lite":{"draws":40,"losses":24,"wins":20},"google/gemini-3.6-flash":{"draws":33,"losses":42,"wins":17},"google/gemini-3.8-flash":{"draws":14,"losses":28,"wins":6},"google/gemma-4-31b-it":{"draws":14,"losses":6,"wins":8},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":19,"losses":15,"wins":8},"gpt-5.4":{"draws":18,"losses":26,"wins":2},"gpt-5.4-mini":{"draws":16,"losses":10,"wins":6},"gpt-5.4-nano":{"draws":15,"losses":12,"wins":21},"gpt-5.5":{"draws":15,"losses":23,"wins":6},"gpt-5.6-luna":{"draws":22,"losses":18,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":35,"wins":7},"gpt-5.6-terra":{"draws":20,"losses":18,"wins":8},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":15,"losses":21,"wins":12},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":21,"losses":2,"wins":11},"inclusionai/ling-3.0-flash":{"draws":23,"losses":4,"wins":7},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":24,"losses":8,"wins":20},"meta/muse-glimmer-30b":{"draws":22,"losses":5,"wins":15},"meta/muse-spark-1.2":{"draws":13,"losses":26,"wins":7},"meta/muse-spark-1.3":{"draws":10,"losses":29,"wins":9},"meta/muse-wonder":{"draws":17,"losses":28,"wins":3},"minimax/minimax-m3":{"draws":10,"losses":4,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":14,"wins":5},"mistralai/mistral-medium-3-5":{"draws":14,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":19,"losses":17,"wins":10},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":10,"wins":10},"o3":{"draws":20,"losses":26,"wins":20},"openai/gpt-oss-120b":{"draws":22,"losses":9,"wins":11},"poolside/laguna-s-2.1":{"draws":26,"losses":10,"wins":10},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":21,"wins":6},"qwen/qwen3.8-27b":{"draws":11,"losses":18,"wins":5},"qwen/qwen3.8-flash":{"draws":16,"losses":12,"wins":4},"qwen/qwen3.8-max":{"draws":18,"losses":18,"wins":12},"qwen/qwen3.8-max-0902":{"draws":17,"losses":24,"wins":7},"stealth/ox-alpha":{"draws":53,"losses":84,"wins":21},"stealth/space-bunny-alpha":{"draws":16,"losses":10,"wins":12},"stepfun/step-3.7-flash":{"draws":10,"losses":9,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":5,"wins":9},"tencent/hy4-preview":{"draws":20,"losses":19,"wins":7},"thinkingmachines/inkling":{"draws":24,"losses":20,"wins":20},"thinkingmachines/inkling-small":{"draws":22,"losses":8,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":14,"losses":31,"wins":3},"x-ai/grok-4.6":{"draws":16,"losses":25,"wins":7},"x-ai/grok-4.7":{"draws":6,"losses":33,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":36,"losses":15,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":9,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":15,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":19,"wins":6},"z-ai/glm-5.2":{"draws":41,"losses":32,"wins":23},"z-ai/glm-5.3":{"draws":10,"losses":32,"wins":4},"z-ai/glm-5.3-flash":{"draws":13,"losses":28,"wins":7},"z-ai/glm-5.3-flashx":{"draws":15,"losses":25,"wins":8}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":18,"wins":12},"claude-fable-5":{"draws":11,"losses":36,"wins":1},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":26,"wins":7},"claude-opus-4-5":{"draws":25,"losses":44,"wins":9},"claude-opus-4-8":{"draws":12,"losses":29,"wins":3},"claude-opus-5":{"draws":9,"losses":68,"wins":5},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":17,"losses":24,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":33,"wins":5},"cohere/north-mini-code":{"draws":6,"losses":8,"wins":4},"deepseek/deepseek-v4-flash":{"draws":28,"losses":26,"wins":18},"deepseek/deepseek-v4-pro":{"draws":14,"losses":24,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":23,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":24,"wins":8},"fireworks/ember-1":{"draws":19,"losses":28,"wins":1},"gemini-3.1-pro-preview":{"draws":10,"losses":18,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":11,"wins":11},"google/gemini-3.5-flash":{"draws":17,"losses":34,"wins":9},"google/gemini-3.5-flash-lite":{"draws":33,"losses":30,"wins":21},"google/gemini-3.6-flash":{"draws":32,"losses":54,"wins":6},"google/gemini-3.8-flash":{"draws":10,"losses":37,"wins":1},"google/gemma-4-31b-it":{"draws":12,"losses":7,"wins":9},"gpt-4.1":{"draws":7,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":19,"losses":18,"wins":5},"gpt-5.4":{"draws":14,"losses":29,"wins":3},"gpt-5.4-mini":{"draws":14,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":15,"losses":17,"wins":16},"gpt-5.5":{"draws":18,"losses":24,"wins":2},"gpt-5.6-luna":{"draws":19,"losses":22,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":39,"wins":2},"gpt-5.6-terra":{"draws":21,"losses":22,"wins":3},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":13,"losses":23,"wins":12},"gpt-6-sol":{"draws":8,"losses":36,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":12,"wins":7},"inclusionai/ling-3.0-flash":{"draws":17,"losses":6,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":23,"wins":13},"meta/muse-glimmer-30b":{"draws":22,"losses":10,"wins":10},"meta/muse-spark-1.2":{"draws":13,"losses":28,"wins":5},"meta/muse-spark-1.3":{"draws":9,"losses":35,"wins":4},"meta/muse-wonder":{"draws":8,"losses":38,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":11,"wins":7},"mistralai/mistral-large-4-0":{"draws":9,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":15,"losses":5,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":18,"losses":23,"wins":5},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":13,"wins":12},"o3":{"draws":14,"losses":46,"wins":6},"openai/gpt-oss-120b":{"draws":18,"losses":17,"wins":7},"poolside/laguna-s-2.1":{"draws":21,"losses":18,"wins":7},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":27,"wins":3},"qwen/qwen3.8-27b":{"draws":9,"losses":21,"wins":4},"qwen/qwen3.8-flash":{"draws":14,"losses":15,"wins":3},"qwen/qwen3.8-max":{"draws":18,"losses":23,"wins":7},"qwen/qwen3.8-max-0902":{"draws":15,"losses":30,"wins":3},"stealth/ox-alpha":{"draws":39,"losses":106,"wins":13},"stealth/space-bunny-alpha":{"draws":15,"losses":17,"wins":6},"stepfun/step-3.7-flash":{"draws":11,"losses":19,"wins":4},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":11,"wins":6},"tencent/hy4-preview":{"draws":15,"losses":27,"wins":4},"thinkingmachines/inkling":{"draws":25,"losses":24,"wins":15},"thinkingmachines/inkling-small":{"draws":19,"losses":16,"wins":13},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":15,"losses":32,"wins":1},"x-ai/grok-4.6":{"draws":16,"losses":31,"wins":1},"x-ai/grok-4.7":{"draws":4,"losses":36,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":27,"losses":28,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":9,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":21,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":22,"wins":5},"z-ai/glm-5.2":{"draws":38,"losses":40,"wins":18},"z-ai/glm-5.3":{"draws":10,"losses":35,"wins":1},"z-ai/glm-5.3-flash":{"draws":15,"losses":29,"wins":4},"z-ai/glm-5.3-flashx":{"draws":10,"losses":34,"wins":4}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":14,"wins":4},"claude-fable-5":{"draws":4,"losses":26,"wins":0},"claude-fable-5-1":{"draws":2,"losses":30,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":25,"wins":0},"claude-opus-4-5":{"draws":13,"losses":35,"wins":2},"claude-opus-4-8":{"draws":3,"losses":26,"wins":1},"claude-opus-5":{"draws":3,"losses":42,"wins":1},"claude-opus-5-5":{"draws":0,"losses":30,"wins":0},"claude-sonnet-5":{"draws":6,"losses":21,"wins":3},"claude-sonnet-5-5":{"draws":4,"losses":23,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":8,"wins":2},"deepseek/deepseek-v4-flash":{"draws":13,"losses":28,"wins":7},"deepseek/deepseek-v4-pro":{"draws":6,"losses":19,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":20,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":16,"wins":3},"fireworks/ember-1":{"draws":8,"losses":22,"wins":0},"gemini-3.1-pro-preview":{"draws":7,"losses":20,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":8,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":31,"wins":1},"google/gemini-3.5-flash-lite":{"draws":10,"losses":37,"wins":5},"google/gemini-3.6-flash":{"draws":12,"losses":44,"wins":2},"google/gemini-3.8-flash":{"draws":5,"losses":25,"wins":0},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":4},"gpt-4.1":{"draws":2,"losses":8,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":5,"losses":21,"wins":0},"gpt-5.4":{"draws":4,"losses":24,"wins":0},"gpt-5.4-mini":{"draws":6,"losses":13,"wins":1},"gpt-5.4-nano":{"draws":7,"losses":22,"wins":7},"gpt-5.5":{"draws":6,"losses":19,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":20,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":26,"wins":1},"gpt-5.6-terra":{"draws":5,"losses":22,"wins":1},"gpt-6-astra":{"draws":2,"losses":28,"wins":0},"gpt-6-luna":{"draws":7,"losses":19,"wins":4},"gpt-6-sol":{"draws":4,"losses":26,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":27,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":11,"wins":5},"inclusionai/ling-3.0-flash":{"draws":4,"losses":11,"wins":5},"meituan/longcat-2.0":{"draws":4,"losses":25,"wins":3},"meta/muse-glimmer-30b":{"draws":8,"losses":12,"wins":4},"meta/muse-spark-1.2":{"draws":8,"losses":18,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":24,"wins":0},"meta/muse-wonder":{"draws":3,"losses":26,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":10,"wins":4},"mistralai/mistral-large-4-0":{"draws":4,"losses":14,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":10,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":8,"losses":20,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":11,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":20,"wins":2},"o3":{"draws":2,"losses":44,"wins":2},"openai/gpt-oss-120b":{"draws":6,"losses":16,"wins":4},"poolside/laguna-s-2.1":{"draws":7,"losses":18,"wins":3},"qwen/qwen3.7-max":{"draws":7,"losses":12,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":14,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":21,"wins":0},"qwen/qwen3.8-27b":{"draws":5,"losses":16,"wins":3},"qwen/qwen3.8-flash":{"draws":5,"losses":14,"wins":1},"qwen/qwen3.8-max":{"draws":8,"losses":22,"wins":0},"qwen/qwen3.8-max-0902":{"draws":7,"losses":23,"wins":0},"stealth/ox-alpha":{"draws":12,"losses":64,"wins":8},"stealth/space-bunny-alpha":{"draws":4,"losses":18,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":19,"wins":1},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":2},"tencent/hy4-preview":{"draws":2,"losses":26,"wins":0},"thinkingmachines/inkling":{"draws":12,"losses":20,"wins":8},"thinkingmachines/inkling-small":{"draws":10,"losses":15,"wins":5},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":7,"wins":3},"x-ai/grok-4.5":{"draws":5,"losses":24,"wins":1},"x-ai/grok-4.6":{"draws":3,"losses":26,"wins":1},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":8,"wins":0},"xiaomi/mimo-v2.5":{"draws":13,"losses":29,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":16,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":17,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":0},"z-ai/glm-5.2":{"draws":12,"losses":42,"wins":6},"z-ai/glm-5.3":{"draws":4,"losses":24,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":21,"wins":2},"z-ai/glm-5.3-flashx":{"draws":8,"losses":21,"wins":1}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":30,"wins":25},"claude-fable-5":{"draws":16,"losses":62,"wins":6},"claude-fable-5-1":{"draws":3,"losses":91,"wins":0},"claude-haiku-5-5":{"draws":18,"losses":45,"wins":19},"claude-opus-4-5":{"draws":39,"losses":72,"wins":27},"claude-opus-4-8":{"draws":21,"losses":51,"wins":8},"claude-opus-5":{"draws":17,"losses":115,"wins":8},"claude-opus-5-5":{"draws":4,"losses":88,"wins":0},"claude-sonnet-5":{"draws":29,"losses":33,"wins":22},"claude-sonnet-5-5":{"draws":17,"losses":58,"wins":9},"cohere/north-mini-code":{"draws":11,"losses":6,"wins":17},"deepseek/deepseek-v4-flash":{"draws":37,"losses":41,"wins":48},"deepseek/deepseek-v4-pro":{"draws":22,"losses":34,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":35,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":43,"wins":12},"fireworks/ember-1":{"draws":31,"losses":41,"wins":12},"gemini-3.1-pro-preview":{"draws":24,"losses":38,"wins":22},"google/gemini-3.1-flash-lite":{"draws":18,"losses":10,"wins":34},"google/gemini-3.5-flash":{"draws":17,"losses":48,"wins":15},"google/gemini-3.5-flash-lite":{"draws":47,"losses":62,"wins":41},"google/gemini-3.6-flash":{"draws":46,"losses":82,"wins":34},"google/gemini-3.8-flash":{"draws":23,"losses":55,"wins":6},"google/gemma-4-31b-it":{"draws":18,"losses":12,"wins":20},"gpt-4.1":{"draws":10,"losses":13,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":23,"losses":32,"wins":19},"gpt-5.4":{"draws":13,"losses":55,"wins":14},"gpt-5.4-mini":{"draws":22,"losses":17,"wins":17},"gpt-5.4-nano":{"draws":17,"losses":33,"wins":38},"gpt-5.5":{"draws":28,"losses":39,"wins":11},"gpt-5.6-luna":{"draws":25,"losses":32,"wins":27},"gpt-5.6-sol":{"draws":7,"losses":70,"wins":7},"gpt-5.6-terra":{"draws":29,"losses":38,"wins":13},"gpt-6-astra":{"draws":3,"losses":79,"wins":2},"gpt-6-luna":{"draws":29,"losses":34,"wins":21},"gpt-6-sol":{"draws":14,"losses":64,"wins":6},"gpt-6.1-sol":{"draws":3,"losses":79,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":24,"losses":13,"wins":23},"inclusionai/ling-3.0-flash":{"draws":24,"losses":9,"wins":27},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":23,"wins":46},"meta/muse-glimmer-30b":{"draws":30,"losses":17,"wins":27},"meta/muse-spark-1.2":{"draws":17,"losses":49,"wins":14},"meta/muse-spark-1.3":{"draws":17,"losses":55,"wins":12},"meta/muse-wonder":{"draws":10,"losses":69,"wins":5},"minimax/minimax-m3":{"draws":10,"losses":18,"wins":18},"mistralai/mistral-large-4-0":{"draws":19,"losses":24,"wins":9},"mistralai/mistral-medium-3-5":{"draws":18,"losses":10,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":30,"losses":33,"wins":17},"nex-agi/nex-n2-pro":{"draws":13,"losses":11,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":21,"wins":25},"o3":{"draws":25,"losses":56,"wins":45},"openai/gpt-oss-120b":{"draws":24,"losses":25,"wins":23},"poolside/laguna-s-2.1":{"draws":29,"losses":22,"wins":27},"qwen/qwen3.7-max":{"draws":16,"losses":23,"wins":11},"qwen/qwen3.7-plus":{"draws":12,"losses":14,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":47,"wins":8},"qwen/qwen3.8-27b":{"draws":10,"losses":35,"wins":15},"qwen/qwen3.8-flash":{"draws":21,"losses":22,"wins":13},"qwen/qwen3.8-max":{"draws":28,"losses":35,"wins":21},"qwen/qwen3.8-max-0902":{"draws":25,"losses":46,"wins":13},"stealth/ox-alpha":{"draws":54,"losses":163,"wins":43},"stealth/space-bunny-alpha":{"draws":23,"losses":27,"wins":18},"stepfun/step-3.7-flash":{"draws":15,"losses":17,"wins":30},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":20,"wins":10},"tencent/hy4-preview":{"draws":26,"losses":47,"wins":9},"thinkingmachines/inkling":{"draws":26,"losses":37,"wins":49},"thinkingmachines/inkling-small":{"draws":30,"losses":21,"wins":33},"unbiased/pareto-26.10-preview":{"draws":0,"losses":27,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":10,"wins":9},"x-ai/grok-4.5":{"draws":16,"losses":55,"wins":13},"x-ai/grok-4.6":{"draws":23,"losses":55,"wins":6},"x-ai/grok-4.7":{"draws":7,"losses":62,"wins":5},"x-ai/grok-build-0.1":{"draws":10,"losses":6,"wins":12},"xiaomi/mimo-v2.5":{"draws":48,"losses":36,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":18,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":35,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":34,"wins":13},"z-ai/glm-5.2":{"draws":59,"losses":70,"wins":39},"z-ai/glm-5.3":{"draws":13,"losses":62,"wins":5},"z-ai/glm-5.3-flash":{"draws":14,"losses":56,"wins":14},"z-ai/glm-5.3-flashx":{"draws":16,"losses":56,"wins":12}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":23,"wins":30},"claude-fable-5":{"draws":19,"losses":59,"wins":12},"claude-fable-5-1":{"draws":6,"losses":93,"wins":1},"claude-haiku-5-5":{"draws":18,"losses":53,"wins":17},"claude-opus-4-5":{"draws":48,"losses":53,"wins":47},"claude-opus-4-8":{"draws":25,"losses":50,"wins":11},"claude-opus-5":{"draws":19,"losses":122,"wins":11},"claude-opus-5-5":{"draws":3,"losses":93,"wins":2},"claude-sonnet-5":{"draws":28,"losses":42,"wins":20},"claude-sonnet-5-5":{"draws":18,"losses":58,"wins":14},"cohere/north-mini-code":{"draws":13,"losses":7,"wins":14},"deepseek/deepseek-v4-flash":{"draws":48,"losses":36,"wins":52},"deepseek/deepseek-v4-pro":{"draws":25,"losses":33,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":35,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":41,"wins":18},"fireworks/ember-1":{"draws":32,"losses":36,"wins":22},"gemini-3.1-pro-preview":{"draws":32,"losses":33,"wins":25},"google/gemini-3.1-flash-lite":{"draws":18,"losses":9,"wins":37},"google/gemini-3.5-flash":{"draws":33,"losses":50,"wins":31},"google/gemini-3.5-flash-lite":{"draws":45,"losses":36,"wins":47},"google/gemini-3.6-flash":{"draws":53,"losses":77,"wins":42},"google/gemini-3.8-flash":{"draws":22,"losses":61,"wins":7},"google/gemma-4-31b-it":{"draws":20,"losses":9,"wins":25},"gpt-4.1":{"draws":11,"losses":4,"wins":15},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":29,"losses":29,"wins":20},"gpt-5.4":{"draws":22,"losses":51,"wins":13},"gpt-5.4-mini":{"draws":21,"losses":18,"wins":21},"gpt-5.4-nano":{"draws":22,"losses":32,"wins":40},"gpt-5.5":{"draws":35,"losses":36,"wins":11},"gpt-5.6-luna":{"draws":28,"losses":28,"wins":34},"gpt-5.6-sol":{"draws":10,"losses":69,"wins":11},"gpt-5.6-terra":{"draws":29,"losses":31,"wins":26},"gpt-6-astra":{"draws":5,"losses":85,"wins":0},"gpt-6-luna":{"draws":33,"losses":35,"wins":22},"gpt-6-sol":{"draws":14,"losses":67,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":83,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":33,"losses":5,"wins":28},"inclusionai/ling-3.0-flash":{"draws":28,"losses":3,"wins":33},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":29,"losses":20,"wins":49},"meta/muse-glimmer-30b":{"draws":37,"losses":13,"wins":28},"meta/muse-spark-1.2":{"draws":22,"losses":42,"wins":22},"meta/muse-spark-1.3":{"draws":25,"losses":49,"wins":16},"meta/muse-wonder":{"draws":18,"losses":60,"wins":12},"minimax/minimax-m3":{"draws":15,"losses":16,"wins":19},"mistralai/mistral-large-4-0":{"draws":20,"losses":27,"wins":9},"mistralai/mistral-medium-3-5":{"draws":21,"losses":8,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":12,"wins":8},"moonshotai/kimi-k3":{"draws":30,"losses":37,"wins":19},"nex-agi/nex-n2-pro":{"draws":13,"losses":11,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":16,"wins":28},"o3":{"draws":27,"losses":52,"wins":49},"openai/gpt-oss-120b":{"draws":26,"losses":23,"wins":29},"poolside/laguna-s-2.1":{"draws":32,"losses":24,"wins":28},"qwen/qwen3.7-max":{"draws":17,"losses":20,"wins":17},"qwen/qwen3.7-plus":{"draws":15,"losses":15,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":39,"wins":19},"qwen/qwen3.8-27b":{"draws":14,"losses":30,"wins":20},"qwen/qwen3.8-flash":{"draws":21,"losses":22,"wins":17},"qwen/qwen3.8-max":{"draws":30,"losses":37,"wins":23},"qwen/qwen3.8-max-0902":{"draws":31,"losses":44,"wins":15},"stealth/ox-alpha":{"draws":69,"losses":142,"wins":65},"stealth/space-bunny-alpha":{"draws":25,"losses":19,"wins":28},"stepfun/step-3.7-flash":{"draws":21,"losses":11,"wins":32},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":21,"losses":19,"wins":10},"tencent/hy4-preview":{"draws":26,"losses":42,"wins":18},"thinkingmachines/inkling":{"draws":37,"losses":31,"wins":50},"thinkingmachines/inkling-small":{"draws":35,"losses":19,"wins":36},"unbiased/pareto-26.10-preview":{"draws":2,"losses":28,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":12},"x-ai/grok-4.5":{"draws":23,"losses":48,"wins":19},"x-ai/grok-4.6":{"draws":20,"losses":56,"wins":14},"x-ai/grok-4.7":{"draws":9,"losses":59,"wins":12},"x-ai/grok-build-0.1":{"draws":14,"losses":5,"wins":11},"xiaomi/mimo-v2.5":{"draws":50,"losses":32,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":15,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":35,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":36,"wins":14},"z-ai/glm-5.2":{"draws":71,"losses":55,"wins":54},"z-ai/glm-5.3":{"draws":13,"losses":66,"wins":7},"z-ai/glm-5.3-flash":{"draws":21,"losses":50,"wins":19},"z-ai/glm-5.3-flashx":{"draws":28,"losses":41,"wins":21}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":26,"wins":32},"claude-fable-5":{"draws":22,"losses":64,"wins":10},"claude-fable-5-1":{"draws":10,"losses":97,"wins":1},"claude-haiku-5-5":{"draws":28,"losses":47,"wins":17},"claude-opus-4-5":{"draws":53,"losses":63,"wins":40},"claude-opus-4-8":{"draws":25,"losses":41,"wins":22},"claude-opus-5":{"draws":23,"losses":126,"wins":15},"claude-opus-5-5":{"draws":4,"losses":99,"wins":1},"claude-sonnet-5":{"draws":31,"losses":43,"wins":22},"claude-sonnet-5-5":{"draws":19,"losses":60,"wins":17},"cohere/north-mini-code":{"draws":13,"losses":4,"wins":19},"deepseek/deepseek-v4-flash":{"draws":51,"losses":35,"wins":58},"deepseek/deepseek-v4-pro":{"draws":29,"losses":39,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":40,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":40,"wins":22},"fireworks/ember-1":{"draws":35,"losses":44,"wins":17},"gemini-3.1-pro-preview":{"draws":32,"losses":38,"wins":26},"google/gemini-3.1-flash-lite":{"draws":25,"losses":9,"wins":30},"google/gemini-3.5-flash":{"draws":34,"losses":64,"wins":22},"google/gemini-3.5-flash-lite":{"draws":64,"losses":48,"wins":56},"google/gemini-3.6-flash":{"draws":39,"losses":87,"wins":26},"google/gemini-3.8-flash":{"draws":25,"losses":59,"wins":12},"google/gemma-4-31b-it":{"draws":23,"losses":11,"wins":22},"gpt-4.1":{"draws":12,"losses":11,"wins":9},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":3},"gpt-5":{"draws":28,"losses":39,"wins":17},"gpt-5.4":{"draws":24,"losses":49,"wins":19},"gpt-5.4-mini":{"draws":23,"losses":17,"wins":24},"gpt-5.4-nano":{"draws":24,"losses":36,"wins":36},"gpt-5.5":{"draws":37,"losses":37,"wins":14},"gpt-5.6-luna":{"draws":37,"losses":28,"wins":31},"gpt-5.6-sol":{"draws":14,"losses":73,"wins":9},"gpt-5.6-terra":{"draws":36,"losses":37,"wins":19},"gpt-6-astra":{"draws":8,"losses":88,"wins":0},"gpt-6-luna":{"draws":34,"losses":31,"wins":31},"gpt-6-sol":{"draws":13,"losses":76,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":90,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":34,"losses":5,"wins":29},"inclusionai/ling-3.0-flash":{"draws":36,"losses":11,"wins":21},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":32,"losses":26,"wins":46},"meta/muse-glimmer-30b":{"draws":41,"losses":16,"wins":27},"meta/muse-spark-1.2":{"draws":21,"losses":53,"wins":18},"meta/muse-spark-1.3":{"draws":25,"losses":54,"wins":17},"meta/muse-wonder":{"draws":16,"losses":68,"wins":12},"minimax/minimax-m3":{"draws":16,"losses":11,"wins":25},"mistralai/mistral-large-4-0":{"draws":18,"losses":25,"wins":17},"mistralai/mistral-medium-3-5":{"draws":29,"losses":8,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":12,"wins":6},"moonshotai/kimi-k3":{"draws":30,"losses":43,"wins":19},"nex-agi/nex-n2-pro":{"draws":16,"losses":5,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":17,"wins":26},"o3":{"draws":27,"losses":74,"wins":31},"openai/gpt-oss-120b":{"draws":36,"losses":18,"wins":30},"poolside/laguna-s-2.1":{"draws":41,"losses":23,"wins":28},"qwen/qwen3.7-max":{"draws":19,"losses":21,"wins":16},"qwen/qwen3.7-plus":{"draws":20,"losses":13,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":44,"wins":20},"qwen/qwen3.8-27b":{"draws":18,"losses":33,"wins":17},"qwen/qwen3.8-flash":{"draws":29,"losses":20,"wins":15},"qwen/qwen3.8-max":{"draws":30,"losses":43,"wins":23},"qwen/qwen3.8-max-0902":{"draws":33,"losses":40,"wins":23},"stealth/ox-alpha":{"draws":85,"losses":160,"wins":71},"stealth/space-bunny-alpha":{"draws":25,"losses":26,"wins":25},"stepfun/step-3.7-flash":{"draws":21,"losses":19,"wins":28},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":20,"losses":14,"wins":18},"tencent/hy4-preview":{"draws":24,"losses":54,"wins":14},"thinkingmachines/inkling":{"draws":43,"losses":24,"wins":61},"thinkingmachines/inkling-small":{"draws":41,"losses":28,"wins":27},"unbiased/pareto-26.10-preview":{"draws":0,"losses":31,"wins":1},"upstage/solar-mini4":{"draws":7,"losses":8,"wins":9},"x-ai/grok-4.5":{"draws":23,"losses":53,"wins":20},"x-ai/grok-4.6":{"draws":29,"losses":57,"wins":10},"x-ai/grok-4.7":{"draws":2,"losses":71,"wins":11},"x-ai/grok-build-0.1":{"draws":13,"losses":4,"wins":15},"xiaomi/mimo-v2.5":{"draws":61,"losses":32,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":16,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":35,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":38,"wins":13},"z-ai/glm-5.2":{"draws":72,"losses":78,"wins":42},"z-ai/glm-5.3":{"draws":20,"losses":67,"wins":5},"z-ai/glm-5.3-flash":{"draws":22,"losses":57,"wins":17},"z-ai/glm-5.3-flashx":{"draws":27,"losses":48,"wins":21}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":10,"wins":20},"claude-fable-5":{"draws":8,"losses":31,"wins":9},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":16,"wins":17},"claude-opus-4-5":{"draws":30,"losses":14,"wins":34},"claude-opus-4-8":{"draws":10,"losses":20,"wins":14},"claude-opus-5":{"draws":14,"losses":56,"wins":12},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":14,"losses":12,"wins":22},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":16},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":11},"deepseek/deepseek-v4-flash":{"draws":18,"losses":12,"wins":42},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":12,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":18},"fireworks/ember-1":{"draws":13,"losses":18,"wins":17},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"wins":23},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":23},"google/gemini-3.5-flash":{"draws":14,"losses":22,"wins":24},"google/gemini-3.5-flash-lite":{"draws":19,"losses":8,"wins":57},"google/gemini-3.6-flash":{"draws":25,"losses":31,"wins":36},"google/gemini-3.8-flash":{"draws":9,"losses":15,"wins":8},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":9,"wins":22},"gpt-5.4":{"draws":12,"losses":17,"wins":17},"gpt-5.4-mini":{"draws":9,"losses":8,"wins":15},"gpt-5.4-nano":{"draws":10,"losses":6,"wins":32},"gpt-5.5":{"draws":15,"losses":13,"wins":16},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":25},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":14},"gpt-5.6-terra":{"draws":18,"losses":11,"wins":17},"gpt-6-astra":{"draws":4,"losses":41,"wins":3},"gpt-6-luna":{"draws":16,"losses":14,"wins":18},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":6,"losses":39,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":21},"inclusionai/ling-3.0-flash":{"draws":13,"losses":0,"wins":21},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":34},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":25},"meta/muse-spark-1.2":{"draws":11,"losses":17,"wins":18},"meta/muse-spark-1.3":{"draws":9,"losses":19,"wins":20},"meta/muse-wonder":{"draws":12,"losses":24,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":16},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":9},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":13,"wins":20},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":3,"wins":24},"o3":{"draws":9,"losses":16,"wins":41},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":32},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":9,"losses":2,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":15,"wins":17},"qwen/qwen3.8-27b":{"draws":10,"losses":8,"wins":16},"qwen/qwen3.8-flash":{"draws":9,"losses":10,"wins":13},"qwen/qwen3.8-max":{"draws":15,"losses":14,"wins":19},"qwen/qwen3.8-max-0902":{"draws":10,"losses":21,"wins":17},"stealth/ox-alpha":{"draws":37,"losses":66,"wins":55},"stealth/space-bunny-alpha":{"draws":14,"losses":3,"wins":21},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":13,"losses":2,"wins":11},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":15},"thinkingmachines/inkling":{"draws":17,"losses":8,"wins":39},"thinkingmachines/inkling-small":{"draws":16,"losses":5,"wins":27},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":24,"wins":14},"x-ai/grok-4.6":{"draws":15,"losses":21,"wins":12},"x-ai/grok-4.7":{"draws":4,"losses":28,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":29,"losses":2,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":3,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":15,"wins":8},"z-ai/glm-5.2":{"draws":32,"losses":25,"wins":39},"z-ai/glm-5.3":{"draws":11,"losses":26,"wins":9},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":18},"z-ai/glm-5.3-flashx":{"draws":8,"losses":22,"wins":18}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":7},"claude-fable-5":{"draws":7,"losses":28,"wins":1},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":22,"wins":3},"claude-opus-4-5":{"draws":18,"losses":40,"wins":2},"claude-opus-4-8":{"draws":11,"losses":23,"wins":2},"claude-opus-5":{"draws":8,"losses":47,"wins":3},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":14,"losses":20,"wins":2},"claude-sonnet-5-5":{"draws":5,"losses":23,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":24,"losses":22,"wins":8},"deepseek/deepseek-v4-pro":{"draws":10,"losses":19,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":3},"fireworks/ember-1":{"draws":12,"losses":20,"wins":4},"gemini-3.1-pro-preview":{"draws":13,"losses":19,"wins":4},"google/gemini-3.1-flash-lite":{"draws":7,"losses":10,"wins":11},"google/gemini-3.5-flash":{"draws":17,"losses":24,"wins":5},"google/gemini-3.5-flash-lite":{"draws":26,"losses":27,"wins":11},"google/gemini-3.6-flash":{"draws":23,"losses":40,"wins":5},"google/gemini-3.8-flash":{"draws":13,"losses":21,"wins":2},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":1},"gpt-4.1":{"draws":6,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":15,"wins":1},"gpt-5.4":{"draws":11,"losses":21,"wins":2},"gpt-5.4-mini":{"draws":9,"losses":11,"wins":4},"gpt-5.4-nano":{"draws":9,"losses":23,"wins":6},"gpt-5.5":{"draws":11,"losses":20,"wins":1},"gpt-5.6-luna":{"draws":14,"losses":16,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":29,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":20,"wins":0},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":13,"losses":20,"wins":3},"gpt-6-sol":{"draws":4,"losses":32,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":7,"wins":8},"inclusionai/ling-3.0-flash":{"draws":14,"losses":6,"wins":4},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":20,"wins":10},"meta/muse-glimmer-30b":{"draws":16,"losses":10,"wins":4},"meta/muse-spark-1.2":{"draws":11,"losses":21,"wins":2},"meta/muse-spark-1.3":{"draws":11,"losses":23,"wins":2},"meta/muse-wonder":{"draws":7,"losses":27,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":3},"mistralai/mistral-large-4-0":{"draws":8,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":10,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":19,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":8,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":10,"wins":8},"o3":{"draws":11,"losses":37,"wins":4},"openai/gpt-oss-120b":{"draws":14,"losses":16,"wins":2},"poolside/laguna-s-2.1":{"draws":15,"losses":11,"wins":6},"qwen/qwen3.7-max":{"draws":8,"losses":10,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":22,"wins":3},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":1},"qwen/qwen3.8-flash":{"draws":11,"losses":12,"wins":1},"qwen/qwen3.8-max":{"draws":12,"losses":21,"wins":3},"qwen/qwen3.8-max-0902":{"draws":13,"losses":20,"wins":3},"stealth/ox-alpha":{"draws":28,"losses":69,"wins":5},"stealth/space-bunny-alpha":{"draws":12,"losses":13,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":15,"wins":2},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":3},"tencent/hy4-preview":{"draws":10,"losses":22,"wins":2},"thinkingmachines/inkling":{"draws":15,"losses":19,"wins":10},"thinkingmachines/inkling-small":{"draws":16,"losses":12,"wins":8},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":26,"wins":1},"x-ai/grok-4.6":{"draws":9,"losses":25,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":28,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":27,"losses":22,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":16,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":0},"z-ai/glm-5.2":{"draws":26,"losses":39,"wins":7},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":21,"wins":3},"z-ai/glm-5.3-flashx":{"draws":13,"losses":21,"wins":2}},"gpt-4.1":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":11,"wins":17},"claude-fable-5":{"draws":8,"losses":28,"wins":12},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":23,"wins":8},"claude-opus-4-5":{"draws":32,"losses":29,"wins":17},"claude-opus-4-8":{"draws":14,"losses":25,"wins":5},"claude-opus-5":{"draws":9,"losses":68,"wins":5},"claude-opus-5-5":{"draws":5,"losses":46,"wins":1},"claude-sonnet-5":{"draws":17,"losses":17,"wins":14},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":24,"losses":16,"wins":32},"deepseek/deepseek-v4-pro":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":20,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":24,"wins":11},"fireworks/ember-1":{"draws":14,"losses":19,"wins":15},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":14,"losses":29,"wins":17},"google/gemini-3.5-flash-lite":{"draws":30,"losses":28,"wins":26},"google/gemini-3.6-flash":{"draws":25,"losses":46,"wins":21},"google/gemini-3.8-flash":{"draws":16,"losses":26,"wins":6},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":14,"wins":15},"gpt-5.4":{"draws":13,"losses":24,"wins":9},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":11,"losses":17,"wins":20},"gpt-5.5":{"draws":11,"losses":24,"wins":9},"gpt-5.6-luna":{"draws":17,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":8,"losses":33,"wins":7},"gpt-5.6-terra":{"draws":19,"losses":12,"wins":15},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":10,"losses":19,"wins":19},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":8,"wins":11},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":20},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":18,"losses":10,"wins":24},"meta/muse-glimmer-30b":{"draws":19,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":17,"losses":21,"wins":8},"meta/muse-spark-1.3":{"draws":18,"losses":26,"wins":4},"meta/muse-wonder":{"draws":7,"losses":35,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":13},"mistralai/mistral-large-4-0":{"draws":12,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":13,"losses":21,"wins":12},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":7,"wins":17},"o3":{"draws":13,"losses":26,"wins":27},"openai/gpt-oss-120b":{"draws":13,"losses":9,"wins":20},"poolside/laguna-s-2.1":{"draws":16,"losses":12,"wins":18},"qwen/qwen3.7-max":{"draws":13,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":16,"wins":5},"qwen/qwen3.8-max":{"draws":19,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":23,"wins":7},"stealth/ox-alpha":{"draws":43,"losses":79,"wins":36},"stealth/space-bunny-alpha":{"draws":15,"losses":13,"wins":10},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":19},"stepfun/step-5-preview":{"draws":3,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":13,"losses":24,"wins":9},"thinkingmachines/inkling":{"draws":17,"losses":20,"wins":27},"thinkingmachines/inkling-small":{"draws":17,"losses":13,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":29,"wins":8},"x-ai/grok-4.6":{"draws":19,"losses":23,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":29,"losses":17,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":17,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":35,"losses":38,"wins":23},"z-ai/glm-5.3":{"draws":7,"losses":31,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":28,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":30,"wins":7}},"gpt-4.1-nano":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":4},"claude-fable-5":{"draws":6,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":9,"wins":0},"claude-opus-4-5":{"draws":17,"losses":11,"wins":0},"claude-opus-4-8":{"draws":7,"losses":7,"wins":0},"claude-opus-5":{"draws":8,"losses":18,"wins":0},"claude-opus-5-5":{"draws":2,"losses":16,"wins":0},"claude-sonnet-5":{"draws":9,"losses":9,"wins":0},"claude-sonnet-5-5":{"draws":8,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":3},"deepseek/deepseek-v4-pro":{"draws":10,"losses":4,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":8,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":9,"wins":1},"fireworks/ember-1":{"draws":9,"losses":8,"wins":1},"gemini-3.1-pro-preview":{"draws":11,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":5,"wins":1},"google/gemini-3.5-flash":{"draws":8,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":18,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":14,"losses":18,"wins":2},"google/gemini-3.8-flash":{"draws":6,"losses":12,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":1},"gpt-4.1":{"draws":3,"losses":3,"wins":0},"gpt-5":{"draws":10,"losses":4,"wins":0},"gpt-5.4":{"draws":10,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":1},"gpt-5.5":{"draws":9,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":0},"gpt-6-astra":{"draws":2,"losses":16,"wins":0},"gpt-6-luna":{"draws":9,"losses":7,"wins":2},"gpt-6-sol":{"draws":2,"losses":16,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":17,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":2},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":1},"meta/muse-spark-1.2":{"draws":9,"losses":5,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":0},"meta/muse-wonder":{"draws":9,"losses":9,"wins":0},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":1},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":2},"o3":{"draws":6,"losses":10,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":13,"losses":2,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":11,"wins":1},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"wins":1},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":0},"qwen/qwen3.8-max":{"draws":10,"losses":7,"wins":1},"qwen/qwen3.8-max-0902":{"draws":7,"losses":10,"wins":1},"stealth/ox-alpha":{"draws":33,"losses":34,"wins":5},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":5,"losses":11,"wins":0},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":1},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":9,"losses":9,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":6,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":21,"losses":15,"wins":0},"z-ai/glm-5.3":{"draws":7,"losses":11,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":9,"wins":2},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":0}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":12,"wins":10},"claude-fable-5":{"draws":8,"losses":25,"wins":3},"claude-fable-5-1":{"draws":0,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":18,"wins":10},"claude-opus-4-5":{"draws":16,"losses":25,"wins":17},"claude-opus-4-8":{"draws":8,"losses":17,"wins":7},"claude-opus-5":{"draws":6,"losses":58,"wins":4},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":10,"losses":22,"wins":4},"claude-sonnet-5-5":{"draws":9,"losses":19,"wins":8},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":20,"losses":17,"wins":19},"deepseek/deepseek-v4-pro":{"draws":6,"losses":19,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":11,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":14,"wins":10},"fireworks/ember-1":{"draws":10,"losses":20,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":15},"google/gemini-3.5-flash":{"draws":10,"losses":22,"wins":12},"google/gemini-3.5-flash-lite":{"draws":17,"losses":14,"wins":29},"google/gemini-3.6-flash":{"draws":16,"losses":30,"wins":22},"google/gemini-3.8-flash":{"draws":10,"losses":17,"wins":9},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":7},"gpt-4.1":{"draws":5,"losses":2,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":9,"wins":9},"gpt-5.4":{"draws":5,"losses":23,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":5},"gpt-5.4-nano":{"draws":9,"losses":12,"wins":17},"gpt-5.5":{"draws":14,"losses":18,"wins":2},"gpt-5.6-luna":{"draws":11,"losses":9,"wins":16},"gpt-5.6-sol":{"draws":6,"losses":26,"wins":4},"gpt-5.6-terra":{"draws":8,"losses":19,"wins":7},"gpt-6-astra":{"draws":4,"losses":32,"wins":0},"gpt-6-luna":{"draws":10,"losses":14,"wins":12},"gpt-6-sol":{"draws":4,"losses":28,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":3},"inception/mercury-2.5-preview":{"draws":9,"losses":4,"wins":9},"inclusionai/ling-3.0-flash":{"draws":9,"losses":6,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":10,"wins":15},"meta/muse-glimmer-30b":{"draws":12,"losses":7,"wins":15},"meta/muse-spark-1.2":{"draws":6,"losses":24,"wins":6},"meta/muse-spark-1.3":{"draws":6,"losses":25,"wins":5},"meta/muse-wonder":{"draws":7,"losses":23,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":10},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":10},"nex-agi/nex-n2-pro":{"draws":3,"losses":6,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":4,"wins":13},"o3":{"draws":10,"losses":18,"wins":22},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":18,"losses":8,"wins":14},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":6},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":16,"wins":10},"qwen/qwen3.8-27b":{"draws":5,"losses":12,"wins":7},"qwen/qwen3.8-flash":{"draws":5,"losses":11,"wins":8},"qwen/qwen3.8-max":{"draws":10,"losses":18,"wins":8},"qwen/qwen3.8-max-0902":{"draws":10,"losses":17,"wins":9},"stealth/ox-alpha":{"draws":26,"losses":69,"wins":29},"stealth/space-bunny-alpha":{"draws":7,"losses":9,"wins":12},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":12},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":4},"tencent/hy4-preview":{"draws":9,"losses":16,"wins":9},"thinkingmachines/inkling":{"draws":9,"losses":15,"wins":26},"thinkingmachines/inkling-small":{"draws":16,"losses":8,"wins":12},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":25,"wins":7},"x-ai/grok-4.6":{"draws":13,"losses":18,"wins":5},"x-ai/grok-4.7":{"draws":2,"losses":25,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":17,"losses":9,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":13,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":13,"wins":8},"z-ai/glm-5.2":{"draws":21,"losses":25,"wins":26},"z-ai/glm-5.3":{"draws":5,"losses":24,"wins":5},"z-ai/glm-5.3-flash":{"draws":5,"losses":20,"wins":11},"z-ai/glm-5.3-flashx":{"draws":9,"losses":19,"wins":8}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":14,"wins":18},"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":12,"losses":21,"wins":13},"claude-opus-4-5":{"draws":27,"losses":28,"wins":23},"claude-opus-4-8":{"draws":13,"losses":17,"wins":14},"claude-opus-5":{"draws":15,"losses":61,"wins":6},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":12,"losses":15,"wins":21},"claude-sonnet-5-5":{"draws":11,"losses":27,"wins":10},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":23,"losses":15,"wins":34},"deepseek/deepseek-v4-pro":{"draws":9,"losses":19,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":17,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":21,"wins":12},"fireworks/ember-1":{"draws":19,"losses":15,"wins":14},"gemini-3.1-pro-preview":{"draws":12,"losses":18,"wins":18},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":11,"losses":23,"wins":26},"google/gemini-3.5-flash-lite":{"draws":23,"losses":20,"wins":41},"google/gemini-3.6-flash":{"draws":19,"losses":42,"wins":31},"google/gemini-3.8-flash":{"draws":11,"losses":29,"wins":8},"google/gemma-4-31b-it":{"draws":13,"losses":3,"wins":12},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":16,"wins":17},"gpt-5.4":{"draws":7,"losses":22,"wins":1},"gpt-5.4-mini":{"draws":11,"losses":4,"wins":17},"gpt-5.4-nano":{"draws":8,"losses":17,"wins":23},"gpt-5.5":{"draws":16,"losses":17,"wins":11},"gpt-5.6-luna":{"draws":20,"losses":12,"wins":16},"gpt-5.6-sol":{"draws":9,"losses":27,"wins":12},"gpt-5.6-terra":{"draws":16,"losses":20,"wins":10},"gpt-6-astra":{"draws":1,"losses":43,"wins":4},"gpt-6-luna":{"draws":20,"losses":14,"wins":14},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":1,"wins":17},"inclusionai/ling-3.0-flash":{"draws":8,"losses":8,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":12,"wins":26},"meta/muse-glimmer-30b":{"draws":10,"losses":14,"wins":18},"meta/muse-spark-1.2":{"draws":9,"losses":23,"wins":14},"meta/muse-spark-1.3":{"draws":7,"losses":29,"wins":12},"meta/muse-wonder":{"draws":9,"losses":29,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":13},"mistralai/mistral-large-4-0":{"draws":14,"losses":8,"wins":8},"mistralai/mistral-medium-3-5":{"draws":10,"losses":5,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":12,"losses":16,"wins":18},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":4,"wins":22},"o3":{"draws":9,"losses":29,"wins":28},"openai/gpt-oss-120b":{"draws":10,"losses":12,"wins":20},"poolside/laguna-s-2.1":{"draws":16,"losses":9,"wins":21},"qwen/qwen3.7-max":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-27b":{"draws":9,"losses":12,"wins":13},"qwen/qwen3.8-flash":{"draws":7,"losses":18,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":22,"wins":11},"qwen/qwen3.8-max-0902":{"draws":10,"losses":20,"wins":18},"stealth/ox-alpha":{"draws":38,"losses":80,"wins":40},"stealth/space-bunny-alpha":{"draws":13,"losses":9,"wins":16},"stepfun/step-3.7-flash":{"draws":8,"losses":8,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":23,"wins":12},"thinkingmachines/inkling":{"draws":19,"losses":11,"wins":34},"thinkingmachines/inkling-small":{"draws":16,"losses":9,"wins":23},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":11,"losses":22,"wins":15},"x-ai/grok-4.6":{"draws":12,"losses":28,"wins":8},"x-ai/grok-4.7":{"draws":4,"losses":33,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":21,"losses":12,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":14,"wins":10},"z-ai/glm-5.2":{"draws":28,"losses":29,"wins":39},"z-ai/glm-5.3":{"draws":10,"losses":28,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":26,"wins":16},"z-ai/glm-5.3-flashx":{"draws":15,"losses":21,"wins":12}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":18,"wins":5},"claude-fable-5":{"draws":11,"losses":36,"wins":1},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":30,"wins":2},"claude-opus-4-5":{"draws":36,"losses":35,"wins":7},"claude-opus-4-8":{"draws":11,"losses":30,"wins":3},"claude-opus-5":{"draws":21,"losses":58,"wins":3},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":21,"losses":19,"wins":8},"claude-sonnet-5-5":{"draws":10,"losses":33,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":34,"losses":25,"wins":13},"deepseek/deepseek-v4-pro":{"draws":16,"losses":21,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":23,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":21,"wins":5},"fireworks/ember-1":{"draws":22,"losses":23,"wins":3},"gemini-3.1-pro-preview":{"draws":22,"losses":19,"wins":7},"google/gemini-3.1-flash-lite":{"draws":14,"losses":3,"wins":15},"google/gemini-3.5-flash":{"draws":24,"losses":32,"wins":4},"google/gemini-3.5-flash-lite":{"draws":32,"losses":36,"wins":16},"google/gemini-3.6-flash":{"draws":34,"losses":53,"wins":5},"google/gemini-3.8-flash":{"draws":17,"losses":30,"wins":1},"google/gemma-4-31b-it":{"draws":13,"losses":8,"wins":7},"gpt-4.1":{"draws":7,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":20,"losses":19,"wins":3},"gpt-5.4":{"draws":18,"losses":28,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":7,"wins":2},"gpt-5.4-nano":{"draws":16,"losses":24,"wins":8},"gpt-5.5":{"draws":18,"losses":19,"wins":7},"gpt-5.6-luna":{"draws":20,"losses":20,"wins":8},"gpt-5.6-sol":{"draws":12,"losses":35,"wins":1},"gpt-5.6-terra":{"draws":21,"losses":20,"wins":5},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":22,"losses":23,"wins":3},"gpt-6-sol":{"draws":6,"losses":40,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":18,"losses":9,"wins":7},"inclusionai/ling-3.0-flash":{"draws":21,"losses":9,"wins":4},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":19,"wins":8},"meta/muse-glimmer-30b":{"draws":24,"losses":11,"wins":7},"meta/muse-spark-1.2":{"draws":16,"losses":26,"wins":4},"meta/muse-spark-1.3":{"draws":10,"losses":37,"wins":1},"meta/muse-wonder":{"draws":14,"losses":32,"wins":2},"minimax/minimax-m3":{"draws":9,"losses":13,"wins":4},"mistralai/mistral-large-4-0":{"draws":16,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":14,"losses":7,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":18,"losses":25,"wins":3},"nex-agi/nex-n2-pro":{"draws":9,"losses":9,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":14,"wins":4},"o3":{"draws":18,"losses":41,"wins":7},"openai/gpt-oss-120b":{"draws":21,"losses":15,"wins":6},"poolside/laguna-s-2.1":{"draws":25,"losses":16,"wins":5},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":12,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":26,"wins":2},"qwen/qwen3.8-27b":{"draws":10,"losses":18,"wins":6},"qwen/qwen3.8-flash":{"draws":16,"losses":13,"wins":3},"qwen/qwen3.8-max":{"draws":26,"losses":16,"wins":6},"qwen/qwen3.8-max-0902":{"draws":24,"losses":23,"wins":1},"stealth/ox-alpha":{"draws":59,"losses":87,"wins":12},"stealth/space-bunny-alpha":{"draws":16,"losses":22,"wins":0},"stepfun/step-3.7-flash":{"draws":14,"losses":15,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":11,"wins":3},"tencent/hy4-preview":{"draws":19,"losses":27,"wins":0},"thinkingmachines/inkling":{"draws":25,"losses":26,"wins":13},"thinkingmachines/inkling-small":{"draws":26,"losses":15,"wins":7},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":17,"losses":28,"wins":3},"x-ai/grok-4.6":{"draws":19,"losses":27,"wins":2},"x-ai/grok-4.7":{"draws":7,"losses":35,"wins":0},"x-ai/grok-build-0.1":{"draws":8,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":32,"losses":27,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":10,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":16,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":21,"wins":1},"z-ai/glm-5.2":{"draws":50,"losses":41,"wins":5},"z-ai/glm-5.3":{"draws":15,"losses":30,"wins":1},"z-ai/glm-5.3-flash":{"draws":16,"losses":26,"wins":6},"z-ai/glm-5.3-flashx":{"draws":16,"losses":31,"wins":1}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":28,"wins":22},"claude-fable-5":{"draws":11,"losses":58,"wins":3},"claude-fable-5-1":{"draws":1,"losses":75,"wins":0},"claude-haiku-5-5":{"draws":17,"losses":38,"wins":15},"claude-opus-4-5":{"draws":32,"losses":63,"wins":23},"claude-opus-4-8":{"draws":14,"losses":42,"wins":12},"claude-opus-5":{"draws":11,"losses":106,"wins":3},"claude-opus-5-5":{"draws":5,"losses":75,"wins":0},"claude-sonnet-5":{"draws":23,"losses":33,"wins":16},"claude-sonnet-5-5":{"draws":12,"losses":53,"wins":7},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":16},"deepseek/deepseek-v4-flash":{"draws":30,"losses":42,"wins":42},"deepseek/deepseek-v4-pro":{"draws":11,"losses":30,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":32,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":35,"wins":14},"fireworks/ember-1":{"draws":19,"losses":43,"wins":10},"gemini-3.1-pro-preview":{"draws":22,"losses":35,"wins":15},"google/gemini-3.1-flash-lite":{"draws":12,"losses":13,"wins":25},"google/gemini-3.5-flash":{"draws":20,"losses":54,"wins":16},"google/gemini-3.5-flash-lite":{"draws":35,"losses":47,"wins":42},"google/gemini-3.6-flash":{"draws":28,"losses":83,"wins":25},"google/gemini-3.8-flash":{"draws":18,"losses":45,"wins":9},"google/gemma-4-31b-it":{"draws":15,"losses":10,"wins":17},"gpt-4.1":{"draws":7,"losses":9,"wins":8},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":3},"gpt-5":{"draws":13,"losses":35,"wins":16},"gpt-5.4":{"draws":10,"losses":45,"wins":13},"gpt-5.4-mini":{"draws":17,"losses":15,"wins":16},"gpt-5.4-nano":{"draws":14,"losses":24,"wins":22},"gpt-5.5":{"draws":18,"losses":32,"wins":14},"gpt-5.6-luna":{"draws":22,"losses":30,"wins":20},"gpt-5.6-sol":{"draws":9,"losses":59,"wins":4},"gpt-5.6-terra":{"draws":17,"losses":37,"wins":14},"gpt-6-astra":{"draws":2,"losses":70,"wins":0},"gpt-6-luna":{"draws":16,"losses":42,"wins":14},"gpt-6-sol":{"draws":8,"losses":56,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":65,"wins":2},"inception/mercury-2.5-preview":{"draws":18,"losses":9,"wins":23},"inclusionai/ling-3.0-flash":{"draws":17,"losses":8,"wins":27},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":19,"losses":26,"wins":33},"meta/muse-glimmer-30b":{"draws":18,"losses":19,"wins":23},"meta/muse-spark-1.2":{"draws":12,"losses":38,"wins":18},"meta/muse-spark-1.3":{"draws":12,"losses":52,"wins":8},"meta/muse-wonder":{"draws":5,"losses":55,"wins":12},"minimax/minimax-m3":{"draws":10,"losses":12,"wins":20},"mistralai/mistral-large-4-0":{"draws":8,"losses":25,"wins":11},"mistralai/mistral-medium-3-5":{"draws":11,"losses":9,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":7,"wins":6},"moonshotai/kimi-k3":{"draws":18,"losses":37,"wins":13},"nex-agi/nex-n2-pro":{"draws":10,"losses":14,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":20,"wins":28},"o3":{"draws":14,"losses":57,"wins":37},"openai/gpt-oss-120b":{"draws":24,"losses":24,"wins":16},"poolside/laguna-s-2.1":{"draws":30,"losses":26,"wins":20},"qwen/qwen3.7-max":{"draws":18,"losses":19,"wins":9},"qwen/qwen3.7-plus":{"draws":10,"losses":16,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":40,"wins":13},"qwen/qwen3.8-27b":{"draws":15,"losses":24,"wins":13},"qwen/qwen3.8-flash":{"draws":15,"losses":23,"wins":10},"qwen/qwen3.8-max":{"draws":15,"losses":37,"wins":20},"qwen/qwen3.8-max-0902":{"draws":22,"losses":35,"wins":15},"stealth/ox-alpha":{"draws":49,"losses":123,"wins":50},"stealth/space-bunny-alpha":{"draws":13,"losses":27,"wins":14},"stepfun/step-3.7-flash":{"draws":11,"losses":18,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":12,"losses":21,"wins":7},"tencent/hy4-preview":{"draws":14,"losses":46,"wins":8},"thinkingmachines/inkling":{"draws":25,"losses":40,"wins":29},"thinkingmachines/inkling-small":{"draws":26,"losses":21,"wins":25},"unbiased/pareto-26.10-preview":{"draws":1,"losses":23,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":8,"wins":9},"x-ai/grok-4.5":{"draws":16,"losses":47,"wins":9},"x-ai/grok-4.6":{"draws":14,"losses":46,"wins":12},"x-ai/grok-4.7":{"draws":10,"losses":54,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":8,"wins":10},"xiaomi/mimo-v2.5":{"draws":30,"losses":39,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":20,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":25,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":35,"wins":6},"z-ai/glm-5.2":{"draws":42,"losses":66,"wins":36},"z-ai/glm-5.3":{"draws":13,"losses":48,"wins":7},"z-ai/glm-5.3-flash":{"draws":13,"losses":44,"wins":15},"z-ai/glm-5.3-flashx":{"draws":18,"losses":40,"wins":14}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":9,"wins":12},"claude-fable-5":{"draws":12,"losses":23,"wins":7},"claude-fable-5-1":{"draws":2,"losses":43,"wins":3},"claude-haiku-5-5":{"draws":17,"losses":17,"wins":6},"claude-opus-4-5":{"draws":36,"losses":21,"wins":11},"claude-opus-4-8":{"draws":18,"losses":16,"wins":4},"claude-opus-5":{"draws":15,"losses":64,"wins":1},"claude-opus-5-5":{"draws":8,"losses":38,"wins":0},"claude-sonnet-5":{"draws":22,"losses":10,"wins":10},"claude-sonnet-5-5":{"draws":11,"losses":21,"wins":10},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":34,"losses":8,"wins":20},"deepseek/deepseek-v4-pro":{"draws":19,"losses":13,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":14,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":18,"wins":8},"fireworks/ember-1":{"draws":17,"losses":17,"wins":8},"gemini-3.1-pro-preview":{"draws":16,"losses":15,"wins":11},"google/gemini-3.1-flash-lite":{"draws":13,"losses":0,"wins":13},"google/gemini-3.5-flash":{"draws":22,"losses":20,"wins":10},"google/gemini-3.5-flash-lite":{"draws":38,"losses":13,"wins":21},"google/gemini-3.6-flash":{"draws":28,"losses":38,"wins":14},"google/gemini-3.8-flash":{"draws":19,"losses":16,"wins":7},"google/gemma-4-31b-it":{"draws":13,"losses":3,"wins":8},"gpt-4.1":{"draws":6,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":21,"losses":11,"wins":6},"gpt-5.4":{"draws":12,"losses":18,"wins":10},"gpt-5.4-mini":{"draws":15,"losses":8,"wins":5},"gpt-5.4-nano":{"draws":17,"losses":8,"wins":15},"gpt-5.5":{"draws":15,"losses":9,"wins":2},"gpt-5.6-luna":{"draws":19,"losses":10,"wins":13},"gpt-5.6-sol":{"draws":10,"losses":25,"wins":7},"gpt-5.6-terra":{"draws":23,"losses":11,"wins":6},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":16,"losses":15,"wins":11},"gpt-6-sol":{"draws":10,"losses":30,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":0,"wins":9},"inclusionai/ling-3.0-flash":{"draws":21,"losses":2,"wins":5},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":9,"wins":15},"meta/muse-glimmer-30b":{"draws":20,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":11},"meta/muse-spark-1.3":{"draws":13,"losses":23,"wins":6},"meta/muse-wonder":{"draws":17,"losses":19,"wins":6},"minimax/minimax-m3":{"draws":10,"losses":7,"wins":7},"mistralai/mistral-large-4-0":{"draws":14,"losses":8,"wins":6},"mistralai/mistral-medium-3-5":{"draws":14,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":18,"losses":16,"wins":8},"nex-agi/nex-n2-pro":{"draws":9,"losses":2,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":3,"wins":9},"o3":{"draws":18,"losses":17,"wins":19},"openai/gpt-oss-120b":{"draws":20,"losses":6,"wins":12},"poolside/laguna-s-2.1":{"draws":24,"losses":9,"wins":9},"qwen/qwen3.7-max":{"draws":14,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":17,"wins":8},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":4},"qwen/qwen3.8-flash":{"draws":15,"losses":7,"wins":6},"qwen/qwen3.8-max":{"draws":17,"losses":15,"wins":10},"qwen/qwen3.8-max-0902":{"draws":19,"losses":18,"wins":5},"stealth/ox-alpha":{"draws":47,"losses":68,"wins":27},"stealth/space-bunny-alpha":{"draws":18,"losses":7,"wins":9},"stepfun/step-3.7-flash":{"draws":13,"losses":5,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":7,"wins":3},"tencent/hy4-preview":{"draws":18,"losses":18,"wins":4},"thinkingmachines/inkling":{"draws":26,"losses":7,"wins":25},"thinkingmachines/inkling-small":{"draws":21,"losses":7,"wins":14},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":15,"losses":25,"wins":2},"x-ai/grok-4.6":{"draws":15,"losses":23,"wins":4},"x-ai/grok-4.7":{"draws":5,"losses":26,"wins":7},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":34,"losses":7,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":4,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":12,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":15,"wins":5},"z-ai/glm-5.2":{"draws":37,"losses":23,"wins":24},"z-ai/glm-5.3":{"draws":9,"losses":25,"wins":6},"z-ai/glm-5.3-flash":{"draws":13,"losses":20,"wins":9},"z-ai/glm-5.3-flashx":{"draws":18,"losses":18,"wins":6}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":24,"wins":8},"claude-fable-5":{"draws":9,"losses":36,"wins":3},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":32,"wins":2},"claude-opus-4-5":{"draws":26,"losses":45,"wins":7},"claude-opus-4-8":{"draws":13,"losses":29,"wins":2},"claude-opus-5":{"draws":9,"losses":69,"wins":4},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":12,"losses":30,"wins":6},"claude-sonnet-5-5":{"draws":12,"losses":31,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":7,"wins":6},"deepseek/deepseek-v4-flash":{"draws":29,"losses":30,"wins":13},"deepseek/deepseek-v4-pro":{"draws":14,"losses":26,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":22,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":28,"wins":6},"fireworks/ember-1":{"draws":15,"losses":27,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":26,"wins":10},"google/gemini-3.1-flash-lite":{"draws":7,"losses":16,"wins":9},"google/gemini-3.5-flash":{"draws":11,"losses":43,"wins":6},"google/gemini-3.5-flash-lite":{"draws":23,"losses":43,"wins":18},"google/gemini-3.6-flash":{"draws":25,"losses":62,"wins":5},"google/gemini-3.8-flash":{"draws":6,"losses":39,"wins":3},"google/gemma-4-31b-it":{"draws":10,"losses":15,"wins":3},"gpt-4.1":{"draws":4,"losses":11,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":11,"losses":27,"wins":4},"gpt-5.4":{"draws":13,"losses":29,"wins":4},"gpt-5.4-mini":{"draws":11,"losses":17,"wins":4},"gpt-5.4-nano":{"draws":13,"losses":27,"wins":8},"gpt-5.5":{"draws":13,"losses":28,"wins":3},"gpt-5.6-luna":{"draws":13,"losses":15,"wins":4},"gpt-5.6-sol":{"draws":4,"losses":40,"wins":4},"gpt-5.6-terra":{"draws":15,"losses":24,"wins":7},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":16,"losses":25,"wins":7},"gpt-6-sol":{"draws":9,"losses":37,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":13,"wins":5},"inclusionai/ling-3.0-flash":{"draws":17,"losses":13,"wins":4},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":29,"wins":6},"meta/muse-glimmer-30b":{"draws":17,"losses":22,"wins":3},"meta/muse-spark-1.2":{"draws":14,"losses":25,"wins":7},"meta/muse-spark-1.3":{"draws":12,"losses":34,"wins":2},"meta/muse-wonder":{"draws":9,"losses":36,"wins":3},"minimax/minimax-m3":{"draws":8,"losses":13,"wins":5},"mistralai/mistral-large-4-0":{"draws":8,"losses":19,"wins":3},"mistralai/mistral-medium-3-5":{"draws":10,"losses":10,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":26,"wins":5},"nex-agi/nex-n2-pro":{"draws":9,"losses":6,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":24,"wins":6},"o3":{"draws":8,"losses":52,"wins":6},"openai/gpt-oss-120b":{"draws":19,"losses":15,"wins":8},"poolside/laguna-s-2.1":{"draws":14,"losses":26,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":15,"wins":3},"qwen/qwen3.7-plus":{"draws":10,"losses":11,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":31,"wins":0},"qwen/qwen3.8-27b":{"draws":11,"losses":20,"wins":3},"qwen/qwen3.8-flash":{"draws":12,"losses":15,"wins":5},"qwen/qwen3.8-max":{"draws":12,"losses":29,"wins":7},"qwen/qwen3.8-max-0902":{"draws":14,"losses":31,"wins":3},"stealth/ox-alpha":{"draws":49,"losses":100,"wins":9},"stealth/space-bunny-alpha":{"draws":15,"losses":19,"wins":4},"stepfun/step-3.7-flash":{"draws":11,"losses":16,"wins":7},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":18,"wins":0},"tencent/hy4-preview":{"draws":12,"losses":30,"wins":4},"thinkingmachines/inkling":{"draws":22,"losses":26,"wins":16},"thinkingmachines/inkling-small":{"draws":18,"losses":23,"wins":7},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":15,"losses":32,"wins":1},"x-ai/grok-4.6":{"draws":9,"losses":36,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":38,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":7,"wins":4},"xiaomi/mimo-v2.5":{"draws":28,"losses":35,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":15,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":18,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":25,"wins":1},"z-ai/glm-5.2":{"draws":36,"losses":53,"wins":7},"z-ai/glm-5.3":{"draws":9,"losses":36,"wins":1},"z-ai/glm-5.3-flash":{"draws":14,"losses":29,"wins":5},"z-ai/glm-5.3-flashx":{"draws":12,"losses":34,"wins":2}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":3,"wins":28},"claude-fable-5":{"draws":7,"losses":29,"wins":12},"claude-fable-5-1":{"draws":2,"losses":48,"wins":4},"claude-haiku-5-5":{"draws":4,"losses":22,"wins":20},"claude-opus-4-5":{"draws":21,"losses":13,"wins":44},"claude-opus-4-8":{"draws":9,"losses":21,"wins":14},"claude-opus-5":{"draws":10,"losses":64,"wins":8},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":14,"losses":9,"wins":25},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":17},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":14,"losses":12,"wins":46},"deepseek/deepseek-v4-pro":{"draws":11,"losses":16,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":16,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":21,"wins":13},"fireworks/ember-1":{"draws":11,"losses":18,"wins":19},"gemini-3.1-pro-preview":{"draws":10,"losses":13,"wins":25},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":11,"losses":18,"wins":31},"google/gemini-3.5-flash-lite":{"draws":21,"losses":10,"wins":53},"google/gemini-3.6-flash":{"draws":20,"losses":32,"wins":40},"google/gemini-3.8-flash":{"draws":10,"losses":21,"wins":17},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":4,"losses":5,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":12,"wins":18},"gpt-5.4":{"draws":11,"losses":20,"wins":15},"gpt-5.4-mini":{"draws":14,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":10,"losses":7,"wins":31},"gpt-5.5":{"draws":12,"losses":22,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":24},"gpt-5.6-sol":{"draws":4,"losses":19,"wins":9},"gpt-5.6-terra":{"draws":17,"losses":12,"wins":17},"gpt-6-astra":{"draws":3,"losses":42,"wins":3},"gpt-6-luna":{"draws":12,"losses":11,"wins":25},"gpt-6-sol":{"draws":3,"losses":36,"wins":9},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":0,"wins":21},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":4,"wins":37},"meta/muse-glimmer-30b":{"draws":13,"losses":4,"wins":25},"meta/muse-spark-1.2":{"draws":11,"losses":16,"wins":19},"meta/muse-spark-1.3":{"draws":7,"losses":22,"wins":19},"meta/muse-wonder":{"draws":10,"losses":27,"wins":11},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"mistralai/mistral-large-4-0":{"draws":8,"losses":9,"wins":13},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":10,"losses":15,"wins":21},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":6,"wins":27},"o3":{"draws":6,"losses":13,"wins":47},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":30},"poolside/laguna-s-2.1":{"draws":11,"losses":4,"wins":31},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":19,"wins":18},"qwen/qwen3.8-27b":{"draws":9,"losses":7,"wins":18},"qwen/qwen3.8-flash":{"draws":12,"losses":8,"wins":12},"qwen/qwen3.8-max":{"draws":11,"losses":15,"wins":22},"qwen/qwen3.8-max-0902":{"draws":13,"losses":16,"wins":19},"stealth/ox-alpha":{"draws":35,"losses":60,"wins":63},"stealth/space-bunny-alpha":{"draws":10,"losses":6,"wins":22},"stepfun/step-3.7-flash":{"draws":6,"losses":5,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":15},"tencent/hy4-preview":{"draws":11,"losses":18,"wins":17},"thinkingmachines/inkling":{"draws":18,"losses":5,"wins":41},"thinkingmachines/inkling-small":{"draws":14,"losses":4,"wins":30},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":22,"wins":18},"x-ai/grok-4.6":{"draws":13,"losses":22,"wins":13},"x-ai/grok-4.7":{"draws":6,"losses":23,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":22,"losses":4,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":12},"z-ai/glm-5.2":{"draws":21,"losses":26,"wins":49},"z-ai/glm-5.3":{"draws":7,"losses":27,"wins":12},"z-ai/glm-5.3-flash":{"draws":9,"losses":19,"wins":20},"z-ai/glm-5.3-flashx":{"draws":10,"losses":16,"wins":22}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":8,"wins":17},"claude-fable-5":{"draws":13,"losses":28,"wins":1},"claude-fable-5-1":{"draws":4,"losses":44,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":20,"wins":5},"claude-opus-4-5":{"draws":30,"losses":28,"wins":10},"claude-opus-4-8":{"draws":16,"losses":19,"wins":3},"claude-opus-5":{"draws":11,"losses":51,"wins":8},"claude-opus-5-5":{"draws":3,"losses":42,"wins":1},"claude-sonnet-5":{"draws":20,"losses":16,"wins":6},"claude-sonnet-5-5":{"draws":12,"losses":23,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":25,"losses":12,"wins":27},"deepseek/deepseek-v4-pro":{"draws":13,"losses":17,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":16,"wins":9},"fireworks/ember-1":{"draws":16,"losses":24,"wins":2},"gemini-3.1-pro-preview":{"draws":18,"losses":17,"wins":7},"google/gemini-3.1-flash-lite":{"draws":11,"losses":3,"wins":12},"google/gemini-3.5-flash":{"draws":23,"losses":23,"wins":6},"google/gemini-3.5-flash-lite":{"draws":30,"losses":23,"wins":19},"google/gemini-3.6-flash":{"draws":30,"losses":38,"wins":12},"google/gemini-3.8-flash":{"draws":16,"losses":23,"wins":3},"google/gemma-4-31b-it":{"draws":15,"losses":1,"wins":8},"gpt-4.1":{"draws":4,"losses":9,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":15,"wins":7},"gpt-5.4":{"draws":12,"losses":19,"wins":9},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":5},"gpt-5.4-nano":{"draws":10,"losses":14,"wins":16},"gpt-5.5":{"draws":21,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":16,"losses":16,"wins":10},"gpt-5.6-sol":{"draws":14,"losses":25,"wins":3},"gpt-5.6-terra":{"draws":13,"losses":7,"wins":8},"gpt-6-astra":{"draws":5,"losses":36,"wins":1},"gpt-6-luna":{"draws":17,"losses":18,"wins":7},"gpt-6-sol":{"draws":7,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":3,"wins":12},"inclusionai/ling-3.0-flash":{"draws":14,"losses":6,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":11,"wins":13},"meta/muse-glimmer-30b":{"draws":18,"losses":4,"wins":14},"meta/muse-spark-1.2":{"draws":17,"losses":14,"wins":9},"meta/muse-spark-1.3":{"draws":14,"losses":19,"wins":9},"meta/muse-wonder":{"draws":10,"losses":26,"wins":6},"minimax/minimax-m3":{"draws":10,"losses":5,"wins":7},"mistralai/mistral-large-4-0":{"draws":16,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":6,"wins":11},"o3":{"draws":16,"losses":24,"wins":14},"openai/gpt-oss-120b":{"draws":18,"losses":1,"wins":17},"poolside/laguna-s-2.1":{"draws":26,"losses":5,"wins":7},"qwen/qwen3.7-max":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":17,"wins":6},"qwen/qwen3.8-27b":{"draws":15,"losses":12,"wins":3},"qwen/qwen3.8-flash":{"draws":12,"losses":8,"wins":8},"qwen/qwen3.8-max":{"draws":21,"losses":11,"wins":10},"qwen/qwen3.8-max-0902":{"draws":19,"losses":16,"wins":7},"stealth/ox-alpha":{"draws":53,"losses":67,"wins":20},"stealth/space-bunny-alpha":{"draws":15,"losses":14,"wins":3},"stepfun/step-3.7-flash":{"draws":13,"losses":7,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":5,"wins":4},"tencent/hy4-preview":{"draws":16,"losses":18,"wins":6},"thinkingmachines/inkling":{"draws":19,"losses":15,"wins":20},"thinkingmachines/inkling-small":{"draws":19,"losses":8,"wins":15},"unbiased/pareto-26.10-preview":{"draws":2,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":13,"losses":26,"wins":3},"x-ai/grok-4.6":{"draws":16,"losses":23,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":3},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":31,"losses":9,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":6,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":11,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":16,"wins":4},"z-ai/glm-5.2":{"draws":44,"losses":20,"wins":20},"z-ai/glm-5.3":{"draws":13,"losses":23,"wins":4},"z-ai/glm-5.3-flash":{"draws":14,"losses":21,"wins":7},"z-ai/glm-5.3-flashx":{"draws":13,"losses":24,"wins":5}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":4,"wins":35},"claude-fable-5":{"draws":5,"losses":10,"wins":33},"claude-fable-5-1":{"draws":5,"losses":25,"wins":24},"claude-haiku-5-5":{"draws":5,"losses":3,"wins":38},"claude-opus-4-5":{"draws":8,"losses":7,"wins":63},"claude-opus-4-8":{"draws":5,"losses":7,"wins":32},"claude-opus-5":{"draws":11,"losses":24,"wins":47},"claude-opus-5-5":{"draws":7,"losses":27,"wins":18},"claude-sonnet-5":{"draws":6,"losses":6,"wins":36},"claude-sonnet-5-5":{"draws":5,"losses":11,"wins":32},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":64},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":0,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":2,"wins":35},"fireworks/ember-1":{"draws":9,"losses":2,"wins":37},"gemini-3.1-pro-preview":{"draws":5,"losses":1,"wins":42},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":8,"losses":1,"wins":51},"google/gemini-3.5-flash-lite":{"draws":9,"losses":1,"wins":74},"google/gemini-3.6-flash":{"draws":13,"losses":6,"wins":73},"google/gemini-3.8-flash":{"draws":8,"losses":5,"wins":35},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":24},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":0,"wins":37},"gpt-5.4":{"draws":5,"losses":7,"wins":34},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":28},"gpt-5.4-nano":{"draws":2,"losses":1,"wins":45},"gpt-5.5":{"draws":3,"losses":3,"wins":38},"gpt-5.6-luna":{"draws":8,"losses":1,"wins":39},"gpt-5.6-sol":{"draws":7,"losses":2,"wins":39},"gpt-5.6-terra":{"draws":10,"losses":2,"wins":34},"gpt-6-astra":{"draws":5,"losses":16,"wins":11},"gpt-6-luna":{"draws":8,"losses":4,"wins":36},"gpt-6-sol":{"draws":3,"losses":15,"wins":30},"gpt-6.1-sol":{"draws":6,"losses":23,"wins":19},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":30},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":29},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":2,"wins":45},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":39},"meta/muse-spark-1.2":{"draws":4,"losses":3,"wins":39},"meta/muse-spark-1.3":{"draws":7,"losses":7,"wins":34},"meta/muse-wonder":{"draws":8,"losses":7,"wins":33},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":25},"mistralai/mistral-large-4-0":{"draws":4,"losses":4,"wins":22},"mistralai/mistral-medium-3-5":{"draws":5,"losses":0,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":5,"losses":5,"wins":36},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":36},"o3":{"draws":3,"losses":0,"wins":63},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":34},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":40},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":23},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":3,"wins":42},"qwen/qwen3.8-27b":{"draws":3,"losses":0,"wins":31},"qwen/qwen3.8-flash":{"draws":9,"losses":1,"wins":22},"qwen/qwen3.8-max":{"draws":7,"losses":2,"wins":39},"qwen/qwen3.8-max-0902":{"draws":7,"losses":4,"wins":37},"stealth/ox-alpha":{"draws":20,"losses":8,"wins":130},"stealth/space-bunny-alpha":{"draws":5,"losses":0,"wins":33},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":7,"losses":1,"wins":38},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":56},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":43},"unbiased/pareto-26.10-preview":{"draws":0,"losses":7,"wins":9},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":35},"x-ai/grok-4.6":{"draws":7,"losses":7,"wins":34},"x-ai/grok-4.7":{"draws":6,"losses":9,"wins":27},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":9,"losses":2,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":3,"wins":26},"z-ai/glm-5.2":{"draws":13,"losses":7,"wins":76},"z-ai/glm-5.3":{"draws":10,"losses":4,"wins":32},"z-ai/glm-5.3-flash":{"draws":7,"losses":5,"wins":36},"z-ai/glm-5.3-flashx":{"draws":10,"losses":3,"wins":35}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":12,"wins":16},"claude-fable-5":{"draws":12,"losses":31,"wins":5},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":17,"losses":20,"wins":9},"claude-opus-4-5":{"draws":30,"losses":25,"wins":23},"claude-opus-4-8":{"draws":17,"losses":22,"wins":5},"claude-opus-5":{"draws":17,"losses":60,"wins":5},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":16,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":12,"losses":26,"wins":10},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":24,"losses":19,"wins":29},"deepseek/deepseek-v4-pro":{"draws":15,"losses":15,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":14,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":21,"wins":8},"fireworks/ember-1":{"draws":16,"losses":22,"wins":10},"gemini-3.1-pro-preview":{"draws":18,"losses":21,"wins":9},"google/gemini-3.1-flash-lite":{"draws":14,"losses":4,"wins":14},"google/gemini-3.5-flash":{"draws":22,"losses":23,"wins":15},"google/gemini-3.5-flash-lite":{"draws":40,"losses":15,"wins":29},"google/gemini-3.6-flash":{"draws":37,"losses":40,"wins":15},"google/gemini-3.8-flash":{"draws":14,"losses":26,"wins":8},"google/gemma-4-31b-it":{"draws":12,"losses":7,"wins":9},"gpt-4.1":{"draws":3,"losses":6,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":13,"wins":12},"gpt-5.4":{"draws":17,"losses":21,"wins":8},"gpt-5.4-mini":{"draws":18,"losses":5,"wins":9},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":20},"gpt-5.5":{"draws":21,"losses":18,"wins":5},"gpt-5.6-luna":{"draws":17,"losses":14,"wins":17},"gpt-5.6-sol":{"draws":12,"losses":30,"wins":6},"gpt-5.6-terra":{"draws":18,"losses":13,"wins":15},"gpt-6-astra":{"draws":3,"losses":41,"wins":4},"gpt-6-luna":{"draws":10,"losses":10,"wins":12},"gpt-6-sol":{"draws":8,"losses":34,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":42,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"wins":17},"inclusionai/ling-3.0-flash":{"draws":20,"losses":4,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":12,"wins":20},"meta/muse-glimmer-30b":{"draws":21,"losses":5,"wins":16},"meta/muse-spark-1.2":{"draws":13,"losses":22,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":32,"wins":5},"meta/muse-wonder":{"draws":15,"losses":25,"wins":8},"minimax/minimax-m3":{"draws":12,"losses":2,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":12,"wins":7},"mistralai/mistral-medium-3-5":{"draws":14,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":19,"wins":10},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":5,"wins":14},"o3":{"draws":17,"losses":24,"wins":25},"openai/gpt-oss-120b":{"draws":20,"losses":9,"wins":13},"poolside/laguna-s-2.1":{"draws":23,"losses":9,"wins":14},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":12,"losses":3,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-27b":{"draws":12,"losses":11,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":15,"wins":6},"qwen/qwen3.8-max":{"draws":15,"losses":21,"wins":12},"qwen/qwen3.8-max-0902":{"draws":16,"losses":20,"wins":12},"stealth/ox-alpha":{"draws":44,"losses":75,"wins":39},"stealth/space-bunny-alpha":{"draws":19,"losses":5,"wins":14},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":6,"wins":6},"tencent/hy4-preview":{"draws":15,"losses":21,"wins":10},"thinkingmachines/inkling":{"draws":21,"losses":19,"wins":24},"thinkingmachines/inkling-small":{"draws":21,"losses":12,"wins":15},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":14,"losses":24,"wins":10},"x-ai/grok-4.6":{"draws":14,"losses":24,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":35,"wins":4},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":35,"losses":6,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":4,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":12,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":15,"wins":9},"z-ai/glm-5.2":{"draws":38,"losses":23,"wins":35},"z-ai/glm-5.3":{"draws":8,"losses":29,"wins":9},"z-ai/glm-5.3-flash":{"draws":14,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":10,"losses":27,"wins":11}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":32},"claude-fable-5":{"draws":8,"losses":20,"wins":20},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":9,"losses":14,"wins":23},"claude-opus-4-5":{"draws":15,"losses":11,"wins":52},"claude-opus-4-8":{"draws":7,"losses":16,"wins":21},"claude-opus-5":{"draws":11,"losses":59,"wins":12},"claude-opus-5-5":{"draws":2,"losses":42,"wins":8},"claude-sonnet-5":{"draws":12,"losses":6,"wins":30},"claude-sonnet-5-5":{"draws":5,"losses":21,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":53},"deepseek/deepseek-v4-pro":{"draws":6,"losses":11,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":7,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":18,"wins":21},"fireworks/ember-1":{"draws":11,"losses":12,"wins":25},"gemini-3.1-pro-preview":{"draws":9,"losses":14,"wins":25},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":11,"losses":15,"wins":34},"google/gemini-3.5-flash-lite":{"draws":12,"losses":8,"wins":64},"google/gemini-3.6-flash":{"draws":17,"losses":26,"wins":49},"google/gemini-3.8-flash":{"draws":9,"losses":20,"wins":19},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":23},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":7,"losses":8,"wins":27},"gpt-5.4":{"draws":5,"losses":9,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":7,"losses":3,"wins":38},"gpt-5.5":{"draws":10,"losses":13,"wins":21},"gpt-5.6-luna":{"draws":12,"losses":5,"wins":31},"gpt-5.6-sol":{"draws":5,"losses":23,"wins":20},"gpt-5.6-terra":{"draws":12,"losses":5,"wins":29},"gpt-6-astra":{"draws":3,"losses":41,"wins":4},"gpt-6-luna":{"draws":9,"losses":6,"wins":33},"gpt-6-sol":{"draws":5,"losses":19,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":23},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":42},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":31},"meta/muse-spark-1.2":{"draws":10,"losses":9,"wins":27},"meta/muse-spark-1.3":{"draws":11,"losses":9,"wins":28},"meta/muse-wonder":{"draws":12,"losses":21,"wins":15},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"mistralai/mistral-large-4-0":{"draws":7,"losses":5,"wins":18},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":27},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":1,"wins":36},"o3":{"draws":4,"losses":4,"wins":58},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":10,"losses":3,"wins":33},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":15,"wins":21},"qwen/qwen3.8-27b":{"draws":5,"losses":6,"wins":23},"qwen/qwen3.8-flash":{"draws":5,"losses":9,"wins":18},"qwen/qwen3.8-max":{"draws":12,"losses":12,"wins":24},"qwen/qwen3.8-max-0902":{"draws":11,"losses":11,"wins":26},"stealth/ox-alpha":{"draws":25,"losses":33,"wins":100},"stealth/space-bunny-alpha":{"draws":9,"losses":4,"wins":25},"stepfun/step-3.7-flash":{"draws":6,"losses":1,"wins":27},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":1,"wins":17},"tencent/hy4-preview":{"draws":8,"losses":14,"wins":24},"thinkingmachines/inkling":{"draws":12,"losses":4,"wins":48},"thinkingmachines/inkling-small":{"draws":10,"losses":5,"wins":33},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":13,"losses":13,"wins":22},"x-ai/grok-4.6":{"draws":12,"losses":16,"wins":20},"x-ai/grok-4.7":{"draws":4,"losses":25,"wins":13},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":16,"losses":3,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":17},"z-ai/glm-5.2":{"draws":22,"losses":15,"wins":59},"z-ai/glm-5.3":{"draws":9,"losses":21,"wins":16},"z-ai/glm-5.3-flash":{"draws":7,"losses":17,"wins":24},"z-ai/glm-5.3-flashx":{"draws":7,"losses":21,"wins":20}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":3,"wins":32},"claude-fable-5":{"draws":4,"losses":18,"wins":26},"claude-fable-5-1":{"draws":4,"losses":35,"wins":15},"claude-haiku-5-5":{"draws":8,"losses":4,"wins":34},"claude-opus-4-5":{"draws":18,"losses":9,"wins":51},"claude-opus-4-8":{"draws":4,"losses":9,"wins":31},"claude-opus-5":{"draws":14,"losses":36,"wins":32},"claude-opus-5-5":{"draws":10,"losses":25,"wins":17},"claude-sonnet-5":{"draws":5,"losses":7,"wins":36},"claude-sonnet-5-5":{"draws":2,"losses":17,"wins":29},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":8,"losses":3,"wins":61},"deepseek/deepseek-v4-pro":{"draws":7,"losses":4,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":3,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":4,"wins":35},"fireworks/ember-1":{"draws":9,"losses":7,"wins":32},"gemini-3.1-pro-preview":{"draws":4,"losses":5,"wins":39},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":6,"losses":9,"wins":45},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":74},"google/gemini-3.6-flash":{"draws":9,"losses":14,"wins":69},"google/gemini-3.8-flash":{"draws":14,"losses":7,"wins":27},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":25},"gpt-4.1":{"draws":3,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":5,"losses":4,"wins":33},"gpt-5.4":{"draws":4,"losses":10,"wins":32},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":27},"gpt-5.4-nano":{"draws":5,"losses":3,"wins":40},"gpt-5.5":{"draws":6,"losses":10,"wins":28},"gpt-5.6-luna":{"draws":7,"losses":3,"wins":38},"gpt-5.6-sol":{"draws":8,"losses":9,"wins":31},"gpt-5.6-terra":{"draws":7,"losses":2,"wins":37},"gpt-6-astra":{"draws":5,"losses":35,"wins":8},"gpt-6-luna":{"draws":10,"losses":4,"wins":34},"gpt-6-sol":{"draws":7,"losses":22,"wins":19},"gpt-6.1-sol":{"draws":2,"losses":22,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":27},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":3,"wins":44},"meta/muse-glimmer-30b":{"draws":7,"losses":1,"wins":34},"meta/muse-spark-1.2":{"draws":7,"losses":8,"wins":31},"meta/muse-spark-1.3":{"draws":7,"losses":9,"wins":32},"meta/muse-wonder":{"draws":8,"losses":14,"wins":26},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"mistralai/mistral-large-4-0":{"draws":4,"losses":6,"wins":20},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":34},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":30},"o3":{"draws":2,"losses":7,"wins":57},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":36},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":37},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":23},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":10,"wins":31},"qwen/qwen3.8-27b":{"draws":7,"losses":1,"wins":26},"qwen/qwen3.8-flash":{"draws":7,"losses":2,"wins":23},"qwen/qwen3.8-max":{"draws":6,"losses":4,"wins":38},"qwen/qwen3.8-max-0902":{"draws":9,"losses":8,"wins":31},"stealth/ox-alpha":{"draws":27,"losses":18,"wins":113},"stealth/space-bunny-alpha":{"draws":8,"losses":4,"wins":26},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":19},"tencent/hy4-preview":{"draws":5,"losses":8,"wins":33},"thinkingmachines/inkling":{"draws":9,"losses":5,"wins":50},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":44},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":4},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":10,"losses":8,"wins":30},"x-ai/grok-4.6":{"draws":11,"losses":5,"wins":32},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":16},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":15,"losses":6,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":1,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":11,"wins":14},"z-ai/glm-5.2":{"draws":18,"losses":4,"wins":74},"z-ai/glm-5.3":{"draws":7,"losses":15,"wins":24},"z-ai/glm-5.3-flash":{"draws":5,"losses":9,"wins":34},"z-ai/glm-5.3-flashx":{"draws":13,"losses":8,"wins":27}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":10},"claude-fable-5":{"draws":8,"losses":17,"wins":5},"claude-fable-5-1":{"draws":3,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":16,"wins":3},"claude-opus-4-5":{"draws":23,"losses":20,"wins":5},"claude-opus-4-8":{"draws":11,"losses":8,"wins":7},"claude-opus-5":{"draws":13,"losses":35,"wins":2},"claude-opus-5-5":{"draws":4,"losses":26,"wins":0},"claude-sonnet-5":{"draws":12,"losses":11,"wins":7},"claude-sonnet-5-5":{"draws":8,"losses":15,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":16,"losses":14,"wins":12},"deepseek/deepseek-v4-pro":{"draws":11,"losses":9,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":14,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":12,"wins":3},"fireworks/ember-1":{"draws":13,"losses":12,"wins":5},"gemini-3.1-pro-preview":{"draws":9,"losses":8,"wins":13},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":10},"google/gemini-3.5-flash":{"draws":12,"losses":14,"wins":10},"google/gemini-3.5-flash-lite":{"draws":19,"losses":15,"wins":20},"google/gemini-3.6-flash":{"draws":19,"losses":32,"wins":7},"google/gemini-3.8-flash":{"draws":11,"losses":18,"wins":1},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":6},"gpt-4.1":{"draws":4,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":10,"losses":9,"wins":5},"gpt-5.4":{"draws":15,"losses":11,"wins":2},"gpt-5.4-mini":{"draws":11,"losses":4,"wins":5},"gpt-5.4-nano":{"draws":6,"losses":13,"wins":7},"gpt-5.5":{"draws":13,"losses":9,"wins":4},"gpt-5.6-luna":{"draws":15,"losses":10,"wins":5},"gpt-5.6-sol":{"draws":7,"losses":23,"wins":0},"gpt-5.6-terra":{"draws":13,"losses":10,"wins":5},"gpt-6-astra":{"draws":1,"losses":29,"wins":0},"gpt-6-luna":{"draws":11,"losses":15,"wins":4},"gpt-6-sol":{"draws":7,"losses":22,"wins":1},"gpt-6.1-sol":{"draws":5,"losses":25,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":4},"inclusionai/ling-3.0-flash":{"draws":8,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":12,"losses":9,"wins":11},"meta/muse-glimmer-30b":{"draws":12,"losses":3,"wins":9},"meta/muse-spark-1.2":{"draws":11,"losses":11,"wins":6},"meta/muse-spark-1.3":{"draws":7,"losses":19,"wins":4},"meta/muse-wonder":{"draws":10,"losses":17,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":5},"mistralai/mistral-large-4-0":{"draws":6,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":14,"wins":4},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":8},"o3":{"draws":7,"losses":17,"wins":10},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":9},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":11},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":18,"wins":1},"qwen/qwen3.8-27b":{"draws":9,"losses":12,"wins":1},"qwen/qwen3.8-flash":{"draws":8,"losses":10,"wins":2},"qwen/qwen3.8-max":{"draws":12,"losses":14,"wins":4},"qwen/qwen3.8-max-0902":{"draws":12,"losses":16,"wins":2},"stealth/ox-alpha":{"draws":35,"losses":53,"wins":20},"stealth/space-bunny-alpha":{"draws":8,"losses":11,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":2,"wins":5},"tencent/hy4-preview":{"draws":13,"losses":12,"wins":3},"thinkingmachines/inkling":{"draws":17,"losses":5,"wins":18},"thinkingmachines/inkling-small":{"draws":14,"losses":6,"wins":10},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":11,"losses":16,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":16,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":18,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":14,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":12,"wins":1},"z-ai/glm-5.2":{"draws":28,"losses":23,"wins":9},"z-ai/glm-5.3":{"draws":6,"losses":21,"wins":3},"z-ai/glm-5.3-flash":{"draws":9,"losses":17,"wins":4},"z-ai/glm-5.3-flashx":{"draws":8,"losses":21,"wins":1}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":27,"wins":10},"claude-fable-5":{"draws":14,"losses":49,"wins":3},"claude-fable-5-1":{"draws":5,"losses":67,"wins":0},"claude-haiku-5-5":{"draws":21,"losses":37,"wins":4},"claude-opus-4-5":{"draws":35,"losses":64,"wins":7},"claude-opus-4-8":{"draws":19,"losses":39,"wins":0},"claude-opus-5":{"draws":17,"losses":89,"wins":6},"claude-opus-5-5":{"draws":4,"losses":74,"wins":0},"claude-sonnet-5":{"draws":24,"losses":38,"wins":4},"claude-sonnet-5-5":{"draws":16,"losses":47,"wins":3},"cohere/north-mini-code":{"draws":14,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":49,"losses":33,"wins":20},"deepseek/deepseek-v4-pro":{"draws":24,"losses":24,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":29,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":28,"wins":6},"fireworks/ember-1":{"draws":32,"losses":34,"wins":0},"gemini-3.1-pro-preview":{"draws":29,"losses":32,"wins":5},"google/gemini-3.1-flash-lite":{"draws":18,"losses":12,"wins":8},"google/gemini-3.5-flash":{"draws":28,"losses":49,"wins":5},"google/gemini-3.5-flash-lite":{"draws":50,"losses":46,"wins":18},"google/gemini-3.6-flash":{"draws":46,"losses":68,"wins":10},"google/gemini-3.8-flash":{"draws":23,"losses":43,"wins":0},"google/gemma-4-31b-it":{"draws":23,"losses":8,"wins":5},"gpt-4.1":{"draws":9,"losses":13,"wins":0},"gpt-4.1-nano":{"draws":4,"losses":5,"wins":1},"gpt-5":{"draws":24,"losses":18,"wins":16},"gpt-5.4":{"draws":20,"losses":36,"wins":8},"gpt-5.4-mini":{"draws":21,"losses":17,"wins":6},"gpt-5.4-nano":{"draws":22,"losses":34,"wins":12},"gpt-5.5":{"draws":31,"losses":26,"wins":3},"gpt-5.6-luna":{"draws":37,"losses":22,"wins":7},"gpt-5.6-sol":{"draws":8,"losses":57,"wins":1},"gpt-5.6-terra":{"draws":26,"losses":37,"wins":3},"gpt-6-astra":{"draws":3,"losses":62,"wins":1},"gpt-6-luna":{"draws":26,"losses":33,"wins":7},"gpt-6-sol":{"draws":10,"losses":50,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":63,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":23,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":10},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":38,"losses":24,"wins":8},"meta/muse-glimmer-30b":{"draws":36,"losses":12,"wins":8},"meta/muse-spark-1.2":{"draws":16,"losses":41,"wins":5},"meta/muse-spark-1.3":{"draws":15,"losses":46,"wins":5},"meta/muse-wonder":{"draws":9,"losses":52,"wins":5},"minimax/minimax-m3":{"draws":13,"losses":17,"wins":4},"mistralai/mistral-large-4-0":{"draws":21,"losses":14,"wins":5},"mistralai/mistral-medium-3-5":{"draws":16,"losses":14,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":23,"losses":33,"wins":6},"nex-agi/nex-n2-pro":{"draws":16,"losses":7,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":17,"wins":10},"o3":{"draws":29,"losses":53,"wins":6},"openai/gpt-oss-120b":{"draws":29,"losses":25,"wins":2},"poolside/laguna-s-2.1":{"draws":38,"losses":21,"wins":9},"qwen/qwen3.7-max":{"draws":22,"losses":11,"wins":5},"qwen/qwen3.7-plus":{"draws":13,"losses":10,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":39,"wins":1},"qwen/qwen3.8-27b":{"draws":10,"losses":27,"wins":9},"qwen/qwen3.8-flash":{"draws":20,"losses":23,"wins":1},"qwen/qwen3.8-max":{"draws":27,"losses":32,"wins":7},"qwen/qwen3.8-max-0902":{"draws":29,"losses":34,"wins":3},"stealth/ox-alpha":{"draws":73,"losses":142,"wins":11},"stealth/space-bunny-alpha":{"draws":24,"losses":16,"wins":6},"stepfun/step-3.7-flash":{"draws":25,"losses":14,"wins":9},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":18,"wins":4},"tencent/hy4-preview":{"draws":29,"losses":33,"wins":2},"thinkingmachines/inkling":{"draws":31,"losses":36,"wins":17},"thinkingmachines/inkling-small":{"draws":37,"losses":18,"wins":11},"unbiased/pareto-26.10-preview":{"draws":2,"losses":20,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":15,"losses":48,"wins":3},"x-ai/grok-4.6":{"draws":24,"losses":39,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":49,"wins":3},"x-ai/grok-build-0.1":{"draws":11,"losses":11,"wins":0},"xiaomi/mimo-v2.5":{"draws":45,"losses":35,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":15,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":23,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":34,"wins":3},"z-ai/glm-5.2":{"draws":79,"losses":43,"wins":10},"z-ai/glm-5.3":{"draws":17,"losses":42,"wins":3},"z-ai/glm-5.3-flash":{"draws":25,"losses":31,"wins":10},"z-ai/glm-5.3-flashx":{"draws":25,"losses":35,"wins":6}},"inclusionai/ling-3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":0},"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-5":{"draws":3,"losses":7,"wins":0},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":4,"losses":2,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":0,"wins":1},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":5,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":6,"losses":0,"wins":0},"gpt-5.4":{"draws":5,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":1},"gpt-5.5":{"draws":3,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":0,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":3,"losses":2,"wins":1},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":0,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":5,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":3,"wins":0},"meta/muse-wonder":{"draws":0,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":0},"o3":{"draws":8,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":0},"qwen/qwen3.8-max-0902":{"draws":6,"losses":0,"wins":0},"stealth/ox-alpha":{"draws":6,"losses":9,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":4,"wins":1},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":3,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":2,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":0,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":33,"wins":22},"claude-fable-5":{"draws":11,"losses":64,"wins":9},"claude-fable-5-1":{"draws":0,"losses":91,"wins":3},"claude-haiku-5-5":{"draws":18,"losses":52,"wins":10},"claude-opus-4-5":{"draws":38,"losses":80,"wins":18},"claude-opus-4-8":{"draws":16,"losses":50,"wins":10},"claude-opus-5":{"draws":14,"losses":117,"wins":9},"claude-opus-5-5":{"draws":5,"losses":85,"wins":2},"claude-sonnet-5":{"draws":28,"losses":39,"wins":17},"claude-sonnet-5-5":{"draws":12,"losses":58,"wins":14},"cohere/north-mini-code":{"draws":10,"losses":6,"wins":18},"deepseek/deepseek-v4-flash":{"draws":35,"losses":49,"wins":44},"deepseek/deepseek-v4-pro":{"draws":17,"losses":47,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":35,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":44,"wins":20},"fireworks/ember-1":{"draws":31,"losses":47,"wins":6},"gemini-3.1-pro-preview":{"draws":24,"losses":39,"wins":21},"google/gemini-3.1-flash-lite":{"draws":13,"losses":14,"wins":31},"google/gemini-3.5-flash":{"draws":20,"losses":66,"wins":20},"google/gemini-3.5-flash-lite":{"draws":49,"losses":67,"wins":32},"google/gemini-3.6-flash":{"draws":36,"losses":101,"wins":25},"google/gemini-3.8-flash":{"draws":15,"losses":64,"wins":5},"google/gemma-4-31b-it":{"draws":20,"losses":11,"wins":17},"gpt-4.1":{"draws":8,"losses":14,"wins":6},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":3},"gpt-5":{"draws":20,"losses":35,"wins":21},"gpt-5.4":{"draws":21,"losses":53,"wins":8},"gpt-5.4-mini":{"draws":26,"losses":19,"wins":11},"gpt-5.4-nano":{"draws":16,"losses":44,"wins":28},"gpt-5.5":{"draws":35,"losses":31,"wins":12},"gpt-5.6-luna":{"draws":26,"losses":33,"wins":25},"gpt-5.6-sol":{"draws":10,"losses":69,"wins":5},"gpt-5.6-terra":{"draws":25,"losses":39,"wins":16},"gpt-6-astra":{"draws":5,"losses":79,"wins":0},"gpt-6-luna":{"draws":24,"losses":44,"wins":16},"gpt-6-sol":{"draws":7,"losses":69,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":76,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":23,"losses":14,"wins":19},"inclusionai/ling-3.0-flash":{"draws":27,"losses":13,"wins":20},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":24,"losses":24,"wins":18},"meta/muse-glimmer-30b":{"draws":34,"losses":23,"wins":17},"meta/muse-spark-1.2":{"draws":15,"losses":54,"wins":11},"meta/muse-spark-1.3":{"draws":15,"losses":58,"wins":11},"meta/muse-wonder":{"draws":20,"losses":54,"wins":10},"minimax/minimax-m3":{"draws":11,"losses":18,"wins":17},"mistralai/mistral-large-4-0":{"draws":18,"losses":27,"wins":7},"mistralai/mistral-medium-3-5":{"draws":19,"losses":14,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":15,"wins":2},"moonshotai/kimi-k3":{"draws":28,"losses":36,"wins":16},"nex-agi/nex-n2-pro":{"draws":11,"losses":13,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":23,"wins":17},"o3":{"draws":24,"losses":74,"wins":28},"openai/gpt-oss-120b":{"draws":24,"losses":25,"wins":25},"poolside/laguna-s-2.1":{"draws":34,"losses":32,"wins":18},"qwen/qwen3.7-max":{"draws":17,"losses":21,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":16,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":49,"wins":10},"qwen/qwen3.8-27b":{"draws":14,"losses":36,"wins":10},"qwen/qwen3.8-flash":{"draws":20,"losses":25,"wins":11},"qwen/qwen3.8-max":{"draws":27,"losses":38,"wins":19},"qwen/qwen3.8-max-0902":{"draws":21,"losses":49,"wins":14},"stealth/ox-alpha":{"draws":65,"losses":176,"wins":41},"stealth/space-bunny-alpha":{"draws":22,"losses":33,"wins":11},"stepfun/step-3.7-flash":{"draws":14,"losses":22,"wins":28},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":21,"wins":13},"tencent/hy4-preview":{"draws":19,"losses":51,"wins":12},"thinkingmachines/inkling":{"draws":29,"losses":43,"wins":42},"thinkingmachines/inkling-small":{"draws":33,"losses":25,"wins":26},"unbiased/pareto-26.10-preview":{"draws":1,"losses":26,"wins":1},"upstage/solar-mini4":{"draws":4,"losses":8,"wins":10},"x-ai/grok-4.5":{"draws":16,"losses":54,"wins":14},"x-ai/grok-4.6":{"draws":26,"losses":49,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":64,"wins":5},"x-ai/grok-build-0.1":{"draws":10,"losses":9,"wins":9},"xiaomi/mimo-v2.5":{"draws":38,"losses":43,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":26,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":30,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":37,"wins":5},"z-ai/glm-5.2":{"draws":56,"losses":74,"wins":38},"z-ai/glm-5.3":{"draws":12,"losses":63,"wins":5},"z-ai/glm-5.3-flash":{"draws":19,"losses":48,"wins":17},"z-ai/glm-5.3-flashx":{"draws":16,"losses":56,"wins":12}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":14,"wins":6},"claude-fable-5":{"draws":8,"losses":25,"wins":3},"claude-fable-5-1":{"draws":2,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":23,"wins":3},"claude-opus-4-5":{"draws":18,"losses":35,"wins":5},"claude-opus-4-8":{"draws":7,"losses":22,"wins":3},"claude-opus-5":{"draws":2,"losses":58,"wins":8},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":10,"losses":22,"wins":4},"claude-sonnet-5-5":{"draws":4,"losses":28,"wins":4},"cohere/north-mini-code":{"draws":8,"losses":5,"wins":3},"deepseek/deepseek-v4-flash":{"draws":21,"losses":18,"wins":13},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":17,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":15,"wins":2},"fireworks/ember-1":{"draws":12,"losses":22,"wins":2},"gemini-3.1-pro-preview":{"draws":13,"losses":20,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":10},"google/gemini-3.5-flash":{"draws":13,"losses":27,"wins":6},"google/gemini-3.5-flash-lite":{"draws":23,"losses":26,"wins":15},"google/gemini-3.6-flash":{"draws":18,"losses":45,"wins":7},"google/gemini-3.8-flash":{"draws":11,"losses":21,"wins":4},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":7},"gpt-4.1":{"draws":5,"losses":6,"wins":1},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":12,"losses":16,"wins":6},"gpt-5.4":{"draws":9,"losses":23,"wins":4},"gpt-5.4-mini":{"draws":11,"losses":11,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":19,"wins":11},"gpt-5.5":{"draws":15,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":13,"losses":12,"wins":11},"gpt-5.6-sol":{"draws":4,"losses":31,"wins":1},"gpt-5.6-terra":{"draws":12,"losses":18,"wins":4},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":12,"losses":19,"wins":5},"gpt-6-sol":{"draws":5,"losses":29,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":5,"wins":6},"inclusionai/ling-3.0-flash":{"draws":11,"losses":2,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":16,"wins":11},"meta/muse-glimmer-30b":{"draws":11,"losses":10,"wins":3},"meta/muse-spark-1.2":{"draws":6,"losses":27,"wins":3},"meta/muse-spark-1.3":{"draws":8,"losses":25,"wins":3},"meta/muse-wonder":{"draws":6,"losses":26,"wins":4},"minimax/minimax-m3":{"draws":4,"losses":11,"wins":5},"mistralai/mistral-large-4-0":{"draws":8,"losses":10,"wins":6},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":21,"wins":5},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":9},"o3":{"draws":10,"losses":30,"wins":12},"openai/gpt-oss-120b":{"draws":10,"losses":14,"wins":8},"poolside/laguna-s-2.1":{"draws":14,"losses":15,"wins":7},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":18,"wins":4},"qwen/qwen3.8-27b":{"draws":5,"losses":14,"wins":5},"qwen/qwen3.8-flash":{"draws":13,"losses":6,"wins":5},"qwen/qwen3.8-max":{"draws":11,"losses":20,"wins":5},"qwen/qwen3.8-max-0902":{"draws":13,"losses":20,"wins":3},"stealth/ox-alpha":{"draws":28,"losses":83,"wins":15},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":13,"wins":2},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":2},"thinkingmachines/inkling":{"draws":16,"losses":19,"wins":17},"thinkingmachines/inkling-small":{"draws":17,"losses":8,"wins":11},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":2,"wins":3},"x-ai/grok-4.5":{"draws":8,"losses":24,"wins":4},"x-ai/grok-4.6":{"draws":14,"losses":22,"wins":0},"x-ai/grok-4.7":{"draws":3,"losses":25,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":23,"losses":17,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":11,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":4},"z-ai/glm-5.2":{"draws":32,"losses":27,"wins":13},"z-ai/glm-5.3":{"draws":4,"losses":27,"wins":3},"z-ai/glm-5.3-flash":{"draws":7,"losses":26,"wins":3},"z-ai/glm-5.3-flashx":{"draws":9,"losses":22,"wins":5}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":14},"claude-fable-5":{"draws":7,"losses":36,"wins":5},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":30,"wins":6},"claude-opus-4-5":{"draws":23,"losses":33,"wins":22},"claude-opus-4-8":{"draws":11,"losses":27,"wins":6},"claude-opus-5":{"draws":7,"losses":65,"wins":10},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":15,"losses":19,"wins":14},"claude-sonnet-5-5":{"draws":7,"losses":31,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":21,"losses":21,"wins":30},"deepseek/deepseek-v4-pro":{"draws":9,"losses":21,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":20,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":26,"wins":11},"fireworks/ember-1":{"draws":14,"losses":25,"wins":9},"gemini-3.1-pro-preview":{"draws":13,"losses":22,"wins":13},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":14,"losses":30,"wins":16},"google/gemini-3.5-flash-lite":{"draws":25,"losses":25,"wins":34},"google/gemini-3.6-flash":{"draws":24,"losses":50,"wins":18},"google/gemini-3.8-flash":{"draws":11,"losses":28,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":10},"gpt-4.1":{"draws":4,"losses":5,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":9,"losses":19,"wins":14},"gpt-5.4":{"draws":8,"losses":24,"wins":14},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":11},"gpt-5.4-nano":{"draws":9,"losses":21,"wins":18},"gpt-5.5":{"draws":10,"losses":23,"wins":11},"gpt-5.6-luna":{"draws":11,"losses":19,"wins":18},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":20,"wins":13},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":6,"losses":38,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"inclusionai/ling-3.0-flash":{"draws":12,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":18,"wins":22},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":17},"meta/muse-spark-1.2":{"draws":6,"losses":18,"wins":6},"meta/muse-spark-1.3":{"draws":11,"losses":28,"wins":9},"meta/muse-wonder":{"draws":9,"losses":32,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":13},"mistralai/mistral-large-4-0":{"draws":7,"losses":13,"wins":10},"mistralai/mistral-medium-3-5":{"draws":11,"losses":3,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":22,"wins":14},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":19},"o3":{"draws":8,"losses":35,"wins":23},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":24},"poolside/laguna-s-2.1":{"draws":11,"losses":8,"wins":27},"qwen/qwen3.7-max":{"draws":4,"losses":10,"wins":14},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":25,"wins":7},"qwen/qwen3.8-27b":{"draws":10,"losses":17,"wins":7},"qwen/qwen3.8-flash":{"draws":9,"losses":14,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":23,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":26,"wins":11},"stealth/ox-alpha":{"draws":37,"losses":86,"wins":35},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":6,"losses":15,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":7,"losses":26,"wins":13},"thinkingmachines/inkling":{"draws":23,"losses":15,"wins":26},"thinkingmachines/inkling-small":{"draws":13,"losses":14,"wins":21},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":30,"wins":7},"x-ai/grok-4.6":{"draws":10,"losses":35,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":8},"xiaomi/mimo-v2.5":{"draws":28,"losses":16,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":13,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":20,"wins":7},"z-ai/glm-5.2":{"draws":30,"losses":32,"wins":34},"z-ai/glm-5.3":{"draws":9,"losses":28,"wins":9},"z-ai/glm-5.3-flash":{"draws":8,"losses":28,"wins":12},"z-ai/glm-5.3-flashx":{"draws":9,"losses":24,"wins":15}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":10,"wins":17},"claude-fable-5":{"draws":11,"losses":34,"wins":3},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":29,"wins":4},"claude-opus-4-5":{"draws":29,"losses":30,"wins":19},"claude-opus-4-8":{"draws":12,"losses":27,"wins":5},"claude-opus-5":{"draws":11,"losses":64,"wins":7},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":19,"losses":18,"wins":11},"claude-sonnet-5-5":{"draws":10,"losses":31,"wins":7},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":23,"losses":17,"wins":32},"deepseek/deepseek-v4-pro":{"draws":10,"losses":23,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":21,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":24,"wins":9},"fireworks/ember-1":{"draws":20,"losses":21,"wins":7},"gemini-3.1-pro-preview":{"draws":13,"losses":19,"wins":16},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":17,"losses":28,"wins":15},"google/gemini-3.5-flash-lite":{"draws":28,"losses":22,"wins":34},"google/gemini-3.6-flash":{"draws":19,"losses":48,"wins":25},"google/gemini-3.8-flash":{"draws":14,"losses":30,"wins":4},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":13},"gpt-4.1":{"draws":7,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":19,"wins":10},"gpt-5.4":{"draws":10,"losses":26,"wins":10},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":18,"losses":12,"wins":18},"gpt-5.5":{"draws":16,"losses":20,"wins":8},"gpt-5.6-luna":{"draws":20,"losses":15,"wins":13},"gpt-5.6-sol":{"draws":6,"losses":41,"wins":1},"gpt-5.6-terra":{"draws":13,"losses":24,"wins":9},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":8,"losses":39,"wins":1},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":2,"wins":15},"inclusionai/ling-3.0-flash":{"draws":12,"losses":6,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":10,"wins":23},"meta/muse-glimmer-30b":{"draws":22,"losses":9,"wins":11},"meta/muse-spark-1.2":{"draws":12,"losses":24,"wins":10},"meta/muse-spark-1.3":{"draws":5,"losses":25,"wins":2},"meta/muse-wonder":{"draws":10,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":16},"mistralai/mistral-large-4-0":{"draws":12,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":23,"wins":8},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":5,"wins":19},"o3":{"draws":14,"losses":33,"wins":19},"openai/gpt-oss-120b":{"draws":17,"losses":6,"wins":19},"poolside/laguna-s-2.1":{"draws":18,"losses":17,"wins":11},"qwen/qwen3.7-max":{"draws":11,"losses":10,"wins":7},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":20,"wins":10},"qwen/qwen3.8-27b":{"draws":7,"losses":19,"wins":8},"qwen/qwen3.8-flash":{"draws":11,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":20,"losses":16,"wins":12},"qwen/qwen3.8-max-0902":{"draws":19,"losses":24,"wins":5},"stealth/ox-alpha":{"draws":36,"losses":88,"wins":34},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":8,"losses":7,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":12},"tencent/hy4-preview":{"draws":14,"losses":27,"wins":5},"thinkingmachines/inkling":{"draws":20,"losses":8,"wins":36},"thinkingmachines/inkling-small":{"draws":23,"losses":9,"wins":16},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":10,"losses":32,"wins":6},"x-ai/grok-4.6":{"draws":13,"losses":27,"wins":8},"x-ai/grok-4.7":{"draws":4,"losses":31,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":33,"losses":14,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":9,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":13,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":23,"wins":6},"z-ai/glm-5.2":{"draws":30,"losses":38,"wins":28},"z-ai/glm-5.3":{"draws":9,"losses":34,"wins":3},"z-ai/glm-5.3-flash":{"draws":12,"losses":31,"wins":5},"z-ai/glm-5.3-flashx":{"draws":13,"losses":27,"wins":8}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":23},"claude-fable-5":{"draws":10,"losses":29,"wins":9},"claude-fable-5-1":{"draws":4,"losses":39,"wins":11},"claude-haiku-5-5":{"draws":16,"losses":12,"wins":18},"claude-opus-4-5":{"draws":27,"losses":17,"wins":34},"claude-opus-4-8":{"draws":12,"losses":19,"wins":13},"claude-opus-5":{"draws":11,"losses":54,"wins":17},"claude-opus-5-5":{"draws":0,"losses":43,"wins":9},"claude-sonnet-5":{"draws":17,"losses":10,"wins":21},"claude-sonnet-5-5":{"draws":11,"losses":26,"wins":11},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":16,"losses":18,"wins":38},"deepseek/deepseek-v4-pro":{"draws":9,"losses":15,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":16,"wins":16},"fireworks/ember-1":{"draws":18,"losses":10,"wins":20},"gemini-3.1-pro-preview":{"draws":11,"losses":11,"wins":26},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":12,"losses":14,"wins":34},"google/gemini-3.5-flash-lite":{"draws":20,"losses":12,"wins":52},"google/gemini-3.6-flash":{"draws":27,"losses":30,"wins":35},"google/gemini-3.8-flash":{"draws":17,"losses":18,"wins":13},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":14},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":9,"wins":23},"gpt-5.4":{"draws":15,"losses":17,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":2,"wins":18},"gpt-5.4-nano":{"draws":8,"losses":9,"wins":31},"gpt-5.5":{"draws":18,"losses":12,"wins":14},"gpt-5.6-luna":{"draws":13,"losses":10,"wins":25},"gpt-5.6-sol":{"draws":9,"losses":25,"wins":14},"gpt-5.6-terra":{"draws":18,"losses":9,"wins":19},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":18,"losses":14,"wins":16},"gpt-6-sol":{"draws":6,"losses":32,"wins":10},"gpt-6.1-sol":{"draws":3,"losses":37,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":21},"inclusionai/ling-3.0-flash":{"draws":7,"losses":3,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":6,"wins":32},"meta/muse-glimmer-30b":{"draws":14,"losses":5,"wins":23},"meta/muse-spark-1.2":{"draws":14,"losses":16,"wins":16},"meta/muse-spark-1.3":{"draws":13,"losses":21,"wins":14},"meta/muse-wonder":{"draws":7,"losses":19,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":14},"mistralai/mistral-large-4-0":{"draws":6,"losses":11,"wins":13},"mistralai/mistral-medium-3-5":{"draws":6,"losses":4,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":13,"losses":8,"wins":25},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":1,"wins":20},"o3":{"draws":8,"losses":13,"wins":45},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":25},"poolside/laguna-s-2.1":{"draws":13,"losses":6,"wins":27},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":14},"qwen/qwen3.7-plus":{"draws":11,"losses":0,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":19},"qwen/qwen3.8-27b":{"draws":12,"losses":6,"wins":16},"qwen/qwen3.8-flash":{"draws":11,"losses":4,"wins":17},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":19},"qwen/qwen3.8-max-0902":{"draws":17,"losses":12,"wins":19},"stealth/ox-alpha":{"draws":43,"losses":60,"wins":55},"stealth/space-bunny-alpha":{"draws":15,"losses":7,"wins":16},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":13},"tencent/hy4-preview":{"draws":16,"losses":13,"wins":17},"thinkingmachines/inkling":{"draws":25,"losses":7,"wins":32},"thinkingmachines/inkling-small":{"draws":16,"losses":7,"wins":25},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":15,"losses":15,"wins":18},"x-ai/grok-4.6":{"draws":16,"losses":19,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":24,"losses":7,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":11,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":12,"wins":10},"z-ai/glm-5.2":{"draws":27,"losses":24,"wins":45},"z-ai/glm-5.3":{"draws":6,"losses":26,"wins":14},"z-ai/glm-5.3-flash":{"draws":11,"losses":21,"wins":16},"z-ai/glm-5.3-flashx":{"draws":14,"losses":18,"wins":16}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":20,"wins":8},"claude-fable-5":{"draws":9,"losses":22,"wins":5},"claude-fable-5-1":{"draws":1,"losses":38,"wins":1},"claude-haiku-5-5":{"draws":2,"losses":22,"wins":10},"claude-opus-4-5":{"draws":18,"losses":31,"wins":9},"claude-opus-4-8":{"draws":4,"losses":20,"wins":8},"claude-opus-5":{"draws":9,"losses":55,"wins":4},"claude-opus-5-5":{"draws":2,"losses":37,"wins":1},"claude-sonnet-5":{"draws":8,"losses":17,"wins":11},"claude-sonnet-5-5":{"draws":6,"losses":19,"wins":11},"cohere/north-mini-code":{"draws":0,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":13,"losses":17,"wins":26},"deepseek/deepseek-v4-pro":{"draws":4,"losses":20,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":14,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":20,"wins":10},"fireworks/ember-1":{"draws":7,"losses":25,"wins":4},"gemini-3.1-pro-preview":{"draws":6,"losses":15,"wins":15},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":17},"google/gemini-3.5-flash":{"draws":6,"losses":22,"wins":16},"google/gemini-3.5-flash-lite":{"draws":15,"losses":15,"wins":30},"google/gemini-3.6-flash":{"draws":9,"losses":44,"wins":15},"google/gemini-3.8-flash":{"draws":4,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":9},"gpt-4.1":{"draws":2,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":7,"losses":16,"wins":11},"gpt-5.4":{"draws":4,"losses":17,"wins":13},"gpt-5.4-mini":{"draws":8,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":7,"losses":12,"wins":19},"gpt-5.5":{"draws":8,"losses":18,"wins":8},"gpt-5.6-luna":{"draws":10,"losses":14,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":27,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":18,"wins":10},"gpt-6-astra":{"draws":0,"losses":34,"wins":2},"gpt-6-luna":{"draws":9,"losses":18,"wins":9},"gpt-6-sol":{"draws":2,"losses":29,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":32,"wins":3},"inception/mercury-2.5-preview":{"draws":10,"losses":1,"wins":11},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":15},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":11,"wins":18},"meta/muse-glimmer-30b":{"draws":9,"losses":6,"wins":19},"meta/muse-spark-1.2":{"draws":4,"losses":26,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":29,"wins":5},"meta/muse-wonder":{"draws":5,"losses":23,"wins":8},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":6},"mistralai/mistral-large-4-0":{"draws":4,"losses":12,"wins":8},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":23,"wins":6},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":4,"wins":19},"o3":{"draws":6,"losses":28,"wins":16},"openai/gpt-oss-120b":{"draws":8,"losses":11,"wins":15},"poolside/laguna-s-2.1":{"draws":10,"losses":12,"wins":18},"qwen/qwen3.7-max":{"draws":8,"losses":10,"wins":4},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":23,"wins":6},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":5},"qwen/qwen3.8-flash":{"draws":3,"losses":10,"wins":11},"qwen/qwen3.8-max":{"draws":8,"losses":21,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":25,"wins":4},"stealth/ox-alpha":{"draws":29,"losses":65,"wins":30},"stealth/space-bunny-alpha":{"draws":7,"losses":12,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":16},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":6,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":12,"losses":13,"wins":25},"thinkingmachines/inkling-small":{"draws":8,"losses":7,"wins":21},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":28,"wins":3},"x-ai/grok-4.6":{"draws":7,"losses":27,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":29,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":18,"losses":10,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":17,"losses":25,"wins":30},"z-ai/glm-5.3":{"draws":5,"losses":24,"wins":5},"z-ai/glm-5.3-flash":{"draws":8,"losses":19,"wins":9},"z-ai/glm-5.3-flashx":{"draws":6,"losses":20,"wins":10}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":14,"wins":10},"claude-fable-5":{"draws":10,"losses":24,"wins":8},"claude-fable-5-1":{"draws":3,"losses":43,"wins":2},"claude-haiku-5-5":{"draws":16,"losses":17,"wins":7},"claude-opus-4-5":{"draws":24,"losses":31,"wins":13},"claude-opus-4-8":{"draws":11,"losses":17,"wins":10},"claude-opus-5":{"draws":11,"losses":62,"wins":7},"claude-opus-5-5":{"draws":5,"losses":41,"wins":0},"claude-sonnet-5":{"draws":13,"losses":21,"wins":8},"claude-sonnet-5-5":{"draws":14,"losses":20,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":26,"losses":12,"wins":24},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":14,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":17,"wins":7},"fireworks/ember-1":{"draws":16,"losses":17,"wins":9},"gemini-3.1-pro-preview":{"draws":14,"losses":19,"wins":9},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":15},"google/gemini-3.5-flash":{"draws":19,"losses":20,"wins":13},"google/gemini-3.5-flash-lite":{"draws":35,"losses":15,"wins":22},"google/gemini-3.6-flash":{"draws":27,"losses":42,"wins":11},"google/gemini-3.8-flash":{"draws":14,"losses":21,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":7},"gpt-4.1":{"draws":6,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":19,"losses":10,"wins":9},"gpt-5.4":{"draws":15,"losses":22,"wins":3},"gpt-5.4-mini":{"draws":17,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":9,"losses":14,"wins":17},"gpt-5.5":{"draws":19,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":18,"losses":9,"wins":15},"gpt-5.6-sol":{"draws":10,"losses":27,"wins":5},"gpt-5.6-terra":{"draws":21,"losses":10,"wins":9},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":13,"losses":17,"wins":12},"gpt-6-sol":{"draws":6,"losses":31,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":6,"wins":8},"inclusionai/ling-3.0-flash":{"draws":14,"losses":5,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":10,"wins":13},"meta/muse-glimmer-30b":{"draws":17,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":24,"wins":7},"meta/muse-spark-1.3":{"draws":10,"losses":27,"wins":5},"meta/muse-wonder":{"draws":7,"losses":26,"wins":9},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":6},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":4},"mistralai/mistral-medium-3-5":{"draws":14,"losses":3,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":16,"wins":11},"nex-agi/nex-n2-pro":{"draws":7,"losses":5,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":11},"o3":{"draws":18,"losses":21,"wins":15},"openai/gpt-oss-120b":{"draws":17,"losses":11,"wins":10},"poolside/laguna-s-2.1":{"draws":20,"losses":9,"wins":13},"qwen/qwen3.7-max":{"draws":13,"losses":5,"wins":6},"qwen/qwen3.7-plus":{"draws":9,"losses":1,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":22,"wins":6},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":4},"qwen/qwen3.8-flash":{"draws":12,"losses":7,"wins":9},"qwen/qwen3.8-max":{"draws":16,"losses":18,"wins":8},"qwen/qwen3.8-max-0902":{"draws":17,"losses":20,"wins":5},"stealth/ox-alpha":{"draws":48,"losses":67,"wins":27},"stealth/space-bunny-alpha":{"draws":15,"losses":8,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":10,"wins":4},"tencent/hy4-preview":{"draws":14,"losses":19,"wins":7},"thinkingmachines/inkling":{"draws":24,"losses":15,"wins":19},"thinkingmachines/inkling-small":{"draws":17,"losses":11,"wins":14},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":11,"losses":25,"wins":6},"x-ai/grok-4.6":{"draws":14,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":3},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":31,"losses":11,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":10,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":13,"wins":7},"z-ai/glm-5.2":{"draws":42,"losses":19,"wins":23},"z-ai/glm-5.3":{"draws":9,"losses":24,"wins":7},"z-ai/glm-5.3-flash":{"draws":13,"losses":23,"wins":6},"z-ai/glm-5.3-flashx":{"draws":15,"losses":18,"wins":9}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":15,"wins":8},"claude-fable-5":{"draws":6,"losses":34,"wins":2},"claude-fable-5-1":{"draws":3,"losses":43,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":27,"wins":2},"claude-opus-4-5":{"draws":23,"losses":43,"wins":2},"claude-opus-4-8":{"draws":14,"losses":21,"wins":3},"claude-opus-5":{"draws":10,"losses":58,"wins":6},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":13,"losses":27,"wins":2},"claude-sonnet-5-5":{"draws":7,"losses":32,"wins":3},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":30,"losses":24,"wins":8},"deepseek/deepseek-v4-pro":{"draws":9,"losses":25,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":22,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":23,"wins":3},"fireworks/ember-1":{"draws":13,"losses":28,"wins":1},"gemini-3.1-pro-preview":{"draws":14,"losses":26,"wins":2},"google/gemini-3.1-flash-lite":{"draws":7,"losses":7,"wins":12},"google/gemini-3.5-flash":{"draws":14,"losses":32,"wins":6},"google/gemini-3.5-flash-lite":{"draws":24,"losses":36,"wins":14},"google/gemini-3.6-flash":{"draws":29,"losses":46,"wins":5},"google/gemini-3.8-flash":{"draws":9,"losses":32,"wins":1},"google/gemma-4-31b-it":{"draws":11,"losses":11,"wins":2},"gpt-4.1":{"draws":6,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":12,"losses":17,"wins":7},"gpt-5.4":{"draws":9,"losses":23,"wins":8},"gpt-5.4-mini":{"draws":14,"losses":11,"wins":3},"gpt-5.4-nano":{"draws":10,"losses":27,"wins":5},"gpt-5.5":{"draws":12,"losses":22,"wins":4},"gpt-5.6-luna":{"draws":15,"losses":19,"wins":8},"gpt-5.6-sol":{"draws":4,"losses":35,"wins":3},"gpt-5.6-terra":{"draws":12,"losses":25,"wins":3},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":15,"losses":25,"wins":2},"gpt-6-sol":{"draws":3,"losses":38,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":10,"wins":5},"inclusionai/ling-3.0-flash":{"draws":15,"losses":7,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":18,"wins":10},"meta/muse-glimmer-30b":{"draws":17,"losses":14,"wins":5},"meta/muse-spark-1.2":{"draws":9,"losses":28,"wins":3},"meta/muse-spark-1.3":{"draws":7,"losses":34,"wins":1},"meta/muse-wonder":{"draws":8,"losses":31,"wins":3},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":5},"mistralai/mistral-large-4-0":{"draws":11,"losses":11,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":5,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":28,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":15,"wins":4},"o3":{"draws":13,"losses":37,"wins":4},"openai/gpt-oss-120b":{"draws":15,"losses":18,"wins":3},"poolside/laguna-s-2.1":{"draws":19,"losses":17,"wins":6},"qwen/qwen3.7-max":{"draws":12,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":9,"losses":7,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":30,"wins":1},"qwen/qwen3.8-27b":{"draws":10,"losses":19,"wins":1},"qwen/qwen3.8-flash":{"draws":10,"losses":16,"wins":2},"qwen/qwen3.8-max":{"draws":11,"losses":27,"wins":4},"qwen/qwen3.8-max-0902":{"draws":15,"losses":25,"wins":2},"stealth/ox-alpha":{"draws":34,"losses":93,"wins":13},"stealth/space-bunny-alpha":{"draws":13,"losses":14,"wins":5},"stepfun/step-3.7-flash":{"draws":10,"losses":12,"wins":6},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":3},"tencent/hy4-preview":{"draws":11,"losses":27,"wins":2},"thinkingmachines/inkling":{"draws":21,"losses":27,"wins":8},"thinkingmachines/inkling-small":{"draws":20,"losses":13,"wins":9},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":30,"wins":3},"x-ai/grok-4.6":{"draws":13,"losses":25,"wins":4},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":0},"xiaomi/mimo-v2.5":{"draws":27,"losses":28,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":14,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":23,"wins":2},"z-ai/glm-5.2":{"draws":36,"losses":41,"wins":7},"z-ai/glm-5.3":{"draws":7,"losses":32,"wins":1},"z-ai/glm-5.3-flash":{"draws":15,"losses":23,"wins":4},"z-ai/glm-5.3-flashx":{"draws":7,"losses":31,"wins":4}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":8,"wins":22},"claude-fable-5":{"draws":5,"losses":31,"wins":12},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":12,"losses":19,"wins":15},"claude-opus-4-5":{"draws":30,"losses":16,"wins":32},"claude-opus-4-8":{"draws":11,"losses":16,"wins":17},"claude-opus-5":{"draws":12,"losses":55,"wins":15},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":14,"losses":11,"wins":23},"claude-sonnet-5-5":{"draws":10,"losses":21,"wins":17},"cohere/north-mini-code":{"draws":0,"losses":4,"wins":14},"deepseek/deepseek-v4-flash":{"draws":22,"losses":13,"wins":37},"deepseek/deepseek-v4-pro":{"draws":8,"losses":17,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":20,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":21,"wins":15},"fireworks/ember-1":{"draws":13,"losses":23,"wins":12},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"wins":23},"google/gemini-3.1-flash-lite":{"draws":8,"losses":4,"wins":20},"google/gemini-3.5-flash":{"draws":17,"losses":23,"wins":20},"google/gemini-3.5-flash-lite":{"draws":26,"losses":17,"wins":41},"google/gemini-3.6-flash":{"draws":28,"losses":33,"wins":31},"google/gemini-3.8-flash":{"draws":11,"losses":26,"wins":11},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":15},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":14,"losses":12,"wins":16},"gpt-5.4":{"draws":5,"losses":26,"wins":15},"gpt-5.4-mini":{"draws":12,"losses":10,"wins":10},"gpt-5.4-nano":{"draws":12,"losses":8,"wins":28},"gpt-5.5":{"draws":10,"losses":15,"wins":19},"gpt-5.6-luna":{"draws":14,"losses":9,"wins":25},"gpt-5.6-sol":{"draws":10,"losses":28,"wins":10},"gpt-5.6-terra":{"draws":12,"losses":15,"wins":19},"gpt-6-astra":{"draws":3,"losses":40,"wins":5},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":4,"losses":31,"wins":13},"gpt-6.1-sol":{"draws":2,"losses":38,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.0-flash":{"draws":13,"losses":2,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":16,"losses":10,"wins":26},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":25},"meta/muse-spark-1.2":{"draws":10,"losses":20,"wins":16},"meta/muse-spark-1.3":{"draws":8,"losses":24,"wins":16},"meta/muse-wonder":{"draws":8,"losses":29,"wins":11},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":20},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":11},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":11,"losses":11,"wins":8},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":5,"wins":21},"o3":{"draws":11,"losses":26,"wins":29},"openai/gpt-oss-120b":{"draws":11,"losses":8,"wins":23},"poolside/laguna-s-2.1":{"draws":16,"losses":7,"wins":23},"qwen/qwen3.7-max":{"draws":6,"losses":8,"wins":14},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":17,"wins":20},"qwen/qwen3.8-27b":{"draws":12,"losses":10,"wins":12},"qwen/qwen3.8-flash":{"draws":8,"losses":15,"wins":9},"qwen/qwen3.8-max":{"draws":10,"losses":19,"wins":19},"qwen/qwen3.8-max-0902":{"draws":11,"losses":25,"wins":12},"stealth/ox-alpha":{"draws":41,"losses":65,"wins":52},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":18},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":19,"wins":16},"thinkingmachines/inkling":{"draws":22,"losses":13,"wins":29},"thinkingmachines/inkling-small":{"draws":14,"losses":10,"wins":24},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":15,"losses":19,"wins":14},"x-ai/grok-4.6":{"draws":6,"losses":27,"wins":15},"x-ai/grok-4.7":{"draws":2,"losses":31,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":28,"losses":9,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":37,"losses":19,"wins":40},"z-ai/glm-5.3":{"draws":11,"losses":23,"wins":12},"z-ai/glm-5.3-flash":{"draws":11,"losses":25,"wins":12},"z-ai/glm-5.3-flashx":{"draws":13,"losses":25,"wins":10}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":15,"wins":8},"claude-fable-5":{"draws":12,"losses":29,"wins":1},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":19,"wins":7},"claude-opus-4-5":{"draws":24,"losses":32,"wins":12},"claude-opus-4-8":{"draws":13,"losses":21,"wins":4},"claude-opus-5":{"draws":3,"losses":62,"wins":5},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":18,"losses":16,"wins":8},"claude-sonnet-5-5":{"draws":12,"losses":22,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":22,"losses":26,"wins":14},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":23,"wins":4},"fireworks/ember-1":{"draws":17,"losses":18,"wins":7},"gemini-3.1-pro-preview":{"draws":17,"losses":19,"wins":6},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":14},"google/gemini-3.5-flash":{"draws":19,"losses":21,"wins":12},"google/gemini-3.5-flash-lite":{"draws":29,"losses":20,"wins":25},"google/gemini-3.6-flash":{"draws":23,"losses":42,"wins":15},"google/gemini-3.8-flash":{"draws":13,"losses":23,"wins":6},"google/gemma-4-31b-it":{"draws":13,"losses":6,"wins":7},"gpt-4.1":{"draws":5,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":15,"losses":11,"wins":10},"gpt-5.4":{"draws":14,"losses":16,"wins":10},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":6},"gpt-5.4-nano":{"draws":13,"losses":16,"wins":11},"gpt-5.5":{"draws":17,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":15,"losses":20,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":30,"wins":5},"gpt-5.6-terra":{"draws":18,"losses":15,"wins":7},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":13,"losses":23,"wins":6},"gpt-6-sol":{"draws":7,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":6,"wins":8},"inclusionai/ling-3.0-flash":{"draws":17,"losses":6,"wins":5},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":15,"wins":15},"meta/muse-glimmer-30b":{"draws":20,"losses":5,"wins":11},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":9},"meta/muse-spark-1.3":{"draws":11,"losses":25,"wins":6},"meta/muse-wonder":{"draws":12,"losses":27,"wins":3},"minimax/minimax-m3":{"draws":9,"losses":6,"wins":7},"mistralai/mistral-large-4-0":{"draws":12,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":12,"losses":10,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":9,"wins":8},"o3":{"draws":11,"losses":30,"wins":15},"openai/gpt-oss-120b":{"draws":15,"losses":9,"wins":14},"poolside/laguna-s-2.1":{"draws":19,"losses":11,"wins":10},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":23,"wins":6},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":3},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":4},"qwen/qwen3.8-max":{"draws":17,"losses":23,"wins":2},"qwen/qwen3.8-max-0902":{"draws":17,"losses":18,"wins":7},"stealth/ox-alpha":{"draws":47,"losses":76,"wins":19},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":8,"losses":14,"wins":6},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":8},"tencent/hy4-preview":{"draws":15,"losses":22,"wins":3},"thinkingmachines/inkling":{"draws":20,"losses":17,"wins":17},"thinkingmachines/inkling-small":{"draws":20,"losses":12,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":11,"losses":26,"wins":5},"x-ai/grok-4.6":{"draws":15,"losses":24,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":3},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":28,"losses":17,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":5,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":42,"losses":30,"wins":12},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":14,"losses":23,"wins":5},"z-ai/glm-5.3-flashx":{"draws":12,"losses":26,"wins":4}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":13,"wins":14},"claude-fable-5":{"draws":8,"losses":28,"wins":6},"claude-fable-5-1":{"draws":2,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":19,"wins":12},"claude-opus-4-5":{"draws":19,"losses":38,"wins":11},"claude-opus-4-8":{"draws":6,"losses":22,"wins":10},"claude-opus-5":{"draws":9,"losses":58,"wins":3},"claude-opus-5-5":{"draws":2,"losses":43,"wins":1},"claude-sonnet-5":{"draws":11,"losses":18,"wins":13},"claude-sonnet-5-5":{"draws":5,"losses":31,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":15,"losses":29,"wins":18},"deepseek/deepseek-v4-pro":{"draws":15,"losses":15,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":21,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":24,"wins":6},"fireworks/ember-1":{"draws":12,"losses":21,"wins":9},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":11},"google/gemini-3.1-flash-lite":{"draws":7,"losses":11,"wins":12},"google/gemini-3.5-flash":{"draws":13,"losses":29,"wins":12},"google/gemini-3.5-flash-lite":{"draws":29,"losses":22,"wins":25},"google/gemini-3.6-flash":{"draws":20,"losses":47,"wins":15},"google/gemini-3.8-flash":{"draws":9,"losses":29,"wins":4},"google/gemma-4-31b-it":{"draws":9,"losses":7,"wins":8},"gpt-4.1":{"draws":4,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":13,"losses":16,"wins":9},"gpt-5.4":{"draws":15,"losses":24,"wins":3},"gpt-5.4-mini":{"draws":11,"losses":8,"wins":9},"gpt-5.4-nano":{"draws":5,"losses":21,"wins":16},"gpt-5.5":{"draws":17,"losses":20,"wins":3},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":3,"losses":35,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":20,"wins":6},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":10,"losses":20,"wins":12},"gpt-6-sol":{"draws":4,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":39,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":12,"wins":7},"inclusionai/ling-3.0-flash":{"draws":13,"losses":8,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":23,"wins":10},"meta/muse-glimmer-30b":{"draws":15,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":10,"losses":20,"wins":10},"meta/muse-spark-1.3":{"draws":6,"losses":32,"wins":4},"meta/muse-wonder":{"draws":9,"losses":30,"wins":3},"minimax/minimax-m3":{"draws":5,"losses":10,"wins":7},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":7},"mistralai/mistral-medium-3-5":{"draws":10,"losses":6,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":8,"losses":23,"wins":9},"nex-agi/nex-n2-pro":{"draws":7,"losses":5,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":9},"o3":{"draws":14,"losses":31,"wins":19},"openai/gpt-oss-120b":{"draws":12,"losses":13,"wins":11},"poolside/laguna-s-2.1":{"draws":15,"losses":11,"wins":14},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":7},"qwen/qwen3.7-plus":{"draws":3,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":25,"wins":5},"qwen/qwen3.8-27b":{"draws":7,"losses":16,"wins":7},"qwen/qwen3.8-flash":{"draws":12,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":12,"losses":22,"wins":8},"qwen/qwen3.8-max-0902":{"draws":10,"losses":26,"wins":6},"stealth/ox-alpha":{"draws":30,"losses":86,"wins":26},"stealth/space-bunny-alpha":{"draws":12,"losses":13,"wins":9},"stepfun/step-3.7-flash":{"draws":12,"losses":12,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":6},"tencent/hy4-preview":{"draws":11,"losses":25,"wins":6},"thinkingmachines/inkling":{"draws":17,"losses":19,"wins":22},"thinkingmachines/inkling-small":{"draws":15,"losses":14,"wins":13},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":6,"wins":3},"x-ai/grok-4.5":{"draws":9,"losses":30,"wins":3},"x-ai/grok-4.6":{"draws":13,"losses":25,"wins":4},"x-ai/grok-4.7":{"draws":1,"losses":33,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":21,"losses":21,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":11,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":14,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":21,"wins":3},"z-ai/glm-5.2":{"draws":26,"losses":30,"wins":28},"z-ai/glm-5.3":{"draws":7,"losses":29,"wins":4},"z-ai/glm-5.3-flash":{"draws":5,"losses":26,"wins":11},"z-ai/glm-5.3-flashx":{"draws":6,"losses":29,"wins":7}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":11,"wins":14},"claude-fable-5":{"draws":10,"losses":31,"wins":7},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":17,"losses":19,"wins":10},"claude-opus-4-5":{"draws":18,"losses":38,"wins":22},"claude-opus-4-8":{"draws":14,"losses":22,"wins":8},"claude-opus-5":{"draws":13,"losses":65,"wins":4},"claude-opus-5-5":{"draws":7,"losses":45,"wins":0},"claude-sonnet-5":{"draws":14,"losses":20,"wins":14},"claude-sonnet-5-5":{"draws":8,"losses":31,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":25,"losses":14,"wins":33},"deepseek/deepseek-v4-pro":{"draws":14,"losses":19,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":21,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":13},"fireworks/ember-1":{"draws":17,"losses":24,"wins":7},"gemini-3.1-pro-preview":{"draws":13,"losses":19,"wins":16},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":19,"losses":25,"wins":16},"google/gemini-3.5-flash-lite":{"draws":28,"losses":20,"wins":36},"google/gemini-3.6-flash":{"draws":25,"losses":44,"wins":23},"google/gemini-3.8-flash":{"draws":16,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":12},"gpt-4.1":{"draws":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":18,"losses":11,"wins":13},"gpt-5.4":{"draws":12,"losses":23,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":12,"losses":20,"wins":16},"gpt-5.5":{"draws":13,"losses":20,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":13,"wins":16},"gpt-5.6-sol":{"draws":7,"losses":37,"wins":4},"gpt-5.6-terra":{"draws":18,"losses":13,"wins":15},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":13,"losses":22,"wins":13},"gpt-6-sol":{"draws":2,"losses":44,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":44,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":5,"wins":15},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":9,"wins":27},"meta/muse-glimmer-30b":{"draws":15,"losses":12,"wins":15},"meta/muse-spark-1.2":{"draws":13,"losses":27,"wins":6},"meta/muse-spark-1.3":{"draws":12,"losses":29,"wins":7},"meta/muse-wonder":{"draws":7,"losses":36,"wins":5},"minimax/minimax-m3":{"draws":9,"losses":8,"wins":9},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":13,"losses":3,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":19,"wins":13},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":9,"wins":16},"o3":{"draws":10,"losses":22,"wins":18},"openai/gpt-oss-120b":{"draws":14,"losses":7,"wins":21},"poolside/laguna-s-2.1":{"draws":20,"losses":10,"wins":16},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":26,"wins":11},"qwen/qwen3.8-27b":{"draws":7,"losses":15,"wins":12},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":23,"wins":10},"qwen/qwen3.8-max-0902":{"draws":11,"losses":26,"wins":11},"stealth/ox-alpha":{"draws":44,"losses":82,"wins":32},"stealth/space-bunny-alpha":{"draws":13,"losses":12,"wins":13},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":12,"losses":20,"wins":14},"thinkingmachines/inkling":{"draws":20,"losses":14,"wins":30},"thinkingmachines/inkling-small":{"draws":17,"losses":11,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":10,"losses":27,"wins":11},"x-ai/grok-4.6":{"draws":14,"losses":27,"wins":7},"x-ai/grok-4.7":{"draws":5,"losses":32,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":25,"losses":20,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":13,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":27,"wins":1},"z-ai/glm-5.2":{"draws":36,"losses":27,"wins":33},"z-ai/glm-5.3":{"draws":9,"losses":29,"wins":8},"z-ai/glm-5.3-flash":{"draws":14,"losses":25,"wins":9},"z-ai/glm-5.3-flashx":{"draws":11,"losses":28,"wins":9}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":14,"wins":8},"claude-fable-5":{"draws":7,"losses":26,"wins":3},"claude-fable-5-1":{"draws":0,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":21,"wins":5},"claude-opus-4-5":{"draws":19,"losses":34,"wins":5},"claude-opus-4-8":{"draws":9,"losses":22,"wins":1},"claude-opus-5":{"draws":7,"losses":57,"wins":4},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":12,"losses":20,"wins":4},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":3},"deepseek/deepseek-v4-flash":{"draws":23,"losses":14,"wins":19},"deepseek/deepseek-v4-pro":{"draws":9,"losses":18,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":15,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":4},"fireworks/ember-1":{"draws":14,"losses":20,"wins":2},"gemini-3.1-pro-preview":{"draws":12,"losses":18,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":11},"google/gemini-3.5-flash":{"draws":13,"losses":24,"wins":7},"google/gemini-3.5-flash-lite":{"draws":19,"losses":23,"wins":18},"google/gemini-3.6-flash":{"draws":20,"losses":39,"wins":9},"google/gemini-3.8-flash":{"draws":9,"losses":25,"wins":2},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":9},"gpt-4.1":{"draws":2,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":11,"losses":16,"wins":7},"gpt-5.4":{"draws":7,"losses":21,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":14,"losses":11,"wins":13},"gpt-5.5":{"draws":11,"losses":18,"wins":5},"gpt-5.6-luna":{"draws":15,"losses":14,"wins":7},"gpt-5.6-sol":{"draws":2,"losses":34,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":21,"wins":3},"gpt-6-astra":{"draws":4,"losses":32,"wins":0},"gpt-6-luna":{"draws":12,"losses":17,"wins":7},"gpt-6-sol":{"draws":6,"losses":28,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":7,"wins":7},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":14,"wins":10},"meta/muse-glimmer-30b":{"draws":15,"losses":8,"wins":11},"meta/muse-spark-1.2":{"draws":7,"losses":28,"wins":1},"meta/muse-spark-1.3":{"draws":11,"losses":21,"wins":4},"meta/muse-wonder":{"draws":4,"losses":28,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":7,"wins":8},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":20,"wins":6},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":9},"o3":{"draws":9,"losses":34,"wins":7},"openai/gpt-oss-120b":{"draws":6,"losses":8,"wins":8},"poolside/laguna-s-2.1":{"draws":17,"losses":15,"wins":8},"qwen/qwen3.7-max":{"draws":9,"losses":9,"wins":4},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":19,"wins":3},"qwen/qwen3.8-27b":{"draws":5,"losses":14,"wins":5},"qwen/qwen3.8-flash":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.8-max":{"draws":12,"losses":21,"wins":3},"qwen/qwen3.8-max-0902":{"draws":12,"losses":20,"wins":4},"stealth/ox-alpha":{"draws":34,"losses":80,"wins":10},"stealth/space-bunny-alpha":{"draws":6,"losses":17,"wins":5},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":11,"losses":19,"wins":4},"thinkingmachines/inkling":{"draws":11,"losses":25,"wins":14},"thinkingmachines/inkling-small":{"draws":14,"losses":6,"wins":16},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":10,"losses":21,"wins":5},"x-ai/grok-4.6":{"draws":9,"losses":26,"wins":1},"x-ai/grok-4.7":{"draws":3,"losses":30,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":19,"losses":19,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":32,"losses":28,"wins":12},"z-ai/glm-5.3":{"draws":10,"losses":24,"wins":0},"z-ai/glm-5.3-flash":{"draws":11,"losses":20,"wins":5},"z-ai/glm-5.3-flashx":{"draws":13,"losses":21,"wins":2}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":17,"wins":25},"claude-fable-5":{"draws":10,"losses":48,"wins":14},"claude-fable-5-1":{"draws":0,"losses":79,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":30,"wins":23},"claude-opus-4-5":{"draws":35,"losses":55,"wins":26},"claude-opus-4-8":{"draws":14,"losses":38,"wins":12},"claude-opus-5":{"draws":8,"losses":111,"wins":7},"claude-opus-5-5":{"draws":5,"losses":75,"wins":0},"claude-sonnet-5":{"draws":19,"losses":33,"wins":20},"claude-sonnet-5-5":{"draws":10,"losses":47,"wins":15},"cohere/north-mini-code":{"draws":9,"losses":7,"wins":14},"deepseek/deepseek-v4-flash":{"draws":35,"losses":30,"wins":47},"deepseek/deepseek-v4-pro":{"draws":13,"losses":27,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":28,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":32,"wins":14},"fireworks/ember-1":{"draws":22,"losses":37,"wins":13},"gemini-3.1-pro-preview":{"draws":20,"losses":31,"wins":21},"google/gemini-3.1-flash-lite":{"draws":10,"losses":9,"wins":29},"google/gemini-3.5-flash":{"draws":16,"losses":52,"wins":22},"google/gemini-3.5-flash-lite":{"draws":29,"losses":33,"wins":62},"google/gemini-3.6-flash":{"draws":34,"losses":68,"wins":36},"google/gemini-3.8-flash":{"draws":13,"losses":49,"wins":10},"google/gemma-4-31b-it":{"draws":13,"losses":10,"wins":17},"gpt-4.1":{"draws":5,"losses":12,"wins":7},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":19,"losses":22,"wins":27},"gpt-5.4":{"draws":17,"losses":44,"wins":9},"gpt-5.4-mini":{"draws":18,"losses":15,"wins":15},"gpt-5.4-nano":{"draws":16,"losses":28,"wins":34},"gpt-5.5":{"draws":25,"losses":30,"wins":13},"gpt-5.6-luna":{"draws":21,"losses":23,"wins":28},"gpt-5.6-sol":{"draws":8,"losses":57,"wins":7},"gpt-5.6-terra":{"draws":23,"losses":33,"wins":12},"gpt-6-astra":{"draws":2,"losses":70,"wins":0},"gpt-6-luna":{"draws":20,"losses":25,"wins":27},"gpt-6-sol":{"draws":10,"losses":54,"wins":8},"gpt-6.1-sol":{"draws":4,"losses":67,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":12,"wins":18},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":24},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":26,"losses":20,"wins":34},"meta/muse-glimmer-30b":{"draws":23,"losses":19,"wins":24},"meta/muse-spark-1.2":{"draws":11,"losses":43,"wins":16},"meta/muse-spark-1.3":{"draws":9,"losses":44,"wins":19},"meta/muse-wonder":{"draws":10,"losses":57,"wins":5},"minimax/minimax-m3":{"draws":10,"losses":13,"wins":19},"mistralai/mistral-large-4-0":{"draws":13,"losses":17,"wins":16},"mistralai/mistral-medium-3-5":{"draws":13,"losses":8,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":8,"wins":9},"moonshotai/kimi-k3":{"draws":19,"losses":31,"wins":20},"nex-agi/nex-n2-pro":{"draws":14,"losses":5,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":14,"wins":26},"o3":{"draws":19,"losses":53,"wins":38},"openai/gpt-oss-120b":{"draws":19,"losses":14,"wins":33},"poolside/laguna-s-2.1":{"draws":22,"losses":13,"wins":19},"qwen/qwen3.7-max":{"draws":14,"losses":18,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":42,"wins":10},"qwen/qwen3.8-27b":{"draws":12,"losses":22,"wins":16},"qwen/qwen3.8-flash":{"draws":17,"losses":17,"wins":14},"qwen/qwen3.8-max":{"draws":22,"losses":27,"wins":23},"qwen/qwen3.8-max-0902":{"draws":19,"losses":35,"wins":18},"stealth/ox-alpha":{"draws":55,"losses":133,"wins":60},"stealth/space-bunny-alpha":{"draws":13,"losses":22,"wins":21},"stepfun/step-3.7-flash":{"draws":17,"losses":15,"wins":24},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":14,"wins":14},"tencent/hy4-preview":{"draws":20,"losses":35,"wins":15},"thinkingmachines/inkling":{"draws":22,"losses":29,"wins":49},"thinkingmachines/inkling-small":{"draws":26,"losses":10,"wins":36},"unbiased/pareto-26.10-preview":{"draws":0,"losses":23,"wins":1},"upstage/solar-mini4":{"draws":3,"losses":9,"wins":4},"x-ai/grok-4.5":{"draws":14,"losses":45,"wins":13},"x-ai/grok-4.6":{"draws":20,"losses":42,"wins":10},"x-ai/grok-4.7":{"draws":4,"losses":53,"wins":9},"x-ai/grok-build-0.1":{"draws":8,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":23,"losses":30,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":16,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":25,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":33,"wins":13},"z-ai/glm-5.2":{"draws":52,"losses":48,"wins":44},"z-ai/glm-5.3":{"draws":7,"losses":52,"wins":9},"z-ai/glm-5.3-flash":{"draws":16,"losses":38,"wins":18},"z-ai/glm-5.3-flashx":{"draws":13,"losses":44,"wins":15}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":17,"wins":10},"claude-fable-5":{"draws":8,"losses":29,"wins":5},"claude-fable-5-1":{"draws":0,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":19,"wins":8},"claude-opus-4-5":{"draws":21,"losses":34,"wins":13},"claude-opus-4-8":{"draws":11,"losses":18,"wins":9},"claude-opus-5":{"draws":8,"losses":59,"wins":3},"claude-opus-5-5":{"draws":5,"losses":41,"wins":0},"claude-sonnet-5":{"draws":15,"losses":20,"wins":7},"claude-sonnet-5-5":{"draws":13,"losses":18,"wins":11},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":23,"losses":17,"wins":26},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":23,"wins":7},"fireworks/ember-1":{"draws":13,"losses":22,"wins":7},"gemini-3.1-pro-preview":{"draws":12,"losses":17,"wins":13},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":17},"google/gemini-3.5-flash":{"draws":13,"losses":23,"wins":16},"google/gemini-3.5-flash-lite":{"draws":16,"losses":22,"wins":34},"google/gemini-3.6-flash":{"draws":22,"losses":42,"wins":16},"google/gemini-3.8-flash":{"draws":14,"losses":19,"wins":9},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":10},"gpt-4.1":{"draws":5,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":15,"losses":14,"wins":9},"gpt-5.4":{"draws":11,"losses":20,"wins":9},"gpt-5.4-mini":{"draws":9,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":14,"losses":16,"wins":16},"gpt-5.5":{"draws":14,"losses":17,"wins":7},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":18},"gpt-5.6-sol":{"draws":5,"losses":31,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":22,"wins":5},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":11,"losses":16,"wins":15},"gpt-6-sol":{"draws":9,"losses":28,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":8,"wins":10},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":12,"wins":20},"meta/muse-glimmer-30b":{"draws":14,"losses":7,"wins":15},"meta/muse-spark-1.2":{"draws":6,"losses":25,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":26,"wins":8},"meta/muse-wonder":{"draws":5,"losses":28,"wins":9},"minimax/minimax-m3":{"draws":10,"losses":2,"wins":12},"mistralai/mistral-large-4-0":{"draws":12,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":9,"losses":22,"wins":9},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":13},"o3":{"draws":10,"losses":34,"wins":18},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":15},"poolside/laguna-s-2.1":{"draws":17,"losses":12,"wins":15},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":21,"wins":8},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":10,"wins":10},"qwen/qwen3.8-max":{"draws":18,"losses":17,"wins":7},"qwen/qwen3.8-max-0902":{"draws":11,"losses":22,"wins":9},"stealth/ox-alpha":{"draws":33,"losses":80,"wins":27},"stealth/space-bunny-alpha":{"draws":10,"losses":12,"wins":10},"stepfun/step-3.7-flash":{"draws":9,"losses":10,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":8},"tencent/hy4-preview":{"draws":10,"losses":23,"wins":7},"thinkingmachines/inkling":{"draws":17,"losses":11,"wins":28},"thinkingmachines/inkling-small":{"draws":14,"losses":9,"wins":19},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":11,"losses":23,"wins":8},"x-ai/grok-4.6":{"draws":13,"losses":21,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":26,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":14,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":6,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":15,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":30,"losses":27,"wins":27},"z-ai/glm-5.3":{"draws":8,"losses":28,"wins":4},"z-ai/glm-5.3-flash":{"draws":10,"losses":26,"wins":6},"z-ai/glm-5.3-flashx":{"draws":9,"losses":25,"wins":8}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":13,"wins":7},"claude-fable-5":{"draws":6,"losses":27,"wins":3},"claude-fable-5-1":{"draws":5,"losses":35,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":28,"wins":1},"claude-opus-4-5":{"draws":25,"losses":28,"wins":7},"claude-opus-4-8":{"draws":8,"losses":24,"wins":4},"claude-opus-5":{"draws":6,"losses":45,"wins":7},"claude-opus-5-5":{"draws":3,"losses":33,"wins":0},"claude-sonnet-5":{"draws":11,"losses":20,"wins":5},"claude-sonnet-5-5":{"draws":8,"losses":24,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":17,"losses":25,"wins":12},"deepseek/deepseek-v4-pro":{"draws":10,"losses":19,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":19,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":22,"wins":2},"fireworks/ember-1":{"draws":12,"losses":22,"wins":2},"gemini-3.1-pro-preview":{"draws":12,"losses":22,"wins":2},"google/gemini-3.1-flash-lite":{"draws":7,"losses":9,"wins":12},"google/gemini-3.5-flash":{"draws":11,"losses":30,"wins":5},"google/gemini-3.5-flash-lite":{"draws":18,"losses":36,"wins":10},"google/gemini-3.6-flash":{"draws":23,"losses":44,"wins":3},"google/gemini-3.8-flash":{"draws":9,"losses":24,"wins":3},"google/gemma-4-31b-it":{"draws":7,"losses":9,"wins":6},"gpt-4.1":{"draws":4,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":8,"losses":20,"wins":2},"gpt-5.4":{"draws":6,"losses":27,"wins":1},"gpt-5.4-mini":{"draws":8,"losses":11,"wins":5},"gpt-5.4-nano":{"draws":8,"losses":22,"wins":8},"gpt-5.5":{"draws":11,"losses":19,"wins":2},"gpt-5.6-luna":{"draws":14,"losses":16,"wins":6},"gpt-5.6-sol":{"draws":7,"losses":27,"wins":2},"gpt-5.6-terra":{"draws":11,"losses":21,"wins":2},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":14,"losses":20,"wins":2},"gpt-6-sol":{"draws":7,"losses":28,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":9,"wins":7},"inclusionai/ling-3.0-flash":{"draws":9,"losses":12,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":23,"wins":7},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":5},"meta/muse-spark-1.2":{"draws":10,"losses":17,"wins":7},"meta/muse-spark-1.3":{"draws":5,"losses":27,"wins":4},"meta/muse-wonder":{"draws":4,"losses":30,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":9,"wins":5},"mistralai/mistral-large-4-0":{"draws":4,"losses":17,"wins":1},"mistralai/mistral-medium-3-5":{"draws":9,"losses":9,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":17,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":16,"wins":7},"o3":{"draws":6,"losses":41,"wins":5},"openai/gpt-oss-120b":{"draws":9,"losses":17,"wins":4},"poolside/laguna-s-2.1":{"draws":8,"losses":19,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":12,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":19,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":18,"wins":4},"qwen/qwen3.8-flash":{"draws":7,"losses":12,"wins":5},"qwen/qwen3.8-max":{"draws":16,"losses":18,"wins":2},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":2},"stealth/ox-alpha":{"draws":23,"losses":72,"wins":7},"stealth/space-bunny-alpha":{"draws":8,"losses":19,"wins":3},"stepfun/step-3.7-flash":{"draws":5,"losses":15,"wins":6},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":3},"tencent/hy4-preview":{"draws":9,"losses":20,"wins":5},"thinkingmachines/inkling":{"draws":16,"losses":23,"wins":9},"thinkingmachines/inkling-small":{"draws":15,"losses":18,"wins":3},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":7,"wins":2},"x-ai/grok-4.5":{"draws":12,"losses":23,"wins":1},"x-ai/grok-4.6":{"draws":8,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":3},"x-ai/grok-build-0.1":{"draws":3,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":24,"losses":29,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":16,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":16,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":17,"wins":2},"z-ai/glm-5.2":{"draws":22,"losses":42,"wins":8},"z-ai/glm-5.3":{"draws":8,"losses":24,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":26,"wins":2},"z-ai/glm-5.3-flashx":{"draws":7,"losses":28,"wins":1}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":12,"wins":20},"claude-fable-5":{"draws":10,"losses":31,"wins":7},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":14},"claude-opus-4-5":{"draws":27,"losses":25,"wins":26},"claude-opus-4-8":{"draws":14,"losses":18,"wins":12},"claude-opus-5":{"draws":7,"losses":63,"wins":12},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":15,"losses":10,"wins":23},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":17},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":23,"losses":11,"wins":38},"deepseek/deepseek-v4-pro":{"draws":12,"losses":13,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":22,"wins":16},"fireworks/ember-1":{"draws":12,"losses":20,"wins":16},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":23},"google/gemini-3.5-flash":{"draws":18,"losses":19,"wins":23},"google/gemini-3.5-flash-lite":{"draws":28,"losses":17,"wins":39},"google/gemini-3.6-flash":{"draws":22,"losses":43,"wins":27},"google/gemini-3.8-flash":{"draws":11,"losses":26,"wins":11},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":5,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":13,"wins":19},"gpt-5.4":{"draws":10,"losses":20,"wins":16},"gpt-5.4-mini":{"draws":13,"losses":3,"wins":16},"gpt-5.4-nano":{"draws":11,"losses":12,"wins":25},"gpt-5.5":{"draws":12,"losses":18,"wins":14},"gpt-5.6-luna":{"draws":17,"losses":11,"wins":20},"gpt-5.6-sol":{"draws":8,"losses":33,"wins":7},"gpt-5.6-terra":{"draws":13,"losses":11,"wins":22},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":10,"losses":22,"wins":16},"gpt-6-sol":{"draws":5,"losses":36,"wins":7},"gpt-6.1-sol":{"draws":3,"losses":43,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.0-flash":{"draws":13,"losses":2,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":8,"wins":30},"meta/muse-glimmer-30b":{"draws":14,"losses":11,"wins":17},"meta/muse-spark-1.2":{"draws":10,"losses":14,"wins":22},"meta/muse-spark-1.3":{"draws":11,"losses":19,"wins":18},"meta/muse-wonder":{"draws":10,"losses":24,"wins":14},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":18},"mistralai/mistral-large-4-0":{"draws":5,"losses":11,"wins":14},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":18,"wins":18},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":4,"wins":24},"o3":{"draws":12,"losses":18,"wins":36},"openai/gpt-oss-120b":{"draws":14,"losses":5,"wins":23},"poolside/laguna-s-2.1":{"draws":15,"losses":7,"wins":24},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":14},"qwen/qwen3.7-plus":{"draws":10,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":7},"qwen/qwen3.8-27b":{"draws":12,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":13},"qwen/qwen3.8-max":{"draws":11,"losses":25,"wins":12},"qwen/qwen3.8-max-0902":{"draws":13,"losses":19,"wins":16},"stealth/ox-alpha":{"draws":37,"losses":67,"wins":54},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":13},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":14,"losses":21,"wins":11},"thinkingmachines/inkling":{"draws":19,"losses":12,"wins":33},"thinkingmachines/inkling-small":{"draws":13,"losses":6,"wins":29},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":10,"losses":21,"wins":17},"x-ai/grok-4.6":{"draws":12,"losses":22,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":7,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":14,"wins":10},"z-ai/glm-5.2":{"draws":30,"losses":26,"wins":40},"z-ai/glm-5.3":{"draws":8,"losses":31,"wins":7},"z-ai/glm-5.3-flash":{"draws":12,"losses":21,"wins":15},"z-ai/glm-5.3-flashx":{"draws":12,"losses":25,"wins":11}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":7,"wins":8},"claude-fable-5":{"draws":5,"losses":17,"wins":2},"claude-fable-5-1":{"draws":1,"losses":25,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":15,"wins":2},"claude-opus-4-5":{"draws":17,"losses":19,"wins":2},"claude-opus-4-8":{"draws":5,"losses":12,"wins":3},"claude-opus-5":{"draws":8,"losses":28,"wins":2},"claude-opus-5-5":{"draws":1,"losses":23,"wins":0},"claude-sonnet-5":{"draws":6,"losses":13,"wins":5},"claude-sonnet-5-5":{"draws":8,"losses":14,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":15,"losses":11,"wins":12},"deepseek/deepseek-v4-pro":{"draws":9,"losses":7,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":9,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":10,"wins":2},"fireworks/ember-1":{"draws":12,"losses":11,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":9,"wins":7},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":5},"google/gemini-3.5-flash":{"draws":4,"losses":20,"wins":4},"google/gemini-3.5-flash-lite":{"draws":10,"losses":18,"wins":12},"google/gemini-3.6-flash":{"draws":14,"losses":26,"wins":6},"google/gemini-3.8-flash":{"draws":7,"losses":17,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":3,"wins":3},"gpt-4.1":{"draws":3,"losses":4,"wins":1},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":8,"wins":5},"gpt-5.4":{"draws":7,"losses":12,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":6,"wins":2},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":4},"gpt-5.5":{"draws":8,"losses":9,"wins":3},"gpt-5.6-luna":{"draws":12,"losses":6,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":16,"wins":2},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":7},"gpt-6-astra":{"draws":1,"losses":23,"wins":0},"gpt-6-luna":{"draws":9,"losses":11,"wins":4},"gpt-6-sol":{"draws":7,"losses":16,"wins":1},"gpt-6.1-sol":{"draws":3,"losses":21,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":8},"inclusionai/ling-3.0-flash":{"draws":5,"losses":6,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":5,"wins":8},"meta/muse-glimmer-30b":{"draws":9,"losses":5,"wins":4},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":5},"meta/muse-spark-1.3":{"draws":8,"losses":15,"wins":1},"meta/muse-wonder":{"draws":6,"losses":14,"wins":4},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":2},"mistralai/mistral-large-4-0":{"draws":3,"losses":9,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":11,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":8,"wins":3},"o3":{"draws":4,"losses":19,"wins":5},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":7},"poolside/laguna-s-2.1":{"draws":9,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":8,"wins":4},"qwen/qwen3.8-27b":{"draws":3,"losses":8,"wins":1},"qwen/qwen3.8-flash":{"draws":6,"losses":9,"wins":1},"qwen/qwen3.8-max":{"draws":10,"losses":7,"wins":7},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":2},"stealth/ox-alpha":{"draws":18,"losses":54,"wins":16},"stealth/space-bunny-alpha":{"draws":7,"losses":7,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":5,"losses":15,"wins":2},"thinkingmachines/inkling":{"draws":14,"losses":14,"wins":4},"thinkingmachines/inkling-small":{"draws":12,"losses":7,"wins":5},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":15,"wins":1},"x-ai/grok-4.6":{"draws":8,"losses":13,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":15,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":15,"losses":14,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":6,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":4},"z-ai/glm-5.2":{"draws":20,"losses":22,"wins":6},"z-ai/glm-5.3":{"draws":8,"losses":13,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":3},"z-ai/glm-5.3-flashx":{"draws":7,"losses":15,"wins":2}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":15,"wins":12},"claude-fable-5":{"draws":8,"losses":38,"wins":2},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":31,"wins":2},"claude-opus-4-5":{"draws":31,"losses":40,"wins":7},"claude-opus-4-8":{"draws":12,"losses":30,"wins":2},"claude-opus-5":{"draws":12,"losses":66,"wins":4},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":18,"losses":24,"wins":6},"claude-sonnet-5-5":{"draws":13,"losses":29,"wins":6},"cohere/north-mini-code":{"draws":6,"losses":6,"wins":6},"deepseek/deepseek-v4-flash":{"draws":25,"losses":23,"wins":24},"deepseek/deepseek-v4-pro":{"draws":14,"losses":22,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":24,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":26,"wins":4},"fireworks/ember-1":{"draws":17,"losses":24,"wins":7},"gemini-3.1-pro-preview":{"draws":17,"losses":19,"wins":12},"google/gemini-3.1-flash-lite":{"draws":11,"losses":9,"wins":12},"google/gemini-3.5-flash":{"draws":16,"losses":36,"wins":8},"google/gemini-3.5-flash-lite":{"draws":30,"losses":25,"wins":29},"google/gemini-3.6-flash":{"draws":33,"losses":51,"wins":8},"google/gemini-3.8-flash":{"draws":11,"losses":36,"wins":1},"google/gemma-4-31b-it":{"draws":13,"losses":5,"wins":10},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":24,"wins":9},"gpt-5.4":{"draws":10,"losses":27,"wins":9},"gpt-5.4-mini":{"draws":13,"losses":10,"wins":9},"gpt-5.4-nano":{"draws":13,"losses":18,"wins":17},"gpt-5.5":{"draws":18,"losses":21,"wins":5},"gpt-5.6-luna":{"draws":17,"losses":22,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":6},"gpt-5.6-terra":{"draws":11,"losses":25,"wins":10},"gpt-6-astra":{"draws":6,"losses":42,"wins":0},"gpt-6-luna":{"draws":14,"losses":25,"wins":9},"gpt-6-sol":{"draws":2,"losses":41,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":6,"wins":12},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":15,"wins":17},"meta/muse-glimmer-30b":{"draws":21,"losses":12,"wins":9},"meta/muse-spark-1.2":{"draws":12,"losses":27,"wins":7},"meta/muse-spark-1.3":{"draws":10,"losses":32,"wins":6},"meta/muse-wonder":{"draws":11,"losses":35,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":14,"wins":4},"mistralai/mistral-large-4-0":{"draws":11,"losses":18,"wins":1},"mistralai/mistral-medium-3-5":{"draws":12,"losses":4,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":17,"losses":25,"wins":4},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":11,"wins":12},"o3":{"draws":17,"losses":34,"wins":15},"openai/gpt-oss-120b":{"draws":12,"losses":17,"wins":13},"poolside/laguna-s-2.1":{"draws":20,"losses":17,"wins":9},"qwen/qwen3.7-max":{"draws":11,"losses":14,"wins":3},"qwen/qwen3.7-plus":{"draws":8,"losses":11,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":28,"wins":4},"qwen/qwen3.8-27b":{"draws":7,"losses":16,"wins":11},"qwen/qwen3.8-flash":{"draws":9,"losses":7,"wins":0},"qwen/qwen3.8-max":{"draws":18,"losses":24,"wins":6},"qwen/qwen3.8-max-0902":{"draws":16,"losses":24,"wins":8},"stealth/ox-alpha":{"draws":45,"losses":87,"wins":26},"stealth/space-bunny-alpha":{"draws":15,"losses":14,"wins":9},"stepfun/step-3.7-flash":{"draws":9,"losses":13,"wins":12},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":6},"tencent/hy4-preview":{"draws":11,"losses":30,"wins":5},"thinkingmachines/inkling":{"draws":23,"losses":18,"wins":23},"thinkingmachines/inkling-small":{"draws":21,"losses":12,"wins":15},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":11,"losses":27,"wins":10},"x-ai/grok-4.6":{"draws":17,"losses":28,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":37,"wins":3},"x-ai/grok-build-0.1":{"draws":10,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":30,"losses":27,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":9,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":17,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":37,"losses":43,"wins":16},"z-ai/glm-5.3":{"draws":11,"losses":32,"wins":3},"z-ai/glm-5.3-flash":{"draws":16,"losses":27,"wins":5},"z-ai/glm-5.3-flashx":{"draws":19,"losses":26,"wins":3}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":14},"claude-fable-5":{"draws":11,"losses":22,"wins":15},"claude-fable-5-1":{"draws":2,"losses":49,"wins":3},"claude-haiku-5-5":{"draws":14,"losses":17,"wins":15},"claude-opus-4-5":{"draws":26,"losses":31,"wins":21},"claude-opus-4-8":{"draws":10,"losses":19,"wins":15},"claude-opus-5":{"draws":14,"losses":56,"wins":12},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":19,"losses":16,"wins":13},"claude-sonnet-5-5":{"draws":7,"losses":29,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":32,"losses":11,"wins":29},"deepseek/deepseek-v4-pro":{"draws":13,"losses":12,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":15,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":13},"fireworks/ember-1":{"draws":13,"losses":21,"wins":14},"gemini-3.1-pro-preview":{"draws":15,"losses":17,"wins":16},"google/gemini-3.1-flash-lite":{"draws":11,"losses":1,"wins":20},"google/gemini-3.5-flash":{"draws":24,"losses":16,"wins":20},"google/gemini-3.5-flash-lite":{"draws":32,"losses":21,"wins":31},"google/gemini-3.6-flash":{"draws":24,"losses":36,"wins":32},"google/gemini-3.8-flash":{"draws":10,"losses":20,"wins":18},"google/gemma-4-31b-it":{"draws":14,"losses":4,"wins":10},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":7,"wins":21},"gpt-5.4":{"draws":15,"losses":15,"wins":16},"gpt-5.4-mini":{"draws":15,"losses":8,"wins":9},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":20},"gpt-5.5":{"draws":15,"losses":17,"wins":12},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":8,"losses":31,"wins":9},"gpt-5.6-terra":{"draws":18,"losses":12,"wins":16},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":13,"losses":19,"wins":16},"gpt-6-sol":{"draws":5,"losses":29,"wins":14},"gpt-6.1-sol":{"draws":2,"losses":44,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":5,"wins":14},"inclusionai/ling-3.0-flash":{"draws":10,"losses":7,"wins":17},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":24,"losses":8,"wins":20},"meta/muse-glimmer-30b":{"draws":13,"losses":8,"wins":21},"meta/muse-spark-1.2":{"draws":12,"losses":18,"wins":16},"meta/muse-spark-1.3":{"draws":12,"losses":20,"wins":16},"meta/muse-wonder":{"draws":11,"losses":25,"wins":12},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":10},"mistralai/mistral-large-4-0":{"draws":12,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":8,"losses":5,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":12,"losses":17,"wins":17},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":9,"wins":15},"o3":{"draws":16,"losses":20,"wins":30},"openai/gpt-oss-120b":{"draws":17,"losses":4,"wins":21},"poolside/laguna-s-2.1":{"draws":17,"losses":13,"wins":16},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":20,"wins":15},"qwen/qwen3.8-27b":{"draws":13,"losses":14,"wins":7},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":12},"qwen/qwen3.8-max":{"draws":10,"losses":16,"wins":6},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":14},"stealth/ox-alpha":{"draws":49,"losses":67,"wins":42},"stealth/space-bunny-alpha":{"draws":13,"losses":11,"wins":14},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":5,"wins":9},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":22,"losses":12,"wins":30},"thinkingmachines/inkling-small":{"draws":17,"losses":14,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":12,"losses":20,"wins":16},"x-ai/grok-4.6":{"draws":14,"losses":24,"wins":10},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":25,"losses":18,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":12,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":16,"wins":8},"z-ai/glm-5.2":{"draws":35,"losses":24,"wins":37},"z-ai/glm-5.3":{"draws":10,"losses":26,"wins":10},"z-ai/glm-5.3-flash":{"draws":9,"losses":23,"wins":16},"z-ai/glm-5.3-flashx":{"draws":14,"losses":17,"wins":17}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":5,"wins":19},"claude-fable-5":{"draws":12,"losses":29,"wins":7},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":21,"wins":10},"claude-opus-4-5":{"draws":29,"losses":26,"wins":23},"claude-opus-4-8":{"draws":16,"losses":13,"wins":15},"claude-opus-5":{"draws":11,"losses":68,"wins":3},"claude-opus-5-5":{"draws":2,"losses":48,"wins":2},"claude-sonnet-5":{"draws":17,"losses":14,"wins":17},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":26,"losses":10,"wins":36},"deepseek/deepseek-v4-pro":{"draws":13,"losses":13,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":14,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":19,"wins":8},"fireworks/ember-1":{"draws":18,"losses":12,"wins":18},"gemini-3.1-pro-preview":{"draws":15,"losses":14,"wins":19},"google/gemini-3.1-flash-lite":{"draws":12,"losses":1,"wins":19},"google/gemini-3.5-flash":{"draws":21,"losses":15,"wins":24},"google/gemini-3.5-flash-lite":{"draws":34,"losses":10,"wins":40},"google/gemini-3.6-flash":{"draws":37,"losses":30,"wins":25},"google/gemini-3.8-flash":{"draws":16,"losses":22,"wins":10},"google/gemma-4-31b-it":{"draws":12,"losses":4,"wins":12},"gpt-4.1":{"draws":8,"losses":1,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":11,"wins":16},"gpt-5.4":{"draws":12,"losses":21,"wins":13},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":17,"losses":8,"wins":23},"gpt-5.5":{"draws":22,"losses":12,"wins":10},"gpt-5.6-luna":{"draws":22,"losses":12,"wins":14},"gpt-5.6-sol":{"draws":7,"losses":32,"wins":9},"gpt-5.6-terra":{"draws":17,"losses":17,"wins":12},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":19,"losses":15,"wins":14},"gpt-6-sol":{"draws":6,"losses":36,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":42,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":6,"wins":11},"inclusionai/ling-3.0-flash":{"draws":17,"losses":4,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":8,"wins":29},"meta/muse-glimmer-30b":{"draws":18,"losses":3,"wins":21},"meta/muse-spark-1.2":{"draws":9,"losses":20,"wins":17},"meta/muse-spark-1.3":{"draws":14,"losses":22,"wins":12},"meta/muse-wonder":{"draws":13,"losses":29,"wins":6},"minimax/minimax-m3":{"draws":9,"losses":2,"wins":15},"mistralai/mistral-large-4-0":{"draws":13,"losses":5,"wins":12},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":16,"losses":9,"wins":21},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":2,"wins":16},"o3":{"draws":16,"losses":21,"wins":29},"openai/gpt-oss-120b":{"draws":16,"losses":5,"wins":21},"poolside/laguna-s-2.1":{"draws":19,"losses":8,"wins":19},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":9,"losses":4,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":16,"wins":14},"qwen/qwen3.8-27b":{"draws":12,"losses":11,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":9,"wins":12},"qwen/qwen3.8-max":{"draws":15,"losses":15,"wins":18},"qwen/qwen3.8-max-0902":{"draws":7,"losses":15,"wins":10},"stealth/ox-alpha":{"draws":44,"losses":61,"wins":53},"stealth/space-bunny-alpha":{"draws":13,"losses":6,"wins":19},"stepfun/step-3.7-flash":{"draws":10,"losses":6,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":9},"tencent/hy4-preview":{"draws":14,"losses":22,"wins":10},"thinkingmachines/inkling":{"draws":21,"losses":11,"wins":32},"thinkingmachines/inkling-small":{"draws":21,"losses":2,"wins":25},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":24,"wins":13},"x-ai/grok-4.6":{"draws":16,"losses":27,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":31,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":33,"losses":9,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":44,"losses":16,"wins":36},"z-ai/glm-5.3":{"draws":15,"losses":25,"wins":6},"z-ai/glm-5.3-flash":{"draws":13,"losses":19,"wins":16},"z-ai/glm-5.3-flashx":{"draws":12,"losses":24,"wins":12}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":54,"losses":35,"wins":67},"claude-fable-5":{"draws":34,"losses":110,"wins":24},"claude-fable-5-1":{"draws":5,"losses":189,"wins":2},"claude-haiku-5-5":{"draws":48,"losses":71,"wins":33},"claude-opus-4-5":{"draws":101,"losses":88,"wins":75},"claude-opus-4-8":{"draws":34,"losses":70,"wins":32},"claude-opus-5":{"draws":45,"losses":225,"wins":24},"claude-opus-5-5":{"draws":17,"losses":158,"wins":1},"claude-sonnet-5":{"draws":54,"losses":59,"wins":55},"claude-sonnet-5-5":{"draws":37,"losses":90,"wins":41},"cohere/north-mini-code":{"draws":18,"losses":10,"wins":32},"deepseek/deepseek-v4-flash":{"draws":102,"losses":56,"wins":88},"deepseek/deepseek-v4-pro":{"draws":60,"losses":53,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":54,"losses":66,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":52,"losses":77,"wins":39},"fireworks/ember-1":{"draws":62,"losses":75,"wins":31},"gemini-3.1-pro-preview":{"draws":54,"losses":61,"wins":53},"google/gemini-3.1-flash-lite":{"draws":26,"losses":9,"wins":57},"google/gemini-3.5-flash":{"draws":51,"losses":99,"wins":52},"google/gemini-3.5-flash-lite":{"draws":99,"losses":77,"wins":116},"google/gemini-3.6-flash":{"draws":88,"losses":159,"wins":79},"google/gemini-3.8-flash":{"draws":49,"losses":92,"wins":27},"google/gemma-4-31b-it":{"draws":35,"losses":15,"wins":40},"gpt-4.1":{"draws":23,"losses":18,"wins":15},"gpt-4.1-nano":{"draws":16,"losses":2,"wins":10},"gpt-5":{"draws":59,"losses":50,"wins":41},"gpt-5.4":{"draws":62,"losses":73,"wins":27},"gpt-5.4-mini":{"draws":50,"losses":31,"wins":31},"gpt-5.4-nano":{"draws":46,"losses":46,"wins":54},"gpt-5.5":{"draws":63,"losses":59,"wins":34},"gpt-5.6-luna":{"draws":72,"losses":47,"wins":49},"gpt-5.6-sol":{"draws":34,"losses":111,"wins":23},"gpt-5.6-terra":{"draws":72,"losses":49,"wins":41},"gpt-6-astra":{"draws":11,"losses":156,"wins":1},"gpt-6-luna":{"draws":54,"losses":69,"wins":45},"gpt-6-sol":{"draws":20,"losses":133,"wins":15},"gpt-6.1-sol":{"draws":11,"losses":151,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":50,"losses":11,"wins":47},"inclusionai/ling-3.0-flash":{"draws":59,"losses":13,"wins":44},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":70,"losses":31,"wins":77},"meta/muse-glimmer-30b":{"draws":62,"losses":26,"wins":62},"meta/muse-spark-1.2":{"draws":53,"losses":63,"wins":46},"meta/muse-spark-1.3":{"draws":36,"losses":102,"wins":30},"meta/muse-wonder":{"draws":44,"losses":101,"wins":23},"minimax/minimax-m3":{"draws":26,"losses":18,"wins":40},"mistralai/mistral-large-4-0":{"draws":50,"losses":34,"wins":22},"mistralai/mistral-medium-3-5":{"draws":41,"losses":14,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":12,"wins":11},"moonshotai/kimi-k3":{"draws":54,"losses":63,"wins":45},"nex-agi/nex-n2-pro":{"draws":35,"losses":11,"wins":42},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":53,"losses":22,"wins":53},"o3":{"draws":54,"losses":88,"wins":66},"openai/gpt-oss-120b":{"draws":66,"losses":27,"wins":57},"poolside/laguna-s-2.1":{"draws":76,"losses":37,"wins":57},"qwen/qwen3.7-max":{"draws":35,"losses":25,"wins":30},"qwen/qwen3.7-plus":{"draws":24,"losses":13,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":59,"losses":70,"wins":39},"qwen/qwen3.8-27b":{"draws":43,"losses":44,"wins":33},"qwen/qwen3.8-flash":{"draws":52,"losses":40,"wins":20},"qwen/qwen3.8-max":{"draws":55,"losses":75,"wins":38},"qwen/qwen3.8-max-0902":{"draws":57,"losses":71,"wins":40},"stealth/ox-alpha":{"draws":142,"losses":297,"wins":163},"stealth/space-bunny-alpha":{"draws":55,"losses":37,"wins":38},"stepfun/step-3.7-flash":{"draws":40,"losses":22,"wins":56},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":34,"losses":22,"wins":28},"tencent/hy4-preview":{"draws":51,"losses":80,"wins":31},"thinkingmachines/inkling":{"draws":88,"losses":52,"wins":96},"thinkingmachines/inkling-small":{"draws":76,"losses":26,"wins":66},"unbiased/pareto-26.10-preview":{"draws":0,"losses":56,"wins":0},"upstage/solar-mini4":{"draws":7,"losses":6,"wins":23},"x-ai/grok-4.5":{"draws":48,"losses":74,"wins":46},"x-ai/grok-4.6":{"draws":65,"losses":73,"wins":30},"x-ai/grok-4.7":{"draws":19,"losses":106,"wins":15},"x-ai/grok-build-0.1":{"draws":22,"losses":11,"wins":23},"xiaomi/mimo-v2.5":{"draws":89,"losses":47,"wins":86},"xiaomi/mimo-v2.5-pro":{"draws":34,"losses":27,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":28,"losses":52,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":26,"losses":64,"wins":22},"z-ai/glm-5.2":{"draws":140,"losses":93,"wins":103},"z-ai/glm-5.3":{"draws":34,"losses":108,"wins":20},"z-ai/glm-5.3-flash":{"draws":37,"losses":91,"wins":40},"z-ai/glm-5.3-flashx":{"draws":43,"losses":94,"wins":31}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":12,"wins":9},"claude-fable-5":{"draws":13,"losses":19,"wins":4},"claude-fable-5-1":{"draws":2,"losses":39,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":18,"wins":4},"claude-opus-4-5":{"draws":19,"losses":29,"wins":10},"claude-opus-4-8":{"draws":11,"losses":15,"wins":6},"claude-opus-5":{"draws":11,"losses":54,"wins":3},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":12,"losses":17,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":20,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":10},"deepseek/deepseek-v4-flash":{"draws":26,"losses":12,"wins":14},"deepseek/deepseek-v4-pro":{"draws":12,"losses":17,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":14,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":16,"wins":7},"fireworks/ember-1":{"draws":14,"losses":18,"wins":4},"gemini-3.1-pro-preview":{"draws":16,"losses":14,"wins":6},"google/gemini-3.1-flash-lite":{"draws":9,"losses":1,"wins":12},"google/gemini-3.5-flash":{"draws":17,"losses":19,"wins":8},"google/gemini-3.5-flash-lite":{"draws":26,"losses":16,"wins":20},"google/gemini-3.6-flash":{"draws":19,"losses":42,"wins":7},"google/gemini-3.8-flash":{"draws":11,"losses":19,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":5},"gpt-4.1":{"draws":5,"losses":3,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":13,"losses":12,"wins":7},"gpt-5.4":{"draws":17,"losses":13,"wins":4},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":9},"gpt-5.4-nano":{"draws":11,"losses":9,"wins":12},"gpt-5.5":{"draws":20,"losses":13,"wins":1},"gpt-5.6-luna":{"draws":19,"losses":5,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":29,"wins":0},"gpt-5.6-terra":{"draws":13,"losses":12,"wins":9},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":14,"losses":16,"wins":6},"gpt-6-sol":{"draws":6,"losses":30,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":3,"wins":8},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":2},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":9,"wins":15},"meta/muse-glimmer-30b":{"draws":19,"losses":8,"wins":7},"meta/muse-spark-1.2":{"draws":12,"losses":21,"wins":3},"meta/muse-spark-1.3":{"draws":10,"losses":24,"wins":2},"meta/muse-wonder":{"draws":9,"losses":23,"wins":4},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":6},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":3},"mistralai/mistral-medium-3-5":{"draws":12,"losses":1,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":3},"nex-agi/nex-n2-pro":{"draws":9,"losses":1,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":0,"wins":12},"o3":{"draws":12,"losses":25,"wins":7},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":11},"poolside/laguna-s-2.1":{"draws":20,"losses":8,"wins":8},"qwen/qwen3.7-max":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":0,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":18,"wins":6},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":1},"qwen/qwen3.8-flash":{"draws":11,"losses":7,"wins":6},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":5},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":2},"stealth/ox-alpha":{"draws":46,"losses":67,"wins":13},"stealth/space-bunny-alpha":{"draws":6,"losses":6,"wins":6},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":7},"tencent/hy4-preview":{"draws":15,"losses":16,"wins":3},"thinkingmachines/inkling":{"draws":20,"losses":13,"wins":15},"thinkingmachines/inkling-small":{"draws":18,"losses":10,"wins":8},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":11,"losses":22,"wins":3},"x-ai/grok-4.6":{"draws":16,"losses":16,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":26,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":27,"losses":10,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":14,"wins":3},"z-ai/glm-5.2":{"draws":36,"losses":22,"wins":14},"z-ai/glm-5.3":{"draws":8,"losses":27,"wins":1},"z-ai/glm-5.3-flash":{"draws":14,"losses":19,"wins":3},"z-ai/glm-5.3-flashx":{"draws":14,"losses":16,"wins":6}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":11},"claude-fable-5":{"draws":11,"losses":24,"wins":1},"claude-fable-5-1":{"draws":3,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":22,"wins":4},"claude-opus-4-5":{"draws":18,"losses":25,"wins":15},"claude-opus-4-8":{"draws":11,"losses":18,"wins":3},"claude-opus-5":{"draws":11,"losses":43,"wins":4},"claude-opus-5-5":{"draws":3,"losses":33,"wins":0},"claude-sonnet-5":{"draws":14,"losses":9,"wins":13},"claude-sonnet-5-5":{"draws":8,"losses":18,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":17,"losses":12,"wins":25},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":12,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":19,"wins":5},"fireworks/ember-1":{"draws":14,"losses":15,"wins":7},"gemini-3.1-pro-preview":{"draws":17,"losses":11,"wins":8},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":14},"google/gemini-3.5-flash":{"draws":12,"losses":25,"wins":7},"google/gemini-3.5-flash-lite":{"draws":30,"losses":16,"wins":16},"google/gemini-3.6-flash":{"draws":23,"losses":37,"wins":10},"google/gemini-3.8-flash":{"draws":12,"losses":19,"wins":5},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":8},"gpt-4.1":{"draws":6,"losses":5,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":11,"wins":9},"gpt-5.4":{"draws":12,"losses":17,"wins":5},"gpt-5.4-mini":{"draws":12,"losses":5,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":9},"gpt-5.5":{"draws":14,"losses":13,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":13,"wins":9},"gpt-5.6-sol":{"draws":9,"losses":26,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":14,"wins":8},"gpt-6-astra":{"draws":6,"losses":30,"wins":0},"gpt-6-luna":{"draws":13,"losses":16,"wins":7},"gpt-6-sol":{"draws":9,"losses":24,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":33,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":14},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":10},"meituan/longcat-2.0":{"draws":10,"losses":8,"wins":18},"meta/muse-glimmer-30b":{"draws":13,"losses":11,"wins":6},"meta/muse-spark-1.2":{"draws":14,"losses":10,"wins":10},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":4},"meta/muse-wonder":{"draws":10,"losses":20,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":7,"wins":6},"mistralai/mistral-large-4-0":{"draws":10,"losses":8,"wins":4},"mistralai/mistral-medium-3-5":{"draws":12,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":15,"wins":8},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":3,"wins":13},"o3":{"draws":11,"losses":20,"wins":13},"openai/gpt-oss-120b":{"draws":17,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":15,"losses":6,"wins":9},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":23,"wins":2},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":3},"qwen/qwen3.8-max":{"draws":13,"losses":15,"wins":8},"qwen/qwen3.8-max-0902":{"draws":11,"losses":16,"wins":9},"stealth/ox-alpha":{"draws":32,"losses":68,"wins":24},"stealth/space-bunny-alpha":{"draws":13,"losses":9,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":7},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":2},"tencent/hy4-preview":{"draws":11,"losses":15,"wins":8},"thinkingmachines/inkling":{"draws":20,"losses":7,"wins":21},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":12,"losses":16,"wins":8},"x-ai/grok-4.6":{"draws":12,"losses":19,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":21,"wins":5},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":6},"xiaomi/mimo-v2.5":{"draws":24,"losses":12,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":9,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":13,"wins":3},"z-ai/glm-5.2":{"draws":27,"losses":26,"wins":19},"z-ai/glm-5.3":{"draws":10,"losses":23,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":18,"wins":10},"z-ai/glm-5.3-flashx":{"draws":7,"losses":26,"wins":3}},"stepfun/step-5-preview":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":0},"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-5":{"draws":3,"losses":7,"wins":0},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":3,"losses":3,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":2},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":0,"wins":2},"fireworks/ember-1":{"draws":3,"losses":3,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.8-flash":{"draws":3,"losses":3,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":5,"losses":0,"wins":1},"gpt-5.4":{"draws":5,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":1},"gpt-5.5":{"draws":6,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":3,"losses":2,"wins":1},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":0},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":7,"losses":1,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":0,"losses":6,"wins":0},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":0},"meta/muse-wonder":{"draws":2,"losses":4,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":0},"o3":{"draws":8,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-max-0902":{"draws":5,"losses":1,"wins":0},"stealth/ox-alpha":{"draws":8,"losses":8,"wins":0},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":3,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-4.6":{"draws":4,"losses":2,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":8,"losses":2,"wins":2},"z-ai/glm-5.3":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.3-flash":{"draws":5,"losses":0,"wins":1},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":2}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":14,"wins":9},"claude-fable-5":{"draws":9,"losses":21,"wins":6},"claude-fable-5-1":{"draws":5,"losses":32,"wins":3},"claude-haiku-5-5":{"draws":14,"losses":13,"wins":7},"claude-opus-4-5":{"draws":23,"losses":23,"wins":12},"claude-opus-4-8":{"draws":10,"losses":16,"wins":6},"claude-opus-5":{"draws":13,"losses":50,"wins":9},"claude-opus-5-5":{"draws":5,"losses":35,"wins":0},"claude-sonnet-5":{"draws":13,"losses":14,"wins":9},"claude-sonnet-5-5":{"draws":12,"losses":19,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":3},"deepseek/deepseek-v4-flash":{"draws":18,"losses":17,"wins":17},"deepseek/deepseek-v4-pro":{"draws":13,"losses":14,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":11,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":16,"wins":4},"fireworks/ember-1":{"draws":15,"losses":15,"wins":6},"gemini-3.1-pro-preview":{"draws":11,"losses":17,"wins":8},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":7},"google/gemini-3.5-flash":{"draws":14,"losses":18,"wins":12},"google/gemini-3.5-flash-lite":{"draws":28,"losses":10,"wins":24},"google/gemini-3.6-flash":{"draws":25,"losses":28,"wins":15},"google/gemini-3.8-flash":{"draws":17,"losses":16,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":4},"gpt-4.1":{"draws":4,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":11,"losses":10,"wins":11},"gpt-5.4":{"draws":17,"losses":12,"wins":5},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":11,"losses":7,"wins":16},"gpt-5.5":{"draws":16,"losses":13,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":7,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":2},"gpt-5.6-terra":{"draws":16,"losses":12,"wins":6},"gpt-6-astra":{"draws":7,"losses":29,"wins":0},"gpt-6-luna":{"draws":12,"losses":16,"wins":8},"gpt-6-sol":{"draws":10,"losses":24,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":32,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":5},"inclusionai/ling-3.0-flash":{"draws":14,"losses":1,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":12},"meta/muse-glimmer-30b":{"draws":14,"losses":8,"wins":12},"meta/muse-spark-1.2":{"draws":11,"losses":21,"wins":4},"meta/muse-spark-1.3":{"draws":9,"losses":21,"wins":6},"meta/muse-wonder":{"draws":9,"losses":21,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":8},"mistralai/mistral-large-4-0":{"draws":12,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":10,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":8},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":6,"wins":6},"o3":{"draws":12,"losses":18,"wins":12},"openai/gpt-oss-120b":{"draws":12,"losses":9,"wins":11},"poolside/laguna-s-2.1":{"draws":16,"losses":12,"wins":10},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":17,"wins":6},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":6},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":5},"qwen/qwen3.8-max":{"draws":16,"losses":15,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":18,"wins":6},"stealth/ox-alpha":{"draws":36,"losses":67,"wins":21},"stealth/space-bunny-alpha":{"draws":14,"losses":10,"wins":4},"stepfun/step-3.7-flash":{"draws":11,"losses":4,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":13,"losses":14,"wins":7},"thinkingmachines/inkling":{"draws":16,"losses":17,"wins":17},"thinkingmachines/inkling-small":{"draws":19,"losses":5,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":14,"losses":18,"wins":4},"x-ai/grok-4.6":{"draws":13,"losses":21,"wins":2},"x-ai/grok-4.7":{"draws":9,"losses":23,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":27,"losses":12,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":13,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":31,"losses":23,"wins":18},"z-ai/glm-5.3":{"draws":7,"losses":23,"wins":4},"z-ai/glm-5.3-flash":{"draws":12,"losses":18,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":21,"wins":5}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":7,"wins":21},"claude-fable-5":{"draws":11,"losses":34,"wins":3},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":21,"wins":15},"claude-opus-4-5":{"draws":28,"losses":32,"wins":18},"claude-opus-4-8":{"draws":12,"losses":21,"wins":11},"claude-opus-5":{"draws":11,"losses":62,"wins":9},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":15,"losses":18,"wins":15},"claude-sonnet-5-5":{"draws":11,"losses":27,"wins":10},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":24,"losses":17,"wins":31},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":19,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":17,"wins":15},"fireworks/ember-1":{"draws":20,"losses":20,"wins":8},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":17},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":15,"losses":26,"wins":19},"google/gemini-3.5-flash-lite":{"draws":26,"losses":25,"wins":33},"google/gemini-3.6-flash":{"draws":26,"losses":42,"wins":24},"google/gemini-3.8-flash":{"draws":12,"losses":27,"wins":9},"google/gemma-4-31b-it":{"draws":11,"losses":7,"wins":10},"gpt-4.1":{"draws":7,"losses":6,"wins":3},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":14,"losses":15,"wins":13},"gpt-5.4":{"draws":14,"losses":24,"wins":8},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":12,"losses":15,"wins":21},"gpt-5.5":{"draws":20,"losses":16,"wins":8},"gpt-5.6-luna":{"draws":19,"losses":11,"wins":18},"gpt-5.6-sol":{"draws":9,"losses":35,"wins":4},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":15},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":18,"losses":17,"wins":13},"gpt-6-sol":{"draws":9,"losses":36,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":3,"wins":16},"inclusionai/ling-3.0-flash":{"draws":12,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":8,"wins":26},"meta/muse-glimmer-30b":{"draws":20,"losses":6,"wins":16},"meta/muse-spark-1.2":{"draws":9,"losses":25,"wins":12},"meta/muse-spark-1.3":{"draws":11,"losses":26,"wins":11},"meta/muse-wonder":{"draws":12,"losses":31,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":14},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":14,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":16,"losses":17,"wins":13},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":7,"wins":15},"o3":{"draws":13,"losses":32,"wins":21},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":19},"poolside/laguna-s-2.1":{"draws":16,"losses":11,"wins":19},"qwen/qwen3.7-max":{"draws":10,"losses":8,"wins":10},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":20,"wins":9},"qwen/qwen3.8-27b":{"draws":10,"losses":13,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":11,"wins":10},"qwen/qwen3.8-max":{"draws":18,"losses":15,"wins":15},"qwen/qwen3.8-max-0902":{"draws":17,"losses":21,"wins":10},"stealth/ox-alpha":{"draws":35,"losses":76,"wins":47},"stealth/space-bunny-alpha":{"draws":14,"losses":14,"wins":10},"stepfun/step-3.7-flash":{"draws":8,"losses":10,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":7,"losses":18,"wins":5},"thinkingmachines/inkling":{"draws":18,"losses":15,"wins":31},"thinkingmachines/inkling-small":{"draws":20,"losses":7,"wins":21},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":17,"losses":23,"wins":8},"x-ai/grok-4.6":{"draws":17,"losses":25,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":29,"losses":12,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":7,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":17,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":9},"z-ai/glm-5.2":{"draws":33,"losses":28,"wins":35},"z-ai/glm-5.3":{"draws":10,"losses":31,"wins":5},"z-ai/glm-5.3-flash":{"draws":11,"losses":24,"wins":13},"z-ai/glm-5.3-flashx":{"draws":15,"losses":21,"wins":12}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":22,"wins":19},"claude-fable-5":{"draws":17,"losses":49,"wins":6},"claude-fable-5-1":{"draws":5,"losses":77,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":43,"wins":12},"claude-opus-4-5":{"draws":40,"losses":52,"wins":24},"claude-opus-4-8":{"draws":18,"losses":37,"wins":9},"claude-opus-5":{"draws":17,"losses":99,"wins":14},"claude-opus-5-5":{"draws":6,"losses":70,"wins":0},"claude-sonnet-5":{"draws":24,"losses":34,"wins":14},"claude-sonnet-5-5":{"draws":15,"losses":42,"wins":15},"cohere/north-mini-code":{"draws":7,"losses":9,"wins":10},"deepseek/deepseek-v4-flash":{"draws":37,"losses":37,"wins":30},"deepseek/deepseek-v4-pro":{"draws":19,"losses":33,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":23,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":31,"wins":15},"fireworks/ember-1":{"draws":24,"losses":35,"wins":13},"gemini-3.1-pro-preview":{"draws":20,"losses":31,"wins":21},"google/gemini-3.1-flash-lite":{"draws":10,"losses":17,"wins":19},"google/gemini-3.5-flash":{"draws":22,"losses":50,"wins":18},"google/gemini-3.5-flash-lite":{"draws":32,"losses":51,"wins":45},"google/gemini-3.6-flash":{"draws":45,"losses":75,"wins":20},"google/gemini-3.8-flash":{"draws":13,"losses":49,"wins":10},"google/gemma-4-31b-it":{"draws":18,"losses":12,"wins":10},"gpt-4.1":{"draws":5,"losses":10,"wins":9},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":34,"wins":16},"gpt-5.4":{"draws":19,"losses":40,"wins":11},"gpt-5.4-mini":{"draws":17,"losses":16,"wins":15},"gpt-5.4-nano":{"draws":12,"losses":31,"wins":25},"gpt-5.5":{"draws":18,"losses":38,"wins":12},"gpt-5.6-luna":{"draws":24,"losses":30,"wins":18},"gpt-5.6-sol":{"draws":12,"losses":53,"wins":7},"gpt-5.6-terra":{"draws":22,"losses":30,"wins":16},"gpt-6-astra":{"draws":3,"losses":68,"wins":1},"gpt-6-luna":{"draws":23,"losses":31,"wins":18},"gpt-6-sol":{"draws":13,"losses":56,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":65,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":19,"losses":14,"wins":15},"inclusionai/ling-3.0-flash":{"draws":17,"losses":12,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":21,"losses":24,"wins":31},"meta/muse-glimmer-30b":{"draws":25,"losses":18,"wins":23},"meta/muse-spark-1.2":{"draws":19,"losses":31,"wins":20},"meta/muse-spark-1.3":{"draws":15,"losses":49,"wins":8},"meta/muse-wonder":{"draws":12,"losses":47,"wins":13},"minimax/minimax-m3":{"draws":10,"losses":13,"wins":15},"mistralai/mistral-large-4-0":{"draws":16,"losses":20,"wins":10},"mistralai/mistral-medium-3-5":{"draws":14,"losses":11,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":10,"wins":5},"moonshotai/kimi-k3":{"draws":22,"losses":31,"wins":17},"nex-agi/nex-n2-pro":{"draws":10,"losses":7,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":22,"wins":19},"o3":{"draws":12,"losses":62,"wins":22},"openai/gpt-oss-120b":{"draws":16,"losses":23,"wins":23},"poolside/laguna-s-2.1":{"draws":19,"losses":28,"wins":23},"qwen/qwen3.7-max":{"draws":15,"losses":19,"wins":6},"qwen/qwen3.7-plus":{"draws":11,"losses":14,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":33,"wins":16},"qwen/qwen3.8-27b":{"draws":12,"losses":26,"wins":14},"qwen/qwen3.8-flash":{"draws":14,"losses":24,"wins":10},"qwen/qwen3.8-max":{"draws":26,"losses":31,"wins":15},"qwen/qwen3.8-max-0902":{"draws":19,"losses":41,"wins":12},"stealth/ox-alpha":{"draws":58,"losses":142,"wins":50},"stealth/space-bunny-alpha":{"draws":19,"losses":22,"wins":17},"stepfun/step-3.7-flash":{"draws":12,"losses":28,"wins":10},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":17,"wins":11},"tencent/hy4-preview":{"draws":24,"losses":37,"wins":9},"thinkingmachines/inkling":{"draws":30,"losses":20,"wins":28},"thinkingmachines/inkling-small":{"draws":26,"losses":21,"wins":25},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":7,"wins":5},"x-ai/grok-4.5":{"draws":18,"losses":41,"wins":13},"x-ai/grok-4.6":{"draws":27,"losses":34,"wins":11},"x-ai/grok-4.7":{"draws":5,"losses":50,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":11,"wins":6},"xiaomi/mimo-v2.5":{"draws":35,"losses":44,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":23,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":26,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":29,"wins":5},"z-ai/glm-5.2":{"draws":52,"losses":55,"wins":37},"z-ai/glm-5.3":{"draws":15,"losses":44,"wins":9},"z-ai/glm-5.3-flash":{"draws":19,"losses":40,"wins":13},"z-ai/glm-5.3-flashx":{"draws":16,"losses":44,"wins":12}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":19,"wins":7},"claude-fable-5":{"draws":9,"losses":34,"wins":5},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":29,"wins":5},"claude-opus-4-5":{"draws":26,"losses":45,"wins":7},"claude-opus-4-8":{"draws":13,"losses":29,"wins":2},"claude-opus-5":{"draws":12,"losses":66,"wins":4},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":17,"losses":24,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":32,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":7,"wins":4},"deepseek/deepseek-v4-flash":{"draws":35,"losses":26,"wins":11},"deepseek/deepseek-v4-pro":{"draws":19,"losses":22,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":21,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":26,"wins":8},"fireworks/ember-1":{"draws":16,"losses":28,"wins":4},"gemini-3.1-pro-preview":{"draws":16,"losses":26,"wins":6},"google/gemini-3.1-flash-lite":{"draws":12,"losses":14,"wins":6},"google/gemini-3.5-flash":{"draws":19,"losses":35,"wins":6},"google/gemini-3.5-flash-lite":{"draws":29,"losses":33,"wins":22},"google/gemini-3.6-flash":{"draws":26,"losses":50,"wins":16},"google/gemini-3.8-flash":{"draws":15,"losses":30,"wins":3},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":10},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":21,"losses":17,"wins":4},"gpt-5.4":{"draws":16,"losses":24,"wins":6},"gpt-5.4-mini":{"draws":15,"losses":12,"wins":5},"gpt-5.4-nano":{"draws":18,"losses":18,"wins":12},"gpt-5.5":{"draws":16,"losses":25,"wins":3},"gpt-5.6-luna":{"draws":22,"losses":19,"wins":7},"gpt-5.6-sol":{"draws":10,"losses":36,"wins":2},"gpt-5.6-terra":{"draws":17,"losses":27,"wins":2},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":13,"losses":25,"wins":10},"gpt-6-sol":{"draws":4,"losses":44,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":8,"wins":9},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":23,"wins":11},"meta/muse-glimmer-30b":{"draws":22,"losses":14,"wins":6},"meta/muse-spark-1.2":{"draws":14,"losses":25,"wins":7},"meta/muse-spark-1.3":{"draws":14,"losses":31,"wins":3},"meta/muse-wonder":{"draws":12,"losses":34,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":11,"wins":7},"mistralai/mistral-large-4-0":{"draws":12,"losses":14,"wins":4},"mistralai/mistral-medium-3-5":{"draws":16,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":23,"wins":6},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":14,"wins":8},"o3":{"draws":15,"losses":39,"wins":12},"openai/gpt-oss-120b":{"draws":16,"losses":18,"wins":8},"poolside/laguna-s-2.1":{"draws":23,"losses":19,"wins":4},"qwen/qwen3.7-max":{"draws":10,"losses":14,"wins":4},"qwen/qwen3.7-plus":{"draws":10,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":31,"wins":4},"qwen/qwen3.8-27b":{"draws":9,"losses":19,"wins":6},"qwen/qwen3.8-flash":{"draws":14,"losses":15,"wins":3},"qwen/qwen3.8-max":{"draws":15,"losses":19,"wins":14},"qwen/qwen3.8-max-0902":{"draws":17,"losses":28,"wins":3},"stealth/ox-alpha":{"draws":45,"losses":90,"wins":23},"stealth/space-bunny-alpha":{"draws":13,"losses":17,"wins":8},"stepfun/step-3.7-flash":{"draws":9,"losses":13,"wins":12},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":5},"tencent/hy4-preview":{"draws":14,"losses":27,"wins":5},"thinkingmachines/inkling":{"draws":28,"losses":27,"wins":9},"thinkingmachines/inkling-small":{"draws":14,"losses":12,"wins":6},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":3},"x-ai/grok-4.5":{"draws":14,"losses":31,"wins":3},"x-ai/grok-4.6":{"draws":14,"losses":30,"wins":4},"x-ai/grok-4.7":{"draws":7,"losses":35,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":28,"losses":28,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":9,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":19,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":24,"wins":4},"z-ai/glm-5.2":{"draws":38,"losses":44,"wins":14},"z-ai/glm-5.3":{"draws":9,"losses":36,"wins":1},"z-ai/glm-5.3-flash":{"draws":11,"losses":30,"wins":7},"z-ai/glm-5.3-flashx":{"draws":13,"losses":29,"wins":6}},"unbiased/pareto-26.10-preview":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":42},"claude-fable-5":{"draws":5,"losses":10,"wins":33},"claude-fable-5-1":{"draws":3,"losses":22,"wins":29},"claude-haiku-5-5":{"draws":2,"losses":9,"wins":35},"claude-opus-4-5":{"draws":1,"losses":1,"wins":76},"claude-opus-4-8":{"draws":2,"losses":1,"wins":41},"claude-opus-5":{"draws":3,"losses":29,"wins":50},"claude-opus-5-5":{"draws":1,"losses":26,"wins":25},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":2,"losses":9,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":71},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":43},"fireworks/ember-1":{"draws":1,"losses":1,"wins":46},"gemini-3.1-pro-preview":{"draws":1,"losses":1,"wins":46},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":0,"losses":5,"wins":55},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":81},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":78},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":42},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":1,"wins":40},"gpt-5.4":{"draws":2,"losses":6,"wins":38},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":47},"gpt-5.5":{"draws":1,"losses":4,"wins":39},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":42},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":43},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":39},"gpt-6-astra":{"draws":6,"losses":22,"wins":20},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":5,"losses":9,"wins":34},"gpt-6.1-sol":{"draws":2,"losses":18,"wins":28},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":2,"wins":49},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":42},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":42},"meta/muse-wonder":{"draws":4,"losses":9,"wins":35},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"mistralai/mistral-large-4-0":{"draws":3,"losses":3,"wins":24},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":43},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":41},"o3":{"draws":0,"losses":3,"wins":63},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":42},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":45},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":27},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":42},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":34},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":26},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":41},"stealth/ox-alpha":{"draws":10,"losses":7,"wins":141},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":24},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":41},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":63},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":6,"wins":41},"x-ai/grok-4.6":{"draws":4,"losses":4,"wins":40},"x-ai/grok-4.7":{"draws":3,"losses":8,"wins":31},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":6,"wins":25},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":88},"z-ai/glm-5.3":{"draws":4,"losses":5,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":39},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":42}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":4,"losses":2,"wins":0},"claude-fable-5-1":{"draws":3,"losses":5,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-5":{"draws":8,"losses":1,"wins":1},"claude-opus-4-8":{"draws":6,"losses":0,"wins":0},"claude-opus-5":{"draws":7,"losses":5,"wins":0},"claude-opus-5-5":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":5,"losses":1,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":0,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"fireworks/ember-1":{"draws":5,"losses":1,"wins":0},"gemini-3.1-pro-preview":{"draws":3,"losses":3,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":11,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":11,"losses":1,"wins":0},"google/gemini-3.8-flash":{"draws":2,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":3,"losses":1,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":1},"gpt-5.5":{"draws":5,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":5,"losses":1,"wins":0},"gpt-6-astra":{"draws":2,"losses":4,"wins":0},"gpt-6-luna":{"draws":1,"losses":5,"wins":0},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":5,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":1,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":0,"losses":3,"wins":3},"meta/muse-wonder":{"draws":3,"losses":3,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":1},"o3":{"draws":3,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":3,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":1},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":2},"stealth/ox-alpha":{"draws":10,"losses":8,"wins":0},"stealth/space-bunny-alpha":{"draws":5,"losses":0,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":8,"losses":0,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":0,"wins":1},"x-ai/grok-4.6":{"draws":6,"losses":0,"wins":0},"x-ai/grok-4.7":{"draws":1,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":8,"losses":4,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":5,"losses":1,"wins":0},"z-ai/glm-5.3-flashx":{"draws":5,"losses":1,"wins":0}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":12,"wins":20},"claude-fable-5":{"draws":10,"losses":31,"wins":7},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":27,"losses":26,"wins":25},"claude-opus-4-8":{"draws":17,"losses":16,"wins":11},"claude-opus-5":{"draws":14,"losses":57,"wins":11},"claude-opus-5-5":{"draws":4,"losses":43,"wins":5},"claude-sonnet-5":{"draws":18,"losses":12,"wins":18},"claude-sonnet-5-5":{"draws":15,"losses":20,"wins":13},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":17,"losses":17,"wins":38},"deepseek/deepseek-v4-pro":{"draws":12,"losses":19,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":18,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":18,"wins":18},"fireworks/ember-1":{"draws":16,"losses":13,"wins":19},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":15,"losses":24,"wins":21},"google/gemini-3.5-flash-lite":{"draws":30,"losses":15,"wins":39},"google/gemini-3.6-flash":{"draws":22,"losses":44,"wins":26},"google/gemini-3.8-flash":{"draws":12,"losses":21,"wins":15},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":16},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":18,"wins":16},"gpt-5.4":{"draws":9,"losses":26,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":11,"losses":10,"wins":27},"gpt-5.5":{"draws":11,"losses":22,"wins":11},"gpt-5.6-luna":{"draws":15,"losses":14,"wins":19},"gpt-5.6-sol":{"draws":5,"losses":32,"wins":11},"gpt-5.6-terra":{"draws":15,"losses":17,"wins":14},"gpt-6-astra":{"draws":4,"losses":40,"wins":4},"gpt-6-luna":{"draws":17,"losses":16,"wins":15},"gpt-6-sol":{"draws":6,"losses":30,"wins":12},"gpt-6.1-sol":{"draws":5,"losses":40,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":2,"wins":18},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":20},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":14,"wins":24},"meta/muse-glimmer-30b":{"draws":14,"losses":6,"wins":22},"meta/muse-spark-1.2":{"draws":14,"losses":16,"wins":16},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":16},"meta/muse-wonder":{"draws":9,"losses":28,"wins":11},"minimax/minimax-m3":{"draws":8,"losses":3,"wins":15},"mistralai/mistral-large-4-0":{"draws":7,"losses":13,"wins":10},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":20,"wins":14},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":7,"wins":21},"o3":{"draws":7,"losses":28,"wins":31},"openai/gpt-oss-120b":{"draws":15,"losses":7,"wins":20},"poolside/laguna-s-2.1":{"draws":16,"losses":8,"wins":22},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":18,"wins":15},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":11,"wins":13},"qwen/qwen3.8-max":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":14},"stealth/ox-alpha":{"draws":39,"losses":71,"wins":48},"stealth/space-bunny-alpha":{"draws":15,"losses":7,"wins":16},"stepfun/step-3.7-flash":{"draws":4,"losses":10,"wins":20},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":11,"losses":5,"wins":10},"tencent/hy4-preview":{"draws":11,"losses":24,"wins":11},"thinkingmachines/inkling":{"draws":19,"losses":12,"wins":33},"thinkingmachines/inkling-small":{"draws":16,"losses":5,"wins":27},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":12,"losses":15,"wins":5},"x-ai/grok-4.6":{"draws":17,"losses":22,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":27,"losses":7,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":27,"losses":29,"wins":40},"z-ai/glm-5.3":{"draws":10,"losses":29,"wins":7},"z-ai/glm-5.3-flash":{"draws":6,"losses":29,"wins":13},"z-ai/glm-5.3-flashx":{"draws":12,"losses":24,"wins":12}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":7,"wins":17},"claude-fable-5":{"draws":15,"losses":28,"wins":5},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":16,"losses":17,"wins":13},"claude-opus-4-5":{"draws":27,"losses":23,"wins":28},"claude-opus-4-8":{"draws":12,"losses":20,"wins":12},"claude-opus-5":{"draws":16,"losses":61,"wins":5},"claude-opus-5-5":{"draws":3,"losses":47,"wins":2},"claude-sonnet-5":{"draws":20,"losses":17,"wins":11},"claude-sonnet-5-5":{"draws":13,"losses":27,"wins":8},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":28,"losses":13,"wins":31},"deepseek/deepseek-v4-pro":{"draws":15,"losses":12,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":16,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":19,"wins":9},"fireworks/ember-1":{"draws":20,"losses":23,"wins":5},"gemini-3.1-pro-preview":{"draws":20,"losses":14,"wins":14},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":18},"google/gemini-3.5-flash":{"draws":22,"losses":19,"wins":19},"google/gemini-3.5-flash-lite":{"draws":33,"losses":15,"wins":36},"google/gemini-3.6-flash":{"draws":34,"losses":36,"wins":22},"google/gemini-3.8-flash":{"draws":17,"losses":24,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":11},"gpt-4.1":{"draws":8,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":17,"losses":12,"wins":13},"gpt-5.4":{"draws":15,"losses":24,"wins":7},"gpt-5.4-mini":{"draws":13,"losses":9,"wins":10},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":21},"gpt-5.5":{"draws":20,"losses":17,"wins":7},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":30,"wins":8},"gpt-5.6-terra":{"draws":23,"losses":12,"wins":11},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":21,"losses":11,"wins":16},"gpt-6-sol":{"draws":10,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":7,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":5,"wins":13},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":14,"wins":16},"meta/muse-glimmer-30b":{"draws":22,"losses":3,"wins":17},"meta/muse-spark-1.2":{"draws":16,"losses":13,"wins":17},"meta/muse-spark-1.3":{"draws":14,"losses":22,"wins":12},"meta/muse-wonder":{"draws":20,"losses":26,"wins":2},"minimax/minimax-m3":{"draws":10,"losses":3,"wins":13},"mistralai/mistral-large-4-0":{"draws":13,"losses":7,"wins":10},"mistralai/mistral-medium-3-5":{"draws":15,"losses":4,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":18,"losses":10,"wins":18},"nex-agi/nex-n2-pro":{"draws":10,"losses":2,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":9,"wins":14},"o3":{"draws":14,"losses":25,"wins":27},"openai/gpt-oss-120b":{"draws":20,"losses":6,"wins":16},"poolside/laguna-s-2.1":{"draws":23,"losses":10,"wins":13},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":10},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":20,"wins":10},"qwen/qwen3.8-27b":{"draws":13,"losses":13,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":21,"losses":18,"wins":9},"qwen/qwen3.8-max-0902":{"draws":21,"losses":13,"wins":14},"stealth/ox-alpha":{"draws":61,"losses":72,"wins":25},"stealth/space-bunny-alpha":{"draws":15,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":11,"losses":11,"wins":12},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":18,"losses":18,"wins":10},"thinkingmachines/inkling":{"draws":25,"losses":12,"wins":27},"thinkingmachines/inkling-small":{"draws":20,"losses":10,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":15,"losses":25,"wins":8},"x-ai/grok-4.6":{"draws":14,"losses":17,"wins":1},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":8,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":31,"losses":14,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":22,"wins":5},"z-ai/glm-5.2":{"draws":36,"losses":26,"wins":34},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":6},"z-ai/glm-5.3-flash":{"draws":14,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":14,"losses":29,"wins":5}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":15,"wins":18},"claude-fable-5":{"draws":5,"losses":26,"wins":11},"claude-fable-5-1":{"draws":3,"losses":37,"wins":6},"claude-haiku-5-5":{"draws":10,"losses":14,"wins":18},"claude-opus-4-5":{"draws":13,"losses":26,"wins":31},"claude-opus-4-8":{"draws":11,"losses":18,"wins":13},"claude-opus-5":{"draws":9,"losses":44,"wins":17},"claude-opus-5-5":{"draws":5,"losses":36,"wins":5},"claude-sonnet-5":{"draws":9,"losses":14,"wins":19},"claude-sonnet-5-5":{"draws":12,"losses":18,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":17,"losses":9,"wins":38},"deepseek/deepseek-v4-pro":{"draws":5,"losses":13,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":15,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":19,"wins":17},"fireworks/ember-1":{"draws":6,"losses":14,"wins":22},"gemini-3.1-pro-preview":{"draws":7,"losses":14,"wins":21},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":29},"google/gemini-3.5-flash":{"draws":11,"losses":16,"wins":27},"google/gemini-3.5-flash-lite":{"draws":13,"losses":21,"wins":40},"google/gemini-3.6-flash":{"draws":9,"losses":36,"wins":35},"google/gemini-3.8-flash":{"draws":10,"losses":17,"wins":15},"google/gemma-4-31b-it":{"draws":6,"losses":4,"wins":16},"gpt-4.1":{"draws":3,"losses":2,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":15,"wins":15},"gpt-5.4":{"draws":9,"losses":15,"wins":16},"gpt-5.4-mini":{"draws":9,"losses":2,"wins":17},"gpt-5.4-nano":{"draws":11,"losses":8,"wins":27},"gpt-5.5":{"draws":8,"losses":19,"wins":11},"gpt-5.6-luna":{"draws":9,"losses":10,"wins":23},"gpt-5.6-sol":{"draws":5,"losses":28,"wins":9},"gpt-5.6-terra":{"draws":8,"losses":15,"wins":17},"gpt-6-astra":{"draws":3,"losses":34,"wins":5},"gpt-6-luna":{"draws":7,"losses":13,"wins":22},"gpt-6-sol":{"draws":9,"losses":25,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":20},"inclusionai/ling-3.0-flash":{"draws":8,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":4,"wins":35},"meta/muse-glimmer-30b":{"draws":4,"losses":13,"wins":19},"meta/muse-spark-1.2":{"draws":8,"losses":19,"wins":13},"meta/muse-spark-1.3":{"draws":7,"losses":18,"wins":17},"meta/muse-wonder":{"draws":10,"losses":18,"wins":14},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":15},"mistralai/mistral-large-4-0":{"draws":8,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":11,"losses":17,"wins":12},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":7,"wins":28},"o3":{"draws":8,"losses":24,"wins":30},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":25},"poolside/laguna-s-2.1":{"draws":9,"losses":10,"wins":19},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":11},"qwen/qwen3.7-plus":{"draws":4,"losses":6,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":18,"wins":14},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.8-max":{"draws":9,"losses":15,"wins":18},"qwen/qwen3.8-max-0902":{"draws":10,"losses":16,"wins":16},"stealth/ox-alpha":{"draws":26,"losses":45,"wins":47},"stealth/space-bunny-alpha":{"draws":8,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":22,"wins":10},"thinkingmachines/inkling":{"draws":11,"losses":9,"wins":34},"thinkingmachines/inkling-small":{"draws":10,"losses":1,"wins":31},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":10,"losses":19,"wins":13},"x-ai/grok-4.6":{"draws":9,"losses":16,"wins":17},"x-ai/grok-4.7":{"draws":1,"losses":16,"wins":7},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":17,"losses":11,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":10,"wins":14},"z-ai/glm-5.2":{"draws":22,"losses":22,"wins":40},"z-ai/glm-5.3":{"draws":10,"losses":18,"wins":12},"z-ai/glm-5.3-flash":{"draws":9,"losses":19,"wins":14},"z-ai/glm-5.3-flashx":{"draws":7,"losses":18,"wins":17}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":38,"wins":33},"claude-fable-5":{"draws":14,"losses":86,"wins":2},"claude-fable-5-1":{"draws":5,"losses":105,"wins":2},"claude-haiku-5-5":{"draws":16,"losses":64,"wins":20},"claude-opus-4-5":{"draws":47,"losses":91,"wins":30},"claude-opus-4-8":{"draws":19,"losses":64,"wins":15},"claude-opus-5":{"draws":24,"losses":135,"wins":7},"claude-opus-5-5":{"draws":4,"losses":106,"wins":0},"claude-sonnet-5":{"draws":28,"losses":55,"wins":19},"claude-sonnet-5-5":{"draws":15,"losses":74,"wins":13},"cohere/north-mini-code":{"draws":10,"losses":11,"wins":19},"deepseek/deepseek-v4-flash":{"draws":43,"losses":59,"wins":52},"deepseek/deepseek-v4-pro":{"draws":27,"losses":49,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":47,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":28,"losses":57,"wins":17},"fireworks/ember-1":{"draws":32,"losses":54,"wins":16},"gemini-3.1-pro-preview":{"draws":23,"losses":53,"wins":26},"google/gemini-3.1-flash-lite":{"draws":21,"losses":21,"wins":36},"google/gemini-3.5-flash":{"draws":27,"losses":77,"wins":28},"google/gemini-3.5-flash-lite":{"draws":40,"losses":80,"wins":64},"google/gemini-3.6-flash":{"draws":45,"losses":122,"wins":31},"google/gemini-3.8-flash":{"draws":26,"losses":65,"wins":11},"google/gemma-4-31b-it":{"draws":19,"losses":16,"wins":25},"gpt-4.1":{"draws":9,"losses":16,"wins":9},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":6},"gpt-5":{"draws":24,"losses":47,"wins":19},"gpt-5.4":{"draws":21,"losses":71,"wins":8},"gpt-5.4-mini":{"draws":20,"losses":24,"wins":24},"gpt-5.4-nano":{"draws":18,"losses":54,"wins":40},"gpt-5.5":{"draws":38,"losses":45,"wins":11},"gpt-5.6-luna":{"draws":34,"losses":42,"wins":26},"gpt-5.6-sol":{"draws":11,"losses":82,"wins":9},"gpt-5.6-terra":{"draws":29,"losses":60,"wins":7},"gpt-6-astra":{"draws":7,"losses":94,"wins":1},"gpt-6-luna":{"draws":25,"losses":62,"wins":15},"gpt-6-sol":{"draws":14,"losses":78,"wins":10},"gpt-6.1-sol":{"draws":6,"losses":90,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":11,"wins":35},"inclusionai/ling-3.0-flash":{"draws":25,"losses":18,"wins":29},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":31,"losses":43,"wins":40},"meta/muse-glimmer-30b":{"draws":30,"losses":32,"wins":26},"meta/muse-spark-1.2":{"draws":22,"losses":58,"wins":16},"meta/muse-spark-1.3":{"draws":18,"losses":73,"wins":11},"meta/muse-wonder":{"draws":10,"losses":83,"wins":9},"minimax/minimax-m3":{"draws":13,"losses":20,"wins":23},"mistralai/mistral-large-4-0":{"draws":22,"losses":28,"wins":12},"mistralai/mistral-medium-3-5":{"draws":18,"losses":15,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":12,"wins":9},"moonshotai/kimi-k3":{"draws":27,"losses":55,"wins":14},"nex-agi/nex-n2-pro":{"draws":14,"losses":12,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":28,"wins":36},"o3":{"draws":23,"losses":98,"wins":39},"openai/gpt-oss-120b":{"draws":22,"losses":36,"wins":28},"poolside/laguna-s-2.1":{"draws":26,"losses":42,"wins":28},"qwen/qwen3.7-max":{"draws":20,"losses":24,"wins":18},"qwen/qwen3.7-plus":{"draws":12,"losses":21,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":55,"wins":16},"qwen/qwen3.8-27b":{"draws":12,"losses":45,"wins":19},"qwen/qwen3.8-flash":{"draws":20,"losses":31,"wins":17},"qwen/qwen3.8-max":{"draws":24,"losses":53,"wins":25},"qwen/qwen3.8-max-0902":{"draws":34,"losses":57,"wins":11},"stealth/ox-alpha":{"draws":59,"losses":200,"wins":51},"stealth/space-bunny-alpha":{"draws":26,"losses":33,"wins":23},"stepfun/step-3.7-flash":{"draws":18,"losses":28,"wins":32},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":24,"wins":16},"tencent/hy4-preview":{"draws":26,"losses":67,"wins":7},"thinkingmachines/inkling":{"draws":30,"losses":43,"wins":65},"thinkingmachines/inkling-small":{"draws":33,"losses":27,"wins":42},"unbiased/pareto-26.10-preview":{"draws":2,"losses":32,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":17,"wins":10},"x-ai/grok-4.5":{"draws":18,"losses":72,"wins":12},"x-ai/grok-4.6":{"draws":34,"losses":59,"wins":9},"x-ai/grok-4.7":{"draws":7,"losses":74,"wins":9},"x-ai/grok-build-0.1":{"draws":8,"losses":15,"wins":11},"xiaomi/mimo-v2.5":{"draws":38,"losses":44,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":31,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":44,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":51,"wins":6},"z-ai/glm-5.2":{"draws":64,"losses":91,"wins":49},"z-ai/glm-5.3":{"draws":13,"losses":80,"wins":3},"z-ai/glm-5.3-flash":{"draws":19,"losses":61,"wins":22},"z-ai/glm-5.3-flashx":{"draws":22,"losses":70,"wins":10}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":8},"claude-fable-5":{"draws":6,"losses":34,"wins":2},"claude-fable-5-1":{"draws":0,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":8},"claude-opus-4-5":{"draws":17,"losses":35,"wins":16},"claude-opus-4-8":{"draws":9,"losses":23,"wins":6},"claude-opus-5":{"draws":5,"losses":64,"wins":1},"claude-opus-5-5":{"draws":1,"losses":44,"wins":1},"claude-sonnet-5":{"draws":10,"losses":26,"wins":6},"claude-sonnet-5-5":{"draws":9,"losses":26,"wins":7},"cohere/north-mini-code":{"draws":5,"losses":3,"wins":8},"deepseek/deepseek-v4-flash":{"draws":23,"losses":26,"wins":17},"deepseek/deepseek-v4-pro":{"draws":7,"losses":21,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":22,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":24,"wins":5},"fireworks/ember-1":{"draws":15,"losses":21,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":21,"wins":9},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":22},"google/gemini-3.5-flash":{"draws":13,"losses":25,"wins":14},"google/gemini-3.5-flash-lite":{"draws":21,"losses":32,"wins":19},"google/gemini-3.6-flash":{"draws":17,"losses":51,"wins":12},"google/gemini-3.8-flash":{"draws":12,"losses":25,"wins":5},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":10},"gpt-4.1":{"draws":4,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":13,"losses":14,"wins":11},"gpt-5.4":{"draws":8,"losses":27,"wins":5},"gpt-5.4-mini":{"draws":10,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":16},"gpt-5.5":{"draws":16,"losses":17,"wins":5},"gpt-5.6-luna":{"draws":19,"losses":10,"wins":13},"gpt-5.6-sol":{"draws":4,"losses":32,"wins":6},"gpt-5.6-terra":{"draws":10,"losses":26,"wins":4},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":12,"losses":24,"wins":6},"gpt-6-sol":{"draws":1,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":8,"wins":10},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":12},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":14,"wins":16},"meta/muse-glimmer-30b":{"draws":14,"losses":8,"wins":14},"meta/muse-spark-1.2":{"draws":8,"losses":25,"wins":7},"meta/muse-spark-1.3":{"draws":5,"losses":34,"wins":3},"meta/muse-wonder":{"draws":4,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":7,"wins":10},"mistralai/mistral-large-4-0":{"draws":8,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":20,"wins":9},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":13},"o3":{"draws":13,"losses":35,"wins":14},"openai/gpt-oss-120b":{"draws":13,"losses":15,"wins":10},"poolside/laguna-s-2.1":{"draws":16,"losses":19,"wins":9},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":25,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":18,"wins":6},"qwen/qwen3.8-flash":{"draws":10,"losses":14,"wins":4},"qwen/qwen3.8-max":{"draws":10,"losses":23,"wins":9},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":8},"stealth/ox-alpha":{"draws":33,"losses":84,"wins":23},"stealth/space-bunny-alpha":{"draws":13,"losses":15,"wins":4},"stepfun/step-3.7-flash":{"draws":9,"losses":11,"wins":12},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":24,"wins":5},"thinkingmachines/inkling":{"draws":14,"losses":14,"wins":28},"thinkingmachines/inkling-small":{"draws":18,"losses":8,"wins":16},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":8,"losses":29,"wins":5},"x-ai/grok-4.6":{"draws":11,"losses":29,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":4},"xiaomi/mimo-v2.5":{"draws":24,"losses":19,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":6,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":5},"z-ai/glm-5.2":{"draws":32,"losses":32,"wins":20},"z-ai/glm-5.3":{"draws":8,"losses":31,"wins":1},"z-ai/glm-5.3-flash":{"draws":11,"losses":28,"wins":3},"z-ai/glm-5.3-flashx":{"draws":12,"losses":27,"wins":3}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":10,"wins":17},"claude-fable-5":{"draws":12,"losses":26,"wins":4},"claude-fable-5-1":{"draws":1,"losses":43,"wins":2},"claude-haiku-5-5":{"draws":12,"losses":18,"wins":10},"claude-opus-4-5":{"draws":22,"losses":27,"wins":19},"claude-opus-4-8":{"draws":10,"losses":16,"wins":12},"claude-opus-5":{"draws":8,"losses":56,"wins":6},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":10,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":11},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":14,"wins":31},"deepseek/deepseek-v4-pro":{"draws":10,"losses":17,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":15,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":11},"fireworks/ember-1":{"draws":13,"losses":18,"wins":11},"gemini-3.1-pro-preview":{"draws":9,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":11,"losses":22,"wins":19},"google/gemini-3.5-flash-lite":{"draws":13,"losses":14,"wins":45},"google/gemini-3.6-flash":{"draws":16,"losses":39,"wins":25},"google/gemini-3.8-flash":{"draws":14,"losses":21,"wins":7},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":12},"gpt-4.1":{"draws":6,"losses":1,"wins":7},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":1},"gpt-5":{"draws":12,"losses":18,"wins":8},"gpt-5.4":{"draws":16,"losses":17,"wins":7},"gpt-5.4-mini":{"draws":10,"losses":8,"wins":10},"gpt-5.4-nano":{"draws":16,"losses":9,"wins":21},"gpt-5.5":{"draws":20,"losses":14,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":7,"losses":31,"wins":4},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":9},"gpt-6-astra":{"draws":1,"losses":39,"wins":2},"gpt-6-luna":{"draws":14,"losses":20,"wins":8},"gpt-6-sol":{"draws":4,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":6},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":16},"inclusionai/ling-3.0-flash":{"draws":10,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":9,"wins":23},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":5,"losses":26,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":31,"wins":6},"meta/muse-wonder":{"draws":4,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":11},"mistralai/mistral-large-4-0":{"draws":8,"losses":12,"wins":6},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":14,"losses":18,"wins":8},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":17},"o3":{"draws":9,"losses":21,"wins":32},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":22},"poolside/laguna-s-2.1":{"draws":16,"losses":9,"wins":19},"qwen/qwen3.7-max":{"draws":12,"losses":6,"wins":8},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":17,"wins":11},"qwen/qwen3.8-27b":{"draws":12,"losses":12,"wins":6},"qwen/qwen3.8-flash":{"draws":7,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":14,"wins":13},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":14},"stealth/ox-alpha":{"draws":35,"losses":71,"wins":34},"stealth/space-bunny-alpha":{"draws":10,"losses":11,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":14},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":8,"losses":19,"wins":13},"thinkingmachines/inkling":{"draws":17,"losses":12,"wins":27},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":27,"wins":5},"x-ai/grok-4.6":{"draws":11,"losses":20,"wins":11},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":5},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":26,"losses":4,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":3,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":27,"losses":30,"wins":27},"z-ai/glm-5.3":{"draws":7,"losses":26,"wins":7},"z-ai/glm-5.3-flash":{"draws":10,"losses":24,"wins":8},"z-ai/glm-5.3-flashx":{"draws":13,"losses":19,"wins":10}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":19},"claude-fable-5":{"draws":6,"losses":32,"wins":10},"claude-fable-5-1":{"draws":5,"losses":46,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":21,"wins":12},"claude-opus-4-5":{"draws":28,"losses":25,"wins":25},"claude-opus-4-8":{"draws":9,"losses":22,"wins":13},"claude-opus-5":{"draws":10,"losses":60,"wins":12},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":15,"losses":15,"wins":18},"claude-sonnet-5-5":{"draws":9,"losses":28,"wins":11},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":15},"deepseek/deepseek-v4-flash":{"draws":22,"losses":15,"wins":35},"deepseek/deepseek-v4-pro":{"draws":12,"losses":19,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":18,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":17},"fireworks/ember-1":{"draws":14,"losses":19,"wins":15},"gemini-3.1-pro-preview":{"draws":14,"losses":15,"wins":19},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":12,"losses":26,"wins":22},"google/gemini-3.5-flash-lite":{"draws":21,"losses":17,"wins":46},"google/gemini-3.6-flash":{"draws":28,"losses":42,"wins":22},"google/gemini-3.8-flash":{"draws":13,"losses":19,"wins":16},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":14,"wins":19},"gpt-5.4":{"draws":12,"losses":23,"wins":11},"gpt-5.4-mini":{"draws":13,"losses":4,"wins":15},"gpt-5.4-nano":{"draws":13,"losses":9,"wins":26},"gpt-5.5":{"draws":12,"losses":21,"wins":11},"gpt-5.6-luna":{"draws":14,"losses":12,"wins":22},"gpt-5.6-sol":{"draws":8,"losses":30,"wins":10},"gpt-5.6-terra":{"draws":15,"losses":17,"wins":14},"gpt-6-astra":{"draws":4,"losses":43,"wins":1},"gpt-6-luna":{"draws":10,"losses":17,"wins":21},"gpt-6-sol":{"draws":10,"losses":33,"wins":5},"gpt-6.1-sol":{"draws":6,"losses":35,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":18},"inclusionai/ling-3.0-flash":{"draws":12,"losses":3,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":17,"losses":3,"wins":32},"meta/muse-glimmer-30b":{"draws":15,"losses":6,"wins":21},"meta/muse-spark-1.2":{"draws":9,"losses":19,"wins":18},"meta/muse-spark-1.3":{"draws":10,"losses":24,"wins":14},"meta/muse-wonder":{"draws":8,"losses":28,"wins":12},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":15},"mistralai/mistral-large-4-0":{"draws":10,"losses":11,"wins":9},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":16,"wins":18},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":5,"wins":24},"o3":{"draws":10,"losses":18,"wins":38},"openai/gpt-oss-120b":{"draws":14,"losses":4,"wins":24},"poolside/laguna-s-2.1":{"draws":10,"losses":12,"wins":24},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":11},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":18,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":13},"qwen/qwen3.8-flash":{"draws":9,"losses":12,"wins":11},"qwen/qwen3.8-max":{"draws":19,"losses":13,"wins":16},"qwen/qwen3.8-max-0902":{"draws":10,"losses":19,"wins":19},"stealth/ox-alpha":{"draws":43,"losses":68,"wins":47},"stealth/space-bunny-alpha":{"draws":15,"losses":12,"wins":11},"stepfun/step-3.7-flash":{"draws":5,"losses":7,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":10,"losses":23,"wins":13},"thinkingmachines/inkling":{"draws":21,"losses":10,"wins":33},"thinkingmachines/inkling-small":{"draws":13,"losses":7,"wins":28},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":22,"wins":15},"x-ai/grok-4.6":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":29,"losses":5,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":13,"wins":2},"z-ai/glm-5.2":{"draws":40,"losses":22,"wins":34},"z-ai/glm-5.3":{"draws":10,"losses":28,"wins":8},"z-ai/glm-5.3-flash":{"draws":10,"losses":20,"wins":18},"z-ai/glm-5.3-flashx":{"draws":11,"losses":23,"wins":14}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":51,"losses":43,"wins":38},"claude-fable-5":{"draws":29,"losses":96,"wins":19},"claude-fable-5-1":{"draws":8,"losses":152,"wins":2},"claude-haiku-5-5":{"draws":28,"losses":84,"wins":26},"claude-opus-4-5":{"draws":75,"losses":105,"wins":54},"claude-opus-4-8":{"draws":35,"losses":75,"wins":22},"claude-opus-5":{"draws":32,"losses":193,"wins":21},"claude-opus-5-5":{"draws":9,"losses":142,"wins":5},"claude-sonnet-5":{"draws":46,"losses":64,"wins":34},"claude-sonnet-5-5":{"draws":28,"losses":89,"wins":27},"cohere/north-mini-code":{"draws":15,"losses":3,"wins":36},"deepseek/deepseek-v4-flash":{"draws":73,"losses":51,"wins":92},"deepseek/deepseek-v4-pro":{"draws":45,"losses":53,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":49,"losses":42,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":50,"losses":66,"wins":28},"fireworks/ember-1":{"draws":48,"losses":69,"wins":27},"gemini-3.1-pro-preview":{"draws":43,"losses":64,"wins":37},"google/gemini-3.1-flash-lite":{"draws":18,"losses":17,"wins":61},"google/gemini-3.5-flash":{"draws":41,"losses":88,"wins":51},"google/gemini-3.5-flash-lite":{"draws":78,"losses":86,"wins":88},"google/gemini-3.6-flash":{"draws":85,"losses":127,"wins":64},"google/gemini-3.8-flash":{"draws":40,"losses":80,"wins":24},"google/gemma-4-31b-it":{"draws":35,"losses":14,"wins":35},"gpt-4.1":{"draws":16,"losses":12,"wins":20},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":8},"gpt-5":{"draws":37,"losses":53,"wins":36},"gpt-5.4":{"draws":37,"losses":73,"wins":28},"gpt-5.4-mini":{"draws":43,"losses":21,"wins":32},"gpt-5.4-nano":{"draws":32,"losses":53,"wins":59},"gpt-5.5":{"draws":51,"losses":57,"wins":24},"gpt-5.6-luna":{"draws":50,"losses":40,"wins":54},"gpt-5.6-sol":{"draws":19,"losses":108,"wins":17},"gpt-5.6-terra":{"draws":52,"losses":50,"wins":36},"gpt-6-astra":{"draws":7,"losses":134,"wins":3},"gpt-6-luna":{"draws":53,"losses":57,"wins":34},"gpt-6-sol":{"draws":26,"losses":105,"wins":13},"gpt-6.1-sol":{"draws":12,"losses":128,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":43,"losses":10,"wins":49},"inclusionai/ling-3.0-flash":{"draws":47,"losses":16,"wins":39},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":45,"losses":33,"wins":78},"meta/muse-glimmer-30b":{"draws":59,"losses":22,"wins":45},"meta/muse-spark-1.2":{"draws":33,"losses":66,"wins":39},"meta/muse-spark-1.3":{"draws":29,"losses":85,"wins":30},"meta/muse-wonder":{"draws":30,"losses":95,"wins":19},"minimax/minimax-m3":{"draws":28,"losses":18,"wins":32},"mistralai/mistral-large-4-0":{"draws":29,"losses":43,"wins":18},"mistralai/mistral-medium-3-5":{"draws":41,"losses":8,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":17,"wins":9},"moonshotai/kimi-k3":{"draws":43,"losses":61,"wins":34},"nex-agi/nex-n2-pro":{"draws":28,"losses":11,"wins":33},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":53,"losses":30,"wins":43},"o3":{"draws":36,"losses":93,"wins":69},"openai/gpt-oss-120b":{"draws":42,"losses":33,"wins":51},"poolside/laguna-s-2.1":{"draws":52,"losses":46,"wins":40},"qwen/qwen3.7-max":{"draws":25,"losses":35,"wins":24},"qwen/qwen3.7-plus":{"draws":20,"losses":17,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":58,"losses":56,"wins":30},"qwen/qwen3.8-27b":{"draws":35,"losses":39,"wins":28},"qwen/qwen3.8-flash":{"draws":39,"losses":30,"wins":27},"qwen/qwen3.8-max":{"draws":50,"losses":57,"wins":37},"qwen/qwen3.8-max-0902":{"draws":50,"losses":65,"wins":29},"stealth/ox-alpha":{"draws":122,"losses":253,"wins":99},"stealth/space-bunny-alpha":{"draws":40,"losses":37,"wins":37},"stepfun/step-3.7-flash":{"draws":25,"losses":33,"wins":44},"stepfun/step-5-preview":{"draws":4,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":28,"losses":23,"wins":27},"tencent/hy4-preview":{"draws":36,"losses":77,"wins":25},"thinkingmachines/inkling":{"draws":60,"losses":48,"wins":84},"thinkingmachines/inkling-small":{"draws":53,"losses":35,"wins":56},"unbiased/pareto-26.10-preview":{"draws":2,"losses":45,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":19},"x-ai/grok-4.5":{"draws":35,"losses":90,"wins":19},"x-ai/grok-4.6":{"draws":37,"losses":85,"wins":22},"x-ai/grok-4.7":{"draws":15,"losses":94,"wins":17},"x-ai/grok-build-0.1":{"draws":20,"losses":12,"wins":16},"xiaomi/mimo-v2.5":{"draws":75,"losses":58,"wins":89},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":32,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":53,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":22,"losses":56,"wins":18},"z-ai/glm-5.2":{"draws":85,"losses":85,"wins":70},"z-ai/glm-5.3":{"draws":33,"losses":93,"wins":12},"z-ai/glm-5.3-flash":{"draws":33,"losses":84,"wins":27},"z-ai/glm-5.3-flashx":{"draws":35,"losses":77,"wins":32}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":10,"wins":21},"claude-fable-5":{"draws":9,"losses":28,"wins":11},"claude-fable-5-1":{"draws":5,"losses":47,"wins":2},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":28,"losses":22,"wins":28},"claude-opus-4-8":{"draws":10,"losses":15,"wins":19},"claude-opus-5":{"draws":11,"losses":63,"wins":8},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":17,"losses":11,"wins":20},"claude-sonnet-5-5":{"draws":11,"losses":24,"wins":13},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":27,"losses":8,"wins":37},"deepseek/deepseek-v4-pro":{"draws":17,"losses":14,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":15,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":20,"wins":11},"fireworks/ember-1":{"draws":18,"losses":14,"wins":16},"gemini-3.1-pro-preview":{"draws":11,"losses":17,"wins":20},"google/gemini-3.1-flash-lite":{"draws":11,"losses":1,"wins":20},"google/gemini-3.5-flash":{"draws":19,"losses":21,"wins":20},"google/gemini-3.5-flash-lite":{"draws":26,"losses":13,"wins":45},"google/gemini-3.6-flash":{"draws":24,"losses":33,"wins":35},"google/gemini-3.8-flash":{"draws":12,"losses":23,"wins":13},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":11},"gpt-4.1":{"draws":3,"losses":5,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":11,"wins":18},"gpt-5.4":{"draws":15,"losses":24,"wins":7},"gpt-5.4-mini":{"draws":13,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":24},"gpt-5.5":{"draws":15,"losses":10,"wins":19},"gpt-5.6-luna":{"draws":16,"losses":13,"wins":19},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":16,"losses":14,"wins":16},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":11,"losses":19,"wins":18},"gpt-6-sol":{"draws":8,"losses":30,"wins":10},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":2,"wins":16},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":7,"wins":29},"meta/muse-glimmer-30b":{"draws":10,"losses":10,"wins":22},"meta/muse-spark-1.2":{"draws":11,"losses":26,"wins":9},"meta/muse-spark-1.3":{"draws":9,"losses":21,"wins":18},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":11},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":20,"losses":14,"wins":12},"nex-agi/nex-n2-pro":{"draws":9,"losses":2,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":10,"wins":17},"o3":{"draws":10,"losses":26,"wins":30},"openai/gpt-oss-120b":{"draws":17,"losses":3,"wins":22},"poolside/laguna-s-2.1":{"draws":14,"losses":10,"wins":22},"qwen/qwen3.7-max":{"draws":12,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":14,"wins":16},"qwen/qwen3.8-27b":{"draws":13,"losses":4,"wins":17},"qwen/qwen3.8-flash":{"draws":14,"losses":9,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":19,"wins":14},"qwen/qwen3.8-max-0902":{"draws":18,"losses":18,"wins":12},"stealth/ox-alpha":{"draws":45,"losses":67,"wins":46},"stealth/space-bunny-alpha":{"draws":16,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":10,"losses":3,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":11},"tencent/hy4-preview":{"draws":15,"losses":11,"wins":20},"thinkingmachines/inkling":{"draws":17,"losses":12,"wins":35},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":24},"unbiased/pareto-26.10-preview":{"draws":2,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":15,"losses":15,"wins":18},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":28,"losses":3,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":12,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":36,"losses":22,"wins":38},"z-ai/glm-5.3":{"draws":5,"losses":25,"wins":0},"z-ai/glm-5.3-flash":{"draws":14,"losses":18,"wins":16},"z-ai/glm-5.3-flashx":{"draws":14,"losses":21,"wins":13}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":6,"wins":21},"claude-fable-5":{"draws":12,"losses":28,"wins":8},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-haiku-5-5":{"draws":11,"losses":24,"wins":11},"claude-opus-4-5":{"draws":24,"losses":25,"wins":29},"claude-opus-4-8":{"draws":6,"losses":23,"wins":15},"claude-opus-5":{"draws":16,"losses":56,"wins":10},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":14,"losses":19,"wins":15},"claude-sonnet-5-5":{"draws":10,"losses":23,"wins":15},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":32,"losses":14,"wins":26},"deepseek/deepseek-v4-pro":{"draws":12,"losses":9,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":17,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":19,"wins":14},"fireworks/ember-1":{"draws":14,"losses":16,"wins":18},"gemini-3.1-pro-preview":{"draws":11,"losses":19,"wins":18},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":17},"google/gemini-3.5-flash":{"draws":14,"losses":25,"wins":21},"google/gemini-3.5-flash-lite":{"draws":27,"losses":24,"wins":33},"google/gemini-3.6-flash":{"draws":21,"losses":37,"wins":34},"google/gemini-3.8-flash":{"draws":10,"losses":25,"wins":13},"google/gemma-4-31b-it":{"draws":8,"losses":7,"wins":13},"gpt-4.1":{"draws":2,"losses":7,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":11,"wins":18},"gpt-5.4":{"draws":9,"losses":22,"wins":15},"gpt-5.4-mini":{"draws":13,"losses":11,"wins":8},"gpt-5.4-nano":{"draws":15,"losses":15,"wins":18},"gpt-5.5":{"draws":14,"losses":16,"wins":14},"gpt-5.6-luna":{"draws":21,"losses":11,"wins":16},"gpt-5.6-sol":{"draws":13,"losses":26,"wins":9},"gpt-5.6-terra":{"draws":16,"losses":14,"wins":16},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":15,"losses":13,"wins":20},"gpt-6-sol":{"draws":7,"losses":29,"wins":12},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"inclusionai/ling-3.0-flash":{"draws":15,"losses":3,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":13,"wins":23},"meta/muse-glimmer-30b":{"draws":17,"losses":7,"wins":18},"meta/muse-spark-1.2":{"draws":10,"losses":20,"wins":16},"meta/muse-spark-1.3":{"draws":10,"losses":22,"wins":16},"meta/muse-wonder":{"draws":16,"losses":24,"wins":8},"minimax/minimax-m3":{"draws":9,"losses":5,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":11},"mistralai/mistral-medium-3-5":{"draws":11,"losses":5,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":14,"wins":15},"nex-agi/nex-n2-pro":{"draws":8,"losses":2,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":16,"wins":13},"o3":{"draws":11,"losses":28,"wins":27},"openai/gpt-oss-120b":{"draws":12,"losses":10,"wins":20},"poolside/laguna-s-2.1":{"draws":19,"losses":11,"wins":16},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":10},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":19,"wins":14},"qwen/qwen3.8-27b":{"draws":11,"losses":11,"wins":12},"qwen/qwen3.8-flash":{"draws":13,"losses":11,"wins":8},"qwen/qwen3.8-max":{"draws":17,"losses":19,"wins":12},"qwen/qwen3.8-max-0902":{"draws":14,"losses":23,"wins":11},"stealth/ox-alpha":{"draws":36,"losses":78,"wins":44},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":9,"losses":11,"wins":14},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":11},"tencent/hy4-preview":{"draws":15,"losses":21,"wins":10},"thinkingmachines/inkling":{"draws":19,"losses":18,"wins":27},"thinkingmachines/inkling-small":{"draws":16,"losses":11,"wins":21},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":9,"losses":21,"wins":18},"x-ai/grok-4.6":{"draws":20,"losses":18,"wins":10},"x-ai/grok-4.7":{"draws":6,"losses":30,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":32,"losses":13,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":11,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":39,"losses":22,"wins":35},"z-ai/glm-5.3":{"draws":14,"losses":26,"wins":6},"z-ai/glm-5.3-flash":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.3-flashx":{"draws":15,"losses":23,"wins":10}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":7,"wins":25},"claude-fable-5":{"draws":9,"losses":30,"wins":9},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":22,"wins":11},"claude-opus-4-5":{"draws":22,"losses":24,"wins":32},"claude-opus-4-8":{"draws":11,"losses":21,"wins":12},"claude-opus-5":{"draws":13,"losses":58,"wins":11},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":19,"losses":11,"wins":18},"claude-sonnet-5-5":{"draws":14,"losses":21,"wins":13},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":22,"losses":15,"wins":35},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":16,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":17,"wins":14},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":19,"losses":11,"wins":18},"google/gemini-3.1-flash-lite":{"draws":15,"losses":0,"wins":17},"google/gemini-3.5-flash":{"draws":20,"losses":17,"wins":23},"google/gemini-3.5-flash-lite":{"draws":30,"losses":14,"wins":40},"google/gemini-3.6-flash":{"draws":30,"losses":35,"wins":27},"google/gemini-3.8-flash":{"draws":15,"losses":24,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":17,"losses":10,"wins":15},"gpt-5.4":{"draws":17,"losses":17,"wins":12},"gpt-5.4-mini":{"draws":13,"losses":5,"wins":14},"gpt-5.4-nano":{"draws":12,"losses":11,"wins":25},"gpt-5.5":{"draws":19,"losses":16,"wins":9},"gpt-5.6-luna":{"draws":18,"losses":13,"wins":17},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":13,"losses":16,"wins":17},"gpt-6-astra":{"draws":6,"losses":41,"wins":1},"gpt-6-luna":{"draws":11,"losses":16,"wins":21},"gpt-6-sol":{"draws":9,"losses":29,"wins":10},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":1,"wins":19},"inclusionai/ling-3.0-flash":{"draws":14,"losses":2,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":8,"wins":28},"meta/muse-glimmer-30b":{"draws":16,"losses":4,"wins":22},"meta/muse-spark-1.2":{"draws":10,"losses":18,"wins":18},"meta/muse-spark-1.3":{"draws":10,"losses":23,"wins":15},"meta/muse-wonder":{"draws":11,"losses":30,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":3,"wins":15},"mistralai/mistral-large-4-0":{"draws":13,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":19,"losses":11,"wins":16},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":20},"o3":{"draws":12,"losses":14,"wins":40},"openai/gpt-oss-120b":{"draws":14,"losses":5,"wins":23},"poolside/laguna-s-2.1":{"draws":19,"losses":6,"wins":21},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":13,"wins":18},"qwen/qwen3.8-27b":{"draws":11,"losses":9,"wins":14},"qwen/qwen3.8-flash":{"draws":13,"losses":8,"wins":11},"qwen/qwen3.8-max":{"draws":18,"losses":16,"wins":14},"qwen/qwen3.8-max-0902":{"draws":15,"losses":18,"wins":15},"stealth/ox-alpha":{"draws":36,"losses":69,"wins":53},"stealth/space-bunny-alpha":{"draws":14,"losses":6,"wins":18},"stepfun/step-3.7-flash":{"draws":9,"losses":3,"wins":22},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":13,"losses":21,"wins":12},"thinkingmachines/inkling":{"draws":19,"losses":8,"wins":37},"thinkingmachines/inkling-small":{"draws":16,"losses":7,"wins":25},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":13,"losses":22,"wins":13},"x-ai/grok-4.6":{"draws":12,"losses":22,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":31,"losses":1,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":4,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":12,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":35,"losses":23,"wins":38},"z-ai/glm-5.3":{"draws":12,"losses":28,"wins":6},"z-ai/glm-5.3-flash":{"draws":12,"losses":26,"wins":10},"z-ai/glm-5.3-flashx":{"draws":10,"losses":12,"wins":10}}}}}