{"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":"2026-11-03T09:45:07Z","heatmap_track_id":"full_freedom/intensive","models":[{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-astra:4163374b7b930edd","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":10.427439999999999},"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":3.27234},"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":1.9134900000000001},"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":10.427439999999999}},"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":88.70766670983319,"highest":94.02143981560225,"medium":88.55983489133767,"none":83.54172542255968},"economics_best_value":{"per_model":{"all":true,"highest":true,"none":true},"per_setting":{"highest":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":87.74680387877011,"score":87.74680387877011},"GB2-02":{"attempts":3,"playable":82.40733271927509,"score":82.40733271927509},"GB2-03":{"attempts":3,"playable":88.34794310095322,"score":88.34794310095322},"GB2-04":{"attempts":3,"playable":88.2342978425449,"score":88.2342978425449},"GB2-05":{"attempts":3,"playable":94.726720246701,"score":94.726720246701},"GB2-06":{"attempts":3,"playable":84.3460180060985,"score":84.3460180060985},"GB2-07":{"attempts":3,"playable":95.59569197433962,"score":95.59569197433962},"GB2-08":{"attempts":3,"playable":88.25652590998321,"score":88.25652590998321}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":96.87279774301638,"score":96.87279774301638},"GB2-02":{"attempts":1,"playable":95.26616413308501,"score":95.26616413308501},"GB2-03":{"attempts":1,"playable":97.75180799349795,"score":97.75180799349795},"GB2-04":{"attempts":1,"playable":90.7255765602207,"score":90.7255765602207},"GB2-05":{"attempts":1,"playable":98.98171309758915,"score":98.98171309758915},"GB2-06":{"attempts":1,"playable":84.9047933659165,"score":84.9047933659165},"GB2-07":{"attempts":1,"playable":97.34065328955289,"score":97.34065328955289},"GB2-08":{"attempts":1,"playable":90.32801234193946,"score":90.32801234193946}},"medium":{"GB2-01":{"attempts":1,"playable":74.25826335908518,"score":74.25826335908518},"GB2-02":{"attempts":1,"playable":80.39911125922742,"score":80.39911125922742},"GB2-03":{"attempts":1,"playable":93.95443435607382,"score":93.95443435607382},"GB2-04":{"attempts":1,"playable":91.20521616974094,"score":91.20521616974094},"GB2-05":{"attempts":1,"playable":91.78542707375024,"score":91.78542707375024},"GB2-06":{"attempts":1,"playable":86.02955491654612,"score":86.02955491654612},"GB2-07":{"attempts":1,"playable":96.20764317131163,"score":96.20764317131163},"GB2-08":{"attempts":1,"playable":94.63902882496612,"score":94.63902882496612}},"none":{"GB2-01":{"attempts":1,"playable":92.10935053420877,"score":92.10935053420877},"GB2-02":{"attempts":1,"playable":71.55672276551286,"score":71.55672276551286},"GB2-03":{"attempts":1,"playable":73.3375869532879,"score":73.3375869532879},"GB2-04":{"attempts":1,"playable":82.77210079767308,"score":82.77210079767308},"GB2-05":{"attempts":1,"playable":93.41302056876359,"score":93.41302056876359},"GB2-06":{"attempts":1,"playable":82.1037057358329,"score":82.1037057358329},"GB2-07":{"attempts":1,"playable":93.23877946215433,"score":93.23877946215433},"GB2-08":{"attempts":1,"playable":79.80253656304403,"score":79.80253656304403}}},"id":"gpt-6-astra","is_recent_addition":false,"last_measured_at":"2026-11-03T08:03:22Z","match_totals_all":{"draws":910,"losses":955,"wins":10685},"match_totals_tracks":{"highest":{"draws":108,"losses":186,"wins":3890},"medium":{"draws":271,"losses":337,"wins":3572},"none":{"draws":531,"losses":432,"wins":3223}},"model_slug":"gpt-6-astra","official_rank_by_reasoning":{"highest":2,"medium":2,"none":4},"overall":{"max":98.98171309758915,"mean":88.70766670983319,"min":71.55672276551286},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":1,"overall_ranking_status":"ranked","per_game":{"GB2-01":96.87279774301638,"GB2-02":95.26616413308501,"GB2-03":97.75180799349795,"GB2-04":90.7255765602207,"GB2-05":98.98171309758915,"GB2-06":84.9047933659165,"GB2-07":97.34065328955289,"GB2-08":90.32801234193946},"per_game_all":{"GB2-01":87.74680387877011,"GB2-02":82.40733271927509,"GB2-03":88.34794310095322,"GB2-04":88.2342978425449,"GB2-05":94.726720246701,"GB2-06":84.3460180060985,"GB2-07":95.59569197433962,"GB2-08":88.25652590998321},"per_game_match_totals_all":{"GB2-01":{"draws":60,"losses":162,"wins":1358},"GB2-02":{"draws":419,"losses":60,"wins":1003},"GB2-03":{"draws":185,"losses":95,"wins":1264},"GB2-04":{"draws":169,"losses":103,"wins":1262},"GB2-05":{"draws":0,"losses":80,"wins":1548},"GB2-06":{"draws":77,"losses":203,"wins":1258},"GB2-07":{"draws":0,"losses":61,"wins":1559},"GB2-08":{"draws":0,"losses":191,"wins":1433}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":15,"wins":513},"GB2-02":{"draws":26,"losses":10,"wins":456},"GB2-03":{"draws":11,"losses":4,"wins":501},"GB2-04":{"draws":40,"losses":29,"wins":441},"GB2-05":{"draws":0,"losses":3,"wins":541},"GB2-06":{"draws":31,"losses":62,"wins":419},"GB2-07":{"draws":0,"losses":11,"wins":529},"GB2-08":{"draws":0,"losses":52,"wins":490}},"medium":{"GB2-01":{"draws":36,"losses":118,"wins":372},"GB2-02":{"draws":164,"losses":18,"wins":310},"GB2-03":{"draws":7,"losses":27,"wins":480},"GB2-04":{"draws":45,"losses":24,"wins":443},"GB2-05":{"draws":0,"losses":43,"wins":499},"GB2-06":{"draws":19,"losses":62,"wins":433},"GB2-07":{"draws":0,"losses":17,"wins":523},"GB2-08":{"draws":0,"losses":28,"wins":512}},"none":{"GB2-01":{"draws":24,"losses":29,"wins":473},"GB2-02":{"draws":229,"losses":32,"wins":237},"GB2-03":{"draws":167,"losses":64,"wins":283},"GB2-04":{"draws":84,"losses":50,"wins":378},"GB2-05":{"draws":0,"losses":34,"wins":508},"GB2-06":{"draws":27,"losses":79,"wins":406},"GB2-07":{"draws":0,"losses":33,"wins":507},"GB2-08":{"draws":0,"losses":111,"wins":431}}},"per_game_raw_elo_all":{"GB2-01":2031.308259576493,"GB2-02":1844.2465751319412,"GB2-03":2101.07729526913,"GB2-04":1903.4275277065337,"GB2-05":2597.9038395363423,"GB2-06":2088.112656466421,"GB2-07":2535.9593826967985,"GB2-08":2198.8497634372743},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2278.7209756980533,"GB2-02":2103.2710026385694,"GB2-03":2433.986151504487,"GB2-04":1948.3336181908633,"GB2-05":2965.16049410635,"GB2-06":2099.8112640305408,"GB2-07":2655.0940932691938,"GB2-08":2234.324035421466},"medium":{"GB2-01":1744.0558210654426,"GB2-02":1766.2085832354176,"GB2-03":2181.058499326584,"GB2-04":1960.0958804657719,"GB2-05":2375.491827958938,"GB2-06":2125.7223793222543,"GB2-07":2565.648015275774,"GB2-08":2398.973294952597},"none":{"GB2-01":2071.1479819659835,"GB2-02":1663.2601395218364,"GB2-03":1688.1872349763194,"GB2-04":1801.8530844629665,"GB2-05":2453.0591965437384,"GB2-06":2038.804326046467,"GB2-07":2387.1360395454276,"GB2-08":1963.2519599377601}},"per_game_tracks":{"highest":{"GB2-01":96.87279774301638,"GB2-02":95.26616413308501,"GB2-03":97.75180799349795,"GB2-04":90.7255765602207,"GB2-05":98.98171309758915,"GB2-06":84.9047933659165,"GB2-07":97.34065328955289,"GB2-08":90.32801234193946},"medium":{"GB2-01":74.25826335908518,"GB2-02":80.39911125922742,"GB2-03":93.95443435607382,"GB2-04":91.20521616974094,"GB2-05":91.78542707375024,"GB2-06":86.02955491654612,"GB2-07":96.20764317131163,"GB2-08":94.63902882496612},"none":{"GB2-01":92.10935053420877,"GB2-02":71.55672276551286,"GB2-03":73.3375869532879,"GB2-04":82.77210079767308,"GB2-05":93.41302056876359,"GB2-06":82.1037057358329,"GB2-07":93.23877946215433,"GB2-08":79.80253656304403}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":24,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-31T15:52:54Z","reasoning":{"highest":94.02143981560225,"medium":88.55983489133767,"none":83.54172542255968},"reasoning_agg":{"highest":{"max":98.98171309758915,"mean":94.02143981560225,"min":84.9047933659165},"medium":{"max":96.20764317131163,"mean":88.55983489133767,"min":74.25826335908518},"none":{"max":93.41302056876359,"mean":83.54172542255968,"min":71.55672276551286}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":10.47971439304257},"working_program_strength":{"all":88.70766670983319,"highest":94.02143981560225,"medium":88.55983489133767,"none":83.54172542255968}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5-5:b52ae01f6a026bcf","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":17.677192},"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":3.0063080000000006},"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":3.0063080000000006},"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":1.052792},"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":17.677192}},"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":21.736292},"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":87.56767148236098,"highest":94.85294223819557,"medium":91.55209015780808,"none":76.29798205107926},"economics_best_value":{"per_model":{"highest":true,"medium":true},"per_setting":{"highest":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":88.08581551744548,"score":88.08581551744548},"GB2-02":{"attempts":3,"playable":89.67145554646969,"score":89.67145554646969},"GB2-03":{"attempts":3,"playable":79.93719779926691,"score":79.93719779926691},"GB2-04":{"attempts":3,"playable":83.45707031342103,"score":83.45707031342103},"GB2-05":{"attempts":3,"playable":92.12204524869664,"score":92.12204524869664},"GB2-06":{"attempts":3,"playable":88.22986998450021,"score":88.22986998450021},"GB2-07":{"attempts":3,"playable":93.3499537308248,"score":93.3499537308248},"GB2-08":{"attempts":5,"playable":85.687963718263,"score":85.687963718263}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":82.68901495056332,"score":82.68901495056332},"GB2-02":{"attempts":1,"playable":95.74644355904393,"score":95.74644355904393},"GB2-03":{"attempts":1,"playable":97.2924718635775,"score":97.2924718635775},"GB2-04":{"attempts":1,"playable":94.75739177779393,"score":94.75739177779393},"GB2-05":{"attempts":1,"playable":98.30588648543281,"score":98.30588648543281},"GB2-06":{"attempts":1,"playable":99.44555607615347,"score":99.44555607615347},"GB2-07":{"attempts":1,"playable":97.52982013396796,"score":97.52982013396796},"GB2-08":{"attempts":1,"playable":93.05695305903157,"score":93.05695305903157}},"medium":{"GB2-01":{"attempts":1,"playable":92.94301354173018,"score":92.94301354173018},"GB2-02":{"attempts":1,"playable":94.70758756793307,"score":94.70758756793307},"GB2-03":{"attempts":1,"playable":91.81575402546764,"score":91.81575402546764},"GB2-04":{"attempts":1,"playable":85.57068130804979,"score":85.57068130804979},"GB2-05":{"attempts":1,"playable":87.45258525422871,"score":87.45258525422871},"GB2-06":{"attempts":1,"playable":91.01816853812291,"score":91.01816853812291},"GB2-07":{"attempts":1,"playable":92.15123665314515,"score":92.15123665314515},"GB2-08":{"attempts":2,"playable":96.75769437378725,"score":96.75769437378725}},"none":{"GB2-01":{"attempts":1,"playable":88.62541806004293,"score":88.62541806004293},"GB2-02":{"attempts":1,"playable":78.56033551243208,"score":78.56033551243208},"GB2-03":{"attempts":1,"playable":50.70336750875559,"score":50.70336750875559},"GB2-04":{"attempts":1,"playable":70.0431378544194,"score":70.0431378544194},"GB2-05":{"attempts":1,"playable":90.60766400642844,"score":90.60766400642844},"GB2-06":{"attempts":1,"playable":74.22588533922425,"score":74.22588533922425},"GB2-07":{"attempts":1,"playable":90.36880440536126,"score":90.36880440536126},"GB2-08":{"attempts":2,"playable":67.2492437219702,"score":67.2492437219702}}},"id":"claude-opus-5-5","is_recent_addition":false,"last_measured_at":"2026-11-03T07:15:48Z","match_totals_all":{"draws":960,"losses":1288,"wins":11382},"match_totals_tracks":{"highest":{"draws":80,"losses":165,"wins":3939},"medium":{"draws":140,"losses":296,"wins":4286},"none":{"draws":740,"losses":827,"wins":3157}},"model_slug":"claude-opus-5-5","official_rank_by_reasoning":{"highest":1,"medium":1,"none":9},"overall":{"max":99.44555607615347,"mean":87.56767148236098,"min":50.70336750875559},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":2,"overall_ranking_status":"ranked","per_game":{"GB2-01":82.68901495056332,"GB2-02":95.74644355904393,"GB2-03":97.2924718635775,"GB2-04":94.75739177779393,"GB2-05":98.30588648543281,"GB2-06":99.44555607615347,"GB2-07":97.52982013396796,"GB2-08":93.05695305903157},"per_game_all":{"GB2-01":88.08581551744548,"GB2-02":89.67145554646969,"GB2-03":79.93719779926691,"GB2-04":83.45707031342103,"GB2-05":92.12204524869664,"GB2-06":88.22986998450021,"GB2-07":93.3499537308248,"GB2-08":85.687963718263},"per_game_match_totals_all":{"GB2-01":{"draws":66,"losses":155,"wins":1359},"GB2-02":{"draws":163,"losses":75,"wins":1244},"GB2-03":{"draws":359,"losses":144,"wins":1037},"GB2-04":{"draws":312,"losses":107,"wins":1115},"GB2-05":{"draws":0,"losses":125,"wins":1507},"GB2-06":{"draws":48,"losses":156,"wins":1334},"GB2-07":{"draws":0,"losses":98,"wins":1522},"GB2-08":{"draws":12,"losses":428,"wins":2264}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":9,"losses":87,"wins":430},"GB2-02":{"draws":25,"losses":8,"wins":461},"GB2-03":{"draws":2,"losses":11,"wins":501},"GB2-04":{"draws":44,"losses":5,"wins":463},"GB2-05":{"draws":0,"losses":7,"wins":537},"GB2-06":{"draws":0,"losses":0,"wins":512},"GB2-07":{"draws":0,"losses":10,"wins":530},"GB2-08":{"draws":0,"losses":37,"wins":505}},"medium":{"GB2-01":{"draws":35,"losses":19,"wins":472},"GB2-02":{"draws":20,"losses":16,"wins":458},"GB2-03":{"draws":23,"losses":31,"wins":456},"GB2-04":{"draws":44,"losses":55,"wins":413},"GB2-05":{"draws":0,"losses":68,"wins":476},"GB2-06":{"draws":18,"losses":36,"wins":460},"GB2-07":{"draws":0,"losses":39,"wins":501},"GB2-08":{"draws":0,"losses":32,"wins":1050}},"none":{"GB2-01":{"draws":22,"losses":49,"wins":457},"GB2-02":{"draws":118,"losses":51,"wins":325},"GB2-03":{"draws":334,"losses":102,"wins":80},"GB2-04":{"draws":224,"losses":47,"wins":239},"GB2-05":{"draws":0,"losses":50,"wins":494},"GB2-06":{"draws":30,"losses":120,"wins":362},"GB2-07":{"draws":0,"losses":49,"wins":491},"GB2-08":{"draws":12,"losses":359,"wins":709}}},"per_game_raw_elo_all":{"GB2-01":1980.7066288529938,"GB2-02":1982.5017610578095,"GB2-03":1976.0616254592871,"GB2-04":1855.435616293159,"GB2-05":2456.6156273658003,"GB2-06":2347.3752748589573,"GB2-07":2416.8066389497676,"GB2-08":2196.1151877863763},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1864.8138767290689,"GB2-02":2126.157807616618,"GB2-03":2390.989587932298,"GB2-04":2069.7424796923597,"GB2-05":2842.5430127800305,"GB2-06":2902.2350219720843,"GB2-07":2672.4523221717363,"GB2-08":2330.2716724311917},"medium":{"GB2-01":2097.912473581546,"GB2-02":2079.078498079319,"GB2-03":2089.9580484137095,"GB2-04":1845.7542087720158,"GB2-05":2202.5797207637906,"GB2-06":2257.7302184177324,"GB2-07":2331.224843747549,"GB2-08":2557.48402221564},"none":{"GB2-01":1979.3935362483662,"GB2-02":1742.2689774774922,"GB2-03":1447.237240031855,"GB2-04":1650.8101604151018,"GB2-05":2324.7241485535787,"GB2-06":1882.160584187055,"GB2-07":2246.7427509300182,"GB2-08":1700.5898687122976}},"per_game_tracks":{"highest":{"GB2-01":82.68901495056332,"GB2-02":95.74644355904393,"GB2-03":97.2924718635775,"GB2-04":94.75739177779393,"GB2-05":98.30588648543281,"GB2-06":99.44555607615347,"GB2-07":97.52982013396796,"GB2-08":93.05695305903157},"medium":{"GB2-01":92.94301354173018,"GB2-02":94.70758756793307,"GB2-03":91.81575402546764,"GB2-04":85.57068130804979,"GB2-05":87.45258525422871,"GB2-06":91.01816853812291,"GB2-07":92.15123665314515,"GB2-08":96.75769437378725},"none":{"GB2-01":88.62541806004293,"GB2-02":78.56033551243208,"GB2-03":50.70336750875559,"GB2-04":70.0431378544194,"GB2-05":90.60766400642844,"GB2-06":74.22588533922425,"GB2-07":90.36880440536126,"GB2-08":67.2492437219702}},"program_outcomes":{"all":{"counted_attempts":26,"failed":0,"infra_excluded":1,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":23,"working":26},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":1,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"medium":{"counted_attempts":9,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":8,"working":9},"none":{"counted_attempts":9,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":9,"working":9}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-31T16:11:08Z","reasoning":{"highest":94.85294223819557,"medium":91.55209015780808,"none":76.29798205107926},"reasoning_agg":{"highest":{"max":99.44555607615347,"mean":94.85294223819557,"min":82.68901495056332},"medium":{"max":96.75769437378725,"mean":91.55209015780808,"min":85.57068130804979},"none":{"max":90.60766400642844,"mean":76.29798205107926,"min":50.70336750875559}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":18.554960187116308},"working_program_strength":{"all":87.56767148236098,"highest":94.85294223819557,"medium":91.55209015780808,"none":76.29798205107926}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5-1:0aa5e99bfd3b790d","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":9.233549636276065},"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":6.33905201032609}},"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":9.233549636276067},"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":6.33905201032609},"historical-provider-setting-intensive-variant-1":{"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":11.79121,"mean":5.15427625,"median":3.933625,"min":2.88134,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"run_count":8,"token_priced_attempt_count":10,"total":41.23421},"historical-provider-setting-intensive-variant-2":{"admitted_cell_count":3,"cell_count":3,"cost_basis_counts":{"local_list_price_estimate":3},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":2.970960728273602,"mean":2.501635977071231,"median":2.662375536110322,"min":1.8715716668297693,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":3},"run_count":3,"token_priced_attempt_count":3,"total":7.504907931213694}},"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":87.15733649525475,"highest":93.75102350621675,"medium":82.92426543174263,"none":84.79672054780491},"economics_best_value":{"per_model":{"none":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":83.64284601774382,"score":83.64284601774382},"GB2-02":{"attempts":3,"playable":88.8534102090707,"score":88.8534102090707},"GB2-03":{"attempts":4,"playable":92.54099733280763,"score":92.54099733280763},"GB2-04":{"attempts":4,"playable":74.48405499618073,"score":74.48405499618073},"GB2-05":{"attempts":3,"playable":89.6767612678696,"score":89.6767612678696},"GB2-06":{"attempts":3,"playable":88.5394530485501,"score":88.5394530485501},"GB2-07":{"attempts":4,"playable":90.54049990638357,"score":90.54049990638357},"GB2-08":{"attempts":3,"playable":88.980669183432,"score":88.980669183432}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":92.08906524150485,"score":92.08906524150485},"GB2-02":{"attempts":1,"playable":95.2739687375449,"score":95.2739687375449},"GB2-03":{"attempts":2,"playable":94.846186233981,"score":94.846186233981},"GB2-04":{"attempts":2,"playable":87.38203868292257,"score":87.38203868292257},"GB2-05":{"attempts":1,"playable":92.50705985026498,"score":92.50705985026498},"GB2-06":{"attempts":1,"playable":97.82022915470765,"score":97.82022915470765},"GB2-07":{"attempts":2,"playable":92.60640805857855,"score":92.60640805857855},"GB2-08":{"attempts":1,"playable":97.48323209022956,"score":97.48323209022956}},"medium":{"GB2-01":{"attempts":1,"playable":72.12132718573254,"score":72.12132718573254},"GB2-02":{"attempts":1,"playable":90.3965017610756,"score":90.3965017610756},"GB2-03":{"attempts":1,"playable":90.96320216516021,"score":90.96320216516021},"GB2-04":{"attempts":1,"playable":63.591651889848464,"score":63.591651889848464},"GB2-05":{"attempts":1,"playable":86.44406044456561,"score":86.44406044456561},"GB2-06":{"attempts":1,"playable":86.34488430202435,"score":86.34488430202435},"GB2-07":{"attempts":1,"playable":92.69581197554896,"score":92.69581197554896},"GB2-08":{"attempts":1,"playable":80.83668372998535,"score":80.83668372998535}},"none":{"GB2-01":{"attempts":1,"playable":86.7181456259941,"score":86.7181456259941},"GB2-02":{"attempts":1,"playable":80.88976012859159,"score":80.88976012859159},"GB2-03":{"attempts":1,"playable":91.8136035992817,"score":91.8136035992817},"GB2-04":{"attempts":1,"playable":72.47847441577116,"score":72.47847441577116},"GB2-05":{"attempts":1,"playable":90.07916350877821,"score":90.07916350877821},"GB2-06":{"attempts":1,"playable":81.45324568891832,"score":81.45324568891832},"GB2-07":{"attempts":1,"playable":86.3192796850232,"score":86.3192796850232},"GB2-08":{"attempts":1,"playable":88.62209173008108,"score":88.62209173008108}}},"id":"claude-fable-5-1","is_recent_addition":false,"last_measured_at":"2026-11-03T07:16:04Z","match_totals_all":{"draws":779,"losses":1353,"wins":11978},"match_totals_tracks":{"highest":{"draws":122,"losses":321,"wins":5299},"medium":{"draws":306,"losses":568,"wins":3312},"none":{"draws":351,"losses":464,"wins":3367}},"model_slug":"claude-fable-5-1","official_rank_by_reasoning":{"highest":3,"medium":4,"none":3},"overall":{"max":97.82022915470765,"mean":87.15733649525475,"min":63.591651889848464},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":3,"overall_ranking_status":"ranked","per_game":{"GB2-01":92.08906524150485,"GB2-02":95.2739687375449,"GB2-03":94.846186233981,"GB2-04":87.38203868292257,"GB2-05":92.50705985026498,"GB2-06":97.82022915470765,"GB2-07":92.60640805857855,"GB2-08":97.48323209022956},"per_game_all":{"GB2-01":83.64284601774382,"GB2-02":88.8534102090707,"GB2-03":92.54099733280763,"GB2-04":74.48405499618073,"GB2-05":89.6767612678696,"GB2-06":88.5394530485501,"GB2-07":90.54049990638357,"GB2-08":88.980669183432},"per_game_match_totals_all":{"GB2-01":{"draws":7,"losses":255,"wins":1314},"GB2-02":{"draws":191,"losses":74,"wins":1217},"GB2-03":{"draws":24,"losses":129,"wins":1897},"GB2-04":{"draws":512,"losses":217,"wins":1311},"GB2-05":{"draws":0,"losses":165,"wins":1467},"GB2-06":{"draws":44,"losses":153,"wins":1347},"GB2-07":{"draws":0,"losses":181,"wins":1979},"GB2-08":{"draws":1,"losses":179,"wins":1446}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":40,"wins":482},"GB2-02":{"draws":22,"losses":12,"wins":460},"GB2-03":{"draws":8,"losses":47,"wins":969},"GB2-04":{"draws":86,"losses":91,"wins":841},"GB2-05":{"draws":0,"losses":39,"wins":503},"GB2-06":{"draws":4,"losses":7,"wins":505},"GB2-07":{"draws":0,"losses":73,"wins":1007},"GB2-08":{"draws":0,"losses":12,"wins":532}},"medium":{"GB2-01":{"draws":1,"losses":147,"wins":378},"GB2-02":{"draws":41,"losses":28,"wins":425},"GB2-03":{"draws":13,"losses":41,"wins":462},"GB2-04":{"draws":239,"losses":73,"wins":198},"GB2-05":{"draws":0,"losses":73,"wins":471},"GB2-06":{"draws":12,"losses":64,"wins":438},"GB2-07":{"draws":0,"losses":36,"wins":504},"GB2-08":{"draws":0,"losses":106,"wins":436}},"none":{"GB2-01":{"draws":4,"losses":68,"wins":454},"GB2-02":{"draws":128,"losses":34,"wins":332},"GB2-03":{"draws":3,"losses":41,"wins":466},"GB2-04":{"draws":187,"losses":53,"wins":272},"GB2-05":{"draws":0,"losses":53,"wins":493},"GB2-06":{"draws":28,"losses":82,"wins":404},"GB2-07":{"draws":0,"losses":72,"wins":468},"GB2-08":{"draws":1,"losses":61,"wins":478}}},"per_game_raw_elo_all":{"GB2-01":1908.8804755957726,"GB2-02":1940.1059502459768,"GB2-03":2125.240436344287,"GB2-04":1715.4803143810514,"GB2-05":2292.7741364524995,"GB2-06":2252.884400753826,"GB2-07":2266.9813556039435,"GB2-08":2250.255655579637},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2070.5260940810863,"GB2-02":2103.626340091276,"GB2-03":2227.091047787201,"GB2-04":1880.367308385004,"GB2-05":2408.6216272140546,"GB2-06":2600.289044723486,"GB2-07":2354.4990111236148,"GB2-08":2581.1630944218864},"medium":{"GB2-01":1717.7368756654748,"GB2-02":1943.796369617758,"GB2-03":2058.754074630528,"GB2-04":1590.410842879947,"GB2-05":2166.67715147108,"GB2-06":2133.1704970585556,"GB2-07":2358.7810894767904,"GB2-08":1986.7107044478619},"none":{"GB2-01":1938.378457040757,"GB2-02":1772.8951410288967,"GB2-03":2089.876186615131,"GB2-04":1675.6627918782037,"GB2-05":2303.023630672364,"GB2-06":2025.193660479435,"GB2-07":2087.6639662114258,"GB2-08":2182.8931678691624}},"per_game_tracks":{"highest":{"GB2-01":92.08906524150485,"GB2-02":95.2739687375449,"GB2-03":94.846186233981,"GB2-04":87.38203868292257,"GB2-05":92.50705985026498,"GB2-06":97.82022915470765,"GB2-07":92.60640805857855,"GB2-08":97.48323209022956},"medium":{"GB2-01":72.12132718573254,"GB2-02":90.3965017610756,"GB2-03":90.96320216516021,"GB2-04":63.591651889848464,"GB2-05":86.44406044456561,"GB2-06":86.34488430202435,"GB2-07":92.69581197554896,"GB2-08":80.83668372998535},"none":{"GB2-01":86.7181456259941,"GB2-02":80.88976012859159,"GB2-03":91.8136035992817,"GB2-04":72.47847441577116,"GB2-05":90.07916350877821,"GB2-06":81.45324568891832,"GB2-07":86.3192796850232,"GB2-08":88.62209173008108}},"program_outcomes":{"all":{"counted_attempts":27,"failed":0,"infra_excluded":5,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":24,"working":27},"highest":{"counted_attempts":11,"failed":0,"infra_excluded":5,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":9,"working":11},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-31T17:10:42Z","reasoning":{"highest":93.75102350621677,"medium":82.92426543174263,"none":84.79672054780491},"reasoning_agg":{"highest":{"max":97.82022915470765,"mean":93.75102350621677,"min":87.38203868292257},"medium":{"max":92.69581197554896,"mean":82.92426543174263,"min":63.591651889848464},"none":{"max":91.8136035992817,"mean":84.79672054780491,"min":72.47847441577116}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":10.826758074474142},"working_program_strength":{"all":87.15733649525475,"highest":93.75102350621675,"medium":82.92426543174263,"none":84.79672054780491}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-1-sol:ffe1770d7a9b76a6","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":0.388508}},"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":0.674699},"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":0.388508},"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":84.78450457073968,"highest":91.94771415969157,"medium":86.29296537651543,"none":76.11283417601206},"economics_best_value":{"per_model":{"all":true,"highest":true,"medium":true},"per_setting":{"highest":true,"medium":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":65.36743909584432,"score":65.36743909584432},"GB2-02":{"attempts":3,"playable":79.02525875423606,"score":79.02525875423606},"GB2-03":{"attempts":3,"playable":92.63915033285548,"score":92.63915033285548},"GB2-04":{"attempts":3,"playable":85.12261718399623,"score":85.12261718399623},"GB2-05":{"attempts":3,"playable":93.96794576275852,"score":93.96794576275852},"GB2-06":{"attempts":3,"playable":85.41947524598697,"score":85.41947524598697},"GB2-07":{"attempts":3,"playable":94.34534202670557,"score":94.34534202670557},"GB2-08":{"attempts":3,"playable":82.38880816353434,"score":82.38880816353434}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":74.4874920568879,"score":74.4874920568879},"GB2-02":{"attempts":1,"playable":94.31317778856084,"score":94.31317778856084},"GB2-03":{"attempts":1,"playable":97.75075322056801,"score":97.75075322056801},"GB2-04":{"attempts":1,"playable":94.84108906956128,"score":94.84108906956128},"GB2-05":{"attempts":1,"playable":97.95042907729889,"score":97.95042907729889},"GB2-06":{"attempts":1,"playable":87.74713611306505,"score":87.74713611306505},"GB2-07":{"attempts":1,"playable":95.45708647961332,"score":95.45708647961332},"GB2-08":{"attempts":1,"playable":93.03454947197723,"score":93.03454947197723}},"medium":{"GB2-01":{"attempts":1,"playable":72.84012309764051,"score":72.84012309764051},"GB2-02":{"attempts":1,"playable":78.9804784046893,"score":78.9804784046893},"GB2-03":{"attempts":1,"playable":96.01427197566662,"score":96.01427197566662},"GB2-04":{"attempts":1,"playable":86.82549835993035,"score":86.82549835993035},"GB2-05":{"attempts":1,"playable":94.14053286795257,"score":94.14053286795257},"GB2-06":{"attempts":1,"playable":90.75274132400119,"score":90.75274132400119},"GB2-07":{"attempts":1,"playable":94.34016013834903,"score":94.34016013834903},"GB2-08":{"attempts":1,"playable":76.44991684389393,"score":76.44991684389393}},"none":{"GB2-01":{"attempts":1,"playable":48.77470213300457,"score":48.77470213300457},"GB2-02":{"attempts":1,"playable":63.78212006945806,"score":63.78212006945806},"GB2-03":{"attempts":1,"playable":84.15242580233183,"score":84.15242580233183},"GB2-04":{"attempts":1,"playable":73.70126412249704,"score":73.70126412249704},"GB2-05":{"attempts":1,"playable":89.81287534302405,"score":89.81287534302405},"GB2-06":{"attempts":1,"playable":77.75854830089467,"score":77.75854830089467},"GB2-07":{"attempts":1,"playable":93.23877946215433,"score":93.23877946215433},"GB2-08":{"attempts":1,"playable":77.68195817473186,"score":77.68195817473186}}},"id":"gpt-6.1-sol","is_recent_addition":false,"last_measured_at":"2026-11-03T06:46:10Z","match_totals_all":{"draws":904,"losses":1460,"wins":10174},"match_totals_tracks":{"highest":{"draws":99,"losses":279,"wins":3806},"medium":{"draws":222,"losses":462,"wins":3484},"none":{"draws":583,"losses":719,"wins":2884}},"model_slug":"gpt-6-1-sol","official_rank_by_reasoning":{"highest":4,"medium":3,"none":10},"overall":{"max":97.95042907729889,"mean":84.78450457073968,"min":48.77470213300457},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":4,"overall_ranking_status":"ranked","per_game":{"GB2-01":74.4874920568879,"GB2-02":94.31317778856084,"GB2-03":97.75075322056801,"GB2-04":94.84108906956128,"GB2-05":97.95042907729889,"GB2-06":87.74713611306505,"GB2-07":95.45708647961332,"GB2-08":93.03454947197723},"per_game_all":{"GB2-01":65.36743909584432,"GB2-02":79.02525875423606,"GB2-03":92.63915033285548,"GB2-04":85.12261718399623,"GB2-05":93.96794576275852,"GB2-06":85.41947524598697,"GB2-07":94.34534202670557,"GB2-08":82.38880816353434},"per_game_match_totals_all":{"GB2-01":{"draws":78,"losses":512,"wins":990},"GB2-02":{"draws":466,"losses":88,"wins":930},"GB2-03":{"draws":36,"losses":97,"wins":1405},"GB2-04":{"draws":244,"losses":114,"wins":1168},"GB2-05":{"draws":0,"losses":93,"wins":1531},"GB2-06":{"draws":80,"losses":185,"wins":1275},"GB2-07":{"draws":0,"losses":81,"wins":1541},"GB2-08":{"draws":0,"losses":290,"wins":1334}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":135,"wins":391},"GB2-02":{"draws":36,"losses":10,"wins":448},"GB2-03":{"draws":1,"losses":9,"wins":504},"GB2-04":{"draws":37,"losses":8,"wins":465},"GB2-05":{"draws":0,"losses":9,"wins":533},"GB2-06":{"draws":25,"losses":50,"wins":437},"GB2-07":{"draws":0,"losses":21,"wins":521},"GB2-08":{"draws":0,"losses":37,"wins":507}},"medium":{"GB2-01":{"draws":12,"losses":137,"wins":375},"GB2-02":{"draws":141,"losses":37,"wins":316},"GB2-03":{"draws":4,"losses":17,"wins":489},"GB2-04":{"draws":42,"losses":49,"wins":417},"GB2-05":{"draws":0,"losses":30,"wins":510},"GB2-06":{"draws":23,"losses":35,"wins":454},"GB2-07":{"draws":0,"losses":27,"wins":513},"GB2-08":{"draws":0,"losses":130,"wins":410}},"none":{"GB2-01":{"draws":66,"losses":240,"wins":224},"GB2-02":{"draws":289,"losses":41,"wins":166},"GB2-03":{"draws":31,"losses":71,"wins":412},"GB2-04":{"draws":165,"losses":57,"wins":286},"GB2-05":{"draws":0,"losses":54,"wins":488},"GB2-06":{"draws":32,"losses":100,"wins":384},"GB2-07":{"draws":0,"losses":33,"wins":507},"GB2-08":{"draws":0,"losses":123,"wins":417}}},"per_game_raw_elo_all":{"GB2-01":1649.6138536067458,"GB2-02":1800.2296444192896,"GB2-03":2200.33269359039,"GB2-04":1876.4449830152387,"GB2-05":2525.9229227923856,"GB2-06":2122.5730940157896,"GB2-07":2450.0681418545632,"GB2-08":2045.0126557279084},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1746.9572419645103,"GB2-02":2063.3055938258035,"GB2-03":2433.8798103630993,"GB2-04":2073.028697387991,"GB2-05":2793.766033457615,"GB2-06":2167.4490146680964,"GB2-07":2515.250679498343,"GB2-08":2329.3863353137986},"medium":{"GB2-01":1726.449706064178,"GB2-02":1747.5930726575841,"GB2-03":2295.3418072315753,"GB2-04":1867.6192498395608,"GB2-05":2491.6957241852824,"GB2-06":2249.6781869130145,"GB2-07":2447.817706519919,"GB2-08":1889.438975216637},"none":{"GB2-01":1475.4346127915494,"GB2-02":1589.7902667744806,"GB2-03":1871.776463176497,"GB2-04":1688.6870018181637,"GB2-05":2292.3070107342596,"GB2-06":1950.5920804662571,"GB2-07":2387.1360395454276,"GB2-08":1916.2126566532902}},"per_game_tracks":{"highest":{"GB2-01":74.4874920568879,"GB2-02":94.31317778856084,"GB2-03":97.75075322056801,"GB2-04":94.84108906956128,"GB2-05":97.95042907729889,"GB2-06":87.74713611306505,"GB2-07":95.45708647961332,"GB2-08":93.03454947197723},"medium":{"GB2-01":72.84012309764051,"GB2-02":78.9804784046893,"GB2-03":96.01427197566662,"GB2-04":86.82549835993035,"GB2-05":94.14053286795257,"GB2-06":90.75274132400119,"GB2-07":94.34016013834903,"GB2-08":76.44991684389393},"none":{"GB2-01":48.77470213300457,"GB2-02":63.78212006945806,"GB2-03":84.15242580233183,"GB2-04":73.70126412249704,"GB2-05":89.81287534302405,"GB2-06":77.75854830089467,"GB2-07":93.23877946215433,"GB2-08":77.68195817473186}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":23,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-31T17:01:19Z","reasoning":{"highest":91.94771415969157,"medium":86.29296537651543,"none":76.11283417601206},"reasoning_agg":{"highest":{"max":97.95042907729889,"mean":91.94771415969157,"min":74.4874920568879},"medium":{"max":96.01427197566662,"mean":86.29296537651543,"min":72.84012309764051},"none":{"max":93.23877946215433,"mean":76.11283417601206,"min":48.77470213300457}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":15.834879983679514},"working_program_strength":{"all":84.78450457073968,"highest":91.94771415969157,"medium":86.29296537651543,"none":76.11283417601206}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-1-terra-pro:035fc684c167c1c9","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":0.37864,"mean":0.30133032499999995,"median":0.300062625,"min":0.2459173,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":2.4106425999999996},"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":0.128416,"mean":0.10397188750000001,"median":0.1029425,"min":0.0859153,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.8317751},"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":0.08337900000000001,"mean":0.06485129999999999,"median":0.064133675,"min":0.05121355,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5188104}},"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":0.128416,"mean":0.10397188750000001,"median":0.1029425,"min":0.0859153,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.8317751000000001},"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":0.08337900000000001,"mean":0.06485129999999999,"median":0.064133675,"min":0.05121355,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5188103999999999},"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":0.37864,"mean":0.30133032499999995,"median":0.300062625,"min":0.2459173,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":2.4106426}},"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":0.37864,"mean":0.15671783749999998,"median":0.1029425,"min":0.05121355,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":24},"run_count":24,"token_priced_attempt_count":24,"total":3.7612281000000003},"codegen_latency_ms":{"attempt_count":24,"max_ms":1803300,"mean_ms":278774.4166666667,"min_ms":42551,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":424679,"mean_ms":330938.75,"min_ms":269191,"run_count":8},"medium":{"attempt_count":8,"max_ms":1803300,"mean_ms":405545.875,"min_ms":83659,"run_count":8},"none":{"attempt_count":8,"max_ms":363737,"mean_ms":99838.625,"min_ms":42551,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":60378,"output_mean":22706.0,"output_min":4484,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":60378,"output_mean":47788.875,"output_min":38360,"run_count":8},"medium":{"attempt_count":8,"output_max":17219,"output_mean":13534.125,"output_min":10853,"run_count":8},"none":{"attempt_count":8,"output_max":9247,"output_mean":6795.0,"output_min":4484,"run_count":8}},"display_name":"GPT-6.1 Terra Pro","economics":{"all":82.23680940584825,"highest":84.82629513455853,"medium":78.95834221802923,"none":82.92579086495697},"economics_best_value":{"per_model":{"none":true},"per_setting":{"none":true}},"first_seen_at":"2026-11-03T08:03:16Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":24,"effective_max_output_tokens":[128000],"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,"requested_max_output_token_observations":24,"requested_max_output_tokens":[128000],"total_output_tokens":544944,"total_reasoning_output_tokens":350974,"total_visible_output_tokens":193970,"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":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6.1-terra-pro","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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":46.82342951867012,"score":46.82342951867012},"GB2-02":{"attempts":3,"playable":74.92986946808796,"score":74.92986946808796},"GB2-03":{"attempts":3,"playable":88.47852091260165,"score":88.47852091260165},"GB2-04":{"attempts":3,"playable":84.23563741829592,"score":84.23563741829592},"GB2-05":{"attempts":3,"playable":90.20052905783363,"score":90.20052905783363},"GB2-06":{"attempts":3,"playable":89.84280502305262,"score":89.84280502305262},"GB2-07":{"attempts":3,"playable":94.46620855515839,"score":94.46620855515839},"GB2-08":{"attempts":3,"playable":88.91747529308567,"score":88.91747529308567}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":40.057711810679734,"score":40.057711810679734},"GB2-02":{"attempts":1,"playable":88.2967148832923,"score":88.2967148832923},"GB2-03":{"attempts":1,"playable":94.74825020781462,"score":94.74825020781462},"GB2-04":{"attempts":1,"playable":83.73451028257631,"score":83.73451028257631},"GB2-05":{"attempts":1,"playable":95.78362004943469,"score":95.78362004943469},"GB2-06":{"attempts":1,"playable":90.56481735934975,"score":90.56481735934975},"GB2-07":{"attempts":1,"playable":95.45593795726762,"score":95.45593795726762},"GB2-08":{"attempts":1,"playable":89.96879852605322,"score":89.96879852605322}},"medium":{"GB2-01":{"attempts":1,"playable":33.88767780930909,"score":33.88767780930909},"GB2-02":{"attempts":1,"playable":72.12658908811841,"score":72.12658908811841},"GB2-03":{"attempts":1,"playable":82.97060174130631,"score":82.97060174130631},"GB2-04":{"attempts":1,"playable":83.03299175178623,"score":83.03299175178623},"GB2-05":{"attempts":1,"playable":84.82111123187633,"score":84.82111123187633},"GB2-06":{"attempts":1,"playable":91.96521598577145,"score":91.96521598577145},"GB2-07":{"attempts":1,"playable":93.97123535474157,"score":93.97123535474157},"GB2-08":{"attempts":1,"playable":88.89131478132445,"score":88.89131478132445}},"none":{"GB2-01":{"attempts":1,"playable":66.52489893602156,"score":66.52489893602156},"GB2-02":{"attempts":1,"playable":64.36630443285318,"score":64.36630443285318},"GB2-03":{"attempts":1,"playable":87.71671078868404,"score":87.71671078868404},"GB2-04":{"attempts":1,"playable":85.93941022052522,"score":85.93941022052522},"GB2-05":{"attempts":1,"playable":89.99685589218986,"score":89.99685589218986},"GB2-06":{"attempts":1,"playable":86.9983817240367,"score":86.9983817240367},"GB2-07":{"attempts":1,"playable":93.97145235346595,"score":93.97145235346595},"GB2-08":{"attempts":1,"playable":87.89231257187934,"score":87.89231257187934}}},"id":"gpt-6.1-terra-pro","is_recent_addition":true,"last_measured_at":"2026-11-03T08:03:16Z","match_totals_all":{"draws":1228,"losses":1618,"wins":9682},"match_totals_tracks":{"highest":{"draws":193,"losses":536,"wins":3445},"medium":{"draws":458,"losses":657,"wins":3059},"none":{"draws":577,"losses":425,"wins":3178}},"model_slug":"gpt-6-1-terra-pro","official_rank_by_reasoning":{"highest":8,"medium":5,"none":5},"overall":{"max":95.78362004943469,"mean":82.23680940584825,"min":33.88767780930909},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":5,"overall_ranking_status":"ranked","per_game":{"GB2-01":40.057711810679734,"GB2-02":88.2967148832923,"GB2-03":94.74825020781462,"GB2-04":83.73451028257631,"GB2-05":95.78362004943469,"GB2-06":90.56481735934975,"GB2-07":95.45593795726762,"GB2-08":89.96879852605322},"per_game_all":{"GB2-01":46.82342951867012,"GB2-02":74.92986946808796,"GB2-03":88.47852091260165,"GB2-04":84.23563741829592,"GB2-05":90.20052905783363,"GB2-06":89.84280502305262,"GB2-07":94.46620855515839,"GB2-08":88.91747529308567},"per_game_match_totals_all":{"GB2-01":{"draws":260,"losses":712,"wins":604},"GB2-02":{"draws":579,"losses":93,"wins":804},"GB2-03":{"draws":125,"losses":123,"wins":1290},"GB2-04":{"draws":184,"losses":160,"wins":1186},"GB2-05":{"draws":0,"losses":157,"wins":1469},"GB2-06":{"draws":80,"losses":114,"wins":1344},"GB2-07":{"draws":0,"losses":79,"wins":1539},"GB2-08":{"draws":0,"losses":180,"wins":1446}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":58,"losses":288,"wins":180},"GB2-02":{"draws":47,"losses":36,"wins":409},"GB2-03":{"draws":8,"losses":22,"wins":480},"GB2-04":{"draws":49,"losses":62,"wins":397},"GB2-05":{"draws":0,"losses":21,"wins":521},"GB2-06":{"draws":31,"losses":32,"wins":451},"GB2-07":{"draws":0,"losses":21,"wins":519},"GB2-08":{"draws":0,"losses":54,"wins":488}},"medium":{"GB2-01":{"draws":28,"losses":334,"wins":162},"GB2-02":{"draws":230,"losses":27,"wins":235},"GB2-03":{"draws":111,"losses":38,"wins":367},"GB2-04":{"draws":69,"losses":56,"wins":385},"GB2-05":{"draws":0,"losses":83,"wins":459},"GB2-06":{"draws":20,"losses":30,"wins":462},"GB2-07":{"draws":0,"losses":29,"wins":509},"GB2-08":{"draws":0,"losses":60,"wins":480}},"none":{"GB2-01":{"draws":174,"losses":90,"wins":262},"GB2-02":{"draws":302,"losses":30,"wins":160},"GB2-03":{"draws":6,"losses":63,"wins":443},"GB2-04":{"draws":66,"losses":42,"wins":404},"GB2-05":{"draws":0,"losses":53,"wins":489},"GB2-06":{"draws":29,"losses":52,"wins":431},"GB2-07":{"draws":0,"losses":29,"wins":511},"GB2-08":{"draws":0,"losses":66,"wins":478}}},"per_game_raw_elo_all":{"GB2-01":1457.7086808286629,"GB2-02":1720.1962411250317,"GB2-03":2008.7981936324752,"GB2-04":1824.670240758592,"GB2-05":2334.9442157595563,"GB2-06":2226.9538536374203,"GB2-07":2456.3704338063058,"GB2-08":2192.0026113370186},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1390.8241104312906,"GB2-02":1896.495692696016,"GB2-03":2221.088355171458,"GB2-04":1816.2874817594097,"GB2-05":2593.5686650335556,"GB2-06":2244.0719112212046,"GB2-07":2515.177260057138,"GB2-08":2223.071950540322},"medium":{"GB2-01":1328.4843303796094,"GB2-02":1669.1290324297565,"GB2-03":1846.9082054165403,"GB2-04":1805.7040494060138,"GB2-05":2111.5676586633163,"GB2-06":2287.893382443712,"GB2-07":2426.960971534272,"GB2-08":2190.6967490554734},"none":{"GB2-01":1653.817601675088,"GB2-02":1594.9639982493225,"GB2-03":1958.3980203094284,"GB2-04":1852.019191110353,"GB2-05":2299.6963235817975,"GB2-06":2148.896267247344,"GB2-07":2426.9730698275075,"GB2-08":2162.2391344152607}},"per_game_tracks":{"highest":{"GB2-01":40.057711810679734,"GB2-02":88.2967148832923,"GB2-03":94.74825020781462,"GB2-04":83.73451028257631,"GB2-05":95.78362004943469,"GB2-06":90.56481735934975,"GB2-07":95.45593795726762,"GB2-08":89.96879852605322},"medium":{"GB2-01":33.88767780930909,"GB2-02":72.12658908811841,"GB2-03":82.97060174130631,"GB2-04":83.03299175178623,"GB2-05":84.82111123187633,"GB2-06":91.96521598577145,"GB2-07":93.97123535474157,"GB2-08":88.89131478132445},"none":{"GB2-01":66.52489893602156,"GB2-02":64.36630443285318,"GB2-03":87.71671078868404,"GB2-04":85.93941022052522,"GB2-05":89.99685589218986,"GB2-06":86.9983817240367,"GB2-07":93.97145235346595,"GB2-08":87.89231257187934}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":24,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":84.82629513455853,"medium":78.95834221802923,"none":82.92579086495697},"reasoning_agg":{"highest":{"max":95.78362004943469,"mean":84.82629513455853,"min":40.057711810679734},"medium":{"max":93.97123535474157,"mean":78.95834221802923,"min":33.88767780930909},"none":{"max":93.97145235346595,"mean":82.92579086495697,"min":64.36630443285318}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":5.867952916529305},"working_program_strength":{"all":82.23680940584825,"highest":84.82629513455853,"medium":78.95834221802923,"none":82.92579086495697}},{"canonical_public_row_identity":"publication-row.v1:overall:gemini-4-argon:5891bb750a1513bb","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":0.582036,"mean":0.440512,"median":0.446556,"min":0.29813,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":3.5240959999999997},"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":0.22172,"mean":0.09679175,"median":0.079292,"min":0.064396,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.774334},"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":0.124048,"mean":0.08425525,"median":0.081095,"min":0.062404,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.674042}},"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":0.22172,"mean":0.09679175,"median":0.079292,"min":0.064396,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.7743340000000001},"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":0.124048,"mean":0.08425525,"median":0.081095,"min":0.062404,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.674042},"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":0.582036,"mean":0.440512,"median":0.446556,"min":0.29813,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":3.524096}},"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":0.582036,"mean":0.20718633333333333,"median":0.09228,"min":0.062404,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":28},"run_count":24,"token_priced_attempt_count":28,"total":4.972471999999999},"codegen_latency_ms":{"attempt_count":28,"max_ms":633783,"mean_ms":198313.91666666666,"min_ms":46974,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":633783,"mean_ms":450301.75,"min_ms":322608,"run_count":8},"medium":{"attempt_count":9,"max_ms":152424,"mean_ms":70572.25,"min_ms":46974,"run_count":8},"none":{"attempt_count":8,"max_ms":113522,"mean_ms":74067.75,"min_ms":52299,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":54729,"output_mean":18449.125,"output_min":4647,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":54729,"output_mean":41092.75,"output_min":28061,"run_count":8},"medium":{"attempt_count":9,"output_max":17530,"output_mean":7576.5,"output_min":4801,"run_count":8},"none":{"attempt_count":8,"output_max":10605,"output_mean":6678.125,"output_min":4647,"run_count":8}},"display_name":"Gemini 4 Argon","economics":{"all":81.64849557226177,"highest":89.04254116538289,"medium":76.70214349442308,"none":79.20080205697934},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[943718],"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":[943718],"total_output_tokens":442779,"total_reasoning_output_tokens":206667,"total_visible_output_tokens":236112,"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":943718,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"gemini-4-argon","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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":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":91.7288536621054,"score":91.7288536621054},"GB2-02":{"attempts":3,"playable":78.13476187732887,"score":78.13476187732887},"GB2-03":{"attempts":3,"playable":84.2583815405244,"score":84.2583815405244},"GB2-04":{"attempts":3,"playable":71.13661843698274,"score":71.13661843698274},"GB2-05":{"attempts":3,"playable":90.38848473117282,"score":90.38848473117282},"GB2-06":{"attempts":3,"playable":91.97343170540285,"score":91.97343170540285},"GB2-07":{"attempts":3,"playable":71.93464201135737,"score":71.93464201135737},"GB2-08":{"attempts":3,"playable":73.63279061321973,"score":73.63279061321973}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":94.66861896327353,"score":94.66861896327353},"GB2-02":{"attempts":1,"playable":94.39855818079076,"score":94.39855818079076},"GB2-03":{"attempts":1,"playable":91.55659322400427,"score":91.55659322400427},"GB2-04":{"attempts":1,"playable":70.74565502383922,"score":70.74565502383922},"GB2-05":{"attempts":1,"playable":95.43973831731314,"score":95.43973831731314},"GB2-06":{"attempts":1,"playable":96.88323014326578,"score":96.88323014326578},"GB2-07":{"attempts":1,"playable":82.31617474302877,"score":82.31617474302877},"GB2-08":{"attempts":1,"playable":86.33176072754762,"score":86.33176072754762}},"medium":{"GB2-01":{"attempts":1,"playable":89.29858057221064,"score":89.29858057221064},"GB2-02":{"attempts":1,"playable":63.669059937249685,"score":63.669059937249685},"GB2-03":{"attempts":1,"playable":77.91937657445246,"score":77.91937657445246},"GB2-04":{"attempts":1,"playable":67.43102888941571,"score":67.43102888941571},"GB2-05":{"attempts":1,"playable":88.75033877915386,"score":88.75033877915386},"GB2-06":{"attempts":1,"playable":91.0357040076817,"score":91.0357040076817},"GB2-07":{"attempts":1,"playable":75.68783615647786,"score":75.68783615647786},"GB2-08":{"attempts":1,"playable":59.82522303874266,"score":59.82522303874266}},"none":{"GB2-01":{"attempts":1,"playable":91.219361450832,"score":91.219361450832},"GB2-02":{"attempts":1,"playable":76.33666751394614,"score":76.33666751394614},"GB2-03":{"attempts":1,"playable":83.29917482311647,"score":83.29917482311647},"GB2-04":{"attempts":1,"playable":75.23317139769328,"score":75.23317139769328},"GB2-05":{"attempts":1,"playable":86.97537709705149,"score":86.97537709705149},"GB2-06":{"attempts":1,"playable":88.00136096526107,"score":88.00136096526107},"GB2-07":{"attempts":1,"playable":57.79991513456548,"score":57.79991513456548},"GB2-08":{"attempts":1,"playable":74.74138807336891,"score":74.74138807336891}}},"id":"gemini-4-argon","is_recent_addition":false,"last_measured_at":"2026-11-03T07:16:08Z","match_totals_all":{"draws":1010,"losses":1858,"wins":9686},"match_totals_tracks":{"highest":{"draws":181,"losses":371,"wins":3628},"medium":{"draws":479,"losses":762,"wins":2943},"none":{"draws":350,"losses":725,"wins":3115}},"model_slug":"gemini-4-argon","official_rank_by_reasoning":{"highest":6,"medium":7,"none":7},"overall":{"max":96.88323014326578,"mean":81.64849557226177,"min":57.79991513456548},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":6,"overall_ranking_status":"ranked","per_game":{"GB2-01":94.66861896327353,"GB2-02":94.39855818079076,"GB2-03":91.55659322400427,"GB2-04":70.74565502383922,"GB2-05":95.43973831731314,"GB2-06":96.88323014326578,"GB2-07":82.31617474302877,"GB2-08":86.33176072754762},"per_game_all":{"GB2-01":91.7288536621054,"GB2-02":78.13476187732887,"GB2-03":84.2583815405244,"GB2-04":71.13661843698274,"GB2-05":90.38848473117282,"GB2-06":91.97343170540285,"GB2-07":71.93464201135737,"GB2-08":73.63279061321973},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":129,"wins":1447},"GB2-02":{"draws":372,"losses":149,"wins":963},"GB2-03":{"draws":175,"losses":169,"wins":1190},"GB2-04":{"draws":409,"losses":256,"wins":871},"GB2-05":{"draws":0,"losses":153,"wins":1475},"GB2-06":{"draws":54,"losses":93,"wins":1391},"GB2-07":{"draws":0,"losses":465,"wins":1153},"GB2-08":{"draws":0,"losses":444,"wins":1196}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":27,"wins":497},"GB2-02":{"draws":51,"losses":2,"wins":439},"GB2-03":{"draws":46,"losses":21,"wins":445},"GB2-04":{"draws":74,"losses":119,"wins":321},"GB2-05":{"draws":0,"losses":23,"wins":519},"GB2-06":{"draws":10,"losses":9,"wins":491},"GB2-07":{"draws":0,"losses":95,"wins":443},"GB2-08":{"draws":0,"losses":75,"wins":473}},"medium":{"GB2-01":{"draws":0,"losses":56,"wins":468},"GB2-02":{"draws":167,"losses":102,"wins":225},"GB2-03":{"draws":105,"losses":69,"wins":338},"GB2-04":{"draws":181,"losses":82,"wins":247},"GB2-05":{"draws":0,"losses":60,"wins":484},"GB2-06":{"draws":26,"losses":32,"wins":456},"GB2-07":{"draws":0,"losses":133,"wins":405},"GB2-08":{"draws":0,"losses":228,"wins":320}},"none":{"GB2-01":{"draws":0,"losses":46,"wins":482},"GB2-02":{"draws":154,"losses":45,"wins":299},"GB2-03":{"draws":24,"losses":79,"wins":407},"GB2-04":{"draws":154,"losses":55,"wins":303},"GB2-05":{"draws":0,"losses":70,"wins":472},"GB2-06":{"draws":18,"losses":52,"wins":444},"GB2-07":{"draws":0,"losses":237,"wins":305},"GB2-08":{"draws":0,"losses":141,"wins":403}}},"per_game_raw_elo_all":{"GB2-01":2067.6755968018497,"GB2-02":1790.2610654884584,"GB2-03":1896.5495024641848,"GB2-04":1662.986389678166,"GB2-05":2335.4398673941782,"GB2-06":2317.002742928056,"GB2-07":1781.3884165146258,"GB2-08":1845.7828840111476},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2162.85137207772,"GB2-02":2066.637253790577,"GB2-03":2080.211452989501,"GB2-04":1657.842003409101,"GB2-05":2570.064035548323,"GB2-06":2518.8481454914418,"GB2-07":1970.0922763066662,"GB2-08":2120.1565698401128},"medium":{"GB2-01":1995.1679992338231,"GB2-02":1588.794179975123,"GB2-03":1755.7764004614346,"GB2-04":1625.5231855396585,"GB2-05":2250.8283809703807,"GB2-06":2258.267898288448,"GB2-07":1825.9735371216168,"GB2-08":1564.2969035698623},"none":{"GB2-01":2045.0074190940059,"GB2-02":1715.3517626996756,"GB2-03":1853.6606539416189,"GB2-04":1705.5939800857384,"GB2-05":2185.4271856638316,"GB2-06":2173.892185004278,"GB2-07":1548.0994361155942,"GB2-08":1852.8951786234675}},"per_game_tracks":{"highest":{"GB2-01":94.66861896327353,"GB2-02":94.39855818079076,"GB2-03":91.55659322400427,"GB2-04":70.74565502383922,"GB2-05":95.43973831731314,"GB2-06":96.88323014326578,"GB2-07":82.31617474302877,"GB2-08":86.33176072754762},"medium":{"GB2-01":89.29858057221064,"GB2-02":63.669059937249685,"GB2-03":77.91937657445246,"GB2-04":67.43102888941571,"GB2-05":88.75033877915386,"GB2-06":91.0357040076817,"GB2-07":75.68783615647786,"GB2-08":59.82522303874266},"none":{"GB2-01":91.219361450832,"GB2-02":76.33666751394614,"GB2-03":83.29917482311647,"GB2-04":75.23317139769328,"GB2-05":86.97537709705149,"GB2-06":88.00136096526107,"GB2-07":57.79991513456548,"GB2-08":74.74138807336891}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":20,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-27T23:45:47Z","reasoning":{"highest":89.04254116538289,"medium":76.70214349442308,"none":79.20080205697934},"reasoning_agg":{"highest":{"max":96.88323014326578,"mean":89.04254116538289,"min":70.74565502383922},"medium":{"max":91.0357040076817,"mean":76.70214349442308,"min":59.82522303874266},"none":{"max":91.219361450832,"mean":79.20080205697934,"min":57.79991513456548}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":12.340397670959803},"working_program_strength":{"all":81.64849557226177,"highest":89.04254116538289,"medium":76.70214349442308,"none":79.20080205697934}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-1-terra:1050ec9aaab9c85b","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":0.12554674999999998,"mean":0.10675300000000001,"median":0.108693,"min":0.089838,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.8540239999999999},"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":0.047753000000000004,"mean":0.03952675,"median":0.03939425,"min":0.0330805,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.316214},"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":0.033728,"mean":0.026974875000000002,"median":0.026358625000000004,"min":0.023455499999999997,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.21579899999999996}},"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":0.047753000000000004,"mean":0.03952675,"median":0.03939425,"min":0.0330805,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.316214},"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":0.033728,"mean":0.026974875000000002,"median":0.026358625000000004,"min":0.023455499999999997,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.21579899999999996},"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":0.12554674999999998,"mean":0.10675300000000001,"median":0.108693,"min":0.089838,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.8540239999999999}},"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":0.12554674999999998,"mean":0.05775154166666668,"median":0.03939425,"min":0.023455499999999997,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":24},"run_count":24,"token_priced_attempt_count":24,"total":1.386037},"codegen_output_tokens":{"attempt_count":24,"output_max":23315,"output_mean":9592.583333333334,"output_min":2164,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":23315,"output_mean":19392.875,"output_min":16117,"run_count":8},"medium":{"attempt_count":8,"output_max":7519,"output_mean":5947.625,"output_min":4240,"run_count":8},"none":{"attempt_count":8,"output_max":4714,"output_mean":3437.25,"output_min":2164,"run_count":8}},"display_name":"GPT-6.1 Terra","economics":{"all":81.11095113977684,"highest":85.69361741245469,"medium":78.23026002216754,"none":79.40897598470833},"economics_best_value":{"per_model":{"all":true,"highest":true,"medium":true,"none":true},"per_setting":{"none":true}},"first_seen_at":"2026-11-03T07:10:34Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":24,"effective_max_output_tokens":[128000],"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,"requested_max_output_token_observations":24,"requested_max_output_tokens":[128000],"total_output_tokens":230222,"total_reasoning_output_tokens":132676,"total_visible_output_tokens":97546,"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":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6.1-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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":65.16078340922189,"score":65.16078340922189},"GB2-02":{"attempts":3,"playable":72.63548777478371,"score":72.63548777478371},"GB2-03":{"attempts":3,"playable":74.88824510734212,"score":74.88824510734212},"GB2-04":{"attempts":3,"playable":81.62443031474362,"score":81.62443031474362},"GB2-05":{"attempts":3,"playable":91.00316764918084,"score":91.00316764918084},"GB2-06":{"attempts":3,"playable":88.96063267751076,"score":88.96063267751076},"GB2-07":{"attempts":3,"playable":94.62022240725116,"score":94.62022240725116},"GB2-08":{"attempts":3,"playable":79.99463977818074,"score":79.99463977818074}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":73.43821740424055,"score":73.43821740424055},"GB2-02":{"attempts":1,"playable":76.83932574459934,"score":76.83932574459934},"GB2-03":{"attempts":1,"playable":88.31518366734909,"score":88.31518366734909},"GB2-04":{"attempts":1,"playable":83.6441992595,"score":83.6441992595},"GB2-05":{"attempts":1,"playable":95.07753693624103,"score":95.07753693624103},"GB2-06":{"attempts":1,"playable":89.90968532505246,"score":89.90968532505246},"GB2-07":{"attempts":1,"playable":96.96223715430621,"score":96.96223715430621},"GB2-08":{"attempts":1,"playable":81.36255380834878,"score":81.36255380834878}},"medium":{"GB2-01":{"attempts":1,"playable":61.29924193432552,"score":61.29924193432552},"GB2-02":{"attempts":1,"playable":70.45605767125073,"score":70.45605767125073},"GB2-03":{"attempts":1,"playable":59.54884490276625,"score":59.54884490276625},"GB2-04":{"attempts":1,"playable":78.27010036396689,"score":78.27010036396689},"GB2-05":{"attempts":1,"playable":90.07916350877821,"score":90.07916350877821},"GB2-06":{"attempts":1,"playable":90.56834048013012,"score":90.56834048013012},"GB2-07":{"attempts":1,"playable":95.6431915130611,"score":95.6431915130611},"GB2-08":{"attempts":1,"playable":79.97713980306155,"score":79.97713980306155}},"none":{"GB2-01":{"attempts":1,"playable":60.744890889099636,"score":60.744890889099636},"GB2-02":{"attempts":1,"playable":70.61107990850105,"score":70.61107990850105},"GB2-03":{"attempts":1,"playable":76.800706751911,"score":76.800706751911},"GB2-04":{"attempts":1,"playable":82.95899132076397,"score":82.95899132076397},"GB2-05":{"attempts":1,"playable":87.85280250252325,"score":87.85280250252325},"GB2-06":{"attempts":1,"playable":86.40387222734964,"score":86.40387222734964},"GB2-07":{"attempts":1,"playable":91.25523855438621,"score":91.25523855438621},"GB2-08":{"attempts":1,"playable":78.6442257231319,"score":78.6442257231319}}},"id":"gpt-6.1-terra","is_recent_addition":true,"last_measured_at":"2026-11-03T07:10:34Z","match_totals_all":{"draws":1457,"losses":1668,"wins":9415},"match_totals_tracks":{"highest":{"draws":343,"losses":429,"wins":3408},"medium":{"draws":600,"losses":623,"wins":2961},"none":{"draws":514,"losses":616,"wins":3046}},"model_slug":"gpt-6-1-terra","official_rank_by_reasoning":{"highest":7,"medium":6,"none":6},"overall":{"max":96.96223715430621,"mean":81.11095113977684,"min":59.54884490276625},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":7,"overall_ranking_status":"ranked","per_game":{"GB2-01":73.43821740424055,"GB2-02":76.83932574459934,"GB2-03":88.31518366734909,"GB2-04":83.6441992595,"GB2-05":95.07753693624103,"GB2-06":89.90968532505246,"GB2-07":96.96223715430621,"GB2-08":81.36255380834878},"per_game_all":{"GB2-01":65.16078340922189,"GB2-02":72.63548777478371,"GB2-03":74.88824510734212,"GB2-04":81.62443031474362,"GB2-05":91.00316764918084,"GB2-06":88.96063267751076,"GB2-07":94.62022240725116,"GB2-08":79.99463977818074},"per_game_match_totals_all":{"GB2-01":{"draws":213,"losses":446,"wins":917},"GB2-02":{"draws":642,"losses":98,"wins":736},"GB2-03":{"draws":331,"losses":246,"wins":959},"GB2-04":{"draws":185,"losses":202,"wins":1151},"GB2-05":{"draws":0,"losses":143,"wins":1487},"GB2-06":{"draws":86,"losses":125,"wins":1331},"GB2-07":{"draws":0,"losses":77,"wins":1541},"GB2-08":{"draws":0,"losses":331,"wins":1293}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":38,"losses":121,"wins":365},"GB2-02":{"draws":183,"losses":27,"wins":282},"GB2-03":{"draws":59,"losses":33,"wins":420},"GB2-04":{"draws":45,"losses":65,"wins":404},"GB2-05":{"draws":0,"losses":25,"wins":519},"GB2-06":{"draws":18,"losses":42,"wins":454},"GB2-07":{"draws":0,"losses":13,"wins":525},"GB2-08":{"draws":0,"losses":103,"wins":439}},"medium":{"GB2-01":{"draws":80,"losses":165,"wins":281},"GB2-02":{"draws":214,"losses":43,"wins":233},"GB2-03":{"draws":183,"losses":130,"wins":201},"GB2-04":{"draws":90,"losses":71,"wins":351},"GB2-05":{"draws":0,"losses":53,"wins":493},"GB2-06":{"draws":33,"losses":31,"wins":452},"GB2-07":{"draws":0,"losses":20,"wins":520},"GB2-08":{"draws":0,"losses":110,"wins":430}},"none":{"GB2-01":{"draws":95,"losses":160,"wins":271},"GB2-02":{"draws":245,"losses":28,"wins":221},"GB2-03":{"draws":89,"losses":83,"wins":338},"GB2-04":{"draws":50,"losses":66,"wins":396},"GB2-05":{"draws":0,"losses":65,"wins":475},"GB2-06":{"draws":35,"losses":52,"wins":425},"GB2-07":{"draws":0,"losses":44,"wins":496},"GB2-08":{"draws":0,"losses":118,"wins":424}}},"per_game_raw_elo_all":{"GB2-01":1641.8482624816204,"GB2-02":1675.7011551294827,"GB2-03":1747.9422217830827,"GB2-04":1786.9692913205836,"GB2-05":2355.6497603028743,"GB2-06":2201.2800402255175,"GB2-07":2479.259772674431,"GB2-08":1967.7917437592123},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1733.805042095238,"GB2-02":1721.2630043857375,"GB2-03":1975.065981211471,"GB2-04":1814.9056936851466,"GB2-05":2546.724205922827,"GB2-06":2225.0902471371874,"GB2-07":2622.8183491680466,"GB2-08":1998.7925837531604},"medium":{"GB2-01":1598.7014557601701,"GB2-02":1652.1460150322716,"GB2-03":1530.566157039888,"GB2-04":1741.394979699202,"GB2-05":2303.023630672364,"GB2-06":2244.17631938703,"GB2-07":2527.2824628922103,"GB2-08":1967.1864435946236},"none":{"GB2-01":1593.0382895894525,"GB2-02":1653.6944459704391,"GB2-03":1738.194527097889,"GB2-04":1804.6072005774017,"GB2-05":2217.201444313431,"GB2-06":2134.573554152334,"GB2-07":2287.6785059630374,"GB2-08":1937.396203929853}},"per_game_tracks":{"highest":{"GB2-01":73.43821740424055,"GB2-02":76.83932574459934,"GB2-03":88.31518366734909,"GB2-04":83.6441992595,"GB2-05":95.07753693624103,"GB2-06":89.90968532505246,"GB2-07":96.96223715430621,"GB2-08":81.36255380834878},"medium":{"GB2-01":61.29924193432552,"GB2-02":70.45605767125073,"GB2-03":59.54884490276625,"GB2-04":78.27010036396689,"GB2-05":90.07916350877821,"GB2-06":90.56834048013012,"GB2-07":95.6431915130611,"GB2-08":79.97713980306155},"none":{"GB2-01":60.744890889099636,"GB2-02":70.61107990850105,"GB2-03":76.800706751911,"GB2-04":82.95899132076397,"GB2-05":87.85280250252325,"GB2-06":86.40387222734964,"GB2-07":91.25523855438621,"GB2-08":78.6442257231319}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":24,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":85.69361741245469,"medium":78.23026002216754,"none":79.40897598470833},"reasoning_agg":{"highest":{"max":96.96223715430621,"mean":85.69361741245469,"min":73.43821740424055},"medium":{"max":95.6431915130611,"mean":78.23026002216754,"min":59.54884490276625},"none":{"max":91.25523855438621,"mean":79.40897598470833,"min":60.744890889099636}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":7.463357390287143},"working_program_strength":{"all":81.11095113977684,"highest":85.69361741245469,"medium":78.23026002216754,"none":79.40897598470833}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3-1-pro:2810148fb3ae3498","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":0.520818,"mean":0.45841275000000004,"median":0.456374,"min":0.383384,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":3.6673020000000003},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.228888,"mean":0.1761925,"median":0.1786566,"min":0.1389952,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":1.4095400000000002},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.31477,"mean":0.2003284,"median":0.218258,"min":0.093456,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":1.6026272000000001}},"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":0.228888,"mean":0.1761925,"median":0.1786566,"min":0.1389952,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":1.40954},"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":0.31477,"mean":0.2003284,"median":0.218258,"min":0.093456,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":1.6026272000000001},"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":0.520818,"mean":0.45841275000000004,"median":0.456374,"min":0.383384,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":3.6673019999999994}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.520818,"mean":0.2783112166666667,"median":0.227979,"min":0.093456,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":24},"recorded_attempt_count":24,"run_count":24,"total":6.6794692000000015},"codegen_latency_ms":{"attempt_count":24,"max_ms":1025651,"mean_ms":549120.875,"min_ms":169165,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":1025651,"mean_ms":925239.125,"min_ms":802488,"run_count":8},"medium":{"attempt_count":8,"max_ms":423651,"mean_ms":338545.75,"min_ms":271597,"run_count":8},"none":{"attempt_count":8,"max_ms":617894,"mean_ms":383577.75,"min_ms":169165,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":50450,"output_mean":26378.708333333332,"output_min":7904,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":50450,"output_mean":44271.875,"output_min":36897,"run_count":8},"medium":{"attempt_count":8,"output_max":20868,"output_mean":16395.25,"output_min":12584,"run_count":8},"none":{"attempt_count":8,"output_max":29982,"output_mean":18469.0,"output_min":7904,"run_count":8}},"display_name":"Kimi K3.1 Pro","economics":{"all":78.21590642873734,"highest":83.95265700359703,"medium":71.53879490033779,"none":79.15626738227719},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":24,"effective_max_output_tokens":[943718],"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,"requested_max_output_token_observations":24,"requested_max_output_tokens":[943718],"total_output_tokens":633089,"total_reasoning_output_tokens":510905,"total_visible_output_tokens":122184,"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":943718,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3.1-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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":64.55037702003486,"score":64.55037702003486},"GB2-02":{"attempts":3,"playable":78.33110403576026,"score":78.33110403576026},"GB2-03":{"attempts":3,"playable":62.54033085322203,"score":62.54033085322203},"GB2-04":{"attempts":3,"playable":80.33284264572536,"score":80.33284264572536},"GB2-05":{"attempts":3,"playable":82.9450912500067,"score":82.9450912500067},"GB2-06":{"attempts":3,"playable":87.54384156114469,"score":87.54384156114469},"GB2-07":{"attempts":3,"playable":77.7506347383664,"score":77.7506347383664},"GB2-08":{"attempts":3,"playable":91.73302932563831,"score":91.73302932563831}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":91.87427483434708,"score":91.87427483434708},"GB2-02":{"attempts":1,"playable":78.76036074480821,"score":78.76036074480821},"GB2-03":{"attempts":1,"playable":85.68180521073339,"score":85.68180521073339},"GB2-04":{"attempts":1,"playable":82.58467784027317,"score":82.58467784027317},"GB2-05":{"attempts":1,"playable":88.7427973802502,"score":88.7427973802502},"GB2-06":{"attempts":1,"playable":82.1968788812733,"score":82.1968788812733},"GB2-07":{"attempts":1,"playable":72.28912270619205,"score":72.28912270619205},"GB2-08":{"attempts":1,"playable":89.49133843089871,"score":89.49133843089871}},"medium":{"GB2-01":{"attempts":1,"playable":59.98633635157289,"score":59.98633635157289},"GB2-02":{"attempts":1,"playable":74.51183060895143,"score":74.51183060895143},"GB2-03":{"attempts":1,"playable":14.995697093326946,"score":14.995697093326946},"GB2-04":{"attempts":1,"playable":81.27404122743167,"score":81.27404122743167},"GB2-05":{"attempts":1,"playable":77.7609018095286,"score":77.7609018095286},"GB2-06":{"attempts":1,"playable":89.88916808882026,"score":89.88916808882026},"GB2-07":{"attempts":1,"playable":83.18840548520843,"score":83.18840548520843},"GB2-08":{"attempts":1,"playable":90.70397853786208,"score":90.70397853786208}},"none":{"GB2-01":{"attempts":1,"playable":41.79051987418461,"score":41.79051987418461},"GB2-02":{"attempts":1,"playable":81.72112075352115,"score":81.72112075352115},"GB2-03":{"attempts":1,"playable":86.94349025560575,"score":86.94349025560575},"GB2-04":{"attempts":1,"playable":77.13980886947124,"score":77.13980886947124},"GB2-05":{"attempts":1,"playable":82.33157456024131,"score":82.33157456024131},"GB2-06":{"attempts":1,"playable":90.5454777133405,"score":90.5454777133405},"GB2-07":{"attempts":1,"playable":77.7743760236987,"score":77.7743760236987},"GB2-08":{"attempts":1,"playable":95.00377100815419,"score":95.00377100815419}}},"id":"moonshotai/kimi-k3.1-pro","is_recent_addition":false,"last_measured_at":"2026-11-03T07:06:54Z","match_totals_all":{"draws":1234,"losses":2151,"wins":9170},"match_totals_tracks":{"highest":{"draws":356,"losses":507,"wins":3331},"medium":{"draws":486,"losses":954,"wins":2747},"none":{"draws":392,"losses":690,"wins":3092}},"model_slug":"moonshotai-kimi-k3-1-pro","official_rank_by_reasoning":{"highest":10,"medium":11,"none":8},"overall":{"max":95.00377100815419,"mean":78.21590642873734,"min":14.995697093326946},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":8,"overall_ranking_status":"ranked","per_game":{"GB2-01":91.87427483434708,"GB2-02":78.76036074480821,"GB2-03":85.68180521073339,"GB2-04":82.58467784027317,"GB2-05":88.7427973802502,"GB2-06":82.1968788812733,"GB2-07":72.28912270619205,"GB2-08":89.49133843089871},"per_game_all":{"GB2-01":64.55037702003486,"GB2-02":78.33110403576026,"GB2-03":62.54033085322203,"GB2-04":80.33284264572536,"GB2-05":82.9450912500067,"GB2-06":87.54384156114469,"GB2-07":77.7506347383664,"GB2-08":91.73302932563831},"per_game_match_totals_all":{"GB2-01":{"draws":349,"losses":390,"wins":847},"GB2-02":{"draws":393,"losses":137,"wins":954},"GB2-03":{"draws":74,"losses":552,"wins":915},"GB2-04":{"draws":359,"losses":135,"wins":1038},"GB2-05":{"draws":0,"losses":279,"wins":1347},"GB2-06":{"draws":59,"losses":161,"wins":1320},"GB2-07":{"draws":0,"losses":364,"wins":1256},"GB2-08":{"draws":0,"losses":133,"wins":1493}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":42,"wins":487},"GB2-02":{"draws":151,"losses":34,"wins":313},"GB2-03":{"draws":68,"losses":44,"wins":406},"GB2-04":{"draws":118,"losses":34,"wins":360},"GB2-05":{"draws":0,"losses":60,"wins":480},"GB2-06":{"draws":18,"losses":83,"wins":411},"GB2-07":{"draws":0,"losses":153,"wins":389},"GB2-08":{"draws":0,"losses":57,"wins":485}},"medium":{"GB2-01":{"draws":225,"losses":99,"wins":202},"GB2-02":{"draws":128,"losses":67,"wins":301},"GB2-03":{"draws":1,"losses":440,"wins":68},"GB2-04":{"draws":106,"losses":47,"wins":359},"GB2-05":{"draws":0,"losses":123,"wins":423},"GB2-06":{"draws":26,"losses":38,"wins":452},"GB2-07":{"draws":0,"losses":90,"wins":450},"GB2-08":{"draws":0,"losses":50,"wins":492}},"none":{"GB2-01":{"draws":123,"losses":249,"wins":158},"GB2-02":{"draws":114,"losses":36,"wins":340},"GB2-03":{"draws":5,"losses":68,"wins":441},"GB2-04":{"draws":135,"losses":54,"wins":319},"GB2-05":{"draws":0,"losses":96,"wins":444},"GB2-06":{"draws":15,"losses":40,"wins":457},"GB2-07":{"draws":0,"losses":121,"wins":417},"GB2-08":{"draws":0,"losses":26,"wins":516}}},"per_game_raw_elo_all":{"GB2-01":1685.7316408818333,"GB2-02":1741.3276138673427,"GB2-03":1643.555039590504,"GB2-04":1769.115974919718,"GB2-05":2064.0130533521956,"GB2-06":2169.5922918709125,"GB2-07":1875.0425197211964,"GB2-08":2290.6166080969274},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2064.0196361502826,"GB2-02":1744.7935221994603,"GB2-03":1906.5738914150077,"GB2-04":1799.113775464123,"GB2-05":2250.5407501892987,"GB2-06":2040.7686286851253,"GB2-07":1765.2480898747594,"GB2-08":2208.486041537824},"medium":{"GB2-01":1585.3352321918942,"GB2-02":1694.6439625563783,"GB2-03":1086.2163922891157,"GB2-04":1780.5542603814474,"GB2-05":1908.3217560601954,"GB2-06":2224.5090027659653,"GB2-07":1993.0703493631156,"GB2-08":2246.3809917088815},"none":{"GB2-01":1407.8400543033229,"GB2-02":1784.5453568461899,"GB2-03":1937.8748350673886,"GB2-04":1727.6798889135835,"GB2-05":2033.1766538070935,"GB2-06":2243.4992441616464,"GB2-07":1866.8091199257137,"GB2-08":2416.982791044077}},"per_game_tracks":{"highest":{"GB2-01":91.87427483434708,"GB2-02":78.76036074480821,"GB2-03":85.68180521073339,"GB2-04":82.58467784027317,"GB2-05":88.7427973802502,"GB2-06":82.1968788812733,"GB2-07":72.28912270619205,"GB2-08":89.49133843089871},"medium":{"GB2-01":59.98633635157289,"GB2-02":74.51183060895143,"GB2-03":14.995697093326946,"GB2-04":81.27404122743167,"GB2-05":77.7609018095286,"GB2-06":89.88916808882026,"GB2-07":83.18840548520843,"GB2-08":90.70397853786208},"none":{"GB2-01":41.79051987418461,"GB2-02":81.72112075352115,"GB2-03":86.94349025560575,"GB2-04":77.13980886947124,"GB2-05":82.33157456024131,"GB2-06":90.5454777133405,"GB2-07":77.7743760236987,"GB2-08":95.00377100815419}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":24,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":-2,"rank_movement_baseline_at":"2026-10-27T23:46:32Z","reasoning":{"highest":83.95265700359703,"medium":71.53879490033779,"none":79.15626738227719},"reasoning_agg":{"highest":{"max":91.87427483434708,"mean":83.95265700359703,"min":72.28912270619205},"medium":{"max":90.70397853786208,"mean":71.53879490033779,"min":14.995697093326946},"none":{"max":95.00377100815419,"mean":79.15626738227719,"min":41.79051987418461}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":12.413862103259234},"working_program_strength":{"all":78.21590642873734,"highest":83.95265700359703,"medium":71.53879490033779,"none":79.15626738227719}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5:fa5332f27167944a","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":7.138875000000001},"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":4.570124999999999},"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":33.78345000000001},"codegen_latency_ms":{"attempt_count":48,"max_ms":999214,"mean_ms":286075.0416666667,"min_ms":51907,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":999214,"mean_ms":596693.625,"min_ms":340056,"run_count":16},"medium":{"attempt_count":16,"max_ms":302283,"mean_ms":172049.4375,"min_ms":111251,"run_count":16},"none":{"attempt_count":16,"max_ms":344404,"mean_ms":89482.0625,"min_ms":51907,"run_count":16}},"codegen_output_tokens":{"attempt_count":48,"output_max":88360,"output_mean":25640.5,"output_min":5404,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":88360,"output_mean":52673.75,"output_min":31102,"run_count":16},"medium":{"attempt_count":16,"output_max":25625,"output_mean":15334.8125,"output_min":9676,"run_count":16},"none":{"attempt_count":16,"output_max":28699,"output_mean":8912.9375,"output_min":5404,"run_count":16}},"display_name":"Claude Opus 5","economics":{"all":76.5573818079521,"highest":84.70479738027635,"medium":75.06843339756269,"none":69.89891464601723},"first_seen_at":null,"game_gaps":{"highest":{"GB2-06":"too_slow"},"medium":{"GB2-06":"too_slow"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":71.10433636506615,"score":71.10433636506615},"GB2-02":{"attempts":6,"playable":73.81879812255629,"score":73.81879812255629},"GB2-03":{"attempts":6,"playable":76.00681810680793,"score":76.00681810680793},"GB2-04":{"attempts":6,"playable":57.83281755233448,"score":57.83281755233448},"GB2-05":{"attempts":6,"playable":88.69354873544053,"score":88.69354873544053},"GB2-06":{"attempts":1,"playable":86.165615835979,"score":86.165615835979},"GB2-07":{"attempts":4,"playable":83.83619160430409,"score":83.83619160430409},"GB2-08":{"attempts":6,"playable":79.18692843916791,"score":79.18692843916791}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":68.48487648507606,"score":68.48487648507606},"GB2-02":{"attempts":2,"playable":82.07292471506443,"score":82.07292471506443},"GB2-03":{"attempts":2,"playable":93.28749939543773,"score":93.28749939543773},"GB2-04":{"attempts":2,"playable":79.45654789540566,"score":79.45654789540566},"GB2-05":{"attempts":2,"playable":91.99765733729924,"score":91.99765733729924},"GB2-07":{"attempts":1,"playable":95.26907160084427,"score":95.26907160084427},"GB2-08":{"attempts":2,"playable":82.36500423280701,"score":82.36500423280701}},"medium":{"GB2-01":{"attempts":2,"playable":69.50699185370023,"score":69.50699185370023},"GB2-02":{"attempts":2,"playable":68.9312560766584,"score":68.9312560766584},"GB2-03":{"attempts":2,"playable":84.91747145377292,"score":84.91747145377292},"GB2-04":{"attempts":2,"playable":45.85902320164814,"score":45.85902320164814},"GB2-05":{"attempts":2,"playable":86.95614063980446,"score":86.95614063980446},"GB2-07":{"attempts":2,"playable":82.28017205288373,"score":82.28017205288373},"GB2-08":{"attempts":2,"playable":87.02797850447104,"score":87.02797850447104}},"none":{"GB2-01":{"attempts":2,"playable":75.32114075642214,"score":75.32114075642214},"GB2-02":{"attempts":2,"playable":70.452213575946,"score":70.452213575946},"GB2-03":{"attempts":2,"playable":49.81548347121313,"score":49.81548347121313},"GB2-04":{"attempts":2,"playable":48.18288155994962,"score":48.18288155994962},"GB2-05":{"attempts":2,"playable":87.12684822921793,"score":87.12684822921793},"GB2-06":{"attempts":1,"playable":86.165615835979,"score":86.165615835979},"GB2-07":{"attempts":1,"playable":73.95933115918429,"score":73.95933115918429},"GB2-08":{"attempts":2,"playable":68.16780258022574,"score":68.16780258022574}}},"id":"claude-opus-5","is_recent_addition":false,"last_measured_at":"2026-11-03T07:16:07Z","match_totals_all":{"draws":2756,"losses":3926,"wins":14778},"match_totals_tracks":{"highest":{"draws":401,"losses":902,"wins":5497},"medium":{"draws":1016,"losses":1337,"wins":4995},"none":{"draws":1339,"losses":1687,"wins":4286}},"model_slug":"claude-opus-5","official_rank_by_reasoning":{"highest":9,"medium":8,"none":11},"overall":{"max":95.26907160084427,"mean":76.5573818079521,"min":45.85902320164814},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":9,"overall_ranking_status":"ranked","per_game":{"GB2-01":68.48487648507606,"GB2-02":82.07292471506443,"GB2-03":93.28749939543773,"GB2-04":79.45654789540566,"GB2-05":91.99765733729924,"GB2-07":95.26907160084427,"GB2-08":82.36500423280701},"per_game_all":{"GB2-01":71.10433636506615,"GB2-02":73.81879812255629,"GB2-03":76.00681810680793,"GB2-04":57.83281755233448,"GB2-05":88.69354873544053,"GB2-07":83.83619160430409,"GB2-08":79.18692843916791},"per_game_match_totals_all":{"GB2-01":{"draws":474,"losses":678,"wins":2008},"GB2-02":{"draws":1037,"losses":286,"wins":1643},"GB2-03":{"draws":166,"losses":693,"wins":2221},"GB2-04":{"draws":1030,"losses":814,"wins":1220},"GB2-05":{"draws":0,"losses":363,"wins":2893},"GB2-06":{"draws":24,"losses":59,"wins":435},"GB2-07":{"draws":0,"losses":356,"wins":1806},"GB2-08":{"draws":25,"losses":677,"wins":2552}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":17,"losses":324,"wins":715},"GB2-02":{"draws":198,"losses":84,"wins":704},"GB2-03":{"draws":13,"losses":62,"wins":949},"GB2-04":{"draws":173,"losses":132,"wins":715},"GB2-05":{"draws":0,"losses":84,"wins":1002},"GB2-07":{"draws":0,"losses":22,"wins":518},"GB2-08":{"draws":0,"losses":194,"wins":894}},"medium":{"GB2-01":{"draws":100,"losses":273,"wins":683},"GB2-02":{"draws":438,"losses":99,"wins":451},"GB2-03":{"draws":19,"losses":155,"wins":858},"GB2-04":{"draws":457,"losses":339,"wins":228},"GB2-05":{"draws":0,"losses":140,"wins":942},"GB2-07":{"draws":0,"losses":191,"wins":891},"GB2-08":{"draws":2,"losses":140,"wins":942}},"none":{"GB2-01":{"draws":357,"losses":81,"wins":610},"GB2-02":{"draws":401,"losses":103,"wins":488},"GB2-03":{"draws":134,"losses":476,"wins":414},"GB2-04":{"draws":400,"losses":343,"wins":277},"GB2-05":{"draws":0,"losses":139,"wins":949},"GB2-06":{"draws":24,"losses":59,"wins":435},"GB2-07":{"draws":0,"losses":143,"wins":397},"GB2-08":{"draws":23,"losses":343,"wins":716}}},"per_game_raw_elo_all":{"GB2-01":1745.050688191326,"GB2-02":1695.9372006889373,"GB2-03":1826.8931126556545,"GB2-04":1558.4096862092213,"GB2-05":2315.787309213092,"GB2-07":2107.572173455759,"GB2-08":1969.2883626516148},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1742.3276399556348,"GB2-02":1796.2083847551908,"GB2-03":2152.4803019607843,"GB2-04":1766.0593227282166,"GB2-05":2558.897905357508,"GB2-07":2503.3598243449114,"GB2-08":2033.1576741614524},"medium":{"GB2-01":1697.548353785437,"GB2-02":1637.2154049651504,"GB2-03":1888.8471468171808,"GB2-04":1445.1683087365113,"GB2-05":2197.534419355705,"GB2-07":2025.031956486774,"GB2-08":2154.692950804181},"none":{"GB2-01":1795.2760708329056,"GB2-02":1654.387812346471,"GB2-03":1439.3518891889985,"GB2-04":1464.001427162936,"GB2-05":2190.929602926064,"GB2-06":2128.9255308234497,"GB2-07":1794.3247395355918,"GB2-08":1720.0144629892113}},"per_game_tracks":{"highest":{"GB2-01":68.48487648507606,"GB2-02":82.07292471506443,"GB2-03":93.28749939543773,"GB2-04":79.45654789540566,"GB2-05":91.99765733729924,"GB2-07":95.26907160084427,"GB2-08":82.36500423280701},"medium":{"GB2-01":69.50699185370023,"GB2-02":68.9312560766584,"GB2-03":84.91747145377292,"GB2-04":45.85902320164814,"GB2-05":86.95614063980446,"GB2-07":82.28017205288373,"GB2-08":87.02797850447104},"none":{"GB2-01":75.32114075642214,"GB2-02":70.452213575946,"GB2-03":49.81548347121313,"GB2-04":48.18288155994962,"GB2-05":87.12684822921793,"GB2-06":86.165615835979,"GB2-07":73.95933115918429,"GB2-08":68.16780258022574}},"program_outcomes":{"all":{"counted_attempts":41,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":7,"worked_after_repair":0,"worked_first_time":41,"working":41},"highest":{"counted_attempts":13,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":3,"worked_after_repair":0,"worked_first_time":13,"working":13},"medium":{"counted_attempts":14,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":2,"worked_after_repair":0,"worked_first_time":14,"working":14},"none":{"counted_attempts":14,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":2,"worked_after_repair":0,"worked_first_time":14,"working":14}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-31T17:13:06Z","reasoning":{"highest":84.70479738027635,"medium":75.06843339756269,"none":69.89891464601723},"reasoning_agg":{"highest":{"max":95.26907160084427,"mean":84.70479738027635,"min":68.48487648507606},"medium":{"max":87.02797850447104,"mean":75.06843339756269,"min":45.85902320164814},"none":{"max":87.12684822921793,"mean":69.89891464601723,"min":48.18288155994962}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":14.805882734259114},"working_program_strength":{"all":76.5573818079521,"highest":84.70479738027635,"medium":75.06843339756269,"none":69.89891464601723}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-sol:b754b73699a66f23","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":0.6265165000000001},"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":0.34556800000000004}},"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":0.6265165000000001},"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":72.88024544511332,"highest":79.2956265420889,"medium":74.53533490097121,"none":64.80977489227985},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":35.136399647872814,"score":35.136399647872814},"GB2-02":{"attempts":3,"playable":67.36427321774111,"score":67.36427321774111},"GB2-03":{"attempts":3,"playable":81.79831328626621,"score":81.79831328626621},"GB2-04":{"attempts":3,"playable":67.12520703960656,"score":67.12520703960656},"GB2-05":{"attempts":3,"playable":86.02597090875365,"score":86.02597090875365},"GB2-06":{"attempts":3,"playable":79.18114046433175,"score":79.18114046433175},"GB2-07":{"attempts":3,"playable":80.73407972369628,"score":80.73407972369628},"GB2-08":{"attempts":3,"playable":85.6765792726382,"score":85.6765792726382}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":9.6929848606595,"score":9.6929848606595},"GB2-02":{"attempts":1,"playable":82.13950566150106,"score":82.13950566150106},"GB2-03":{"attempts":1,"playable":93.07209382935443,"score":93.07209382935443},"GB2-04":{"attempts":1,"playable":87.4046433151378,"score":87.4046433151378},"GB2-05":{"attempts":1,"playable":93.05282747567438,"score":93.05282747567438},"GB2-06":{"attempts":1,"playable":88.12191959630647,"score":88.12191959630647},"GB2-07":{"attempts":1,"playable":93.42408341051319,"score":93.42408341051319},"GB2-08":{"attempts":1,"playable":87.45695418756445,"score":87.45695418756445}},"medium":{"GB2-01":{"attempts":1,"playable":37.496606446975534,"score":37.496606446975534},"GB2-02":{"attempts":1,"playable":67.92832552764254,"score":67.92832552764254},"GB2-03":{"attempts":1,"playable":72.6757427245617,"score":72.6757427245617},"GB2-04":{"attempts":1,"playable":71.53664938722638,"score":71.53664938722638},"GB2-05":{"attempts":1,"playable":90.34377125021624,"score":90.34377125021624},"GB2-06":{"attempts":1,"playable":78.65171285953568,"score":78.65171285953568},"GB2-07":{"attempts":1,"playable":92.69521536086322,"score":92.69521536086322},"GB2-08":{"attempts":1,"playable":84.9546556507483,"score":84.9546556507483}},"none":{"GB2-01":{"attempts":1,"playable":58.219607635983394,"score":58.219607635983394},"GB2-02":{"attempts":1,"playable":52.024988464079726,"score":52.024988464079726},"GB2-03":{"attempts":1,"playable":79.6471033048825,"score":79.6471033048825},"GB2-04":{"attempts":1,"playable":42.434328416455486,"score":42.434328416455486},"GB2-05":{"attempts":1,"playable":74.68131400037029,"score":74.68131400037029},"GB2-06":{"attempts":1,"playable":70.76978893715311,"score":70.76978893715311},"GB2-07":{"attempts":1,"playable":56.08294039971244,"score":56.08294039971244},"GB2-08":{"attempts":1,"playable":84.61812797960181,"score":84.61812797960181}}},"id":"gpt-6-sol","is_recent_addition":false,"last_measured_at":"2026-11-03T07:14:29Z","match_totals_all":{"draws":1588,"losses":2654,"wins":8316},"match_totals_tracks":{"highest":{"draws":254,"losses":739,"wins":3191},"medium":{"draws":628,"losses":766,"wins":2796},"none":{"draws":706,"losses":1149,"wins":2329}},"model_slug":"gpt-6-sol","official_rank_by_reasoning":{"highest":12,"medium":9,"none":12},"overall":{"max":93.42408341051319,"mean":72.88024544511332,"min":9.6929848606595},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":10,"overall_ranking_status":"ranked","per_game":{"GB2-01":9.6929848606595,"GB2-02":82.13950566150106,"GB2-03":93.07209382935443,"GB2-04":87.4046433151378,"GB2-05":93.05282747567438,"GB2-06":88.12191959630647,"GB2-07":93.42408341051319,"GB2-08":87.45695418756445},"per_game_all":{"GB2-01":35.136399647872814,"GB2-02":67.36427321774111,"GB2-03":81.79831328626621,"GB2-04":67.12520703960656,"GB2-05":86.02597090875365,"GB2-06":79.18114046433175,"GB2-07":80.73407972369628,"GB2-08":85.6765792726382},"per_game_match_totals_all":{"GB2-01":{"draws":207,"losses":925,"wins":446},"GB2-02":{"draws":674,"losses":163,"wins":651},"GB2-03":{"draws":81,"losses":258,"wins":1205},"GB2-04":{"draws":520,"losses":259,"wins":753},"GB2-05":{"draws":0,"losses":227,"wins":1399},"GB2-06":{"draws":95,"losses":279,"wins":1166},"GB2-07":{"draws":0,"losses":314,"wins":1310},"GB2-08":{"draws":11,"losses":229,"wins":1386}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":31,"losses":460,"wins":33},"GB2-02":{"draws":141,"losses":21,"wins":334},"GB2-03":{"draws":5,"losses":33,"wins":478},"GB2-04":{"draws":54,"losses":40,"wins":416},"GB2-05":{"draws":0,"losses":36,"wins":506},"GB2-06":{"draws":23,"losses":49,"wins":440},"GB2-07":{"draws":0,"losses":32,"wins":512},"GB2-08":{"draws":0,"losses":68,"wins":472}},"medium":{"GB2-01":{"draws":160,"losses":252,"wins":116},"GB2-02":{"draws":226,"losses":52,"wins":220},"GB2-03":{"draws":42,"losses":130,"wins":342},"GB2-04":{"draws":155,"losses":74,"wins":283},"GB2-05":{"draws":0,"losses":51,"wins":489},"GB2-06":{"draws":39,"losses":92,"wins":385},"GB2-07":{"draws":0,"losses":36,"wins":504},"GB2-08":{"draws":6,"losses":79,"wins":457}},"none":{"GB2-01":{"draws":16,"losses":213,"wins":297},"GB2-02":{"draws":307,"losses":90,"wins":97},"GB2-03":{"draws":34,"losses":95,"wins":385},"GB2-04":{"draws":311,"losses":145,"wins":54},"GB2-05":{"draws":0,"losses":140,"wins":404},"GB2-06":{"draws":33,"losses":138,"wins":341},"GB2-07":{"draws":0,"losses":246,"wins":294},"GB2-08":{"draws":5,"losses":82,"wins":457}}},"per_game_raw_elo_all":{"GB2-01":1306.5326720623486,"GB2-02":1636.9452323889782,"GB2-03":1868.259338216244,"GB2-04":1654.121728126823,"GB2-05":2195.258882710729,"GB2-06":1987.385178972793,"GB2-07":2093.507434065495,"GB2-08":2103.8884709714935},"per_game_raw_elo_tracks":{"highest":{"GB2-01":986.6789612701613,"GB2-02":1790.5707500031122,"GB2-03":2140.9102304568887,"GB2-04":1878.2690340971883,"GB2-05":2434.960816340879,"GB2-06":2176.975058899426,"GB2-07":2397.0301492220938,"GB2-08":2150.2341437768005},"medium":{"GB2-01":1365.3381500013543,"GB2-02":1627.6088332293393,"GB2-03":1679.283473813499,"GB2-04":1665.8894754883365,"GB2-05":2313.814101902944,"GB2-06":1968.2765432447754,"GB2-07":2358.7504298348463,"GB2-08":2084.9112025998525},"none":{"GB2-01":1567.5809049155303,"GB2-02":1492.6561139344828,"GB2-03":1784.5843103783443,"GB2-04":1418.2066747949443,"GB2-05":1837.0017298883643,"GB2-06":1816.9039347741773,"GB2-07":1524.7417231395448,"GB2-08":2076.520066537828}},"per_game_tracks":{"highest":{"GB2-01":9.6929848606595,"GB2-02":82.13950566150106,"GB2-03":93.07209382935443,"GB2-04":87.4046433151378,"GB2-05":93.05282747567438,"GB2-06":88.12191959630647,"GB2-07":93.42408341051319,"GB2-08":87.45695418756445},"medium":{"GB2-01":37.496606446975534,"GB2-02":67.92832552764254,"GB2-03":72.6757427245617,"GB2-04":71.53664938722638,"GB2-05":90.34377125021624,"GB2-06":78.65171285953568,"GB2-07":92.69521536086322,"GB2-08":84.9546556507483},"none":{"GB2-01":58.219607635983394,"GB2-02":52.024988464079726,"GB2-03":79.6471033048825,"GB2-04":42.434328416455486,"GB2-05":74.68131400037029,"GB2-06":70.76978893715311,"GB2-07":56.08294039971244,"GB2-08":84.61812797960181}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":23,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-31T17:15:04Z","reasoning":{"highest":79.2956265420889,"medium":74.53533490097121,"none":64.80977489227985},"reasoning_agg":{"highest":{"max":93.42408341051319,"mean":79.2956265420889,"min":9.6929848606595},"medium":{"max":92.69521536086322,"mean":74.53533490097121,"min":37.496606446975534},"none":{"max":84.61812797960181,"mean":64.80977489227985,"min":42.434328416455486}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":14.48585164980905},"working_program_strength":{"all":72.88024544511332,"highest":79.2956265420889,"medium":74.53533490097121,"none":64.80977489227985}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-sol:3d87e03198419df8","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":9.22798375},"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":66.73017914228382,"highest":79.58534119765571,"medium":65.75491483322462,"none":54.85028139597112},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":72.9532325911872,"score":72.9532325911872},"GB2-02":{"attempts":3,"playable":61.98602783892685,"score":61.98602783892685},"GB2-03":{"attempts":3,"playable":62.9078111189771,"score":62.9078111189771},"GB2-04":{"attempts":3,"playable":66.69112250442704,"score":66.69112250442704},"GB2-05":{"attempts":3,"playable":65.94610977735238,"score":65.94610977735238},"GB2-06":{"attempts":3,"playable":59.953416076094506,"score":59.953416076094506},"GB2-07":{"attempts":3,"playable":67.34388190494228,"score":67.34388190494228},"GB2-08":{"attempts":3,"playable":76.05983132636317,"score":76.05983132636317}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":73.91555522136504,"score":73.91555522136504},"GB2-02":{"attempts":1,"playable":75.26970595439437,"score":75.26970595439437},"GB2-03":{"attempts":1,"playable":77.22098567844743,"score":77.22098567844743},"GB2-04":{"attempts":1,"playable":82.07745401136162,"score":82.07745401136162},"GB2-05":{"attempts":1,"playable":73.49889108163175,"score":73.49889108163175},"GB2-06":{"attempts":1,"playable":82.84946140510947,"score":82.84946140510947},"GB2-07":{"attempts":1,"playable":86.67937935151342,"score":86.67937935151342},"GB2-08":{"attempts":1,"playable":85.17129687742255,"score":85.17129687742255}},"medium":{"GB2-01":{"attempts":1,"playable":67.06302785283923,"score":67.06302785283923},"GB2-02":{"attempts":1,"playable":66.3556975056672,"score":66.3556975056672},"GB2-03":{"attempts":1,"playable":59.76432683392234,"score":59.76432683392234},"GB2-04":{"attempts":1,"playable":77.86092508090375,"score":77.86092508090375},"GB2-05":{"attempts":1,"playable":73.94504228300622,"score":73.94504228300622},"GB2-06":{"attempts":1,"playable":38.363237037303314,"score":38.363237037303314},"GB2-07":{"attempts":1,"playable":68.95259056051943,"score":68.95259056051943},"GB2-08":{"attempts":1,"playable":73.73447151163545,"score":73.73447151163545}},"none":{"GB2-01":{"attempts":1,"playable":77.88111469935734,"score":77.88111469935734},"GB2-02":{"attempts":1,"playable":44.332680056719,"score":44.332680056719},"GB2-03":{"attempts":1,"playable":51.73812084456152,"score":51.73812084456152},"GB2-04":{"attempts":1,"playable":40.13498842101576,"score":40.13498842101576},"GB2-05":{"attempts":1,"playable":50.39439596741916,"score":50.39439596741916},"GB2-06":{"attempts":1,"playable":58.64754978587076,"score":58.64754978587076},"GB2-07":{"attempts":1,"playable":46.39967580279401,"score":46.39967580279401},"GB2-08":{"attempts":1,"playable":69.27372559003152,"score":69.27372559003152}}},"id":"gpt-5.6-sol","is_recent_addition":false,"last_measured_at":"2026-11-03T06:43:09Z","match_totals_all":{"draws":1705,"losses":3422,"wins":7413},"match_totals_tracks":{"highest":{"draws":309,"losses":715,"wins":3154},"medium":{"draws":561,"losses":1193,"wins":2430},"none":{"draws":835,"losses":1514,"wins":1829}},"model_slug":"gpt-5-6-sol","official_rank_by_reasoning":{"highest":11,"medium":15,"none":15},"overall":{"max":86.67937935151342,"mean":66.73017914228382,"min":38.363237037303314},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":11,"overall_ranking_status":"ranked","per_game":{"GB2-01":73.91555522136504,"GB2-02":75.26970595439437,"GB2-03":77.22098567844743,"GB2-04":82.07745401136162,"GB2-05":73.49889108163175,"GB2-06":82.84946140510947,"GB2-07":86.67937935151342,"GB2-08":85.17129687742255},"per_game_all":{"GB2-01":72.9532325911872,"GB2-02":61.98602783892685,"GB2-03":62.9078111189771,"GB2-04":66.69112250442704,"GB2-05":65.94610977735238,"GB2-06":59.953416076094506,"GB2-07":67.34388190494228,"GB2-08":76.05983132636317},"per_game_match_totals_all":{"GB2-01":{"draws":129,"losses":365,"wins":1084},"GB2-02":{"draws":773,"losses":193,"wins":514},"GB2-03":{"draws":203,"losses":506,"wins":831},"GB2-04":{"draws":545,"losses":253,"wins":732},"GB2-05":{"draws":0,"losses":554,"wins":1070},"GB2-06":{"draws":18,"losses":629,"wins":895},"GB2-07":{"draws":0,"losses":543,"wins":1077},"GB2-08":{"draws":37,"losses":379,"wins":1210}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":14,"losses":131,"wins":381},"GB2-02":{"draws":183,"losses":35,"wins":274},"GB2-03":{"draws":6,"losses":123,"wins":387},"GB2-04":{"draws":95,"losses":48,"wins":367},"GB2-05":{"draws":0,"losses":144,"wins":396},"GB2-06":{"draws":11,"losses":83,"wins":418},"GB2-07":{"draws":0,"losses":70,"wins":470},"GB2-08":{"draws":0,"losses":81,"wins":461}},"medium":{"GB2-01":{"draws":114,"losses":118,"wins":296},"GB2-02":{"draws":225,"losses":60,"wins":211},"GB2-03":{"draws":54,"losses":193,"wins":265},"GB2-04":{"draws":132,"losses":52,"wins":326},"GB2-05":{"draws":0,"losses":142,"wins":400},"GB2-06":{"draws":5,"losses":326,"wins":183},"GB2-07":{"draws":0,"losses":172,"wins":368},"GB2-08":{"draws":31,"losses":130,"wins":381}},"none":{"GB2-01":{"draws":1,"losses":116,"wins":407},"GB2-02":{"draws":365,"losses":98,"wins":29},"GB2-03":{"draws":143,"losses":190,"wins":179},"GB2-04":{"draws":318,"losses":153,"wins":39},"GB2-05":{"draws":0,"losses":268,"wins":274},"GB2-06":{"draws":2,"losses":220,"wins":294},"GB2-07":{"draws":0,"losses":301,"wins":239},"GB2-08":{"draws":6,"losses":168,"wins":368}}},"per_game_raw_elo_all":{"GB2-01":1730.4920593830896,"GB2-02":1582.8553113397293,"GB2-03":1578.0158717801098,"GB2-04":1642.6959791540219,"GB2-05":1696.6910007734305,"GB2-06":1642.0331394531956,"GB2-07":1735.8626915977904,"GB2-08":1887.4088567007375},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1739.7478072447561,"GB2-02":1703.1075449528896,"GB2-03":1744.708482857853,"GB2-04":1791.8104865737896,"GB2-05":1811.9627838472463,"GB2-06":2054.6378619334046,"GB2-07":2099.9859308188306,"GB2-08":2090.356132390557},"medium":{"GB2-01":1659.7077835178238,"GB2-02":1612.947125282412,"GB2-03":1532.7078405712114,"GB2-04":1736.372292443576,"GB2-05":1821.2706876894422,"GB2-06":1272.2553920106598,"GB2-07":1710.6110652357575,"GB2-08":1831.655887910379},"none":{"GB2-01":1792.020587386689,"GB2-02":1432.5112637838865,"GB2-03":1456.631291911265,"GB2-04":1399.9051584447002,"GB2-05":1456.8395307836026,"GB2-06":1599.2061644155222,"GB2-07":1396.991078738784,"GB2-08":1740.2145498012767}},"per_game_tracks":{"highest":{"GB2-01":73.91555522136504,"GB2-02":75.26970595439437,"GB2-03":77.22098567844743,"GB2-04":82.07745401136162,"GB2-05":73.49889108163175,"GB2-06":82.84946140510947,"GB2-07":86.67937935151342,"GB2-08":85.17129687742255},"medium":{"GB2-01":67.06302785283923,"GB2-02":66.3556975056672,"GB2-03":59.76432683392234,"GB2-04":77.86092508090375,"GB2-05":73.94504228300622,"GB2-06":38.363237037303314,"GB2-07":68.95259056051943,"GB2-08":73.73447151163545},"none":{"GB2-01":77.88111469935734,"GB2-02":44.332680056719,"GB2-03":51.73812084456152,"GB2-04":40.13498842101576,"GB2-05":50.39439596741916,"GB2-06":58.64754978587076,"GB2-07":46.39967580279401,"GB2-08":69.27372559003152}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":23,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-31T16:44:29Z","reasoning":{"highest":79.58534119765571,"medium":65.75491483322462,"none":54.85028139597112},"reasoning_agg":{"highest":{"max":86.67937935151342,"mean":79.58534119765571,"min":73.49889108163175},"medium":{"max":77.86092508090375,"mean":65.75491483322462,"min":38.363237037303314},"none":{"max":77.88111469935734,"mean":54.85028139597112,"min":40.13498842101576}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.735059801684585},"working_program_strength":{"all":66.73017914228382,"highest":79.58534119765571,"medium":65.75491483322462,"none":54.85028139597112}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5:f502312e3827252c","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":2.3088499999999996}},"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":4.187099999999999},"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":2.30885},"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":18.2605},"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":65.78044095193722,"highest":74.9634054562224,"medium":64.26752635484789,"none":58.11039104474136},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":76.40726993309049,"score":76.40726993309049},"GB2-02":{"attempts":3,"playable":59.94156570305614,"score":59.94156570305614},"GB2-03":{"attempts":3,"playable":46.41873576784966,"score":46.41873576784966},"GB2-04":{"attempts":3,"playable":58.010626469212774,"score":58.010626469212774},"GB2-05":{"attempts":3,"playable":61.793920655740685,"score":61.793920655740685},"GB2-06":{"attempts":3,"playable":78.87242038478361,"score":78.87242038478361},"GB2-07":{"attempts":3,"playable":65.13026315021087,"score":65.13026315021087},"GB2-08":{"attempts":3,"playable":79.66872555155349,"score":79.66872555155349}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":84.39465743461668,"score":84.39465743461668},"GB2-02":{"attempts":1,"playable":79.48731485086431,"score":79.48731485086431},"GB2-03":{"attempts":1,"playable":84.81792704245386,"score":84.81792704245386},"GB2-04":{"attempts":1,"playable":84.41805928124262,"score":84.41805928124262},"GB2-05":{"attempts":1,"playable":53.712752853187105,"score":53.712752853187105},"GB2-06":{"attempts":1,"playable":84.85513438802744,"score":84.85513438802744},"GB2-07":{"attempts":1,"playable":63.84822440191803,"score":63.84822440191803},"GB2-08":{"attempts":1,"playable":64.17317339746917,"score":64.17317339746917}},"medium":{"GB2-01":{"attempts":1,"playable":74.69978231606483,"score":74.69978231606483},"GB2-02":{"attempts":1,"playable":57.2394677134915,"score":57.2394677134915},"GB2-03":{"attempts":1,"playable":21.03808175917327,"score":21.03808175917327},"GB2-04":{"attempts":1,"playable":51.454506651185284,"score":51.454506651185284},"GB2-05":{"attempts":1,"playable":66.49301598996618,"score":66.49301598996618},"GB2-06":{"attempts":1,"playable":78.77394783902152,"score":78.77394783902152},"GB2-07":{"attempts":1,"playable":71.41767377966049,"score":71.41767377966049},"GB2-08":{"attempts":1,"playable":93.02373479022006,"score":93.02373479022006}},"none":{"GB2-01":{"attempts":1,"playable":70.12737004858998,"score":70.12737004858998},"GB2-02":{"attempts":1,"playable":43.09791454481261,"score":43.09791454481261},"GB2-03":{"attempts":1,"playable":33.40019850192188,"score":33.40019850192188},"GB2-04":{"attempts":1,"playable":38.15931347521042,"score":38.15931347521042},"GB2-05":{"attempts":1,"playable":65.17599312406875,"score":65.17599312406875},"GB2-06":{"attempts":1,"playable":72.98817892730189,"score":72.98817892730189},"GB2-07":{"attempts":1,"playable":60.12489126905408,"score":60.12489126905408},"GB2-08":{"attempts":1,"playable":81.80926846697125,"score":81.80926846697125}}},"id":"claude-fable-5","is_recent_addition":false,"last_measured_at":"2026-11-03T08:06:32Z","match_totals_all":{"draws":1990,"losses":3372,"wins":7190},"match_totals_tracks":{"highest":{"draws":311,"losses":927,"wins":2944},"medium":{"draws":754,"losses":1132,"wins":2300},"none":{"draws":925,"losses":1313,"wins":1946}},"model_slug":"claude-fable-5","official_rank_by_reasoning":{"highest":14,"medium":18,"none":13},"overall":{"max":93.02373479022006,"mean":65.78044095193722,"min":21.03808175917327},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":12,"overall_ranking_status":"ranked","per_game":{"GB2-01":84.39465743461668,"GB2-02":79.48731485086431,"GB2-03":84.81792704245386,"GB2-04":84.41805928124262,"GB2-05":53.712752853187105,"GB2-06":84.85513438802744,"GB2-07":63.84822440191803,"GB2-08":64.17317339746917},"per_game_all":{"GB2-01":76.40726993309049,"GB2-02":59.94156570305614,"GB2-03":46.41873576784966,"GB2-04":58.010626469212774,"GB2-05":61.793920655740685,"GB2-06":78.87242038478361,"GB2-07":65.13026315021087,"GB2-08":79.66872555155349},"per_game_match_totals_all":{"GB2-01":{"draws":110,"losses":320,"wins":1150},"GB2-02":{"draws":786,"losses":220,"wins":484},"GB2-03":{"draws":338,"losses":680,"wins":516},"GB2-04":{"draws":665,"losses":327,"wins":538},"GB2-05":{"draws":0,"losses":620,"wins":1004},"GB2-06":{"draws":61,"losses":300,"wins":1185},"GB2-07":{"draws":0,"losses":583,"wins":1039},"GB2-08":{"draws":30,"losses":322,"wins":1274}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":82,"wins":443},"GB2-02":{"draws":131,"losses":40,"wins":325},"GB2-03":{"draws":53,"losses":56,"wins":403},"GB2-04":{"draws":72,"losses":47,"wins":391},"GB2-05":{"draws":0,"losses":249,"wins":291},"GB2-06":{"draws":24,"losses":66,"wins":426},"GB2-07":{"draws":0,"losses":202,"wins":340},"GB2-08":{"draws":30,"losses":185,"wins":325}},"medium":{"GB2-01":{"draws":43,"losses":113,"wins":372},"GB2-02":{"draws":292,"losses":73,"wins":133},"GB2-03":{"draws":97,"losses":364,"wins":49},"GB2-04":{"draws":291,"losses":110,"wins":111},"GB2-05":{"draws":0,"losses":182,"wins":360},"GB2-06":{"draws":31,"losses":95,"wins":388},"GB2-07":{"draws":0,"losses":158,"wins":382},"GB2-08":{"draws":0,"losses":37,"wins":505}},"none":{"GB2-01":{"draws":66,"losses":125,"wins":335},"GB2-02":{"draws":363,"losses":107,"wins":26},"GB2-03":{"draws":188,"losses":260,"wins":64},"GB2-04":{"draws":302,"losses":170,"wins":36},"GB2-05":{"draws":0,"losses":189,"wins":353},"GB2-06":{"draws":6,"losses":139,"wins":371},"GB2-07":{"draws":0,"losses":223,"wins":317},"GB2-08":{"draws":0,"losses":100,"wins":444}}},"per_game_raw_elo_all":{"GB2-01":1779.3553841630253,"GB2-02":1570.4726651033307,"GB2-03":1448.0762486366402,"GB2-04":1566.7869053134957,"GB2-05":1615.4948436284258,"GB2-06":1976.0096017291805,"GB2-07":1654.7250718628293,"GB2-08":1993.3057991450996},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1894.1800291820343,"GB2-02":1754.1272179720015,"GB2-03":1886.5297676301657,"GB2-04":1826.9415224080763,"GB2-05":1500.0248694604004,"GB2-06":2098.688915235067,"GB2-07":1633.344973010986,"GB2-08":1641.8127891477757},"medium":{"GB2-01":1749.6588295447582,"GB2-02":1534.4374695802499,"GB2-03":1165.4376186997495,"GB2-04":1489.4176340299564,"GB2-05":1683.8034165252666,"GB2-06":1970.7117232749065,"GB2-07":1750.5749749974316,"GB2-08":2328.959696239519},"none":{"GB2-01":1694.2272937622827,"GB2-02":1422.8533077577406,"GB2-03":1292.261359580006,"GB2-04":1384.0015595024552,"GB2-05":1662.6562448996099,"GB2-06":1858.628166677568,"GB2-07":1580.2552675800698,"GB2-08":2009.1449120480042}},"per_game_tracks":{"highest":{"GB2-01":84.39465743461668,"GB2-02":79.48731485086431,"GB2-03":84.81792704245386,"GB2-04":84.41805928124262,"GB2-05":53.712752853187105,"GB2-06":84.85513438802744,"GB2-07":63.84822440191803,"GB2-08":64.17317339746917},"medium":{"GB2-01":74.69978231606483,"GB2-02":57.2394677134915,"GB2-03":21.03808175917327,"GB2-04":51.454506651185284,"GB2-05":66.49301598996618,"GB2-06":78.77394783902152,"GB2-07":71.41767377966049,"GB2-08":93.02373479022006},"none":{"GB2-01":70.12737004858998,"GB2-02":43.09791454481261,"GB2-03":33.40019850192188,"GB2-04":38.15931347521042,"GB2-05":65.17599312406875,"GB2-06":72.98817892730189,"GB2-07":60.12489126905408,"GB2-08":81.80926846697125}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":24,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-31T16:44:22Z","reasoning":{"highest":74.9634054562224,"medium":64.26752635484789,"none":58.11039104474136},"reasoning_agg":{"highest":{"max":84.85513438802744,"mean":74.9634054562224,"min":53.712752853187105},"medium":{"max":93.02373479022006,"mean":64.26752635484789,"min":21.03808175917327},"none":{"max":81.80926846697125,"mean":58.11039104474136,"min":33.40019850192188}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":16.85301441148104},"working_program_strength":{"all":65.78044095193722,"highest":74.9634054562224,"medium":64.26752635484789,"none":58.11039104474136}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-wonder:9b8b47ef6c870217","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":3.9007552},"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":0.9656475999999999}},"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":64.54496922701287,"highest":77.13502356194412,"medium":61.46168804117117,"none":55.03819607792333},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":67.28273634893907,"score":67.28273634893907},"GB2-02":{"attempts":3,"playable":54.5606510373529,"score":54.5606510373529},"GB2-03":{"attempts":3,"playable":44.59669336470578,"score":44.59669336470578},"GB2-04":{"attempts":3,"playable":57.13333078706458,"score":57.13333078706458},"GB2-05":{"attempts":3,"playable":86.2854049875628,"score":86.2854049875628},"GB2-06":{"attempts":3,"playable":74.3000554030898,"score":74.3000554030898},"GB2-07":{"attempts":3,"playable":70.04243974354921,"score":70.04243974354921},"GB2-08":{"attempts":3,"playable":62.15844214383892,"score":62.15844214383892}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":83.76762127689865,"score":83.76762127689865},"GB2-02":{"attempts":1,"playable":65.96194607140139,"score":65.96194607140139},"GB2-03":{"attempts":1,"playable":81.42250069816227,"score":81.42250069816227},"GB2-04":{"attempts":1,"playable":80.44540461202337,"score":80.44540461202337},"GB2-05":{"attempts":1,"playable":92.02541072906538,"score":92.02541072906538},"GB2-06":{"attempts":1,"playable":83.37551772903966,"score":83.37551772903966},"GB2-07":{"attempts":1,"playable":71.92110807745739,"score":71.92110807745739},"GB2-08":{"attempts":1,"playable":58.16067930150498,"score":58.16067930150498}},"medium":{"GB2-01":{"attempts":1,"playable":50.769518816354875,"score":50.769518816354875},"GB2-02":{"attempts":1,"playable":55.55078373183257,"score":55.55078373183257},"GB2-03":{"attempts":1,"playable":35.539690040342784,"score":35.539690040342784},"GB2-04":{"attempts":1,"playable":38.29787664988664,"score":38.29787664988664},"GB2-05":{"attempts":1,"playable":83.60446400652674,"score":83.60446400652674},"GB2-06":{"attempts":1,"playable":74.06780366716444,"score":74.06780366716444},"GB2-07":{"attempts":1,"playable":85.45697771170127,"score":85.45697771170127},"GB2-08":{"attempts":1,"playable":68.40638970556006,"score":68.40638970556006}},"none":{"GB2-01":{"attempts":1,"playable":67.31106895356368,"score":67.31106895356368},"GB2-02":{"attempts":1,"playable":42.169223308824726,"score":42.169223308824726},"GB2-03":{"attempts":1,"playable":16.8278893556123,"score":16.8278893556123},"GB2-04":{"attempts":1,"playable":52.65671109928375,"score":52.65671109928375},"GB2-05":{"attempts":1,"playable":83.22634022709626,"score":83.22634022709626},"GB2-06":{"attempts":1,"playable":65.4568448130653,"score":65.4568448130653},"GB2-07":{"attempts":1,"playable":52.74923344148898,"score":52.74923344148898},"GB2-08":{"attempts":1,"playable":59.908257424451705,"score":59.908257424451705}}},"id":"meta/muse-wonder","is_recent_addition":false,"last_measured_at":"2026-11-03T07:15:41Z","match_totals_all":{"draws":2288,"losses":3391,"wins":6891},"match_totals_tracks":{"highest":{"draws":545,"losses":711,"wins":2934},"medium":{"draws":682,"losses":1292,"wins":2216},"none":{"draws":1061,"losses":1388,"wins":1741}},"model_slug":"meta-muse-wonder","official_rank_by_reasoning":{"highest":13,"medium":21,"none":14},"overall":{"max":92.02541072906538,"mean":64.54496922701287,"min":16.8278893556123},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":13,"overall_ranking_status":"ranked","per_game":{"GB2-01":83.76762127689865,"GB2-02":65.96194607140139,"GB2-03":81.42250069816227,"GB2-04":80.44540461202337,"GB2-05":92.02541072906538,"GB2-06":83.37551772903966,"GB2-07":71.92110807745739,"GB2-08":58.16067930150498},"per_game_all":{"GB2-01":67.28273634893907,"GB2-02":54.5606510373529,"GB2-03":44.59669336470578,"GB2-04":57.13333078706458,"GB2-05":86.2854049875628,"GB2-06":74.3000554030898,"GB2-07":70.04243974354921,"GB2-08":62.15844214383892},"per_game_match_totals_all":{"GB2-01":{"draws":176,"losses":429,"wins":971},"GB2-02":{"draws":960,"losses":213,"wins":313},"GB2-03":{"draws":288,"losses":742,"wins":516},"GB2-04":{"draws":597,"losses":378,"wins":559},"GB2-05":{"draws":0,"losses":222,"wins":1408},"GB2-06":{"draws":90,"losses":361,"wins":1097},"GB2-07":{"draws":0,"losses":497,"wins":1123},"GB2-08":{"draws":177,"losses":549,"wins":904}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":6,"losses":83,"wins":439},"GB2-02":{"draws":283,"losses":33,"wins":180},"GB2-03":{"draws":88,"losses":58,"wins":368},"GB2-04":{"draws":66,"losses":71,"wins":371},"GB2-05":{"draws":0,"losses":42,"wins":502},"GB2-06":{"draws":24,"losses":74,"wins":420},"GB2-07":{"draws":0,"losses":155,"wins":385},"GB2-08":{"draws":78,"losses":195,"wins":269}},"medium":{"GB2-01":{"draws":4,"losses":257,"wins":263},"GB2-02":{"draws":303,"losses":76,"wins":119},"GB2-03":{"draws":107,"losses":291,"wins":116},"GB2-04":{"draws":215,"losses":215,"wins":82},"GB2-05":{"draws":0,"losses":89,"wins":455},"GB2-06":{"draws":28,"losses":122,"wins":364},"GB2-07":{"draws":0,"losses":77,"wins":463},"GB2-08":{"draws":25,"losses":165,"wins":354}},"none":{"GB2-01":{"draws":166,"losses":89,"wins":269},"GB2-02":{"draws":374,"losses":104,"wins":14},"GB2-03":{"draws":93,"losses":393,"wins":32},"GB2-04":{"draws":316,"losses":92,"wins":106},"GB2-05":{"draws":0,"losses":91,"wins":451},"GB2-06":{"draws":38,"losses":165,"wins":313},"GB2-07":{"draws":0,"losses":265,"wins":275},"GB2-08":{"draws":74,"losses":189,"wins":281}}},"per_game_raw_elo_all":{"GB2-01":1680.0768100585228,"GB2-02":1515.2167454231574,"GB2-03":1413.6182556714077,"GB2-04":1551.1483089338765,"GB2-05":2173.0495535562654,"GB2-06":1888.100741092274,"GB2-07":1766.2065470953573,"GB2-08":1608.3306927429885},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1883.1177752646825,"GB2-02":1609.3404043416945,"GB2-03":1816.6108036796918,"GB2-04":1769.3159949354135,"GB2-05":2386.316009746293,"GB2-06":2065.9701578239146,"GB2-07":1759.0130566464684,"GB2-08":1536.298586506377},"medium":{"GB2-01":1494.6739672866165,"GB2-02":1520.742824524999,"GB2-03":1311.9433603962573,"GB2-04":1385.123670701336,"GB2-05":2072.3332655375098,"GB2-06":1879.1439856310863,"GB2-07":2059.4656918581077,"GB2-08":1722.9754807186066},"none":{"GB2-01":1662.4386876242697,"GB2-02":1415.567007402779,"GB2-03":1112.3006029382736,"GB2-04":1499.00526116488,"GB2-05":2060.4993853849937,"GB2-06":1719.1880798218208,"GB2-07":1480.140892781495,"GB2-08":1565.7180110039817}},"per_game_tracks":{"highest":{"GB2-01":83.76762127689865,"GB2-02":65.96194607140139,"GB2-03":81.42250069816227,"GB2-04":80.44540461202337,"GB2-05":92.02541072906538,"GB2-06":83.37551772903966,"GB2-07":71.92110807745739,"GB2-08":58.16067930150498},"medium":{"GB2-01":50.769518816354875,"GB2-02":55.55078373183257,"GB2-03":35.539690040342784,"GB2-04":38.29787664988664,"GB2-05":83.60446400652674,"GB2-06":74.06780366716444,"GB2-07":85.45697771170127,"GB2-08":68.40638970556006},"none":{"GB2-01":67.31106895356368,"GB2-02":42.169223308824726,"GB2-03":16.8278893556123,"GB2-04":52.65671109928375,"GB2-05":83.22634022709626,"GB2-06":65.4568448130653,"GB2-07":52.74923344148898,"GB2-08":59.908257424451705}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":21,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":-2,"rank_movement_baseline_at":"2026-10-31T17:11:15Z","reasoning":{"highest":77.13502356194412,"medium":61.46168804117117,"none":55.03819607792333},"reasoning_agg":{"highest":{"max":92.02541072906538,"mean":77.13502356194412,"min":58.16067930150498},"medium":{"max":85.45697771170127,"mean":61.46168804117117,"min":35.539690040342784},"none":{"max":83.22634022709626,"mean":55.03819607792333,"min":16.8278893556123}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":22.096827484020793},"working_program_strength":{"all":64.54496922701287,"highest":77.13502356194412,"medium":61.46168804117117,"none":55.03819607792333}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3:0d963419cc256497","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":0.43181688}},"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":0.43181688},"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":6.08478824},"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":64.14228086181281,"highest":72.08827892832991,"medium":69.79400185486702,"none":50.54456180224146},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":58.08140882858018,"score":38.720939219053456},"GB2-02":{"attempts":3,"playable":56.203824050376596,"score":56.203824050376596},"GB2-03":{"attempts":3,"playable":66.57603439284146,"score":66.57603439284146},"GB2-04":{"attempts":3,"playable":68.57786210928369,"score":68.57786210928369},"GB2-05":{"attempts":3,"playable":69.58117992966147,"score":69.58117992966147},"GB2-06":{"attempts":3,"playable":75.32733644317732,"score":75.32733644317732},"GB2-07":{"attempts":3,"playable":73.51415649637799,"score":73.51415649637799},"GB2-08":{"attempts":3,"playable":64.63691425373032,"score":64.63691425373032}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":72.2087824977079,"score":72.2087824977079},"GB2-03":{"attempts":1,"playable":82.8296530495335,"score":82.8296530495335},"GB2-04":{"attempts":1,"playable":76.04824924224316,"score":76.04824924224316},"GB2-05":{"attempts":1,"playable":88.20060732903195,"score":88.20060732903195},"GB2-06":{"attempts":1,"playable":89.2527265877972,"score":89.2527265877972},"GB2-07":{"attempts":1,"playable":76.38695145343422,"score":76.38695145343422},"GB2-08":{"attempts":1,"playable":91.77926126689133,"score":91.77926126689133}},"medium":{"GB2-01":{"attempts":1,"playable":49.27886929931405,"score":49.27886929931405},"GB2-02":{"attempts":1,"playable":52.79509694726209,"score":52.79509694726209},"GB2-03":{"attempts":1,"playable":76.31896273107533,"score":76.31896273107533},"GB2-04":{"attempts":1,"playable":82.54654773056312,"score":82.54654773056312},"GB2-05":{"attempts":1,"playable":63.98257028732965,"score":63.98257028732965},"GB2-06":{"attempts":1,"playable":90.37657708763285,"score":90.37657708763285},"GB2-07":{"attempts":1,"playable":74.47961985634501,"score":74.47961985634501},"GB2-08":{"attempts":1,"playable":68.57377089941392,"score":68.57377089941392}},"none":{"GB2-01":{"attempts":1,"playable":66.88394835784631,"score":66.88394835784631},"GB2-02":{"attempts":1,"playable":43.60759270615981,"score":43.60759270615981},"GB2-03":{"attempts":1,"playable":40.57948739791557,"score":40.57948739791557},"GB2-04":{"attempts":1,"playable":47.13878935504477,"score":47.13878935504477},"GB2-05":{"attempts":1,"playable":56.56036217262284,"score":56.56036217262284},"GB2-06":{"attempts":1,"playable":46.3527056541019,"score":46.3527056541019},"GB2-07":{"attempts":1,"playable":69.67589817935475,"score":69.67589817935475},"GB2-08":{"attempts":1,"playable":33.55771059488575,"score":33.55771059488575}}},"id":"z-ai/glm-5.3","is_recent_addition":false,"last_measured_at":"2026-11-03T07:03:32Z","match_totals_all":{"draws":2024,"losses":3055,"wins":6951},"match_totals_tracks":{"highest":{"draws":401,"losses":453,"wins":2796},"medium":{"draws":598,"losses":995,"wins":2595},"none":{"draws":1025,"losses":1607,"wins":1560}},"model_slug":"z-ai-glm-5-3","official_rank_by_reasoning":{"highest":15,"medium":13,"none":19},"overall":{"max":91.77926126689133,"mean":64.14228086181281,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":14,"overall_ranking_status":"ranked","per_game":{"GB2-02":72.2087824977079,"GB2-03":82.8296530495335,"GB2-04":76.04824924224316,"GB2-05":88.20060732903195,"GB2-06":89.2527265877972,"GB2-07":76.38695145343422,"GB2-08":91.77926126689133},"per_game_all":{"GB2-02":56.203824050376596,"GB2-03":66.57603439284146,"GB2-04":68.57786210928369,"GB2-05":69.58117992966147,"GB2-06":75.32733644317732,"GB2-07":73.51415649637799,"GB2-08":64.63691425373032},"per_game_match_totals_all":{"GB2-01":{"draws":176,"losses":356,"wins":522},"GB2-02":{"draws":943,"losses":197,"wins":346},"GB2-03":{"draws":168,"losses":460,"wins":910},"GB2-04":{"draws":572,"losses":212,"wins":748},"GB2-05":{"draws":0,"losses":496,"wins":1130},"GB2-06":{"draws":60,"losses":361,"wins":1125},"GB2-07":{"draws":0,"losses":437,"wins":1183},"GB2-08":{"draws":105,"losses":536,"wins":987}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":222,"losses":31,"wins":241},"GB2-03":{"draws":7,"losses":90,"wins":411},"GB2-04":{"draws":143,"losses":56,"wins":311},"GB2-05":{"draws":0,"losses":63,"wins":477},"GB2-06":{"draws":29,"losses":40,"wins":447},"GB2-07":{"draws":0,"losses":129,"wins":411},"GB2-08":{"draws":0,"losses":44,"wins":498}},"medium":{"GB2-01":{"draws":86,"losses":225,"wins":215},"GB2-02":{"draws":331,"losses":75,"wins":90},"GB2-03":{"draws":30,"losses":116,"wins":370},"GB2-04":{"draws":98,"losses":44,"wins":368},"GB2-05":{"draws":0,"losses":198,"wins":346},"GB2-06":{"draws":23,"losses":37,"wins":454},"GB2-07":{"draws":0,"losses":140,"wins":400},"GB2-08":{"draws":30,"losses":160,"wins":352}},"none":{"GB2-01":{"draws":90,"losses":131,"wins":307},"GB2-02":{"draws":390,"losses":91,"wins":15},"GB2-03":{"draws":131,"losses":254,"wins":129},"GB2-04":{"draws":331,"losses":112,"wins":69},"GB2-05":{"draws":0,"losses":235,"wins":307},"GB2-06":{"draws":8,"losses":284,"wins":224},"GB2-07":{"draws":0,"losses":168,"wins":372},"GB2-08":{"draws":75,"losses":332,"wins":137}}},"per_game_raw_elo_all":{"GB2-02":1531.8563334567718,"GB2-03":1644.0314480907302,"GB2-04":1656.250130382786,"GB2-05":1804.0400663453565,"GB2-06":1947.6986937832291,"GB2-07":1788.3650100954512,"GB2-08":1736.94998524063},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1669.9822849965185,"GB2-03":1844.047900912441,"GB2-04":1714.8845529025052,"GB2-05":2230.090870185968,"GB2-06":2206.8406079099304,"GB2-07":1839.3027083063182,"GB2-08":2282.6888544662547},"medium":{"GB2-01":1480.293589920969,"GB2-02":1498.743351264652,"GB2-03":1730.8569395099164,"GB2-04":1798.5592135554493,"GB2-05":1644.0898895459154,"GB2-06":2238.530932914374,"GB2-07":1803.6700882533642,"GB2-08":1726.2874120456681},"none":{"GB2-01":1657.7424497246536,"GB2-02":1426.8433641091453,"GB2-03":1357.1895038498328,"GB2-04":1455.3066246904039,"GB2-05":1537.9394393041857,"GB2-06":1397.724540525383,"GB2-07":1722.1222337266715,"GB2-08":1201.8736892099673}},"per_game_tracks":{"highest":{"GB2-02":72.2087824977079,"GB2-03":82.8296530495335,"GB2-04":76.04824924224316,"GB2-05":88.20060732903195,"GB2-06":89.2527265877972,"GB2-07":76.38695145343422,"GB2-08":91.77926126689133},"medium":{"GB2-01":49.27886929931405,"GB2-02":52.79509694726209,"GB2-03":76.31896273107533,"GB2-04":82.54654773056312,"GB2-05":63.98257028732965,"GB2-06":90.37657708763285,"GB2-07":74.47961985634501,"GB2-08":68.57377089941392},"none":{"GB2-01":66.88394835784631,"GB2-02":43.60759270615981,"GB2-03":40.57948739791557,"GB2-04":47.13878935504477,"GB2-05":56.56036217262284,"GB2-06":46.3527056541019,"GB2-07":69.67589817935475,"GB2-08":33.55771059488575}},"program_outcomes":{"all":{"counted_attempts":24,"failed":1,"infra_excluded":0,"success_rate":0.9583333333333334,"too_slow":0,"worked_after_repair":2,"worked_first_time":21,"working":23},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":-2,"rank_movement_baseline_at":"2026-10-31T17:09:35Z","reasoning":{"highest":72.08827892832991,"medium":69.79400185486702,"none":50.54456180224146},"reasoning_agg":{"highest":{"max":91.77926126689133,"mean":72.08827892832991,"min":0.0},"medium":{"max":90.37657708763285,"mean":69.79400185486702,"min":49.27886929931405},"none":{"max":69.67589817935475,"mean":50.54456180224146,"min":33.55771059488575}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":21.543717126088453},"working_program_strength":{"all":67.57505604887614,"highest":82.3866044895199,"medium":69.79400185486702,"none":50.54456180224146}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-7:04004322efc61b5f","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":3.189754},"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":0.663736}},"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":0.6637360000000001},"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":10.089050000000002},"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":63.43761335194878,"highest":71.54538293774029,"medium":72.0257942668107,"none":46.74166285129533},"first_seen_at":null,"game_gaps":{"highest":{"GB2-04":"failed"},"medium":{"GB2-06":"failed"},"none":{"GB2-03":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":53.88957535501448,"score":53.88957535501448},"GB2-02":{"attempts":3,"playable":73.0138126648753,"score":73.0138126648753},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":78.15781505196438,"score":52.105210034642916},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":67.34841467596662,"score":44.898943117311084},"GB2-05":{"attempts":3,"playable":74.97457045282262,"score":74.97457045282262},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":83.98718580465193,"score":55.991457203101284},"GB2-07":{"attempts":3,"playable":68.05817851303475,"score":68.05817851303475},"GB2-08":{"attempts":3,"playable":84.56915947478772,"score":84.56915947478772}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":57.4740603471587,"score":57.4740603471587},"GB2-02":{"attempts":1,"playable":88.14182709312306,"score":88.14182709312306},"GB2-03":{"attempts":1,"playable":86.56028767691203,"score":86.56028767691203},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":92.68800624966387,"score":92.68800624966387},"GB2-06":{"attempts":1,"playable":88.40318364286708,"score":88.40318364286708},"GB2-07":{"attempts":1,"playable":76.22865067592505,"score":76.22865067592505},"GB2-08":{"attempts":1,"playable":82.86704781627246,"score":82.86704781627246}},"medium":{"GB2-01":{"attempts":1,"playable":78.00315189088639,"score":78.00315189088639},"GB2-02":{"attempts":1,"playable":79.33443136556622,"score":79.33443136556622},"GB2-03":{"attempts":1,"playable":69.75534242701671,"score":69.75534242701671},"GB2-04":{"attempts":1,"playable":92.28904698654856,"score":92.28904698654856},"GB2-05":{"attempts":1,"playable":92.14919637840455,"score":92.14919637840455},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":74.16800726936594,"score":74.16800726936594},"GB2-08":{"attempts":1,"playable":90.50717781669728,"score":90.50717781669728}},"none":{"GB2-01":{"attempts":1,"playable":26.191513826998385,"score":26.191513826998385},"GB2-02":{"attempts":1,"playable":51.565179535936636,"score":51.565179535936636},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":42.4077823653847,"score":42.4077823653847},"GB2-05":{"attempts":1,"playable":40.08650873039942,"score":40.08650873039942},"GB2-06":{"attempts":1,"playable":79.57118796643678,"score":79.57118796643678},"GB2-07":{"attempts":1,"playable":53.77787759381326,"score":53.77787759381326},"GB2-08":{"attempts":1,"playable":80.33325279139343,"score":80.33325279139343}}},"id":"x-ai/grok-4.7","is_recent_addition":false,"last_measured_at":"2026-11-03T07:05:28Z","match_totals_all":{"draws":1054,"losses":2553,"wins":7393},"match_totals_tracks":{"highest":{"draws":164,"losses":596,"wins":2902},"medium":{"draws":222,"losses":553,"wins":2891},"none":{"draws":668,"losses":1404,"wins":1600}},"model_slug":"x-ai-grok-4-7","official_rank_by_reasoning":{"highest":16,"medium":10,"none":28},"overall":{"max":92.68800624966387,"mean":63.43761335194878,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":15,"overall_ranking_status":"ranked","per_game":{"GB2-01":57.4740603471587,"GB2-02":88.14182709312306,"GB2-03":86.56028767691203,"GB2-05":92.68800624966387,"GB2-06":88.40318364286708,"GB2-07":76.22865067592505,"GB2-08":82.86704781627246},"per_game_all":{"GB2-01":53.88957535501448,"GB2-02":73.0138126648753,"GB2-05":74.97457045282262,"GB2-07":68.05817851303475,"GB2-08":84.56915947478772},"per_game_match_totals_all":{"GB2-01":{"draws":206,"losses":630,"wins":744},"GB2-02":{"draws":500,"losses":161,"wins":815},"GB2-03":{"draws":115,"losses":182,"wins":727},"GB2-04":{"draws":186,"losses":250,"wins":588},"GB2-05":{"draws":0,"losses":403,"wins":1221},"GB2-06":{"draws":47,"losses":142,"wins":837},"GB2-07":{"draws":0,"losses":532,"wins":1090},"GB2-08":{"draws":0,"losses":253,"wins":1371}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":218,"wins":295},"GB2-02":{"draws":52,"losses":34,"wins":404},"GB2-03":{"draws":87,"losses":29,"wins":394},"GB2-05":{"draws":0,"losses":38,"wins":502},"GB2-06":{"draws":12,"losses":53,"wins":447},"GB2-07":{"draws":0,"losses":130,"wins":412},"GB2-08":{"draws":0,"losses":94,"wins":448}},"medium":{"GB2-01":{"draws":35,"losses":99,"wins":392},"GB2-02":{"draws":112,"losses":50,"wins":332},"GB2-03":{"draws":28,"losses":153,"wins":333},"GB2-04":{"draws":47,"losses":17,"wins":446},"GB2-05":{"draws":0,"losses":41,"wins":501},"GB2-07":{"draws":0,"losses":142,"wins":398},"GB2-08":{"draws":0,"losses":51,"wins":489}},"none":{"GB2-01":{"draws":158,"losses":313,"wins":57},"GB2-02":{"draws":336,"losses":77,"wins":79},"GB2-04":{"draws":139,"losses":233,"wins":142},"GB2-05":{"draws":0,"losses":324,"wins":218},"GB2-06":{"draws":35,"losses":89,"wins":390},"GB2-07":{"draws":0,"losses":260,"wins":280},"GB2-08":{"draws":0,"losses":108,"wins":434}}},"per_game_raw_elo_all":{"GB2-01":1532.6069695053582,"GB2-02":1711.4930219686905,"GB2-05":2044.1007520859378,"GB2-07":1709.373809545117,"GB2-08":2083.0983489891855},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1560.1583723214737,"GB2-02":1893.3042572829797,"GB2-03":1928.0951232784287,"GB2-05":2417.220430260986,"GB2-06":2184.2389343869745,"GB2-07":1836.2553975358805,"GB2-08":2034.0191764520978},"medium":{"GB2-01":1793.7237072902788,"GB2-02":1752.1430708804487,"GB2-03":1642.0502580183588,"GB2-04":1988.7824325119902,"GB2-05":2391.971943810474,"GB2-07":1798.0553249043103,"GB2-08":2240.0325376668325},"none":{"GB2-01":1243.9388289043216,"GB2-02":1489.0317377426436,"GB2-04":1417.9963413170447,"GB2-05":1323.1098821863536,"GB2-06":1986.691554710825,"GB2-07":1493.8107061951598,"GB2-08":1975.2433328486256}},"per_game_tracks":{"highest":{"GB2-01":57.4740603471587,"GB2-02":88.14182709312306,"GB2-03":86.56028767691203,"GB2-05":92.68800624966387,"GB2-06":88.40318364286708,"GB2-07":76.22865067592505,"GB2-08":82.86704781627246},"medium":{"GB2-01":78.00315189088639,"GB2-02":79.33443136556622,"GB2-03":69.75534242701671,"GB2-04":92.28904698654856,"GB2-05":92.14919637840455,"GB2-07":74.16800726936594,"GB2-08":90.50717781669728},"none":{"GB2-01":26.191513826998385,"GB2-02":51.565179535936636,"GB2-04":42.4077823653847,"GB2-05":40.08650873039942,"GB2-06":79.57118796643678,"GB2-07":53.77787759381326,"GB2-08":80.33325279139343}},"program_outcomes":{"all":{"counted_attempts":24,"failed":3,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":2,"worked_first_time":19,"working":21},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":1,"worked_first_time":6,"working":7},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":1,"worked_first_time":6,"working":7}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":-2,"rank_movement_baseline_at":"2026-10-31T11:42:27Z","reasoning":{"highest":71.54538293774029,"medium":72.0257942668107,"none":46.741662851295324},"reasoning_agg":{"highest":{"max":92.68800624966387,"mean":71.54538293774029,"min":0.0},"medium":{"max":92.28904698654856,"mean":72.0257942668107,"min":0.0},"none":{"max":80.33325279139343,"mean":46.741662851295324,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":25.284131415515382},"working_program_strength":{"all":72.5001295450843,"highest":81.76615192884604,"medium":82.31519344778367,"none":53.41904325862323}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-1-flash-1017:eb3e551d4b592621","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":0.11170938600000001,"mean":0.07554854925,"median":0.075366243,"min":0.03476295,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.604388394},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.065551536,"mean":0.04201661175,"median":0.0380097,"min":0.02021175,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.336132894},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00749985,"mean":0.0058554465,"median":0.006206184,"min":0.00308565,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.04684357200000001}},"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":0.065551536,"mean":0.04201661175,"median":0.0380097,"min":0.02021175,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.336132894},"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":0.00749985,"mean":0.0058554465,"median":0.006206184,"min":0.00308565,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.046843572},"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":0.11170938600000001,"mean":0.07554854925,"median":0.075366243,"min":0.03476295,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.604388394}},"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":0.11170938600000001,"mean":0.0411402025,"median":0.037120068,"min":0.00308565,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"recorded_attempt_count":27,"run_count":24,"total":0.98736486},"codegen_latency_ms":{"attempt_count":27,"max_ms":473334,"mean_ms":151724.33333333334,"min_ms":8145,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":473334,"mean_ms":299503.0,"min_ms":228847,"run_count":8},"medium":{"attempt_count":8,"max_ms":206258,"mean_ms":144560.375,"min_ms":109598,"run_count":8},"none":{"attempt_count":9,"max_ms":15039,"mean_ms":11109.625,"min_ms":8145,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":101363,"output_mean":34770.375,"output_min":2168,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":101363,"output_mean":66009.25,"output_min":55824,"run_count":8},"medium":{"attempt_count":8,"output_max":52800,"output_mean":35105.0,"output_min":27852,"run_count":8},"none":{"attempt_count":9,"output_max":4467,"output_mean":3196.875,"output_min":2168,"run_count":8}},"display_name":"DeepSeek V4.1 Flash 1017","economics":{"all":61.31262080978641,"highest":69.74574933651701,"medium":64.27392422993681,"none":49.91818886290539},"economics_best_value":{"per_model":{"all":true,"none":true}},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"effective_max_output_tokens":[393216],"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":[393216],"total_output_tokens":834489,"total_reasoning_output_tokens":719894,"total_visible_output_tokens":114595,"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":393216,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4.1-flash-1017","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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":73.58993309102632,"score":73.58993309102632},"GB2-02":{"attempts":3,"playable":55.19324957060244,"score":55.19324957060244},"GB2-03":{"attempts":3,"playable":44.51014465828272,"score":44.51014465828272},"GB2-04":{"attempts":3,"playable":59.330921909773004,"score":59.330921909773004},"GB2-05":{"attempts":3,"playable":59.68723211072779,"score":59.68723211072779},"GB2-06":{"attempts":3,"playable":66.13392873667719,"score":66.13392873667719},"GB2-07":{"attempts":3,"playable":58.04698844245846,"score":58.04698844245846},"GB2-08":{"attempts":3,"playable":74.0085679587433,"score":74.0085679587433}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":67.2834907151903,"score":67.2834907151903},"GB2-02":{"attempts":1,"playable":79.56973000237281,"score":79.56973000237281},"GB2-03":{"attempts":1,"playable":45.61058762318383,"score":45.61058762318383},"GB2-04":{"attempts":1,"playable":69.24553517031161,"score":69.24553517031161},"GB2-05":{"attempts":1,"playable":70.69730425071555,"score":70.69730425071555},"GB2-06":{"attempts":1,"playable":74.7090959978435,"score":74.7090959978435},"GB2-07":{"attempts":1,"playable":70.51699814112501,"score":70.51699814112501},"GB2-08":{"attempts":1,"playable":80.33325279139343,"score":80.33325279139343}},"medium":{"GB2-01":{"attempts":1,"playable":81.84302568980287,"score":81.84302568980287},"GB2-02":{"attempts":1,"playable":42.99663062186767,"score":42.99663062186767},"GB2-03":{"attempts":1,"playable":49.36150005277055,"score":49.36150005277055},"GB2-04":{"attempts":1,"playable":67.0726812757106,"score":67.0726812757106},"GB2-05":{"attempts":1,"playable":58.59135878586872,"score":58.59135878586872},"GB2-06":{"attempts":1,"playable":80.49252869857578,"score":80.49252869857578},"GB2-07":{"attempts":1,"playable":71.40287034416846,"score":71.40287034416846},"GB2-08":{"attempts":1,"playable":62.43079837072988,"score":62.43079837072988}},"none":{"GB2-01":{"attempts":1,"playable":71.6432828680858,"score":71.6432828680858},"GB2-02":{"attempts":1,"playable":43.013388087566845,"score":43.013388087566845},"GB2-03":{"attempts":1,"playable":38.55834629889377,"score":38.55834629889377},"GB2-04":{"attempts":1,"playable":41.67454928329681,"score":41.67454928329681},"GB2-05":{"attempts":1,"playable":49.773033295599106,"score":49.773033295599106},"GB2-06":{"attempts":1,"playable":43.2001615136123,"score":43.2001615136123},"GB2-07":{"attempts":1,"playable":32.221096842081906,"score":32.221096842081906},"GB2-08":{"attempts":1,"playable":79.26165271410657,"score":79.26165271410657}}},"id":"deepseek/deepseek-v4.1-flash-1017","is_recent_addition":false,"last_measured_at":"2026-11-03T07:10:23Z","match_totals_all":{"draws":2221,"losses":3854,"wins":6469},"match_totals_tracks":{"highest":{"draws":585,"losses":1007,"wins":2594},"medium":{"draws":654,"losses":1202,"wins":2326},"none":{"draws":982,"losses":1645,"wins":1549}},"model_slug":"deepseek-deepseek-v4-1-flash-1017","official_rank_by_reasoning":{"highest":17,"medium":17,"none":20},"overall":{"max":81.84302568980287,"mean":61.31262080978641,"min":32.221096842081906},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":16,"overall_ranking_status":"ranked","per_game":{"GB2-01":67.2834907151903,"GB2-02":79.56973000237281,"GB2-03":45.61058762318383,"GB2-04":69.24553517031161,"GB2-05":70.69730425071555,"GB2-06":74.7090959978435,"GB2-07":70.51699814112501,"GB2-08":80.33325279139343},"per_game_all":{"GB2-01":73.58993309102632,"GB2-02":55.19324957060244,"GB2-03":44.51014465828272,"GB2-04":59.330921909773004,"GB2-05":59.68723211072779,"GB2-06":66.13392873667719,"GB2-07":58.04698844245846,"GB2-08":74.0085679587433},"per_game_match_totals_all":{"GB2-01":{"draws":168,"losses":335,"wins":1075},"GB2-02":{"draws":853,"losses":252,"wins":375},"GB2-03":{"draws":373,"losses":711,"wins":458},"GB2-04":{"draws":771,"losses":256,"wins":503},"GB2-05":{"draws":0,"losses":657,"wins":969},"GB2-06":{"draws":56,"losses":511,"wins":975},"GB2-07":{"draws":0,"losses":699,"wins":921},"GB2-08":{"draws":0,"losses":433,"wins":1193}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":108,"losses":119,"wins":299},"GB2-02":{"draws":101,"losses":54,"wins":339},"GB2-03":{"draws":92,"losses":249,"wins":175},"GB2-04":{"draws":261,"losses":33,"wins":218},"GB2-05":{"draws":0,"losses":160,"wins":382},"GB2-06":{"draws":23,"losses":121,"wins":368},"GB2-07":{"draws":0,"losses":163,"wins":379},"GB2-08":{"draws":0,"losses":108,"wins":434}},"medium":{"GB2-01":{"draws":0,"losses":96,"wins":430},"GB2-02":{"draws":369,"losses":103,"wins":22},"GB2-03":{"draws":57,"losses":246,"wins":211},"GB2-04":{"draws":201,"losses":74,"wins":235},"GB2-05":{"draws":0,"losses":227,"wins":317},"GB2-06":{"draws":27,"losses":88,"wins":397},"GB2-07":{"draws":0,"losses":158,"wins":382},"GB2-08":{"draws":0,"losses":210,"wins":332}},"none":{"GB2-01":{"draws":60,"losses":120,"wins":346},"GB2-02":{"draws":383,"losses":95,"wins":14},"GB2-03":{"draws":224,"losses":216,"wins":72},"GB2-04":{"draws":309,"losses":149,"wins":50},"GB2-05":{"draws":0,"losses":270,"wins":270},"GB2-06":{"draws":6,"losses":302,"wins":210},"GB2-07":{"draws":0,"losses":378,"wins":160},"GB2-08":{"draws":0,"losses":115,"wins":427}}},"per_game_raw_elo_all":{"GB2-01":1741.7291849417427,"GB2-02":1533.1507933564262,"GB2-03":1392.0183232622232,"GB2-04":1559.0932912713622,"GB2-05":1590.5206456105104,"GB2-06":1748.2738654522036,"GB2-07":1565.500775162421,"GB2-08":1845.4558772050957},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1662.1345470489055,"GB2-02":1755.2016289820256,"GB2-03":1401.7274295612692,"GB2-04":1642.9507252697938,"GB2-05":1757.0121246802005,"GB2-06":1891.402658885924,"GB2-07":1735.7255115932312,"GB2-08":1975.2433328486256},"medium":{"GB2-01":1851.0378824580187,"GB2-02":1422.0597173435813,"GB2-03":1435.1455617046972,"GB2-04":1622.1502986801042,"GB2-05":1565.7264499579521,"GB2-06":2005.3903965714285,"GB2-07":1750.3283991850376,"GB2-08":1609.9974314343801},"none":{"GB2-01":1712.0151253183042,"GB2-02":1422.191033743672,"GB2-03":1339.181978520703,"GB2-04":1412.178849864188,"GB2-05":1448.823362193379,"GB2-06":1348.0285408992584,"GB2-07":1210.4484147089945,"GB2-08":1951.1268673322816}},"per_game_tracks":{"highest":{"GB2-01":67.2834907151903,"GB2-02":79.56973000237281,"GB2-03":45.61058762318383,"GB2-04":69.24553517031161,"GB2-05":70.69730425071555,"GB2-06":74.7090959978435,"GB2-07":70.51699814112501,"GB2-08":80.33325279139343},"medium":{"GB2-01":81.84302568980287,"GB2-02":42.99663062186767,"GB2-03":49.36150005277055,"GB2-04":67.0726812757106,"GB2-05":58.59135878586872,"GB2-06":80.49252869857578,"GB2-07":71.40287034416846,"GB2-08":62.43079837072988},"none":{"GB2-01":71.6432828680858,"GB2-02":43.013388087566845,"GB2-03":38.55834629889377,"GB2-04":41.67454928329681,"GB2-05":49.773033295599106,"GB2-06":43.2001615136123,"GB2-07":32.221096842081906,"GB2-08":79.26165271410657}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":21,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-27T23:45:40Z","reasoning":{"highest":69.74574933651701,"medium":64.27392422993681,"none":49.91818886290539},"reasoning_agg":{"highest":{"max":80.33325279139343,"mean":69.74574933651701,"min":45.61058762318383},"medium":{"max":81.84302568980287,"mean":64.27392422993681,"min":42.99663062186767},"none":{"max":79.26165271410657,"mean":49.91818886290539,"min":32.221096842081906}},"reasoning_labels":{"highest":"Max","medium":"High","none":"None"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":19.82756047361162},"working_program_strength":{"all":61.31262080978641,"highest":69.74574933651701,"medium":64.27392422993681,"none":49.91818886290539}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5-5:4ef54dba72bc4f61","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":4.385362},"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":0.327498}},"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":0.48637800000000003},"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":5.199238},"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":60.37641882587666,"highest":91.25547431221523,"medium":50.155466446791685,"none":39.718315718623074},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":57.174801121038406,"score":57.174801121038406},"GB2-02":{"attempts":3,"playable":61.079182028766496,"score":61.079182028766496},"GB2-03":{"attempts":3,"playable":57.597266874106595,"score":57.597266874106595},"GB2-04":{"attempts":3,"playable":55.312365389798344,"score":55.312365389798344},"GB2-05":{"attempts":3,"playable":42.920598999149234,"score":42.920598999149234},"GB2-06":{"attempts":3,"playable":60.44835824021698,"score":60.44835824021698},"GB2-07":{"attempts":3,"playable":69.1139598421699,"score":69.1139598421699},"GB2-08":{"attempts":3,"playable":79.36481811176736,"score":79.36481811176736}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":78.5947508965668,"score":78.5947508965668},"GB2-02":{"attempts":1,"playable":96.02280979202162,"score":96.02280979202162},"GB2-03":{"attempts":1,"playable":94.75053060358901,"score":94.75053060358901},"GB2-04":{"attempts":1,"playable":82.25257055994042,"score":82.25257055994042},"GB2-05":{"attempts":1,"playable":97.2356914854446,"score":97.2356914854446},"GB2-06":{"attempts":1,"playable":90.09855302005252,"score":90.09855302005252},"GB2-07":{"attempts":1,"playable":92.1543049292443,"score":92.1543049292443},"GB2-08":{"attempts":1,"playable":98.93458321086258,"score":98.93458321086258}},"medium":{"GB2-01":{"attempts":1,"playable":44.880252102403006,"score":44.880252102403006},"GB2-02":{"attempts":1,"playable":41.57864866979928,"score":41.57864866979928},"GB2-03":{"attempts":1,"playable":31.07020684053248,"score":31.07020684053248},"GB2-04":{"attempts":1,"playable":40.08143795079809,"score":40.08143795079809},"GB2-05":{"attempts":1,"playable":18.13635386898222,"score":18.13635386898222},"GB2-06":{"attempts":1,"playable":74.5194763236649,"score":74.5194763236649},"GB2-07":{"attempts":1,"playable":69.84857070780896,"score":69.84857070780896},"GB2-08":{"attempts":1,"playable":81.12878511034455,"score":81.12878511034455}},"none":{"GB2-01":{"attempts":1,"playable":48.04940036414542,"score":48.04940036414542},"GB2-02":{"attempts":1,"playable":45.63608762447859,"score":45.63608762447859},"GB2-03":{"attempts":1,"playable":46.971063178198285,"score":46.971063178198285},"GB2-04":{"attempts":1,"playable":43.603087658656506,"score":43.603087658656506},"GB2-05":{"attempts":1,"playable":13.389751643020869,"score":13.389751643020869},"GB2-06":{"attempts":1,"playable":16.727045376933543,"score":16.727045376933543},"GB2-07":{"attempts":1,"playable":45.33900388945645,"score":45.33900388945645},"GB2-08":{"attempts":1,"playable":58.03108601409497,"score":58.03108601409497}}},"id":"claude-sonnet-5-5","is_recent_addition":false,"last_measured_at":"2026-11-03T07:16:08Z","match_totals_all":{"draws":2109,"losses":3996,"wins":6435},"match_totals_tracks":{"highest":{"draws":313,"losses":202,"wins":3667},"medium":{"draws":936,"losses":1645,"wins":1597},"none":{"draws":860,"losses":2149,"wins":1171}},"model_slug":"claude-sonnet-5-5","official_rank_by_reasoning":{"highest":5,"medium":37,"none":43},"overall":{"max":98.93458321086258,"mean":60.37641882587666,"min":13.389751643020869},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":17,"overall_ranking_status":"ranked","per_game":{"GB2-01":78.5947508965668,"GB2-02":96.02280979202162,"GB2-03":94.75053060358901,"GB2-04":82.25257055994042,"GB2-05":97.2356914854446,"GB2-06":90.09855302005252,"GB2-07":92.1543049292443,"GB2-08":98.93458321086258},"per_game_all":{"GB2-01":57.174801121038406,"GB2-02":61.079182028766496,"GB2-03":57.597266874106595,"GB2-04":55.312365389798344,"GB2-05":42.920598999149234,"GB2-06":60.44835824021698,"GB2-07":69.1139598421699,"GB2-08":79.36481811176736},"per_game_match_totals_all":{"GB2-01":{"draws":215,"losses":570,"wins":789},"GB2-02":{"draws":785,"losses":196,"wins":499},"GB2-03":{"draws":339,"losses":509,"wins":688},"GB2-04":{"draws":698,"losses":354,"wins":484},"GB2-05":{"draws":0,"losses":926,"wins":696},"GB2-06":{"draws":37,"losses":603,"wins":908},"GB2-07":{"draws":0,"losses":514,"wins":1108},"GB2-08":{"draws":35,"losses":324,"wins":1263}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":154,"losses":36,"wins":334},"GB2-02":{"draws":26,"losses":6,"wins":460},"GB2-03":{"draws":0,"losses":26,"wins":484},"GB2-04":{"draws":96,"losses":47,"wins":371},"GB2-05":{"draws":0,"losses":13,"wins":527},"GB2-06":{"draws":32,"losses":34,"wins":452},"GB2-07":{"draws":0,"losses":39,"wins":503},"GB2-08":{"draws":5,"losses":1,"wins":536}},"medium":{"GB2-01":{"draws":14,"losses":283,"wins":227},"GB2-02":{"draws":382,"losses":104,"wins":8},"GB2-03":{"draws":220,"losses":258,"wins":38},"GB2-04":{"draws":315,"losses":154,"wins":39},"GB2-05":{"draws":0,"losses":444,"wins":98},"GB2-06":{"draws":2,"losses":133,"wins":379},"GB2-07":{"draws":0,"losses":167,"wins":373},"GB2-08":{"draws":3,"losses":102,"wins":435}},"none":{"GB2-01":{"draws":47,"losses":251,"wins":228},"GB2-02":{"draws":377,"losses":86,"wins":31},"GB2-03":{"draws":119,"losses":225,"wins":166},"GB2-04":{"draws":287,"losses":153,"wins":74},"GB2-05":{"draws":0,"losses":469,"wins":71},"GB2-06":{"draws":3,"losses":436,"wins":77},"GB2-07":{"draws":0,"losses":308,"wins":232},"GB2-08":{"draws":27,"losses":221,"wins":292}}},"per_game_raw_elo_all":{"GB2-01":1569.4624265981354,"GB2-02":1664.659320286479,"GB2-03":1635.1131919166166,"GB2-04":1540.4137599957985,"GB2-05":1521.4854601233462,"GB2-06":1679.0039951021656,"GB2-07":1813.1656341157511,"GB2-08":2098.5203117323877},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1802.0722494523454,"GB2-02":2140.375136884801,"GB2-03":2221.2095825176975,"GB2-04":1794.3140803831072,"GB2-05":2713.8648299302786,"GB2-06":2230.4771710955715,"GB2-07":2331.3777458275845,"GB2-08":2767.995007980034},"medium":{"GB2-01":1437.8691089194017,"GB2-02":1410.9206667112392,"GB2-03":1270.3302724574228,"GB2-04":1399.4765694937162,"GB2-05":975.8402789566893,"GB2-06":1887.7720479073782,"GB2-07":1724.895231299923,"GB2-08":1993.4082037027388},"none":{"GB2-01":1468.4459214226595,"GB2-02":1442.6821572633971,"GB2-03":1413.7997207747296,"GB2-04":1427.4506301105723,"GB2-05":874.7512714830705,"GB2-06":918.7627663035477,"GB2-07":1383.223925219746,"GB2-08":1534.15772351439}},"per_game_tracks":{"highest":{"GB2-01":78.5947508965668,"GB2-02":96.02280979202162,"GB2-03":94.75053060358901,"GB2-04":82.25257055994042,"GB2-05":97.2356914854446,"GB2-06":90.09855302005252,"GB2-07":92.1543049292443,"GB2-08":98.93458321086258},"medium":{"GB2-01":44.880252102403006,"GB2-02":41.57864866979928,"GB2-03":31.07020684053248,"GB2-04":40.08143795079809,"GB2-05":18.13635386898222,"GB2-06":74.5194763236649,"GB2-07":69.84857070780896,"GB2-08":81.12878511034455},"none":{"GB2-01":48.04940036414542,"GB2-02":45.63608762447859,"GB2-03":46.971063178198285,"GB2-04":43.603087658656506,"GB2-05":13.389751643020869,"GB2-06":16.727045376933543,"GB2-07":45.33900388945645,"GB2-08":58.03108601409497}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":20,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-31T16:54:52Z","reasoning":{"highest":91.25547431221523,"medium":50.155466446791685,"none":39.718315718623074},"reasoning_agg":{"highest":{"max":98.93458321086258,"mean":91.25547431221523,"min":78.5947508965668},"medium":{"max":81.12878511034455,"mean":50.155466446791685,"min":18.13635386898222},"none":{"max":58.03108601409497,"mean":39.718315718623074,"min":13.389751643020869}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":51.53715859359215},"working_program_strength":{"all":60.37641882587666,"highest":91.25547431221523,"medium":50.155466446791685,"none":39.718315718623074}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-6:0e946827094010a6","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":0.25482999999999995}},"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":3.145718000000001},"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":59.04278520800761,"highest":64.82622046233612,"medium":68.56454234332578,"none":43.737592818360916},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":57.70857909455757,"score":57.70857909455757},"GB2-02":{"attempts":3,"playable":59.55997486566299,"score":59.55997486566299},"GB2-03":{"attempts":3,"playable":53.20643824121308,"score":53.20643824121308},"GB2-04":{"attempts":3,"playable":54.91897154596065,"score":54.91897154596065},"GB2-05":{"attempts":3,"playable":70.36311603561042,"score":70.36311603561042},"GB2-06":{"attempts":3,"playable":50.322925291195354,"score":50.322925291195354},"GB2-07":{"attempts":3,"playable":68.16372493092047,"score":68.16372493092047},"GB2-08":{"attempts":3,"playable":58.0985516589403,"score":58.0985516589403}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":48.974323330993066,"score":48.974323330993066},"GB2-02":{"attempts":1,"playable":81.91718157310746,"score":81.91718157310746},"GB2-03":{"attempts":1,"playable":50.93525997581485,"score":50.93525997581485},"GB2-04":{"attempts":1,"playable":58.66500871144814,"score":58.66500871144814},"GB2-05":{"attempts":1,"playable":83.04751377206915,"score":83.04751377206915},"GB2-06":{"attempts":1,"playable":63.1085882015784,"score":63.1085882015784},"GB2-07":{"attempts":1,"playable":74.47961985634501,"score":74.47961985634501},"GB2-08":{"attempts":1,"playable":57.48226827733285,"score":57.48226827733285}},"medium":{"GB2-01":{"attempts":1,"playable":59.815182424881876,"score":59.815182424881876},"GB2-02":{"attempts":1,"playable":53.55316895685881,"score":53.55316895685881},"GB2-03":{"attempts":1,"playable":64.99090118209733,"score":64.99090118209733},"GB2-04":{"attempts":1,"playable":64.33798000378722,"score":64.33798000378722},"GB2-05":{"attempts":1,"playable":79.69364466469693,"score":79.69364466469693},"GB2-06":{"attempts":1,"playable":75.70593284431966,"score":75.70593284431966},"GB2-07":{"attempts":1,"playable":74.31755066404733,"score":74.31755066404733},"GB2-08":{"attempts":1,"playable":76.10197800591709,"score":76.10197800591709}},"none":{"GB2-01":{"attempts":1,"playable":64.33623152779779,"score":64.33623152779779},"GB2-02":{"attempts":1,"playable":43.20957406702271,"score":43.20957406702271},"GB2-03":{"attempts":1,"playable":43.69315356572705,"score":43.69315356572705},"GB2-04":{"attempts":1,"playable":41.75392592264659,"score":41.75392592264659},"GB2-05":{"attempts":1,"playable":48.34818967006519,"score":48.34818967006519},"GB2-06":{"attempts":1,"playable":12.154254827688003,"score":12.154254827688003},"GB2-07":{"attempts":1,"playable":55.69400427236905,"score":55.69400427236905},"GB2-08":{"attempts":1,"playable":40.71140869357096,"score":40.71140869357096}}},"id":"x-ai/grok-4.6","is_recent_addition":false,"last_measured_at":"2026-11-03T07:13:05Z","match_totals_all":{"draws":2895,"losses":3815,"wins":5858},"match_totals_tracks":{"highest":{"draws":791,"losses":1124,"wins":2281},"medium":{"draws":803,"losses":941,"wins":2444},"none":{"draws":1301,"losses":1750,"wins":1133}},"model_slug":"x-ai-grok-4-6","official_rank_by_reasoning":{"highest":24,"medium":14,"none":32},"overall":{"max":83.04751377206915,"mean":59.04278520800761,"min":12.154254827688003},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":18,"overall_ranking_status":"ranked","per_game":{"GB2-01":48.974323330993066,"GB2-02":81.91718157310746,"GB2-03":50.93525997581485,"GB2-04":58.66500871144814,"GB2-05":83.04751377206915,"GB2-06":63.1085882015784,"GB2-07":74.47961985634501,"GB2-08":57.48226827733285},"per_game_all":{"GB2-01":57.70857909455757,"GB2-02":59.55997486566299,"GB2-03":53.20643824121308,"GB2-04":54.91897154596065,"GB2-05":70.36311603561042,"GB2-06":50.322925291195354,"GB2-07":68.16372493092047,"GB2-08":58.0985516589403},"per_game_match_totals_all":{"GB2-01":{"draws":445,"losses":448,"wins":683},"GB2-02":{"draws":769,"losses":232,"wins":483},"GB2-03":{"draws":616,"losses":458,"wins":474},"GB2-04":{"draws":848,"losses":289,"wins":401},"GB2-05":{"draws":0,"losses":483,"wins":1145},"GB2-06":{"draws":45,"losses":759,"wins":742},"GB2-07":{"draws":0,"losses":530,"wins":1090},"GB2-08":{"draws":172,"losses":616,"wins":840}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":250,"losses":146,"wins":132},"GB2-02":{"draws":71,"losses":57,"wins":364},"GB2-03":{"draws":107,"losses":215,"wins":196},"GB2-04":{"draws":278,"losses":80,"wins":156},"GB2-05":{"draws":0,"losses":92,"wins":450},"GB2-06":{"draws":30,"losses":182,"wins":306},"GB2-07":{"draws":0,"losses":140,"wins":400},"GB2-08":{"draws":55,"losses":212,"wins":277}},"medium":{"GB2-01":{"draws":129,"losses":147,"wins":248},"GB2-02":{"draws":311,"losses":82,"wins":105},"GB2-03":{"draws":99,"losses":143,"wins":272},"GB2-04":{"draws":254,"losses":62,"wins":196},"GB2-05":{"draws":0,"losses":112,"wins":432},"GB2-06":{"draws":10,"losses":122,"wins":382},"GB2-07":{"draws":0,"losses":141,"wins":399},"GB2-08":{"draws":0,"losses":132,"wins":410}},"none":{"GB2-01":{"draws":66,"losses":155,"wins":303},"GB2-02":{"draws":387,"losses":93,"wins":14},"GB2-03":{"draws":410,"losses":100,"wins":6},"GB2-04":{"draws":316,"losses":147,"wins":49},"GB2-05":{"draws":0,"losses":279,"wins":263},"GB2-06":{"draws":5,"losses":455,"wins":54},"GB2-07":{"draws":0,"losses":249,"wins":291},"GB2-08":{"draws":117,"losses":272,"wins":153}}},"per_game_raw_elo_all":{"GB2-01":1563.757380481399,"GB2-02":1571.9471865123212,"GB2-03":1473.7292985906233,"GB2-04":1519.3037256579646,"GB2-05":1814.537788147788,"GB2-06":1471.746290193392,"GB2-07":1707.967988601773,"GB2-08":1565.4062760869485},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1477.358323137341,"GB2-02":1787.35488222756,"GB2-03":1449.336788411559,"GB2-04":1548.0305391091106,"GB2-05":2054.9622307413824,"GB2-06":1677.0831926402839,"GB2-07":1803.6700882533642,"GB2-08":1525.1530974802165},"medium":{"GB2-01":1583.6042057710629,"GB2-02":1504.7587556115254,"GB2-03":1587.091426373269,"GB2-04":1597.0712402743598,"GB2-05":1958.1690416734532,"GB2-06":1910.5761801934068,"GB2-07":1800.743197714701,"GB2-08":1881.943695641476},"none":{"GB2-01":1630.3096125357933,"GB2-02":1423.727921697878,"GB2-03":1384.7596809870422,"GB2-04":1412.809397590423,"GB2-05":1430.482092028528,"GB2-06":827.5794977464852,"GB2-07":1519.4906798372544,"GB2-08":1289.1220351391526}},"per_game_tracks":{"highest":{"GB2-01":48.974323330993066,"GB2-02":81.91718157310746,"GB2-03":50.93525997581485,"GB2-04":58.66500871144814,"GB2-05":83.04751377206915,"GB2-06":63.1085882015784,"GB2-07":74.47961985634501,"GB2-08":57.48226827733285},"medium":{"GB2-01":59.815182424881876,"GB2-02":53.55316895685881,"GB2-03":64.99090118209733,"GB2-04":64.33798000378722,"GB2-05":79.69364466469693,"GB2-06":75.70593284431966,"GB2-07":74.31755066404733,"GB2-08":76.10197800591709},"none":{"GB2-01":64.33623152779779,"GB2-02":43.20957406702271,"GB2-03":43.69315356572705,"GB2-04":41.75392592264659,"GB2-05":48.34818967006519,"GB2-06":12.154254827688003,"GB2-07":55.69400427236905,"GB2-08":40.71140869357096}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":21,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":-2,"rank_movement_baseline_at":"2026-10-31T17:02:38Z","reasoning":{"highest":64.82622046233612,"medium":68.56454234332578,"none":43.737592818360916},"reasoning_agg":{"highest":{"max":83.04751377206915,"mean":64.82622046233612,"min":48.974323330993066},"medium":{"max":79.69364466469693,"mean":68.56454234332578,"min":53.55316895685881},"none":{"max":64.33623152779779,"mean":43.737592818360916,"min":12.154254827688003}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.826949524964867},"working_program_strength":{"all":59.04278520800761,"highest":64.82622046233612,"medium":68.56454234332578,"none":43.737592818360916}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-8-flash:7fdf302c5dd6848a","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":1.1454976827810865},"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":0.5746151281850016},"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":0.25553343903391196},"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":1.9756462499999998},"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":58.95088732463628,"highest":64.20197253787775,"medium":59.24898099412766,"none":53.401708441903395},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":59.05525815779479,"score":59.05525815779479},"GB2-02":{"attempts":3,"playable":49.229614965784144,"score":49.229614965784144},"GB2-03":{"attempts":3,"playable":67.69226430772547,"score":67.69226430772547},"GB2-04":{"attempts":3,"playable":50.525566179298174,"score":50.525566179298174},"GB2-05":{"attempts":3,"playable":56.287750178365854,"score":56.287750178365854},"GB2-06":{"attempts":3,"playable":77.30650354559444,"score":77.30650354559444},"GB2-07":{"attempts":3,"playable":54.94230283225745,"score":54.94230283225745},"GB2-08":{"attempts":3,"playable":56.56783843026986,"score":56.56783843026986}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":53.36003994015394,"score":53.36003994015394},"GB2-02":{"attempts":1,"playable":69.0457357944127,"score":69.0457357944127},"GB2-03":{"attempts":1,"playable":69.74540641938347,"score":69.74540641938347},"GB2-04":{"attempts":1,"playable":46.504546980499754,"score":46.504546980499754},"GB2-05":{"attempts":1,"playable":63.84200164861299,"score":63.84200164861299},"GB2-06":{"attempts":1,"playable":86.40463834022155,"score":86.40463834022155},"GB2-07":{"attempts":1,"playable":67.82948956929422,"score":67.82948956929422},"GB2-08":{"attempts":1,"playable":56.88392161044339,"score":56.88392161044339}},"medium":{"GB2-01":{"attempts":1,"playable":69.4139613118113,"score":69.4139613118113},"GB2-02":{"attempts":1,"playable":39.02463242054744,"score":39.02463242054744},"GB2-03":{"attempts":1,"playable":82.71813080802619,"score":82.71813080802619},"GB2-04":{"attempts":1,"playable":60.58773505309384,"score":60.58773505309384},"GB2-05":{"attempts":1,"playable":52.21002867304346,"score":52.21002867304346},"GB2-06":{"attempts":1,"playable":75.27527488818954,"score":75.27527488818954},"GB2-07":{"attempts":1,"playable":55.726999020189496,"score":55.726999020189496},"GB2-08":{"attempts":1,"playable":39.035085778120035,"score":39.035085778120035}},"none":{"GB2-01":{"attempts":1,"playable":54.391773221419136,"score":54.391773221419136},"GB2-02":{"attempts":1,"playable":39.61847668239227,"score":39.61847668239227},"GB2-03":{"attempts":1,"playable":50.613255695766725,"score":50.613255695766725},"GB2-04":{"attempts":1,"playable":44.48441650430092,"score":44.48441650430092},"GB2-05":{"attempts":1,"playable":52.811220213441125,"score":52.811220213441125},"GB2-06":{"attempts":1,"playable":70.23959740837222,"score":70.23959740837222},"GB2-07":{"attempts":1,"playable":41.27041990728862,"score":41.27041990728862},"GB2-08":{"attempts":1,"playable":73.78450790224616,"score":73.78450790224616}}},"id":"google/gemini-3.8-flash","is_recent_addition":false,"last_measured_at":"2026-11-03T07:07:06Z","match_totals_all":{"draws":2392,"losses":4087,"wins":6085},"match_totals_tracks":{"highest":{"draws":426,"losses":1327,"wins":2435},"medium":{"draws":974,"losses":1259,"wins":1951},"none":{"draws":992,"losses":1501,"wins":1699}},"model_slug":"google-gemini-3-8-flash","official_rank_by_reasoning":{"highest":26,"medium":24,"none":17},"overall":{"max":86.40463834022155,"mean":58.95088732463628,"min":39.02463242054744},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":19,"overall_ranking_status":"ranked","per_game":{"GB2-01":53.36003994015394,"GB2-02":69.0457357944127,"GB2-03":69.74540641938347,"GB2-04":46.504546980499754,"GB2-05":63.84200164861299,"GB2-06":86.40463834022155,"GB2-07":67.82948956929422,"GB2-08":56.88392161044339},"per_game_all":{"GB2-01":59.05525815779479,"GB2-02":49.229614965784144,"GB2-03":67.69226430772547,"GB2-04":50.525566179298174,"GB2-05":56.287750178365854,"GB2-06":77.30650354559444,"GB2-07":54.94230283225745,"GB2-08":56.56783843026986},"per_game_match_totals_all":{"GB2-01":{"draws":326,"losses":489,"wins":769},"GB2-02":{"draws":950,"losses":294,"wins":236},"GB2-03":{"draws":202,"losses":428,"wins":908},"GB2-04":{"draws":707,"losses":426,"wins":401},"GB2-05":{"draws":0,"losses":712,"wins":916},"GB2-06":{"draws":38,"losses":338,"wins":1170},"GB2-07":{"draws":0,"losses":759,"wins":867},"GB2-08":{"draws":169,"losses":641,"wins":818}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":47,"losses":224,"wins":257},"GB2-02":{"draws":206,"losses":55,"wins":233},"GB2-03":{"draws":10,"losses":162,"wins":342},"GB2-04":{"draws":92,"losses":234,"wins":184},"GB2-05":{"draws":0,"losses":198,"wins":346},"GB2-06":{"draws":29,"losses":55,"wins":430},"GB2-07":{"draws":0,"losses":179,"wins":363},"GB2-08":{"draws":42,"losses":220,"wins":280}},"medium":{"GB2-01":{"draws":81,"losses":122,"wins":325},"GB2-02":{"draws":369,"losses":123,"wins":2},"GB2-03":{"draws":103,"losses":43,"wins":366},"GB2-04":{"draws":303,"losses":57,"wins":152},"GB2-05":{"draws":0,"losses":257,"wins":283},"GB2-06":{"draws":4,"losses":128,"wins":384},"GB2-07":{"draws":0,"losses":248,"wins":292},"GB2-08":{"draws":114,"losses":281,"wins":147}},"none":{"GB2-01":{"draws":198,"losses":143,"wins":187},"GB2-02":{"draws":375,"losses":116,"wins":1},"GB2-03":{"draws":89,"losses":223,"wins":200},"GB2-04":{"draws":312,"losses":135,"wins":65},"GB2-05":{"draws":0,"losses":257,"wins":287},"GB2-06":{"draws":5,"losses":155,"wins":356},"GB2-07":{"draws":0,"losses":332,"wins":212},"GB2-08":{"draws":13,"losses":140,"wins":391}}},"per_game_raw_elo_all":{"GB2-01":1578.540690988504,"GB2-02":1474.7924119595893,"GB2-03":1643.3836195631986,"GB2-04":1482.9977309573524,"GB2-05":1536.8397583206618,"GB2-06":1947.959428283308,"GB2-07":1514.471512379354,"GB2-08":1538.8408277823225},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1519.7693738681162,"GB2-02":1638.2973729644311,"GB2-03":1641.9287661308854,"GB2-04":1450.3135419813548,"GB2-05":1641.937321593645,"GB2-06":2134.5917972098932,"GB2-07":1693.0501533838492,"GB2-08":1515.4488642732354},"medium":{"GB2-01":1686.0297376547203,"GB2-02":1390.673013568861,"GB2-03":1841.7998809286644,"GB2-04":1564.2755198600514,"GB2-05":1480.3711158532835,"GB2-06":1902.274186692032,"GB2-07":1519.9356060030143,"GB2-08":1268.367388438842},"none":{"GB2-01":1529.822961442675,"GB2-02":1395.406849345476,"GB2-03":1446.4222116300466,"GB2-04":1434.4041310306513,"GB2-05":1488.2108375150565,"GB2-06":1807.0123009479987,"GB2-07":1330.4287777511986,"GB2-08":1832.70623063489}},"per_game_tracks":{"highest":{"GB2-01":53.36003994015394,"GB2-02":69.0457357944127,"GB2-03":69.74540641938347,"GB2-04":46.504546980499754,"GB2-05":63.84200164861299,"GB2-06":86.40463834022155,"GB2-07":67.82948956929422,"GB2-08":56.88392161044339},"medium":{"GB2-01":69.4139613118113,"GB2-02":39.02463242054744,"GB2-03":82.71813080802619,"GB2-04":60.58773505309384,"GB2-05":52.21002867304346,"GB2-06":75.27527488818954,"GB2-07":55.726999020189496,"GB2-08":39.035085778120035},"none":{"GB2-01":54.391773221419136,"GB2-02":39.61847668239227,"GB2-03":50.613255695766725,"GB2-04":44.48441650430092,"GB2-05":52.811220213441125,"GB2-06":70.23959740837222,"GB2-07":41.27041990728862,"GB2-08":73.78450790224616}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":23,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-31T16:50:35Z","reasoning":{"highest":64.20197253787775,"medium":59.24898099412766,"none":53.401708441903395},"reasoning_agg":{"highest":{"max":86.40463834022155,"mean":64.20197253787775,"min":46.504546980499754},"medium":{"max":82.71813080802619,"mean":59.24898099412766,"min":39.02463242054744},"none":{"max":73.78450790224616,"mean":53.401708441903395,"min":39.61847668239227}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.800264095974356},"working_program_strength":{"all":58.95088732463628,"highest":64.20197253787775,"medium":59.24898099412766,"none":53.401708441903395}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-3:a8f2ad3145988995","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":0.19110975}},"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":0.41740125},"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":1.98947125}},"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":57.8192863096106,"highest":68.69216508240976,"medium":64.73061244265412,"none":40.03508140376793},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":57.703267711114215,"score":57.703267711114215},"GB2-02":{"attempts":3,"playable":54.76552576093517,"score":54.76552576093517},"GB2-03":{"attempts":3,"playable":65.49088881712971,"score":65.49088881712971},"GB2-04":{"attempts":3,"playable":51.80470053135068,"score":51.80470053135068},"GB2-05":{"attempts":3,"playable":57.37490102525894,"score":57.37490102525894},"GB2-06":{"attempts":3,"playable":66.30266442777229,"score":66.30266442777229},"GB2-07":{"attempts":3,"playable":48.85875952950867,"score":48.85875952950867},"GB2-08":{"attempts":3,"playable":60.25358267381512,"score":60.25358267381512}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":74.98182320501323,"score":74.98182320501323},"GB2-02":{"attempts":1,"playable":60.8718782015092,"score":60.8718782015092},"GB2-03":{"attempts":1,"playable":80.9235878071107,"score":80.9235878071107},"GB2-04":{"attempts":1,"playable":50.09041705161278,"score":50.09041705161278},"GB2-05":{"attempts":1,"playable":76.39819416070492,"score":76.39819416070492},"GB2-06":{"attempts":1,"playable":82.15784536784014,"score":82.15784536784014},"GB2-07":{"attempts":1,"playable":56.60037962905702,"score":56.60037962905702},"GB2-08":{"attempts":1,"playable":67.51319523643002,"score":67.51319523643002}},"medium":{"GB2-01":{"attempts":1,"playable":72.78411003236003,"score":72.78411003236003},"GB2-02":{"attempts":1,"playable":57.17305116050188,"score":57.17305116050188},"GB2-03":{"attempts":1,"playable":61.96790561002234,"score":61.96790561002234},"GB2-04":{"attempts":1,"playable":62.42485550350669,"score":62.42485550350669},"GB2-05":{"attempts":1,"playable":56.934675322611916,"score":56.934675322611916},"GB2-06":{"attempts":1,"playable":78.84990776779823,"score":78.84990776779823},"GB2-07":{"attempts":1,"playable":52.74923344148898,"score":52.74923344148898},"GB2-08":{"attempts":1,"playable":74.96116070294285,"score":74.96116070294285}},"none":{"GB2-01":{"attempts":1,"playable":25.3438698959694,"score":25.3438698959694},"GB2-02":{"attempts":1,"playable":46.25164792079444,"score":46.25164792079444},"GB2-03":{"attempts":1,"playable":53.58117303425608,"score":53.58117303425608},"GB2-04":{"attempts":1,"playable":42.89882903893259,"score":42.89882903893259},"GB2-05":{"attempts":1,"playable":38.791833592459994,"score":38.791833592459994},"GB2-06":{"attempts":1,"playable":37.900240147678446,"score":37.900240147678446},"GB2-07":{"attempts":1,"playable":37.22666551798002,"score":37.22666551798002},"GB2-08":{"attempts":1,"playable":38.28639208207248,"score":38.28639208207248}}},"id":"meta/muse-spark-1.3","is_recent_addition":false,"last_measured_at":"2026-11-03T07:16:19Z","match_totals_all":{"draws":2160,"losses":4360,"wins":6032},"match_totals_tracks":{"highest":{"draws":544,"losses":1072,"wins":2562},"medium":{"draws":634,"losses":1202,"wins":2352},"none":{"draws":982,"losses":2086,"wins":1118}},"model_slug":"meta-muse-spark-1-3","official_rank_by_reasoning":{"highest":18,"medium":16,"none":41},"overall":{"max":82.15784536784014,"mean":57.8192863096106,"min":25.3438698959694},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":20,"overall_ranking_status":"ranked","per_game":{"GB2-01":74.98182320501323,"GB2-02":60.8718782015092,"GB2-03":80.9235878071107,"GB2-04":50.09041705161278,"GB2-05":76.39819416070492,"GB2-06":82.15784536784014,"GB2-07":56.60037962905702,"GB2-08":67.51319523643002},"per_game_all":{"GB2-01":57.703267711114215,"GB2-02":54.76552576093517,"GB2-03":65.49088881712971,"GB2-04":51.80470053135068,"GB2-05":57.37490102525894,"GB2-06":66.30266442777229,"GB2-07":48.85875952950867,"GB2-08":60.25358267381512},"per_game_match_totals_all":{"GB2-01":{"draws":105,"losses":621,"wins":856},"GB2-02":{"draws":951,"losses":214,"wins":317},"GB2-03":{"draws":182,"losses":474,"wins":882},"GB2-04":{"draws":690,"losses":416,"wins":430},"GB2-05":{"draws":0,"losses":696,"wins":934},"GB2-06":{"draws":58,"losses":503,"wins":979},"GB2-07":{"draws":0,"losses":860,"wins":760},"GB2-08":{"draws":174,"losses":576,"wins":874}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":4,"losses":131,"wins":393},"GB2-02":{"draws":273,"losses":63,"wins":158},"GB2-03":{"draws":36,"losses":87,"wins":391},"GB2-04":{"draws":146,"losses":188,"wins":174},"GB2-05":{"draws":0,"losses":129,"wins":413},"GB2-06":{"draws":35,"losses":75,"wins":402},"GB2-07":{"draws":0,"losses":243,"wins":297},"GB2-08":{"draws":50,"losses":156,"wins":334}},"medium":{"GB2-01":{"draws":0,"losses":144,"wins":382},"GB2-02":{"draws":308,"losses":64,"wins":122},"GB2-03":{"draws":58,"losses":179,"wins":275},"GB2-04":{"draws":252,"losses":73,"wins":187},"GB2-05":{"draws":0,"losses":236,"wins":310},"GB2-06":{"draws":13,"losses":104,"wins":399},"GB2-07":{"draws":0,"losses":265,"wins":275},"GB2-08":{"draws":3,"losses":137,"wins":402}},"none":{"GB2-01":{"draws":101,"losses":346,"wins":81},"GB2-02":{"draws":370,"losses":87,"wins":37},"GB2-03":{"draws":88,"losses":208,"wins":216},"GB2-04":{"draws":292,"losses":155,"wins":69},"GB2-05":{"draws":0,"losses":331,"wins":211},"GB2-06":{"draws":10,"losses":324,"wins":178},"GB2-07":{"draws":0,"losses":352,"wins":188},"GB2-08":{"draws":121,"losses":283,"wins":138}}},"per_game_raw_elo_all":{"GB2-01":1570.9828309235484,"GB2-02":1515.3385912191352,"GB2-03":1611.9707087026247,"GB2-04":1493.5390628490588,"GB2-05":1574.7977713070484,"GB2-06":1759.0606787015283,"GB2-07":1429.8090438230338,"GB2-08":1607.388921559031},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1753.2701903576385,"GB2-02":1564.6394455945335,"GB2-03":1807.33758127721,"GB2-04":1478.5951354928884,"GB2-05":1875.604765603448,"GB2-06":2039.945247870308,"GB2-07":1531.7497589546795,"GB2-08":1705.4266796738311},"medium":{"GB2-01":1725.7658654565737,"GB2-02":1533.8952224862853,"GB2-03":1555.0283889100015,"GB2-04":1580.137862842805,"GB2-05":1543.0069835462832,"GB2-06":1972.2269252956585,"GB2-07":1480.140892781495,"GB2-08":1857.5598006507694},"none":{"GB2-01":1233.9124369564336,"GB2-02":1447.4811055765872,"GB2-03":1473.5461559206633,"GB2-04":1421.8841902114834,"GB2-05":1305.7815647714137,"GB2-06":1265.0098629386187,"GB2-07":1277.5364797329266,"GB2-08":1259.1802843524922}},"per_game_tracks":{"highest":{"GB2-01":74.98182320501323,"GB2-02":60.8718782015092,"GB2-03":80.9235878071107,"GB2-04":50.09041705161278,"GB2-05":76.39819416070492,"GB2-06":82.15784536784014,"GB2-07":56.60037962905702,"GB2-08":67.51319523643002},"medium":{"GB2-01":72.78411003236003,"GB2-02":57.17305116050188,"GB2-03":61.96790561002234,"GB2-04":62.42485550350669,"GB2-05":56.934675322611916,"GB2-06":78.84990776779823,"GB2-07":52.74923344148898,"GB2-08":74.96116070294285},"none":{"GB2-01":25.3438698959694,"GB2-02":46.25164792079444,"GB2-03":53.58117303425608,"GB2-04":42.89882903893259,"GB2-05":38.791833592459994,"GB2-06":37.900240147678446,"GB2-07":37.22666551798002,"GB2-08":38.28639208207248}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":22,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":-2,"rank_movement_baseline_at":"2026-10-31T17:01:44Z","reasoning":{"highest":68.69216508240976,"medium":64.73061244265412,"none":40.03508140376793},"reasoning_agg":{"highest":{"max":82.15784536784014,"mean":68.69216508240976,"min":50.09041705161278},"medium":{"max":78.84990776779823,"mean":64.73061244265412,"min":52.74923344148898},"none":{"max":53.58117303425608,"mean":40.03508140376793,"min":25.3438698959694}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":28.657083678641825},"working_program_strength":{"all":57.8192863096106,"highest":68.69216508240976,"medium":64.73061244265412,"none":40.03508140376793}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-5:55ca101cc0f270a3","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":1.6998544000000002},"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":56.57338722071663,"highest":61.4489234446838,"medium":60.10860665324294,"none":48.162631564223176},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":71.66601488550894,"score":71.66601488550894},"GB2-02":{"attempts":3,"playable":50.68879148689945,"score":50.68879148689945},"GB2-03":{"attempts":3,"playable":37.974266181239365,"score":37.974266181239365},"GB2-04":{"attempts":3,"playable":42.1766205622146,"score":42.1766205622146},"GB2-05":{"attempts":3,"playable":58.5978195597607,"score":58.5978195597607},"GB2-06":{"attempts":3,"playable":44.62233710602417,"score":44.62233710602417},"GB2-07":{"attempts":3,"playable":59.41524386142665,"score":59.41524386142665},"GB2-08":{"attempts":3,"playable":87.44600412265918,"score":87.44600412265918}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":82.14444723963726,"score":82.14444723963726},"GB2-02":{"attempts":1,"playable":57.73874624441757,"score":57.73874624441757},"GB2-03":{"attempts":1,"playable":43.29032476765347,"score":43.29032476765347},"GB2-04":{"attempts":1,"playable":43.12702158666115,"score":43.12702158666115},"GB2-05":{"attempts":1,"playable":70.97342521163192,"score":70.97342521163192},"GB2-06":{"attempts":1,"playable":51.105943378804994,"score":51.105943378804994},"GB2-07":{"attempts":1,"playable":54.475344612876064,"score":54.475344612876064},"GB2-08":{"attempts":1,"playable":88.7361345157879,"score":88.7361345157879}},"medium":{"GB2-01":{"attempts":1,"playable":81.81790833821499,"score":81.81790833821499},"GB2-02":{"attempts":1,"playable":51.83350786166944,"score":51.83350786166944},"GB2-03":{"attempts":1,"playable":55.261906281327,"score":55.261906281327},"GB2-04":{"attempts":1,"playable":41.67454928329681,"score":41.67454928329681},"GB2-05":{"attempts":1,"playable":64.24409547457053,"score":64.24409547457053},"GB2-06":{"attempts":1,"playable":42.55409142684448,"score":42.55409142684448},"GB2-07":{"attempts":1,"playable":56.832338989467644,"score":56.832338989467644},"GB2-08":{"attempts":1,"playable":86.65045557055258,"score":86.65045557055258}},"none":{"GB2-01":{"attempts":1,"playable":51.035689078674565,"score":51.035689078674565},"GB2-02":{"attempts":1,"playable":42.49412035461134,"score":42.49412035461134},"GB2-03":{"attempts":1,"playable":15.370567494737628,"score":15.370567494737628},"GB2-04":{"attempts":1,"playable":41.72829081668584,"score":41.72829081668584},"GB2-05":{"attempts":1,"playable":40.575937993079656,"score":40.575937993079656},"GB2-06":{"attempts":1,"playable":40.20697651242304,"score":40.20697651242304},"GB2-07":{"attempts":1,"playable":66.93804798193626,"score":66.93804798193626},"GB2-08":{"attempts":1,"playable":86.95142228163705,"score":86.95142228163705}}},"id":"x-ai/grok-4.5","is_recent_addition":false,"last_measured_at":"2026-11-03T07:15:17Z","match_totals_all":{"draws":2586,"losses":4246,"wins":5710},"match_totals_tracks":{"highest":{"draws":679,"losses":1306,"wins":2193},"medium":{"draws":855,"losses":1274,"wins":2049},"none":{"draws":1052,"losses":1666,"wins":1468}},"model_slug":"x-ai-grok-4-5","official_rank_by_reasoning":{"highest":32,"medium":23,"none":26},"overall":{"max":88.7361345157879,"mean":56.57338722071663,"min":15.370567494737628},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":21,"overall_ranking_status":"ranked","per_game":{"GB2-01":82.14444723963726,"GB2-02":57.73874624441757,"GB2-03":43.29032476765347,"GB2-04":43.12702158666115,"GB2-05":70.97342521163192,"GB2-06":51.105943378804994,"GB2-07":54.475344612876064,"GB2-08":88.7361345157879},"per_game_all":{"GB2-01":71.66601488550894,"GB2-02":50.68879148689945,"GB2-03":37.974266181239365,"GB2-04":42.1766205622146,"GB2-05":58.5978195597607,"GB2-06":44.62233710602417,"GB2-07":59.41524386142665,"GB2-08":87.44600412265918},"per_game_match_totals_all":{"GB2-01":{"draws":408,"losses":245,"wins":925},"GB2-02":{"draws":923,"losses":288,"wins":269},"GB2-03":{"draws":328,"losses":826,"wins":382},"GB2-04":{"draws":915,"losses":448,"wins":167},"GB2-05":{"draws":0,"losses":673,"wins":953},"GB2-06":{"draws":12,"losses":878,"wins":648},"GB2-07":{"draws":0,"losses":683,"wins":941},"GB2-08":{"draws":0,"losses":205,"wins":1425}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":109,"losses":40,"wins":377},"GB2-02":{"draws":239,"losses":95,"wins":158},"GB2-03":{"draws":115,"losses":247,"wins":150},"GB2-04":{"draws":212,"losses":191,"wins":107},"GB2-05":{"draws":0,"losses":158,"wins":384},"GB2-06":{"draws":4,"losses":258,"wins":250},"GB2-07":{"draws":0,"losses":256,"wins":284},"GB2-08":{"draws":0,"losses":61,"wins":483}},"medium":{"GB2-01":{"draws":48,"losses":72,"wins":406},"GB2-02":{"draws":319,"losses":85,"wins":90},"GB2-03":{"draws":139,"losses":173,"wins":198},"GB2-04":{"draws":345,"losses":131,"wins":32},"GB2-05":{"draws":0,"losses":194,"wins":348},"GB2-06":{"draws":4,"losses":303,"wins":205},"GB2-07":{"draws":0,"losses":243,"wins":301},"GB2-08":{"draws":0,"losses":73,"wins":469}},"none":{"GB2-01":{"draws":251,"losses":133,"wins":142},"GB2-02":{"draws":365,"losses":108,"wins":21},"GB2-03":{"draws":74,"losses":406,"wins":34},"GB2-04":{"draws":358,"losses":126,"wins":28},"GB2-05":{"draws":0,"losses":321,"wins":221},"GB2-06":{"draws":4,"losses":317,"wins":193},"GB2-07":{"draws":0,"losses":184,"wins":356},"GB2-08":{"draws":0,"losses":71,"wins":473}}},"per_game_raw_elo_all":{"GB2-01":1734.5908301976144,"GB2-02":1482.5962152576292,"GB2-03":1320.7167161059583,"GB2-04":1416.1578618991543,"GB2-05":1579.967335654673,"GB2-06":1370.9176730386655,"GB2-07":1572.4607473241285,"GB2-08":2150.431282225757},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1855.891262190983,"GB2-02":1538.524044611245,"GB2-03":1381.1973689566737,"GB2-04":1423.6889553918213,"GB2-05":1762.1806130295533,"GB2-06":1473.7574083914842,"GB2-07":1503.1235940005054,"GB2-08":2186.185963594368},"medium":{"GB2-01":1850.636108266459,"GB2-02":1491.1459300052627,"GB2-03":1489.215752508012,"GB2-04":1412.178849864188,"GB2-05":1648.1133586866697,"GB2-06":1337.886373348104,"GB2-07":1534.899821679631,"GB2-08":2128.5468837009535},"none":{"GB2-01":1497.2451201354015,"GB2-02":1418.1186711563792,"GB2-03":1091.737026853189,"GB2-04":1412.605780441454,"GB2-05":1329.6080352477957,"GB2-06":1301.1092373764081,"GB2-07":1679.358826292249,"GB2-08":2136.56099938195}},"per_game_tracks":{"highest":{"GB2-01":82.14444723963726,"GB2-02":57.73874624441757,"GB2-03":43.29032476765347,"GB2-04":43.12702158666115,"GB2-05":70.97342521163192,"GB2-06":51.105943378804994,"GB2-07":54.475344612876064,"GB2-08":88.7361345157879},"medium":{"GB2-01":81.81790833821499,"GB2-02":51.83350786166944,"GB2-03":55.261906281327,"GB2-04":41.67454928329681,"GB2-05":64.24409547457053,"GB2-06":42.55409142684448,"GB2-07":56.832338989467644,"GB2-08":86.65045557055258},"none":{"GB2-01":51.035689078674565,"GB2-02":42.49412035461134,"GB2-03":15.370567494737628,"GB2-04":41.72829081668584,"GB2-05":40.575937993079656,"GB2-06":40.20697651242304,"GB2-07":66.93804798193626,"GB2-08":86.95142228163705}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":20,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":-2,"rank_movement_baseline_at":"2026-10-31T17:04:13Z","reasoning":{"highest":61.4489234446838,"medium":60.10860665324294,"none":48.162631564223176},"reasoning_agg":{"highest":{"max":88.7361345157879,"mean":61.4489234446838,"min":43.12702158666115},"medium":{"max":86.65045557055258,"mean":60.10860665324294,"min":41.67454928329681},"none":{"max":86.95142228163705,"mean":48.162631564223176,"min":15.370567494737628}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":13.286291880460624},"working_program_strength":{"all":56.57338722071663,"highest":61.4489234446838,"medium":60.10860665324294,"none":48.162631564223176}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flashx:c228ee386657944a","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":0.48296143999999996},"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":0.21156558000000003},"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":0.06816269999999999}},"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":0.21156558},"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":0.0681627},"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":0.48296143999999996}},"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":55.92169694602037,"highest":67.56963825022014,"medium":50.57773253418553,"none":49.61772005365545},"economics_best_value":{"per_model":{"all":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":60.14279529583815,"score":60.14279529583815},"GB2-02":{"attempts":3,"playable":53.49434408703792,"score":53.49434408703792},"GB2-03":{"attempts":3,"playable":61.080538383206154,"score":61.080538383206154},"GB2-04":{"attempts":3,"playable":60.86468082309755,"score":60.86468082309755},"GB2-05":{"attempts":3,"playable":53.5982197396901,"score":53.5982197396901},"GB2-06":{"attempts":3,"playable":64.44973426031724,"score":64.44973426031724},"GB2-07":{"attempts":3,"playable":64.20567242845401,"score":64.20567242845401},"GB2-08":{"attempts":3,"playable":29.537590550521823,"score":29.537590550521823}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":40.566605278188284,"score":40.566605278188284},"GB2-02":{"attempts":1,"playable":67.75215551390845,"score":67.75215551390845},"GB2-03":{"attempts":1,"playable":82.57855822792163,"score":82.57855822792163},"GB2-04":{"attempts":1,"playable":77.09901043648169,"score":77.09901043648169},"GB2-05":{"attempts":1,"playable":75.79090628959139,"score":75.79090628959139},"GB2-06":{"attempts":1,"playable":79.7556898448504,"score":79.7556898448504},"GB2-07":{"attempts":1,"playable":70.36661506655636,"score":70.36661506655636},"GB2-08":{"attempts":1,"playable":46.6475653442628,"score":46.6475653442628}},"medium":{"GB2-01":{"attempts":1,"playable":75.52952475276055,"score":75.52952475276055},"GB2-02":{"attempts":1,"playable":51.46039818190764,"score":51.46039818190764},"GB2-03":{"attempts":1,"playable":54.880044434329164,"score":54.880044434329164},"GB2-04":{"attempts":1,"playable":54.84237987374199,"score":54.84237987374199},"GB2-05":{"attempts":1,"playable":38.5489068828315,"score":38.5489068828315},"GB2-06":{"attempts":1,"playable":53.12924419832399,"score":53.12924419832399},"GB2-07":{"attempts":1,"playable":58.51848889391281,"score":58.51848889391281},"GB2-08":{"attempts":1,"playable":17.712873055676567,"score":17.712873055676567}},"none":{"GB2-01":{"attempts":1,"playable":64.33225585656561,"score":64.33225585656561},"GB2-02":{"attempts":1,"playable":41.27047856529767,"score":41.27047856529767},"GB2-03":{"attempts":1,"playable":45.78301248736767,"score":45.78301248736767},"GB2-04":{"attempts":1,"playable":50.65265215906896,"score":50.65265215906896},"GB2-05":{"attempts":1,"playable":46.4548460466474,"score":46.4548460466474},"GB2-06":{"attempts":1,"playable":60.46426873777732,"score":60.46426873777732},"GB2-07":{"attempts":1,"playable":63.73191332489283,"score":63.73191332489283},"GB2-08":{"attempts":1,"playable":24.2523332516261,"score":24.2523332516261}}},"id":"z-ai/glm-5.3-flashx","is_recent_addition":false,"last_measured_at":"2026-11-03T06:49:54Z","match_totals_all":{"draws":2351,"losses":4503,"wins":5692},"match_totals_tracks":{"highest":{"draws":519,"losses":1138,"wins":2527},"medium":{"draws":778,"losses":1735,"wins":1665},"none":{"draws":1054,"losses":1630,"wins":1500}},"model_slug":"z-ai-glm-5-3-flashx","official_rank_by_reasoning":{"highest":20,"medium":35,"none":22},"overall":{"max":82.57855822792163,"mean":55.92169694602037,"min":17.712873055676567},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":22,"overall_ranking_status":"ranked","per_game":{"GB2-01":40.566605278188284,"GB2-02":67.75215551390845,"GB2-03":82.57855822792163,"GB2-04":77.09901043648169,"GB2-05":75.79090628959139,"GB2-06":79.7556898448504,"GB2-07":70.36661506655636,"GB2-08":46.6475653442628},"per_game_all":{"GB2-01":60.14279529583815,"GB2-02":53.49434408703792,"GB2-03":61.080538383206154,"GB2-04":60.86468082309755,"GB2-05":53.5982197396901,"GB2-06":64.44973426031724,"GB2-07":64.20567242845401,"GB2-08":29.537590550521823},"per_game_match_totals_all":{"GB2-01":{"draws":123,"losses":572,"wins":885},"GB2-02":{"draws":960,"losses":227,"wins":293},"GB2-03":{"draws":167,"losses":548,"wins":821},"GB2-04":{"draws":796,"losses":220,"wins":516},"GB2-05":{"draws":0,"losses":755,"wins":869},"GB2-06":{"draws":46,"losses":544,"wins":954},"GB2-07":{"draws":0,"losses":598,"wins":1022},"GB2-08":{"draws":259,"losses":1039,"wins":332}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":3,"losses":313,"wins":210},"GB2-02":{"draws":227,"losses":51,"wins":214},"GB2-03":{"draws":7,"losses":92,"wins":415},"GB2-04":{"draws":159,"losses":43,"wins":312},"GB2-05":{"draws":0,"losses":132,"wins":408},"GB2-06":{"draws":23,"losses":94,"wins":397},"GB2-07":{"draws":0,"losses":164,"wins":376},"GB2-08":{"draws":100,"losses":249,"wins":195}},"medium":{"GB2-01":{"draws":6,"losses":126,"wins":392},"GB2-02":{"draws":356,"losses":67,"wins":69},"GB2-03":{"draws":51,"losses":220,"wins":241},"GB2-04":{"draws":297,"losses":89,"wins":124},"GB2-05":{"draws":0,"losses":332,"wins":210},"GB2-06":{"draws":18,"losses":241,"wins":255},"GB2-07":{"draws":0,"losses":232,"wins":308},"GB2-08":{"draws":50,"losses":428,"wins":66}},"none":{"GB2-01":{"draws":114,"losses":133,"wins":283},"GB2-02":{"draws":377,"losses":109,"wins":10},"GB2-03":{"draws":109,"losses":236,"wins":165},"GB2-04":{"draws":340,"losses":88,"wins":80},"GB2-05":{"draws":0,"losses":291,"wins":251},"GB2-06":{"draws":5,"losses":209,"wins":302},"GB2-07":{"draws":0,"losses":202,"wins":338},"GB2-08":{"draws":109,"losses":362,"wins":71}}},"per_game_raw_elo_all":{"GB2-01":1595.48764789673,"GB2-02":1507.5477860941376,"GB2-03":1575.9643655971397,"GB2-04":1575.6122692952906,"GB2-05":1523.4226143073395,"GB2-06":1709.2406035792046,"GB2-07":1640.9649540854516,"GB2-08":1150.2166837380107},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1395.8378163726552,"GB2-02":1625.9449832848338,"GB2-03":1839.0049995299178,"GB2-04":1727.1939704047074,"GB2-05":1861.6300152387814,"GB2-06":1990.415141554243,"GB2-07":1733.2753112733994,"GB2-08":1365.591112977534},"medium":{"GB2-01":1760.3576111161278,"GB2-02":1488.206787431089,"GB2-03":1485.6327314700231,"GB2-04":1516.5932684322363,"GB2-05":1302.5057863113204,"GB2-06":1506.7308094896894,"GB2-07":1557.9682573555474,"GB2-08":997.646278050009},"none":{"GB2-01":1630.2675162014073,"GB2-02":1408.4915875664901,"GB2-03":1403.2553657914789,"GB2-04":1483.049569048928,"GB2-05":1406.1320413719166,"GB2-06":1630.5758596936812,"GB2-07":1631.6512936274082,"GB2-08":1087.412660186489}},"per_game_tracks":{"highest":{"GB2-01":40.566605278188284,"GB2-02":67.75215551390845,"GB2-03":82.57855822792163,"GB2-04":77.09901043648169,"GB2-05":75.79090628959139,"GB2-06":79.7556898448504,"GB2-07":70.36661506655636,"GB2-08":46.6475653442628},"medium":{"GB2-01":75.52952475276055,"GB2-02":51.46039818190764,"GB2-03":54.880044434329164,"GB2-04":54.84237987374199,"GB2-05":38.5489068828315,"GB2-06":53.12924419832399,"GB2-07":58.51848889391281,"GB2-08":17.712873055676567},"none":{"GB2-01":64.33225585656561,"GB2-02":41.27047856529767,"GB2-03":45.78301248736767,"GB2-04":50.65265215906896,"GB2-05":46.4548460466474,"GB2-06":60.46426873777732,"GB2-07":63.73191332489283,"GB2-08":24.2523332516261}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":5,"worked_first_time":19,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":-2,"rank_movement_baseline_at":"2026-10-31T16:39:40Z","reasoning":{"highest":67.56963825022014,"medium":50.57773253418553,"none":49.61772005365545},"reasoning_agg":{"highest":{"max":82.57855822792163,"mean":67.56963825022014,"min":40.566605278188284},"medium":{"max":75.52952475276055,"mean":50.57773253418553,"min":17.712873055676567},"none":{"max":64.33225585656561,"mean":49.61772005365545,"min":24.2523332516261}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":17.95191819656469},"working_program_strength":{"all":55.92169694602037,"highest":67.56963825022014,"medium":50.57773253418553,"none":49.61772005365545}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-haiku-5-5:c169a5f28df68275","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":0.0249632}},"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":0.09558080000000001},"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":55.45747899691775,"highest":72.80204438714073,"medium":55.6640782759257,"none":37.90631432768682},"economics_best_value":{"per_model":{"all":true,"highest":true}},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"infra_excluded"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":39.113246494897616,"score":39.113246494897616},"GB2-02":{"attempts":3,"playable":57.36843200451009,"score":57.36843200451009},"GB2-03":{"attempts":2,"playable":53.53373452947278,"score":53.53373452947278},"GB2-04":{"attempts":3,"playable":62.67115421393432,"score":62.67115421393432},"GB2-05":{"attempts":3,"playable":51.04923266423631,"score":51.04923266423631},"GB2-06":{"attempts":3,"playable":67.24578772540649,"score":67.24578772540649},"GB2-07":{"attempts":3,"playable":56.77574999907622,"score":56.77574999907622},"GB2-08":{"attempts":3,"playable":49.479724391252184,"score":49.479724391252184}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":39.83153314436582,"score":39.83153314436582},"GB2-02":{"attempts":1,"playable":68.73943293517692,"score":68.73943293517692},"GB2-04":{"attempts":1,"playable":78.54953651806652,"score":78.54953651806652},"GB2-05":{"attempts":1,"playable":83.58486991404158,"score":83.58486991404158},"GB2-06":{"attempts":1,"playable":89.88872050565753,"score":89.88872050565753},"GB2-07":{"attempts":1,"playable":64.86939454484632,"score":64.86939454484632},"GB2-08":{"attempts":1,"playable":84.1508231478304,"score":84.1508231478304}},"medium":{"GB2-01":{"attempts":1,"playable":43.97029802933223,"score":43.97029802933223},"GB2-02":{"attempts":1,"playable":61.482982567193204,"score":61.482982567193204},"GB2-03":{"attempts":1,"playable":65.19808673473601,"score":65.19808673473601},"GB2-04":{"attempts":1,"playable":68.11203056929618,"score":68.11203056929618},"GB2-05":{"attempts":1,"playable":54.311130660711314,"score":54.311130660711314},"GB2-06":{"attempts":1,"playable":65.21555496433561,"score":65.21555496433561},"GB2-07":{"attempts":1,"playable":55.17200780288047,"score":55.17200780288047},"GB2-08":{"attempts":1,"playable":31.850534878920556,"score":31.850534878920556}},"none":{"GB2-01":{"attempts":1,"playable":33.537908310994794,"score":33.537908310994794},"GB2-02":{"attempts":1,"playable":41.88288051116017,"score":41.88288051116017},"GB2-03":{"attempts":1,"playable":41.869382324209546,"score":41.869382324209546},"GB2-04":{"attempts":1,"playable":41.351895554440276,"score":41.351895554440276},"GB2-05":{"attempts":1,"playable":15.251697417956029,"score":15.251697417956029},"GB2-06":{"attempts":1,"playable":46.63308770622633,"score":46.63308770622633},"GB2-07":{"attempts":1,"playable":50.28584764950186,"score":50.28584764950186},"GB2-08":{"attempts":1,"playable":32.437815147005615,"score":32.437815147005615}}},"id":"claude-haiku-5-5","is_recent_addition":false,"last_measured_at":"2026-11-03T07:14:34Z","match_totals_all":{"draws":2631,"losses":4273,"wins":5124},"match_totals_tracks":{"highest":{"draws":404,"losses":813,"wins":2451},"medium":{"draws":954,"losses":1436,"wins":1788},"none":{"draws":1273,"losses":2024,"wins":885}},"model_slug":"claude-haiku-5-5","official_rank_by_reasoning":{"medium":27,"none":49},"overall":{"max":89.88872050565753,"mean":55.45747899691775,"min":15.251697417956029},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":23,"overall_ranking_status":"partial","per_game":{"GB2-01":39.83153314436582,"GB2-02":68.73943293517692,"GB2-04":78.54953651806652,"GB2-05":83.58486991404158,"GB2-06":89.88872050565753,"GB2-07":64.86939454484632,"GB2-08":84.1508231478304},"per_game_all":{"GB2-01":39.113246494897616,"GB2-02":57.36843200451009,"GB2-04":62.67115421393432,"GB2-05":51.04923266423631,"GB2-06":67.24578772540649,"GB2-07":56.77574999907622,"GB2-08":49.479724391252184},"per_game_match_totals_all":{"GB2-01":{"draws":268,"losses":829,"wins":477},"GB2-02":{"draws":873,"losses":213,"wins":396},"GB2-03":{"draws":282,"losses":363,"wins":381},"GB2-04":{"draws":635,"losses":272,"wins":625},"GB2-05":{"draws":0,"losses":796,"wins":830},"GB2-06":{"draws":60,"losses":491,"wins":993},"GB2-07":{"draws":0,"losses":727,"wins":893},"GB2-08":{"draws":513,"losses":582,"wins":529}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":34,"losses":301,"wins":191},"GB2-02":{"draws":224,"losses":48,"wins":222},"GB2-04":{"draws":107,"losses":61,"wins":344},"GB2-05":{"draws":0,"losses":89,"wins":453},"GB2-06":{"draws":38,"losses":32,"wins":444},"GB2-07":{"draws":0,"losses":196,"wins":344},"GB2-08":{"draws":1,"losses":86,"wins":453}},"medium":{"GB2-01":{"draws":142,"losses":224,"wins":158},"GB2-02":{"draws":259,"losses":67,"wins":168},"GB2-03":{"draws":96,"losses":143,"wins":273},"GB2-04":{"draws":206,"losses":66,"wins":238},"GB2-05":{"draws":0,"losses":247,"wins":295},"GB2-06":{"draws":6,"losses":182,"wins":326},"GB2-07":{"draws":0,"losses":252,"wins":288},"GB2-08":{"draws":245,"losses":255,"wins":42}},"none":{"GB2-01":{"draws":92,"losses":304,"wins":128},"GB2-02":{"draws":390,"losses":98,"wins":6},"GB2-03":{"draws":186,"losses":220,"wins":108},"GB2-04":{"draws":322,"losses":145,"wins":43},"GB2-05":{"draws":0,"losses":460,"wins":82},"GB2-06":{"draws":16,"losses":277,"wins":223},"GB2-07":{"draws":0,"losses":279,"wins":261},"GB2-08":{"draws":267,"losses":241,"wins":34}}},"per_game_raw_elo_all":{"GB2-01":1380.8290874878567,"GB2-02":1539.5001852888763,"GB2-04":1595.490619186118,"GB2-05":1498.665802492181,"GB2-06":1780.4971023038504,"GB2-07":1536.154786123486,"GB2-08":1478.2184054222914},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1388.5909384200336,"GB2-02":1635.3436124925865,"GB2-04":1744.8643669105209,"GB2-05":2071.7158504267873,"GB2-06":2224.496331429073,"GB2-07":1648.326994695822,"GB2-08":2064.9957437441753},"medium":{"GB2-01":1429.0571888158188,"GB2-02":1569.8413663415545,"GB2-03":1589.3593289296487,"GB2-04":1631.9938093000892,"GB2-05":1507.9101908725324,"GB2-06":1714.828642685393,"GB2-07":1512.4645542447906,"GB2-08":1181.2866016057249},"none":{"GB2-01":1324.8391352277176,"GB2-02":1413.3155770324875,"GB2-03":1368.6253392473336,"GB2-04":1409.6136813477433,"GB2-05":916.3713661772232,"GB2-06":1402.1663327970848,"GB2-07":1447.672809429846,"GB2-08":1188.3728709169732}},"per_game_tracks":{"highest":{"GB2-01":39.83153314436582,"GB2-02":68.73943293517692,"GB2-04":78.54953651806652,"GB2-05":83.58486991404158,"GB2-06":89.88872050565753,"GB2-07":64.86939454484632,"GB2-08":84.1508231478304},"medium":{"GB2-01":43.97029802933223,"GB2-02":61.482982567193204,"GB2-03":65.19808673473601,"GB2-04":68.11203056929618,"GB2-05":54.311130660711314,"GB2-06":65.21555496433561,"GB2-07":55.17200780288047,"GB2-08":31.850534878920556},"none":{"GB2-01":33.537908310994794,"GB2-02":41.88288051116017,"GB2-03":41.869382324209546,"GB2-04":41.351895554440276,"GB2-05":15.251697417956029,"GB2-06":46.63308770622633,"GB2-07":50.28584764950186,"GB2-08":32.437815147005615}},"program_outcomes":{"all":{"counted_attempts":23,"failed":0,"infra_excluded":1,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":22,"working":23},"highest":{"counted_attempts":7,"failed":0,"infra_excluded":1,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":72.80204438714073,"medium":55.6640782759257,"none":37.90631432768682},"reasoning_agg":{"highest":{"max":89.88872050565753,"mean":72.80204438714073,"min":39.83153314436582},"medium":{"max":68.11203056929618,"mean":55.6640782759257,"min":31.850534878920556},"none":{"max":50.28584764950186,"mean":37.90631432768682,"min":15.251697417956029}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":34.8957300594539},"working_program_strength":{"all":55.45747899691775,"highest":72.80204438714073,"medium":55.6640782759257,"none":37.90631432768682}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-open:fa3d224e721a03ab","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.15589245,"mean":0.12161143124999997,"median":0.124379975,"min":0.08796145,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.9728914499999998},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0828612,"mean":0.042346231250000005,"median":0.032108575,"min":0.0286407,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.33876984999999993},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.053624950000000005,"mean":0.0276842,"median":0.025075325,"min":0.0206182,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.2214736}},"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":0.0828612,"mean":0.042346231250000005,"median":0.032108575,"min":0.0286407,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.33876985000000004},"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":0.053624950000000005,"mean":0.0276842,"median":0.025075325,"min":0.0206182,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.2214736},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.15589245,"mean":0.12161143124999997,"median":0.124379975,"min":0.08796145,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.9728914500000001}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.15589245,"mean":0.06388062083333333,"median":0.033168575000000006,"min":0.0206182,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"recorded_attempt_count":27,"run_count":24,"total":1.5331348999999999},"codegen_latency_ms":{"attempt_count":27,"max_ms":402561,"mean_ms":145436.875,"min_ms":29772,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":402561,"mean_ms":298657.375,"min_ms":177131,"run_count":8},"medium":{"attempt_count":10,"max_ms":176476,"mean_ms":81184.125,"min_ms":41325,"run_count":8},"none":{"attempt_count":9,"max_ms":171955,"mean_ms":56469.125,"min_ms":29772,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":34389,"output_mean":12379.875,"output_min":2743,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":34389,"output_mean":26327.25,"output_min":17727,"run_count":8},"medium":{"attempt_count":10,"output_max":13963,"output_mean":6880.875,"output_min":3882,"run_count":8},"none":{"attempt_count":9,"output_max":7898,"output_mean":3931.5,"output_min":2743,"run_count":8}},"display_name":"Muse Spark Open","economics":{"all":55.44781446470719,"highest":59.19397100902525,"medium":52.79791053075513,"none":54.35156185434119},"first_seen_at":"2026-11-03T06:57:14Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"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":28,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"requested_max_output_token_observations":27,"requested_max_output_tokens":[943718],"total_output_tokens":297117,"total_reasoning_output_tokens":186663,"total_visible_output_tokens":110454,"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":943718,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-open","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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":67.93166307209967,"score":67.93166307209967},"GB2-02":{"attempts":3,"playable":44.03920855251005,"score":44.03920855251005},"GB2-03":{"attempts":3,"playable":50.94437517028543,"score":50.94437517028543},"GB2-04":{"attempts":3,"playable":43.101843105084015,"score":43.101843105084015},"GB2-05":{"attempts":3,"playable":49.12883909288261,"score":49.12883909288261},"GB2-06":{"attempts":3,"playable":60.04864288866298,"score":60.04864288866298},"GB2-07":{"attempts":3,"playable":53.057613226124325,"score":53.057613226124325},"GB2-08":{"attempts":3,"playable":75.3303306100084,"score":75.3303306100084}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":90.85089778068843,"score":90.85089778068843},"GB2-02":{"attempts":1,"playable":44.3855418105866,"score":44.3855418105866},"GB2-03":{"attempts":1,"playable":65.27607850729964,"score":65.27607850729964},"GB2-04":{"attempts":1,"playable":37.991210522174626,"score":37.991210522174626},"GB2-05":{"attempts":1,"playable":38.056768832158774,"score":38.056768832158774},"GB2-06":{"attempts":1,"playable":47.19725888953744,"score":47.19725888953744},"GB2-07":{"attempts":1,"playable":71.93525036146143,"score":71.93525036146143},"GB2-08":{"attempts":1,"playable":77.85876136829498,"score":77.85876136829498}},"medium":{"GB2-01":{"attempts":1,"playable":49.84645433572505,"score":49.84645433572505},"GB2-02":{"attempts":1,"playable":43.201748181705184,"score":43.201748181705184},"GB2-03":{"attempts":1,"playable":32.21875578770826,"score":32.21875578770826},"GB2-04":{"attempts":1,"playable":46.005430284517494,"score":46.005430284517494},"GB2-05":{"attempts":1,"playable":54.29812831741129,"score":54.29812831741129},"GB2-06":{"attempts":1,"playable":74.51647779580203,"score":74.51647779580203},"GB2-07":{"attempts":1,"playable":55.52623916748494,"score":55.52623916748494},"GB2-08":{"attempts":1,"playable":66.77005037568678,"score":66.77005037568678}},"none":{"GB2-01":{"attempts":1,"playable":63.09763709988553,"score":63.09763709988553},"GB2-02":{"attempts":1,"playable":44.530335665238354,"score":44.530335665238354},"GB2-03":{"attempts":1,"playable":55.338291215848386,"score":55.338291215848386},"GB2-04":{"attempts":1,"playable":45.30888850855994,"score":45.30888850855994},"GB2-05":{"attempts":1,"playable":55.031620129077766,"score":55.031620129077766},"GB2-06":{"attempts":1,"playable":58.43219198064949,"score":58.43219198064949},"GB2-07":{"attempts":1,"playable":31.711350149426604,"score":31.711350149426604},"GB2-08":{"attempts":1,"playable":81.36218008604347,"score":81.36218008604347}}},"id":"meta/muse-spark-open","is_recent_addition":true,"last_measured_at":"2026-11-03T06:57:14Z","match_totals_all":{"draws":2467,"losses":4428,"wins":5575},"match_totals_tracks":{"highest":{"draws":657,"losses":1366,"wins":2089},"medium":{"draws":976,"losses":1523,"wins":1677},"none":{"draws":834,"losses":1539,"wins":1809}},"model_slug":"meta-muse-spark-open","official_rank_by_reasoning":{"highest":35,"medium":31,"none":16},"overall":{"max":90.85089778068843,"mean":55.44781446470719,"min":31.711350149426604},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":24,"overall_ranking_status":"ranked","per_game":{"GB2-01":90.85089778068843,"GB2-02":44.3855418105866,"GB2-03":65.27607850729964,"GB2-04":37.991210522174626,"GB2-05":38.056768832158774,"GB2-06":47.19725888953744,"GB2-07":71.93525036146143,"GB2-08":77.85876136829498},"per_game_all":{"GB2-01":67.93166307209967,"GB2-02":44.03920855251005,"GB2-03":50.94437517028543,"GB2-04":43.101843105084015,"GB2-05":49.12883909288261,"GB2-06":60.04864288866298,"GB2-07":53.057613226124325,"GB2-08":75.3303306100084},"per_game_match_totals_all":{"GB2-01":{"draws":205,"losses":405,"wins":968},"GB2-02":{"draws":1025,"losses":291,"wins":92},"GB2-03":{"draws":305,"losses":641,"wins":592},"GB2-04":{"draws":883,"losses":450,"wins":197},"GB2-05":{"draws":0,"losses":827,"wins":799},"GB2-06":{"draws":49,"losses":614,"wins":881},"GB2-07":{"draws":0,"losses":787,"wins":831},"GB2-08":{"draws":0,"losses":413,"wins":1215}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":48,"wins":480},"GB2-02":{"draws":311,"losses":84,"wins":31},"GB2-03":{"draws":61,"losses":160,"wins":291},"GB2-04":{"draws":266,"losses":190,"wins":54},"GB2-05":{"draws":0,"losses":333,"wins":207},"GB2-06":{"draws":19,"losses":274,"wins":223},"GB2-07":{"draws":0,"losses":155,"wins":385},"GB2-08":{"draws":0,"losses":122,"wins":418}},"medium":{"GB2-01":{"draws":126,"losses":202,"wins":198},"GB2-02":{"draws":360,"losses":105,"wins":25},"GB2-03":{"draws":137,"losses":291,"wins":84},"GB2-04":{"draws":327,"losses":118,"wins":63},"GB2-05":{"draws":0,"losses":249,"wins":295},"GB2-06":{"draws":26,"losses":121,"wins":365},"GB2-07":{"draws":0,"losses":249,"wins":289},"GB2-08":{"draws":0,"losses":188,"wins":358}},"none":{"GB2-01":{"draws":79,"losses":155,"wins":290},"GB2-02":{"draws":354,"losses":102,"wins":36},"GB2-03":{"draws":107,"losses":190,"wins":217},"GB2-04":{"draws":290,"losses":142,"wins":80},"GB2-05":{"draws":0,"losses":245,"wins":297},"GB2-06":{"draws":4,"losses":219,"wins":293},"GB2-07":{"draws":0,"losses":383,"wins":157},"GB2-08":{"draws":0,"losses":103,"wins":439}}},"per_game_raw_elo_all":{"GB2-01":1712.622356755837,"GB2-02":1430.215214840566,"GB2-03":1453.7881550345166,"GB2-04":1423.3078359050598,"GB2-05":1440.3467335472217,"GB2-06":1631.4504227315608,"GB2-07":1493.3135550555007,"GB2-08":1869.9537722215039},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2034.8102502424063,"GB2-02":1432.9241448675673,"GB2-03":1590.2155931336124,"GB2-04":1382.6387208341373,"GB2-05":1295.8440192695152,"GB2-06":1411.117469516762,"GB2-07":1759.2515991486548,"GB2-08":1920.0861079222746},"medium":{"GB2-01":1485.766010341537,"GB2-02":1423.666631717824,"GB2-03":1281.2146824446386,"GB2-04":1446.384543326668,"GB2-05":1507.738440733593,"GB2-06":1887.7146762871912,"GB2-07":1517.2299216521078,"GB2-08":1690.9912506460373},"none":{"GB2-01":1617.2908096835674,"GB2-02":1434.0548679363067,"GB2-03":1489.9341895252996,"GB2-04":1440.9002435543744,"GB2-05":1517.4577406385572,"GB2-06":1595.5191223907293,"GB2-07":1203.4591443657398,"GB2-08":1998.7839580962002}},"per_game_tracks":{"highest":{"GB2-01":90.85089778068843,"GB2-02":44.3855418105866,"GB2-03":65.27607850729964,"GB2-04":37.991210522174626,"GB2-05":38.056768832158774,"GB2-06":47.19725888953744,"GB2-07":71.93525036146143,"GB2-08":77.85876136829498},"medium":{"GB2-01":49.84645433572505,"GB2-02":43.201748181705184,"GB2-03":32.21875578770826,"GB2-04":46.005430284517494,"GB2-05":54.29812831741129,"GB2-06":74.51647779580203,"GB2-07":55.52623916748494,"GB2-08":66.77005037568678},"none":{"GB2-01":63.09763709988553,"GB2-02":44.530335665238354,"GB2-03":55.338291215848386,"GB2-04":45.30888850855994,"GB2-05":55.031620129077766,"GB2-06":58.43219198064949,"GB2-07":31.711350149426604,"GB2-08":81.36218008604347}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":21,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":59.19397100902525,"medium":52.79791053075513,"none":54.35156185434119},"reasoning_agg":{"highest":{"max":90.85089778068843,"mean":59.19397100902525,"min":37.991210522174626},"medium":{"max":74.51647779580203,"mean":52.79791053075513,"min":32.21875578770826},"none":{"max":81.36218008604347,"mean":54.35156185434119,"min":31.711350149426604}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":6.396060478270115},"working_program_strength":{"all":55.44781446470719,"highest":59.19397100902525,"medium":52.79791053075513,"none":54.35156185434119}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flash:3a66a45fd2484e0f","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":0.11920932499999999},"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":0.11920932499999999}},"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":55.15560597317792,"highest":57.456317553244205,"medium":61.3820917509263,"none":46.62840861536324},"economics_best_value":{"per_model":{"all":true,"highest":true,"medium":true,"none":true},"per_setting":{"medium":true,"none":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":56.695188379531764,"score":56.695188379531764},"GB2-02":{"attempts":3,"playable":51.60581334995921,"score":51.60581334995921},"GB2-03":{"attempts":3,"playable":69.78892381456298,"score":69.78892381456298},"GB2-04":{"attempts":3,"playable":71.40475905813713,"score":71.40475905813713},"GB2-05":{"attempts":3,"playable":50.60592714568264,"score":50.60592714568264},"GB2-06":{"attempts":3,"playable":45.03216427309267,"score":45.03216427309267},"GB2-07":{"attempts":3,"playable":70.2279028942471,"score":70.2279028942471},"GB2-08":{"attempts":3,"playable":25.884168870209844,"score":25.884168870209844}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":64.05544234824092,"score":64.05544234824092},"GB2-02":{"attempts":1,"playable":65.56607930276833,"score":65.56607930276833},"GB2-03":{"attempts":1,"playable":76.57278573292541,"score":76.57278573292541},"GB2-04":{"attempts":1,"playable":78.40725494365654,"score":78.40725494365654},"GB2-05":{"attempts":1,"playable":71.16407438439963,"score":71.16407438439963},"GB2-06":{"attempts":1,"playable":15.705936828901255,"score":15.705936828901255},"GB2-07":{"attempts":1,"playable":67.72186251776958,"score":67.72186251776958},"GB2-08":{"attempts":1,"playable":20.457104367292025,"score":20.457104367292025}},"medium":{"GB2-01":{"attempts":1,"playable":69.24738370801556,"score":69.24738370801556},"GB2-02":{"attempts":1,"playable":45.338709401809794,"score":45.338709401809794},"GB2-03":{"attempts":1,"playable":78.3297551455029,"score":78.3297551455029},"GB2-04":{"attempts":1,"playable":72.98943326412221,"score":72.98943326412221},"GB2-05":{"attempts":1,"playable":45.64786084565047,"score":45.64786084565047},"GB2-06":{"attempts":1,"playable":78.46763736968447,"score":78.46763736968447},"GB2-07":{"attempts":1,"playable":73.66335602460023,"score":73.66335602460023},"GB2-08":{"attempts":1,"playable":27.372598248024772,"score":27.372598248024772}},"none":{"GB2-01":{"attempts":1,"playable":36.78273908233879,"score":36.78273908233879},"GB2-02":{"attempts":1,"playable":43.91265134529952,"score":43.91265134529952},"GB2-03":{"attempts":1,"playable":54.46423056526064,"score":54.46423056526064},"GB2-04":{"attempts":1,"playable":62.817588966632634,"score":62.817588966632634},"GB2-05":{"attempts":1,"playable":35.00584620699782,"score":35.00584620699782},"GB2-06":{"attempts":1,"playable":40.9229186206923,"score":40.9229186206923},"GB2-07":{"attempts":1,"playable":69.29849014037146,"score":69.29849014037146},"GB2-08":{"attempts":1,"playable":29.822803995312725,"score":29.822803995312725}}},"id":"z-ai/glm-5.3-flash","is_recent_addition":false,"last_measured_at":"2026-11-03T06:51:36Z","match_totals_all":{"draws":2156,"losses":4697,"wins":5711},"match_totals_tracks":{"highest":{"draws":468,"losses":1593,"wins":2127},"medium":{"draws":717,"losses":1298,"wins":2169},"none":{"draws":971,"losses":1806,"wins":1415}},"model_slug":"z-ai-glm-5-3-flash","official_rank_by_reasoning":{"highest":36,"medium":22,"none":29},"overall":{"max":78.46763736968447,"mean":55.15560597317792,"min":15.705936828901255},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":25,"overall_ranking_status":"ranked","per_game":{"GB2-01":64.05544234824092,"GB2-02":65.56607930276833,"GB2-03":76.57278573292541,"GB2-04":78.40725494365654,"GB2-05":71.16407438439963,"GB2-06":15.705936828901255,"GB2-07":67.72186251776958,"GB2-08":20.457104367292025},"per_game_all":{"GB2-01":56.695188379531764,"GB2-02":51.60581334995921,"GB2-03":69.78892381456298,"GB2-04":71.40475905813713,"GB2-05":50.60592714568264,"GB2-06":45.03216427309267,"GB2-07":70.2279028942471,"GB2-08":25.884168870209844},"per_game_match_totals_all":{"GB2-01":{"draws":252,"losses":561,"wins":765},"GB2-02":{"draws":980,"losses":247,"wins":259},"GB2-03":{"draws":154,"losses":420,"wins":964},"GB2-04":{"draws":515,"losses":198,"wins":819},"GB2-05":{"draws":0,"losses":807,"wins":825},"GB2-06":{"draws":56,"losses":842,"wins":650},"GB2-07":{"draws":0,"losses":494,"wins":1126},"GB2-08":{"draws":199,"losses":1128,"wins":303}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":6,"losses":188,"wins":334},"GB2-02":{"draws":255,"losses":49,"wins":192},"GB2-03":{"draws":10,"losses":124,"wins":378},"GB2-04":{"draws":145,"losses":43,"wins":324},"GB2-05":{"draws":0,"losses":157,"wins":385},"GB2-06":{"draws":13,"losses":434,"wins":67},"GB2-07":{"draws":0,"losses":179,"wins":361},"GB2-08":{"draws":39,"losses":419,"wins":86}},"medium":{"GB2-01":{"draws":20,"losses":152,"wins":352},"GB2-02":{"draws":357,"losses":99,"wins":40},"GB2-03":{"draws":26,"losses":106,"wins":378},"GB2-04":{"draws":163,"losses":62,"wins":285},"GB2-05":{"draws":0,"losses":297,"wins":249},"GB2-06":{"draws":35,"losses":95,"wins":386},"GB2-07":{"draws":0,"losses":145,"wins":395},"GB2-08":{"draws":116,"losses":342,"wins":84}},"none":{"GB2-01":{"draws":226,"losses":221,"wins":79},"GB2-02":{"draws":368,"losses":99,"wins":27},"GB2-03":{"draws":118,"losses":190,"wins":208},"GB2-04":{"draws":207,"losses":93,"wins":210},"GB2-05":{"draws":0,"losses":353,"wins":191},"GB2-06":{"draws":8,"losses":313,"wins":197},"GB2-07":{"draws":0,"losses":170,"wins":370},"GB2-08":{"draws":44,"losses":367,"wins":133}}},"per_game_raw_elo_all":{"GB2-01":1556.5394369592343,"GB2-02":1491.7769205057946,"GB2-03":1659.6272060027288,"GB2-04":1669.242817263439,"GB2-05":1471.7324677952329,"GB2-06":1392.184957101547,"GB2-07":1732.1846433216613,"GB2-08":1106.8010618328258},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1627.3415004363098,"GB2-02":1605.7386498125074,"GB2-03":1734.7061483368357,"GB2-04":1743.0937966583083,"GB2-05":1765.7787808145652,"GB2-06":899.6195010280913,"GB2-07":1691.385997643837,"GB2-08":1036.9791690466482},"medium":{"GB2-01":1684.1305953882113,"GB2-02":1440.3630497160973,"GB2-03":1762.4285532366587,"GB2-04":1681.0572697863913,"GB2-05":1395.737830561598,"GB2-06":1964.6164142632833,"GB2-07":1789.0726877671796,"GB2-08":1126.6950653629651},"none":{"GB2-01":1358.1462150531818,"GB2-02":1429.2290619887794,"GB2-03":1481.7469164346917,"GB2-04":1583.5773853456178,"GB2-05":1253.6807920095348,"GB2-06":1312.3189560132669,"GB2-07":1716.0952445539667,"GB2-08":1156.728951088864}},"per_game_tracks":{"highest":{"GB2-01":64.05544234824092,"GB2-02":65.56607930276833,"GB2-03":76.57278573292541,"GB2-04":78.40725494365654,"GB2-05":71.16407438439963,"GB2-06":15.705936828901255,"GB2-07":67.72186251776958,"GB2-08":20.457104367292025},"medium":{"GB2-01":69.24738370801556,"GB2-02":45.338709401809794,"GB2-03":78.3297551455029,"GB2-04":72.98943326412221,"GB2-05":45.64786084565047,"GB2-06":78.46763736968447,"GB2-07":73.66335602460023,"GB2-08":27.372598248024772},"none":{"GB2-01":36.78273908233879,"GB2-02":43.91265134529952,"GB2-03":54.46423056526064,"GB2-04":62.817588966632634,"GB2-05":35.00584620699782,"GB2-06":40.9229186206923,"GB2-07":69.29849014037146,"GB2-08":29.822803995312725}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":20,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T16:55:05Z","reasoning":{"highest":57.456317553244205,"medium":61.3820917509263,"none":46.62840861536324},"reasoning_agg":{"highest":{"max":78.40725494365654,"mean":57.456317553244205,"min":15.705936828901255},"medium":{"max":78.46763736968447,"mean":61.3820917509263,"min":27.372598248024772},"none":{"max":69.29849014037146,"mean":46.62840861536324,"min":29.822803995312725}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":14.753683135563058},"working_program_strength":{"all":55.15560597317792,"highest":57.456317553244205,"medium":61.3820917509263,"none":46.62840861536324}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max-0902:27f0ad746deb6345","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":3.189024},"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":0.873722},"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":0.873722},"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":0.9697739999999999},"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":3.189024}},"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":5.032520000000002},"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":53.41274808974029,"highest":68.12262042723142,"medium":43.093723223143364,"none":49.021900618846075},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":46.73787902559662,"score":46.73787902559662},"GB2-02":{"attempts":3,"playable":45.581062689667114,"score":45.581062689667114},"GB2-03":{"attempts":3,"playable":59.46114345042224,"score":59.46114345042224},"GB2-04":{"attempts":3,"playable":54.63583739180757,"score":54.63583739180757},"GB2-05":{"attempts":3,"playable":62.8361244393304,"score":62.8361244393304},"GB2-06":{"attempts":3,"playable":65.5154762064385,"score":65.5154762064385},"GB2-07":{"attempts":3,"playable":49.27496905440605,"score":49.27496905440605},"GB2-08":{"attempts":3,"playable":43.259492460253824,"score":43.259492460253824}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":74.57733223442922,"score":74.57733223442922},"GB2-02":{"attempts":1,"playable":48.057534541955675,"score":48.057534541955675},"GB2-03":{"attempts":1,"playable":69.65566978251928,"score":69.65566978251928},"GB2-04":{"attempts":1,"playable":83.08949593233552,"score":83.08949593233552},"GB2-05":{"attempts":1,"playable":90.88190062301813,"score":90.88190062301813},"GB2-06":{"attempts":1,"playable":61.01541527152252,"score":61.01541527152252},"GB2-07":{"attempts":1,"playable":74.3759847580142,"score":74.3759847580142},"GB2-08":{"attempts":1,"playable":43.32763027405686,"score":43.32763027405686}},"medium":{"GB2-01":{"attempts":1,"playable":25.616034658133348,"score":25.616034658133348},"GB2-02":{"attempts":1,"playable":47.60709014544417,"score":47.60709014544417},"GB2-03":{"attempts":1,"playable":55.422154498165014,"score":55.422154498165014},"GB2-04":{"attempts":1,"playable":44.02157838025399,"score":44.02157838025399},"GB2-05":{"attempts":1,"playable":41.08148212629456,"score":41.08148212629456},"GB2-06":{"attempts":1,"playable":56.773235833950466,"score":56.773235833950466},"GB2-07":{"attempts":1,"playable":35.48770442617648,"score":35.48770442617648},"GB2-08":{"attempts":1,"playable":38.74050571672888,"score":38.74050571672888}},"none":{"GB2-01":{"attempts":1,"playable":40.02027018422729,"score":40.02027018422729},"GB2-02":{"attempts":1,"playable":41.078563381601484,"score":41.078563381601484},"GB2-03":{"attempts":1,"playable":53.30560607058242,"score":53.30560607058242},"GB2-04":{"attempts":1,"playable":36.79643786283317,"score":36.79643786283317},"GB2-05":{"attempts":1,"playable":56.544990568678486,"score":56.544990568678486},"GB2-06":{"attempts":1,"playable":78.75777751384256,"score":78.75777751384256},"GB2-07":{"attempts":1,"playable":37.961217979027474,"score":37.961217979027474},"GB2-08":{"attempts":1,"playable":47.71034138997572,"score":47.71034138997572}}},"id":"qwen/qwen3.8-max-0902","is_recent_addition":false,"last_measured_at":"2026-11-03T08:07:14Z","match_totals_all":{"draws":2924,"losses":4544,"wins":5080},"match_totals_tracks":{"highest":{"draws":824,"losses":959,"wins":2401},"medium":{"draws":977,"losses":1959,"wins":1244},"none":{"draws":1123,"losses":1626,"wins":1435}},"model_slug":"qwen-qwen3-8-max-0902","official_rank_by_reasoning":{"highest":19,"medium":50,"none":25},"overall":{"max":90.88190062301813,"mean":53.41274808974029,"min":25.616034658133348},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":26,"overall_ranking_status":"ranked","per_game":{"GB2-01":74.57733223442922,"GB2-02":48.057534541955675,"GB2-03":69.65566978251928,"GB2-04":83.08949593233552,"GB2-05":90.88190062301813,"GB2-06":61.01541527152252,"GB2-07":74.3759847580142,"GB2-08":43.32763027405686},"per_game_all":{"GB2-01":46.73787902559662,"GB2-02":45.581062689667114,"GB2-03":59.46114345042224,"GB2-04":54.63583739180757,"GB2-05":62.8361244393304,"GB2-06":65.5154762064385,"GB2-07":49.27496905440605,"GB2-08":43.259492460253824},"per_game_match_totals_all":{"GB2-01":{"draws":307,"losses":691,"wins":578},"GB2-02":{"draws":1063,"losses":295,"wins":126},"GB2-03":{"draws":287,"losses":522,"wins":733},"GB2-04":{"draws":718,"losses":355,"wins":459},"GB2-05":{"draws":0,"losses":603,"wins":1021},"GB2-06":{"draws":101,"losses":499,"wins":938},"GB2-07":{"draws":0,"losses":852,"wins":772},"GB2-08":{"draws":448,"losses":727,"wins":453}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":133,"wins":389},"GB2-02":{"draws":342,"losses":93,"wins":61},"GB2-03":{"draws":98,"losses":118,"wins":296},"GB2-04":{"draws":90,"losses":45,"wins":373},"GB2-05":{"draws":0,"losses":48,"wins":492},"GB2-06":{"draws":50,"losses":183,"wins":281},"GB2-07":{"draws":0,"losses":141,"wins":403},"GB2-08":{"draws":242,"losses":198,"wins":106}},"medium":{"GB2-01":{"draws":97,"losses":345,"wins":84},"GB2-02":{"draws":356,"losses":86,"wins":50},"GB2-03":{"draws":94,"losses":198,"wins":226},"GB2-04":{"draws":322,"losses":132,"wins":56},"GB2-05":{"draws":0,"losses":318,"wins":222},"GB2-06":{"draws":16,"losses":223,"wins":273},"GB2-07":{"draws":0,"losses":362,"wins":178},"GB2-08":{"draws":92,"losses":295,"wins":155}},"none":{"GB2-01":{"draws":208,"losses":213,"wins":105},"GB2-02":{"draws":365,"losses":116,"wins":15},"GB2-03":{"draws":95,"losses":206,"wins":211},"GB2-04":{"draws":306,"losses":178,"wins":30},"GB2-05":{"draws":0,"losses":237,"wins":307},"GB2-06":{"draws":35,"losses":93,"wins":384},"GB2-07":{"draws":0,"losses":349,"wins":191},"GB2-08":{"draws":114,"losses":234,"wins":192}}},"per_game_raw_elo_all":{"GB2-01":1458.5682689767345,"GB2-02":1442.1952539234906,"GB2-03":1534.1857297053054,"GB2-04":1536.7331253859404,"GB2-05":1736.751222074231,"GB2-06":1725.971375834415,"GB2-07":1447.8329657972674,"GB2-08":1322.2791007090666},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1748.0988149832824,"GB2-02":1461.5610059477774,"GB2-03":1640.8329841292273,"GB2-04":1806.5440162222656,"GB2-05":2336.2290615172988,"GB2-06":1640.1870040113067,"GB2-07":1801.7968108593834,"GB2-08":1322.1618162751072},"medium":{"GB2-01":1237.1513507830077,"GB2-02":1458.0475978028974,"GB2-03":1490.7236343795278,"GB2-04":1430.7539228387884,"GB2-05":1336.2927964854198,"GB2-06":1567.3377649657066,"GB2-07":1254.4977778116881,"GB2-08":1264.7472069542575},"none":{"GB2-01":1390.4546411639135,"GB2-02":1406.977158019797,"GB2-03":1471.0005706071606,"GB2-04":1372.9014370967673,"GB2-05":1537.7318082199747,"GB2-06":1970.3893585262326,"GB2-07":1287.2043087207312,"GB2-08":1379.9282788978355}},"per_game_tracks":{"highest":{"GB2-01":74.57733223442922,"GB2-02":48.057534541955675,"GB2-03":69.65566978251928,"GB2-04":83.08949593233552,"GB2-05":90.88190062301813,"GB2-06":61.01541527152252,"GB2-07":74.3759847580142,"GB2-08":43.32763027405686},"medium":{"GB2-01":25.616034658133348,"GB2-02":47.60709014544417,"GB2-03":55.422154498165014,"GB2-04":44.02157838025399,"GB2-05":41.08148212629456,"GB2-06":56.773235833950466,"GB2-07":35.48770442617648,"GB2-08":38.74050571672888},"none":{"GB2-01":40.02027018422729,"GB2-02":41.078563381601484,"GB2-03":53.30560607058242,"GB2-04":36.79643786283317,"GB2-05":56.544990568678486,"GB2-06":78.75777751384256,"GB2-07":37.961217979027474,"GB2-08":47.71034138997572}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":5,"worked_first_time":19,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T16:53:32Z","reasoning":{"highest":68.12262042723142,"medium":43.093723223143364,"none":49.021900618846075},"reasoning_agg":{"highest":{"max":90.88190062301813,"mean":68.12262042723142,"min":43.32763027405686},"medium":{"max":56.773235833950466,"mean":43.093723223143364,"min":25.616034658133348},"none":{"max":78.75777751384256,"mean":49.021900618846075,"min":36.79643786283317}},"reasoning_labels":{"highest":"Xhigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":25.02889720408806},"working_program_strength":{"all":53.41274808974029,"highest":68.12262042723142,"medium":43.093723223143364,"none":49.021900618846075}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4:6761d8d2ef5e7731","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":2.266995},"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":0.7687025000000002}},"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":0.7687025000000003},"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":53.37363290805924,"highest":61.808721129713234,"medium":53.48991105054554,"none":44.82226654391896},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":89.96503184917776,"score":89.96503184917776},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":41.76734414095217,"score":27.844896093968114},"GB2-03":{"attempts":3,"playable":39.1016145175846,"score":39.1016145175846},"GB2-04":{"attempts":3,"playable":41.83854406555822,"score":41.83854406555822},"GB2-05":{"attempts":3,"playable":70.28628519695987,"score":70.28628519695987},"GB2-06":{"attempts":3,"playable":70.6470245061884,"score":70.6470245061884},"GB2-07":{"attempts":3,"playable":45.36094782189266,"score":45.36094782189266},"GB2-08":{"attempts":3,"playable":41.944719213144324,"score":41.944719213144324}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":94.78986263317816,"score":94.78986263317816},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":42.28003370070694,"score":42.28003370070694},"GB2-04":{"attempts":1,"playable":55.136277920389695,"score":55.136277920389695},"GB2-05":{"attempts":1,"playable":83.95945127401728,"score":83.95945127401728},"GB2-06":{"attempts":1,"playable":78.5577454093257,"score":78.5577454093257},"GB2-07":{"attempts":1,"playable":75.52058529619651,"score":75.52058529619651},"GB2-08":{"attempts":1,"playable":64.22581280389157,"score":64.22581280389157}},"medium":{"GB2-01":{"attempts":1,"playable":97.05312536114015,"score":97.05312536114015},"GB2-02":{"attempts":1,"playable":45.23746707474166,"score":45.23746707474166},"GB2-03":{"attempts":1,"playable":43.63038214206019,"score":43.63038214206019},"GB2-04":{"attempts":1,"playable":31.982596573370053,"score":31.982596573370053},"GB2-05":{"attempts":1,"playable":68.10800402053215,"score":68.10800402053215},"GB2-06":{"attempts":1,"playable":73.15688656726256,"score":73.15688656726256},"GB2-07":{"attempts":1,"playable":32.813748448636346,"score":32.813748448636346},"GB2-08":{"attempts":1,"playable":35.93707821662118,"score":35.93707821662118}},"none":{"GB2-01":{"attempts":1,"playable":78.05210755321494,"score":78.05210755321494},"GB2-02":{"attempts":1,"playable":38.29722120716268,"score":38.29722120716268},"GB2-03":{"attempts":1,"playable":31.394427709986676,"score":31.394427709986676},"GB2-04":{"attempts":1,"playable":38.39675770291491,"score":38.39675770291491},"GB2-05":{"attempts":1,"playable":58.791400296330195,"score":58.791400296330195},"GB2-06":{"attempts":1,"playable":60.22644154197692,"score":60.22644154197692},"GB2-07":{"attempts":1,"playable":27.74850972084511,"score":27.74850972084511},"GB2-08":{"attempts":1,"playable":25.671266618920228,"score":25.671266618920228}}},"id":"gpt-5.4","is_recent_addition":false,"last_measured_at":"2026-11-03T07:13:49Z","match_totals_all":{"draws":2421,"losses":4258,"wins":5395},"match_totals_tracks":{"highest":{"draws":489,"losses":863,"wins":2342},"medium":{"draws":970,"losses":1510,"wins":1708},"none":{"draws":962,"losses":1885,"wins":1345}},"model_slug":"gpt-5-4","official_rank_by_reasoning":{"highest":31,"medium":30,"none":31},"overall":{"max":97.05312536114015,"mean":53.37363290805924,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":27,"overall_ranking_status":"ranked","per_game":{"GB2-01":94.78986263317816,"GB2-03":42.28003370070694,"GB2-04":55.136277920389695,"GB2-05":83.95945127401728,"GB2-06":78.5577454093257,"GB2-07":75.52058529619651,"GB2-08":64.22581280389157},"per_game_all":{"GB2-01":89.96503184917776,"GB2-03":39.1016145175846,"GB2-04":41.83854406555822,"GB2-05":70.28628519695987,"GB2-06":70.6470245061884,"GB2-07":45.36094782189266,"GB2-08":41.944719213144324},"per_game_match_totals_all":{"GB2-01":{"draws":80,"losses":117,"wins":1387},"GB2-02":{"draws":726,"losses":226,"wins":38},"GB2-03":{"draws":555,"losses":701,"wins":284},"GB2-04":{"draws":831,"losses":495,"wins":206},"GB2-05":{"draws":0,"losses":487,"wins":1145},"GB2-06":{"draws":58,"losses":436,"wins":1050},"GB2-07":{"draws":0,"losses":915,"wins":707},"GB2-08":{"draws":171,"losses":881,"wins":578}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":19,"wins":494},"GB2-03":{"draws":147,"losses":237,"wins":130},"GB2-04":{"draws":267,"losses":103,"wins":142},"GB2-05":{"draws":0,"losses":87,"wins":455},"GB2-06":{"draws":36,"losses":94,"wins":384},"GB2-07":{"draws":0,"losses":134,"wins":406},"GB2-08":{"draws":24,"losses":189,"wins":331}},"medium":{"GB2-01":{"draws":8,"losses":10,"wins":510},"GB2-02":{"draws":374,"losses":91,"wins":31},"GB2-03":{"draws":230,"losses":188,"wins":94},"GB2-04":{"draws":258,"losses":223,"wins":27},"GB2-05":{"draws":0,"losses":174,"wins":370},"GB2-06":{"draws":15,"losses":134,"wins":367},"GB2-07":{"draws":0,"losses":376,"wins":164},"GB2-08":{"draws":85,"losses":314,"wins":145}},"none":{"GB2-01":{"draws":57,"losses":88,"wins":383},"GB2-02":{"draws":352,"losses":135,"wins":7},"GB2-03":{"draws":178,"losses":276,"wins":60},"GB2-04":{"draws":306,"losses":169,"wins":37},"GB2-05":{"draws":0,"losses":226,"wins":320},"GB2-06":{"draws":7,"losses":208,"wins":299},"GB2-07":{"draws":0,"losses":405,"wins":137},"GB2-08":{"draws":62,"losses":378,"wins":102}}},"per_game_raw_elo_all":{"GB2-01":2084.5149399892293,"GB2-03":1343.2944937635373,"GB2-04":1412.4633236562568,"GB2-05":1787.6364888043352,"GB2-06":1818.2245420995193,"GB2-07":1396.348491320875,"GB2-08":1326.2820370379281},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2168.044216667133,"GB2-03":1372.2604448306959,"GB2-04":1518.9767240010513,"GB2-05":2083.5983367082104,"GB2-06":1966.4070627609144,"GB2-07":1822.8327531315797,"GB2-08":1642.7891611868035},"medium":{"GB2-01":2291.0918846038758,"GB2-02":1439.5733576697849,"GB2-03":1384.2045795822878,"GB2-04":1332.4894926078096,"GB2-05":1710.8061429287402,"GB2-06":1861.8244920204443,"GB2-07":1218.530857550381,"GB2-08":1230.5975875148326},"none":{"GB2-01":1794.4087186966788,"GB2-02":1384.8489608059076,"GB2-03":1273.4184568776286,"GB2-04":1385.9237543599097,"GB2-05":1568.5049867760542,"GB2-06":1626.4420715171993,"GB2-07":1147.6818632806642,"GB2-08":1105.4593624121485}},"per_game_tracks":{"highest":{"GB2-01":94.78986263317816,"GB2-03":42.28003370070694,"GB2-04":55.136277920389695,"GB2-05":83.95945127401728,"GB2-06":78.5577454093257,"GB2-07":75.52058529619651,"GB2-08":64.22581280389157},"medium":{"GB2-01":97.05312536114015,"GB2-02":45.23746707474166,"GB2-03":43.63038214206019,"GB2-04":31.982596573370053,"GB2-05":68.10800402053215,"GB2-06":73.15688656726256,"GB2-07":32.813748448636346,"GB2-08":35.93707821662118},"none":{"GB2-01":78.05210755321494,"GB2-02":38.29722120716268,"GB2-03":31.394427709986676,"GB2-04":38.39675770291491,"GB2-05":58.791400296330195,"GB2-06":60.22644154197692,"GB2-07":27.74850972084511,"GB2-08":25.671266618920228}},"program_outcomes":{"all":{"counted_attempts":24,"failed":1,"infra_excluded":0,"success_rate":0.9583333333333334,"too_slow":0,"worked_after_repair":2,"worked_first_time":21,"working":23},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T16:10:51Z","reasoning":{"highest":61.80872112971323,"medium":53.48991105054554,"none":44.82226654391896},"reasoning_agg":{"highest":{"max":94.78986263317816,"mean":61.80872112971323,"min":0.0},"medium":{"max":97.05312536114015,"mean":53.48991105054554,"min":31.982596573370053},"none":{"max":78.05210755321494,"mean":44.82226654391896,"min":25.671266618920228}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":16.98645458579427},"working_program_strength":{"all":56.31690534280748,"highest":70.63853843395798,"medium":53.48991105054554,"none":44.82226654391896}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-2-4t-a95b:0e40c4e24db66bc0","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":3.454226856819533},"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":3.454226856819533}},"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":52.74982417855364,"highest":66.70684727740532,"medium":42.14472314599955,"none":49.397902112256034},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":47.668865614494514,"score":47.668865614494514},"GB2-02":{"attempts":3,"playable":48.00793978314986,"score":48.00793978314986},"GB2-03":{"attempts":3,"playable":56.70641061276128,"score":56.70641061276128},"GB2-04":{"attempts":3,"playable":42.61997111877891,"score":42.61997111877891},"GB2-05":{"attempts":3,"playable":48.896071067873926,"score":48.896071067873926},"GB2-06":{"attempts":3,"playable":60.469235166227946,"score":60.469235166227946},"GB2-07":{"attempts":3,"playable":47.511654190133214,"score":47.511654190133214},"GB2-08":{"attempts":3,"playable":70.11844587500941,"score":70.11844587500941}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":57.067294364577705,"score":57.067294364577705},"GB2-02":{"attempts":1,"playable":52.48576587548867,"score":52.48576587548867},"GB2-03":{"attempts":1,"playable":79.28500129650119,"score":79.28500129650119},"GB2-04":{"attempts":1,"playable":45.60828115851949,"score":45.60828115851949},"GB2-05":{"attempts":1,"playable":65.94613527385536,"score":65.94613527385536},"GB2-06":{"attempts":1,"playable":77.35988772618457,"score":77.35988772618457},"GB2-07":{"attempts":1,"playable":67.54864875381715,"score":67.54864875381715},"GB2-08":{"attempts":1,"playable":88.35376377029837,"score":88.35376377029837}},"medium":{"GB2-01":{"attempts":1,"playable":51.29319580629157,"score":51.29319580629157},"GB2-02":{"attempts":1,"playable":42.90448904965713,"score":42.90448904965713},"GB2-03":{"attempts":1,"playable":42.3644956488082,"score":42.3644956488082},"GB2-04":{"attempts":1,"playable":37.275720047119606,"score":37.275720047119606},"GB2-05":{"attempts":1,"playable":47.334632042049755,"score":47.334632042049755},"GB2-06":{"attempts":1,"playable":43.899832539182434,"score":43.899832539182434},"GB2-07":{"attempts":1,"playable":31.657514988537116,"score":31.657514988537116},"GB2-08":{"attempts":1,"playable":40.42790504635056,"score":40.42790504635056}},"none":{"GB2-01":{"attempts":1,"playable":34.64610667261427,"score":34.64610667261427},"GB2-02":{"attempts":1,"playable":48.63356442430377,"score":48.63356442430377},"GB2-03":{"attempts":1,"playable":48.46973489297444,"score":48.46973489297444},"GB2-04":{"attempts":1,"playable":44.97591215069765,"score":44.97591215069765},"GB2-05":{"attempts":1,"playable":33.40744588771669,"score":33.40744588771669},"GB2-06":{"attempts":1,"playable":60.14798523331684,"score":60.14798523331684},"GB2-07":{"attempts":1,"playable":43.32879882804538,"score":43.32879882804538},"GB2-08":{"attempts":1,"playable":81.57366880837931,"score":81.57366880837931}}},"id":"qwen/qwen3.8-2.4t-a95b","is_recent_addition":false,"last_measured_at":"2026-11-03T07:10:02Z","match_totals_all":{"draws":3059,"losses":4536,"wins":4961},"match_totals_tracks":{"highest":{"draws":837,"losses":996,"wins":2349},"medium":{"draws":1215,"losses":1877,"wins":1094},"none":{"draws":1007,"losses":1663,"wins":1518}},"model_slug":"qwen-qwen3-8-2-4t-a95b","official_rank_by_reasoning":{"highest":22,"medium":53,"none":24},"overall":{"max":88.35376377029837,"mean":52.74982417855364,"min":31.657514988537116},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":28,"overall_ranking_status":"ranked","per_game":{"GB2-01":57.067294364577705,"GB2-02":52.48576587548867,"GB2-03":79.28500129650119,"GB2-04":45.60828115851949,"GB2-05":65.94613527385536,"GB2-06":77.35988772618457,"GB2-07":67.54864875381715,"GB2-08":88.35376377029837},"per_game_all":{"GB2-01":47.668865614494514,"GB2-02":48.00793978314986,"GB2-03":56.70641061276128,"GB2-04":42.61997111877891,"GB2-05":48.896071067873926,"GB2-06":60.469235166227946,"GB2-07":47.511654190133214,"GB2-08":70.11844587500941},"per_game_match_totals_all":{"GB2-01":{"draws":600,"losses":533,"wins":449},"GB2-02":{"draws":1067,"losses":253,"wins":156},"GB2-03":{"draws":230,"losses":589,"wins":725},"GB2-04":{"draws":955,"losses":423,"wins":156},"GB2-05":{"draws":0,"losses":831,"wins":795},"GB2-06":{"draws":90,"losses":586,"wins":866},"GB2-07":{"draws":0,"losses":883,"wins":741},"GB2-08":{"draws":117,"losses":438,"wins":1073}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":150,"losses":153,"wins":225},"GB2-02":{"draws":338,"losses":71,"wins":83},"GB2-03":{"draws":13,"losses":108,"wins":395},"GB2-04":{"draws":301,"losses":134,"wins":75},"GB2-05":{"draws":0,"losses":186,"wins":356},"GB2-06":{"draws":35,"losses":101,"wins":376},"GB2-07":{"draws":0,"losses":180,"wins":360},"GB2-08":{"draws":0,"losses":63,"wins":479}},"medium":{"GB2-01":{"draws":259,"losses":127,"wins":138},"GB2-02":{"draws":363,"losses":107,"wins":24},"GB2-03":{"draws":159,"losses":231,"wins":124},"GB2-04":{"draws":293,"losses":180,"wins":37},"GB2-05":{"draws":0,"losses":285,"wins":257},"GB2-06":{"draws":24,"losses":289,"wins":203},"GB2-07":{"draws":0,"losses":384,"wins":158},"GB2-08":{"draws":117,"losses":274,"wins":153}},"none":{"GB2-01":{"draws":191,"losses":253,"wins":86},"GB2-02":{"draws":366,"losses":75,"wins":49},"GB2-03":{"draws":58,"losses":250,"wins":206},"GB2-04":{"draws":361,"losses":109,"wins":44},"GB2-05":{"draws":0,"losses":360,"wins":182},"GB2-06":{"draws":31,"losses":196,"wins":287},"GB2-07":{"draws":0,"losses":319,"wins":223},"GB2-08":{"draws":0,"losses":101,"wins":441}}},"per_game_raw_elo_all":{"GB2-01":1464.0659136100592,"GB2-02":1461.229998038538,"GB2-03":1526.1774291678976,"GB2-04":1419.451337642714,"GB2-05":1441.0940210700985,"GB2-06":1642.2873160884849,"GB2-07":1416.19562098345,"GB2-08":1821.494556283126},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1556.124256696984,"GB2-02":1496.2955795983848,"GB2-03":1778.3671260442425,"GB2-04":1443.2578301701028,"GB2-05":1674.9332161055074,"GB2-06":1942.7563764319952,"GB2-07":1688.7142823123586,"GB2-08":2175.2172394960107},"medium":{"GB2-01":1499.7338690818538,"GB2-02":1421.3375496071367,"GB2-03":1373.0078723802242,"GB2-04":1376.8187230702547,"GB2-05":1417.4494073945025,"GB2-06":1359.0253915707135,"GB2-07":1202.7188795957795,"GB2-08":1285.5919528491156},"none":{"GB2-01":1336.3396150513395,"GB2-02":1466.0568649100928,"GB2-03":1427.1572890792258,"GB2-04":1438.2774596877844,"GB2-05":1230.8994397102863,"GB2-06":1625.0801802627464,"GB2-07":1357.153701042212,"GB2-08":2003.6744765042508}},"per_game_tracks":{"highest":{"GB2-01":57.067294364577705,"GB2-02":52.48576587548867,"GB2-03":79.28500129650119,"GB2-04":45.60828115851949,"GB2-05":65.94613527385536,"GB2-06":77.35988772618457,"GB2-07":67.54864875381715,"GB2-08":88.35376377029837},"medium":{"GB2-01":51.29319580629157,"GB2-02":42.90448904965713,"GB2-03":42.3644956488082,"GB2-04":37.275720047119606,"GB2-05":47.334632042049755,"GB2-06":43.899832539182434,"GB2-07":31.657514988537116,"GB2-08":40.42790504635056},"none":{"GB2-01":34.64610667261427,"GB2-02":48.63356442430377,"GB2-03":48.46973489297444,"GB2-04":44.97591215069765,"GB2-05":33.40744588771669,"GB2-06":60.14798523331684,"GB2-07":43.32879882804538,"GB2-08":81.57366880837931}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":21,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T16:57:25Z","reasoning":{"highest":66.70684727740532,"medium":42.14472314599955,"none":49.397902112256034},"reasoning_agg":{"highest":{"max":88.35376377029837,"mean":66.70684727740532,"min":45.60828115851949},"medium":{"max":51.29319580629157,"mean":42.14472314599955,"min":31.657514988537116},"none":{"max":81.57366880837931,"mean":49.397902112256034,"min":33.40744588771669}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.562124131405767},"working_program_strength":{"all":52.74982417855364,"highest":66.70684727740532,"medium":42.14472314599955,"none":49.397902112256034}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-1-flash:9e10a6aabf043ef4","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":0.15272934000000002},"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":0.21121388999999996}},"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":0.3927312839999999},"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":52.06829141972133,"highest":67.4132922747764,"medium":54.29190246306105,"none":34.49967952132653},"economics_best_value":{"per_model":{"highest":true},"per_setting":{"highest":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":57.06555944132697,"score":57.06555944132697},"GB2-02":{"attempts":3,"playable":51.5445475894011,"score":51.5445475894011},"GB2-03":{"attempts":3,"playable":52.47848085052953,"score":52.47848085052953},"GB2-04":{"attempts":3,"playable":49.90439932901898,"score":49.90439932901898},"GB2-05":{"attempts":3,"playable":53.16671488880678,"score":53.16671488880678},"GB2-06":{"attempts":3,"playable":59.92192442562836,"score":59.92192442562836},"GB2-07":{"attempts":3,"playable":55.2378728381052,"score":55.2378728381052},"GB2-08":{"attempts":3,"playable":37.226831994953706,"score":37.226831994953706}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":60.22722203238764,"score":60.22722203238764},"GB2-02":{"attempts":1,"playable":56.165866774669894,"score":56.165866774669894},"GB2-03":{"attempts":1,"playable":58.31418759676854,"score":58.31418759676854},"GB2-04":{"attempts":1,"playable":73.561663711975,"score":73.561663711975},"GB2-05":{"attempts":1,"playable":79.62678556787507,"score":79.62678556787507},"GB2-06":{"attempts":1,"playable":79.21957705968167,"score":79.21957705968167},"GB2-07":{"attempts":1,"playable":73.47641390707015,"score":73.47641390707015},"GB2-08":{"attempts":1,"playable":58.71462154778327,"score":58.71462154778327}},"medium":{"GB2-01":{"attempts":1,"playable":66.9042030268171,"score":66.9042030268171},"GB2-02":{"attempts":1,"playable":57.20667523671399,"score":57.20667523671399},"GB2-03":{"attempts":1,"playable":53.357780619008246,"score":53.357780619008246},"GB2-04":{"attempts":1,"playable":37.875195032370804,"score":37.875195032370804},"GB2-05":{"attempts":1,"playable":50.9888692205061,"score":50.9888692205061},"GB2-06":{"attempts":1,"playable":73.96732786003572,"score":73.96732786003572},"GB2-07":{"attempts":1,"playable":67.79661540201677,"score":67.79661540201677},"GB2-08":{"attempts":1,"playable":26.238553307019657,"score":26.238553307019657}},"none":{"GB2-01":{"attempts":1,"playable":44.06525326477619,"score":44.06525326477619},"GB2-02":{"attempts":1,"playable":41.26110075681939,"score":41.26110075681939},"GB2-03":{"attempts":1,"playable":45.7634743358118,"score":45.7634743358118},"GB2-04":{"attempts":1,"playable":38.27633924271112,"score":38.27633924271112},"GB2-05":{"attempts":1,"playable":28.88448987803916,"score":28.88448987803916},"GB2-06":{"attempts":1,"playable":26.578868357167696,"score":26.578868357167696},"GB2-07":{"attempts":1,"playable":24.440589205228658,"score":24.440589205228658},"GB2-08":{"attempts":1,"playable":26.727321130058208,"score":26.727321130058208}}},"id":"deepseek/deepseek-v4.1-flash","is_recent_addition":false,"last_measured_at":"2026-11-03T07:14:21Z","match_totals_all":{"draws":2943,"losses":4694,"wins":4915},"match_totals_tracks":{"highest":{"draws":678,"losses":1062,"wins":2448},"medium":{"draws":1146,"losses":1388,"wins":1652},"none":{"draws":1119,"losses":2244,"wins":815}},"model_slug":"deepseek-deepseek-v4-1-flash","official_rank_by_reasoning":{"highest":21,"medium":29,"none":55},"overall":{"max":79.62678556787507,"mean":52.06829141972133,"min":24.440589205228658},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":29,"overall_ranking_status":"ranked","per_game":{"GB2-01":60.22722203238764,"GB2-02":56.165866774669894,"GB2-03":58.31418759676854,"GB2-04":73.561663711975,"GB2-05":79.62678556787507,"GB2-06":79.21957705968167,"GB2-07":73.47641390707015,"GB2-08":58.71462154778327},"per_game_all":{"GB2-01":57.06555944132697,"GB2-02":51.5445475894011,"GB2-03":52.47848085052953,"GB2-04":49.90439932901898,"GB2-05":53.16671488880678,"GB2-06":59.92192442562836,"GB2-07":55.2378728381052,"GB2-08":37.226831994953706},"per_game_match_totals_all":{"GB2-01":{"draws":478,"losses":442,"wins":658},"GB2-02":{"draws":1016,"losses":230,"wins":238},"GB2-03":{"draws":324,"losses":613,"wins":605},"GB2-04":{"draws":741,"losses":416,"wins":375},"GB2-05":{"draws":0,"losses":763,"wins":863},"GB2-06":{"draws":74,"losses":598,"wins":874},"GB2-07":{"draws":0,"losses":746,"wins":874},"GB2-08":{"draws":310,"losses":886,"wins":428}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":201,"wins":306},"GB2-02":{"draws":300,"losses":73,"wins":121},"GB2-03":{"draws":60,"losses":198,"wins":256},"GB2-04":{"draws":157,"losses":62,"wins":291},"GB2-05":{"draws":0,"losses":111,"wins":431},"GB2-06":{"draws":31,"losses":93,"wins":394},"GB2-07":{"draws":0,"losses":146,"wins":394},"GB2-08":{"draws":109,"losses":178,"wins":255}},"medium":{"GB2-01":{"draws":290,"losses":30,"wins":206},"GB2-02":{"draws":325,"losses":56,"wins":115},"GB2-03":{"draws":154,"losses":178,"wins":184},"GB2-04":{"draws":265,"losses":192,"wins":55},"GB2-05":{"draws":0,"losses":266,"wins":276},"GB2-06":{"draws":30,"losses":122,"wins":360},"GB2-07":{"draws":0,"losses":179,"wins":361},"GB2-08":{"draws":82,"losses":365,"wins":95}},"none":{"GB2-01":{"draws":167,"losses":211,"wins":146},"GB2-02":{"draws":391,"losses":101,"wins":2},"GB2-03":{"draws":110,"losses":237,"wins":165},"GB2-04":{"draws":319,"losses":162,"wins":29},"GB2-05":{"draws":0,"losses":386,"wins":156},"GB2-06":{"draws":13,"losses":383,"wins":120},"GB2-07":{"draws":0,"losses":421,"wins":119},"GB2-08":{"draws":119,"losses":343,"wins":78}}},"per_game_raw_elo_all":{"GB2-01":1558.572686193953,"GB2-02":1489.432273330982,"GB2-03":1464.3287285970302,"GB2-04":1484.608797185659,"GB2-05":1528.0372969842508,"GB2-06":1647.6729496303208,"GB2-07":1525.6127680163834,"GB2-08":1258.9272921062482},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1587.7758222057716,"GB2-02":1525.7095016876794,"GB2-03":1518.4219170908166,"GB2-04":1687.1798820353565,"GB2-05":1956.374167066378,"GB2-06":1979.6225007404537,"GB2-07":1785.7784907643106,"GB2-08":1545.5128214191811},"medium":{"GB2-01":1657.964475130368,"GB2-02":1534.1697013126793,"GB2-03":1471.4820651862271,"GB2-04":1381.6971801021655,"GB2-05":1464.5240246051214,"GB2-06":1877.228382194791,"GB2-07":1692.5415109889832,"GB2-08":1112.5835516191592},"none":{"GB2-01":1429.9777612457192,"GB2-02":1408.4176169925875,"GB2-03":1403.0822035140473,"GB2-04":1384.9493294194551,"GB2-05":1163.2136992812534,"GB2-06":1086.1679659557176,"GB2-07":1098.5183022958568,"GB2-08":1118.6855032804042}},"per_game_tracks":{"highest":{"GB2-01":60.22722203238764,"GB2-02":56.165866774669894,"GB2-03":58.31418759676854,"GB2-04":73.561663711975,"GB2-05":79.62678556787507,"GB2-06":79.21957705968167,"GB2-07":73.47641390707015,"GB2-08":58.71462154778327},"medium":{"GB2-01":66.9042030268171,"GB2-02":57.20667523671399,"GB2-03":53.357780619008246,"GB2-04":37.875195032370804,"GB2-05":50.9888692205061,"GB2-06":73.96732786003572,"GB2-07":67.79661540201677,"GB2-08":26.238553307019657},"none":{"GB2-01":44.06525326477619,"GB2-02":41.26110075681939,"GB2-03":45.7634743358118,"GB2-04":38.27633924271112,"GB2-05":28.88448987803916,"GB2-06":26.578868357167696,"GB2-07":24.440589205228658,"GB2-08":26.727321130058208}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":22,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T16:48:53Z","reasoning":{"highest":67.4132922747764,"medium":54.29190246306105,"none":34.49967952132653},"reasoning_agg":{"highest":{"max":79.62678556787507,"mean":67.4132922747764,"min":56.165866774669894},"medium":{"max":73.96732786003572,"mean":54.29190246306105,"min":26.238553307019657},"none":{"max":45.7634743358118,"mean":34.49967952132653,"min":24.440589205228658}},"reasoning_labels":{"highest":"Max","medium":"High","none":"None"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":32.91361275344987},"working_program_strength":{"all":52.06829141972133,"highest":67.4132922747764,"medium":54.29190246306105,"none":34.49967952132653}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-2:813f8bca2684fd6a","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":0.376168},"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":0.19141049999999998}},"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":51.681597100610084,"highest":57.41349351094803,"medium":57.23716916921808,"none":40.39412862166415},"first_seen_at":null,"game_gaps":{"medium":{"GB2-06":"too_slow"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":66.23410809318067,"score":66.23410809318067},"GB2-02":{"attempts":3,"playable":44.53388052656262,"score":44.53388052656262},"GB2-03":{"attempts":3,"playable":51.09663214940255,"score":51.09663214940255},"GB2-04":{"attempts":3,"playable":46.29946569168386,"score":46.29946569168386},"GB2-05":{"attempts":3,"playable":51.2859243472891,"score":51.2859243472891},"GB2-06":{"attempts":2,"playable":21.75533914283867,"score":21.75533914283867},"GB2-07":{"attempts":3,"playable":56.222634249715526,"score":56.222634249715526},"GB2-08":{"attempts":3,"playable":64.1975159287479,"score":64.1975159287479}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":78.75780847689778,"score":78.75780847689778},"GB2-02":{"attempts":1,"playable":46.88375217438697,"score":46.88375217438697},"GB2-03":{"attempts":1,"playable":58.99196272332564,"score":58.99196272332564},"GB2-04":{"attempts":1,"playable":47.76464925104473,"score":47.76464925104473},"GB2-05":{"attempts":1,"playable":58.042916983375434,"score":58.042916983375434},"GB2-06":{"attempts":1,"playable":25.10064892627943,"score":25.10064892627943},"GB2-07":{"attempts":1,"playable":72.7435920716409,"score":72.7435920716409},"GB2-08":{"attempts":1,"playable":71.02261748063336,"score":71.02261748063336}},"medium":{"GB2-01":{"attempts":1,"playable":84.82664589000842,"score":84.82664589000842},"GB2-02":{"attempts":1,"playable":45.85637855514981,"score":45.85637855514981},"GB2-03":{"attempts":1,"playable":48.731796242674996,"score":48.731796242674996},"GB2-04":{"attempts":1,"playable":44.38756916549173,"score":44.38756916549173},"GB2-05":{"attempts":1,"playable":47.20621794701579,"score":47.20621794701579},"GB2-07":{"attempts":1,"playable":62.031727387072344,"score":62.031727387072344},"GB2-08":{"attempts":1,"playable":67.61984899711348,"score":67.61984899711348}},"none":{"GB2-01":{"attempts":1,"playable":35.11786991263583,"score":35.11786991263583},"GB2-02":{"attempts":1,"playable":40.86151085015107,"score":40.86151085015107},"GB2-03":{"attempts":1,"playable":45.56613748220701,"score":45.56613748220701},"GB2-04":{"attempts":1,"playable":46.74617865851511,"score":46.74617865851511},"GB2-05":{"attempts":1,"playable":48.608638111476075,"score":48.608638111476075},"GB2-06":{"attempts":1,"playable":18.41002935939791,"score":18.41002935939791},"GB2-07":{"attempts":1,"playable":33.89258329043333,"score":33.89258329043333},"GB2-08":{"attempts":1,"playable":53.950081308496856,"score":53.950081308496856}}},"id":"meta/muse-spark-1.2","is_recent_addition":false,"last_measured_at":"2026-11-03T06:46:54Z","match_totals_all":{"draws":2441,"losses":4745,"wins":4850},"match_totals_tracks":{"highest":{"draws":706,"losses":1458,"wins":2012},"medium":{"draws":784,"losses":1210,"wins":1676},"none":{"draws":951,"losses":2077,"wins":1162}},"model_slug":"meta-muse-spark-1-2","official_rank_by_reasoning":{"highest":37,"medium":26,"none":40},"overall":{"max":84.82664589000842,"mean":51.681597100610084,"min":18.41002935939791},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":30,"overall_ranking_status":"ranked","per_game":{"GB2-01":78.75780847689778,"GB2-02":46.88375217438697,"GB2-03":58.99196272332564,"GB2-04":47.76464925104473,"GB2-05":58.042916983375434,"GB2-06":25.10064892627943,"GB2-07":72.7435920716409,"GB2-08":71.02261748063336},"per_game_all":{"GB2-01":66.23410809318067,"GB2-02":44.53388052656262,"GB2-03":51.09663214940255,"GB2-04":46.29946569168386,"GB2-05":51.2859243472891,"GB2-07":56.222634249715526,"GB2-08":64.1975159287479},"per_game_match_totals_all":{"GB2-01":{"draws":198,"losses":437,"wins":945},"GB2-02":{"draws":1089,"losses":296,"wins":95},"GB2-03":{"draws":200,"losses":694,"wins":642},"GB2-04":{"draws":912,"losses":389,"wins":233},"GB2-05":{"draws":0,"losses":791,"wins":833},"GB2-06":{"draws":23,"losses":811,"wins":194},"GB2-07":{"draws":0,"losses":735,"wins":889},"GB2-08":{"draws":19,"losses":592,"wins":1019}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":4,"losses":111,"wins":413},"GB2-02":{"draws":368,"losses":84,"wins":40},"GB2-03":{"draws":20,"losses":213,"wins":277},"GB2-04":{"draws":284,"losses":132,"wins":94},"GB2-05":{"draws":0,"losses":227,"wins":313},"GB2-06":{"draws":20,"losses":385,"wins":109},"GB2-07":{"draws":0,"losses":150,"wins":390},"GB2-08":{"draws":10,"losses":156,"wins":376}},"medium":{"GB2-01":{"draws":24,"losses":68,"wins":434},"GB2-02":{"draws":368,"losses":90,"wins":36},"GB2-03":{"draws":110,"losses":223,"wins":181},"GB2-04":{"draws":273,"losses":155,"wins":84},"GB2-05":{"draws":0,"losses":285,"wins":255},"GB2-07":{"draws":0,"losses":212,"wins":328},"GB2-08":{"draws":9,"losses":177,"wins":358}},"none":{"GB2-01":{"draws":170,"losses":258,"wins":98},"GB2-02":{"draws":353,"losses":122,"wins":19},"GB2-03":{"draws":70,"losses":258,"wins":184},"GB2-04":{"draws":355,"losses":102,"wins":55},"GB2-05":{"draws":0,"losses":279,"wins":265},"GB2-06":{"draws":3,"losses":426,"wins":85},"GB2-07":{"draws":0,"losses":373,"wins":171},"GB2-08":{"draws":0,"losses":259,"wins":285}}},"per_game_raw_elo_all":{"GB2-01":1682.5308797965445,"GB2-02":1434.0235644557988,"GB2-03":1451.9657689577543,"GB2-04":1448.6972892375634,"GB2-05":1469.2597859917653,"GB2-07":1537.7769512507082,"GB2-08":1650.8541633097793},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1804.4009845126577,"GB2-02":1452.4082346426048,"GB2-03":1525.0623923017356,"GB2-04":1460.2356246499414,"GB2-05":1558.1493435299772,"GB2-06":1062.244258101879,"GB2-07":1773.0295383982311,"GB2-08":1775.5327676420309},"medium":{"GB2-01":1901.9978626522434,"GB2-02":1444.3997442503594,"GB2-03":1429.5012977568833,"GB2-04":1433.6405784836038,"GB2-05":1415.7980782742538,"GB2-07":1607.167674068318,"GB2-08":1707.5109007249062},"none":{"GB2-01":1341.193792224733,"GB2-02":1405.2627144744317,"GB2-03":1401.3336168146448,"GB2-04":1452.2156645791442,"GB2-05":1433.8319361710649,"GB2-06":949.2491810790012,"GB2-07":1233.1336412855753,"GB2-08":1469.5188215624014}},"per_game_tracks":{"highest":{"GB2-01":78.75780847689778,"GB2-02":46.88375217438697,"GB2-03":58.99196272332564,"GB2-04":47.76464925104473,"GB2-05":58.042916983375434,"GB2-06":25.10064892627943,"GB2-07":72.7435920716409,"GB2-08":71.02261748063336},"medium":{"GB2-01":84.82664589000842,"GB2-02":45.85637855514981,"GB2-03":48.731796242674996,"GB2-04":44.38756916549173,"GB2-05":47.20621794701579,"GB2-07":62.031727387072344,"GB2-08":67.61984899711348},"none":{"GB2-01":35.11786991263583,"GB2-02":40.86151085015107,"GB2-03":45.56613748220701,"GB2-04":46.74617865851511,"GB2-05":48.608638111476075,"GB2-06":18.41002935939791,"GB2-07":33.89258329043333,"GB2-08":53.950081308496856}},"program_outcomes":{"all":{"counted_attempts":23,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":1,"worked_after_repair":1,"worked_first_time":22,"working":23},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":7,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":1,"worked_after_repair":0,"worked_first_time":7,"working":7},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T17:00:58Z","reasoning":{"highest":57.41349351094803,"medium":57.23716916921808,"none":40.39412862166415},"reasoning_agg":{"highest":{"max":78.75780847689778,"mean":57.41349351094803,"min":25.10064892627943},"medium":{"max":84.82664589000842,"mean":57.23716916921808,"min":44.38756916549173},"none":{"max":53.950081308496856,"mean":40.39412862166415,"min":18.41002935939791}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":17.019364889283878},"working_program_strength":{"all":51.681597100610084,"highest":57.41349351094803,"medium":57.23716916921808,"none":40.39412862166415}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy4-preview:3df3f49bc7c18786","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":0.969381525},"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":1.086615744},"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":1.0866157440000002},"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":0.9693815250000001}},"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":50.91008913757545,"highest":61.38418060337782,"medium":49.07619537534519,"none":42.26989143400332},"first_seen_at":null,"game_gaps":{"medium":{"GB2-02":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":49.15236148362688,"score":49.15236148362688},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":59.55665541744912,"score":39.70443694496608},"GB2-03":{"attempts":3,"playable":57.470695849270044,"score":57.470695849270044},"GB2-04":{"attempts":3,"playable":43.136140927559076,"score":43.136140927559076},"GB2-05":{"attempts":3,"playable":54.64943795222468,"score":54.64943795222468},"GB2-06":{"attempts":3,"playable":57.176940183952986,"score":57.176940183952986},"GB2-07":{"attempts":3,"playable":59.005822055902534,"score":59.005822055902534},"GB2-08":{"attempts":3,"playable":46.98487770310129,"score":46.98487770310129}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":52.89138386814176,"score":52.89138386814176},"GB2-02":{"attempts":1,"playable":77.13462054083618,"score":77.13462054083618},"GB2-03":{"attempts":1,"playable":70.09265117251351,"score":70.09265117251351},"GB2-04":{"attempts":1,"playable":54.86221693747453,"score":54.86221693747453},"GB2-05":{"attempts":1,"playable":67.39275791941763,"score":67.39275791941763},"GB2-06":{"attempts":1,"playable":77.93331459363245,"score":77.93331459363245},"GB2-07":{"attempts":1,"playable":65.73144509795603,"score":65.73144509795603},"GB2-08":{"attempts":1,"playable":25.03505469705049,"score":25.03505469705049}},"medium":{"GB2-01":{"attempts":1,"playable":50.104065549072544,"score":50.104065549072544},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":40.101002244564384,"score":40.101002244564384},"GB2-04":{"attempts":1,"playable":34.37095264458405,"score":34.37095264458405},"GB2-05":{"attempts":1,"playable":49.16325610533917,"score":49.16325610533917},"GB2-06":{"attempts":1,"playable":57.06801027954573,"score":57.06801027954573},"GB2-07":{"attempts":1,"playable":75.23803193496164,"score":75.23803193496164},"GB2-08":{"attempts":1,"playable":86.564244244694,"score":86.564244244694}},"none":{"GB2-01":{"attempts":1,"playable":44.46163503366634,"score":44.46163503366634},"GB2-02":{"attempts":1,"playable":41.97869029406207,"score":41.97869029406207},"GB2-03":{"attempts":1,"playable":62.21843413073223,"score":62.21843413073223},"GB2-04":{"attempts":1,"playable":40.17525320061864,"score":40.17525320061864},"GB2-05":{"attempts":1,"playable":47.392299831917235,"score":47.392299831917235},"GB2-06":{"attempts":1,"playable":36.52949567868078,"score":36.52949567868078},"GB2-07":{"attempts":1,"playable":36.047989134789916,"score":36.047989134789916},"GB2-08":{"attempts":1,"playable":29.355334167559388,"score":29.355334167559388}}},"id":"tencent/hy4-preview","is_recent_addition":false,"last_measured_at":"2026-11-03T08:03:04Z","match_totals_all":{"draws":2455,"losses":4556,"wins":5055},"match_totals_tracks":{"highest":{"draws":844,"losses":1246,"wins":2100},"medium":{"draws":576,"losses":1353,"wins":1767},"none":{"draws":1035,"losses":1957,"wins":1188}},"model_slug":"tencent-hy4-preview","official_rank_by_reasoning":{"highest":33,"medium":38,"none":35},"overall":{"max":86.564244244694,"mean":50.91008913757545,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":31,"overall_ranking_status":"ranked","per_game":{"GB2-01":52.89138386814176,"GB2-02":77.13462054083618,"GB2-03":70.09265117251351,"GB2-04":54.86221693747453,"GB2-05":67.39275791941763,"GB2-06":77.93331459363245,"GB2-07":65.73144509795603,"GB2-08":25.03505469705049},"per_game_all":{"GB2-01":49.15236148362688,"GB2-03":57.470695849270044,"GB2-04":43.136140927559076,"GB2-05":54.64943795222468,"GB2-06":57.176940183952986,"GB2-07":59.005822055902534,"GB2-08":46.98487770310129},"per_game_match_totals_all":{"GB2-01":{"draws":366,"losses":624,"wins":590},"GB2-02":{"draws":519,"losses":149,"wins":316},"GB2-03":{"draws":449,"losses":471,"wins":624},"GB2-04":{"draws":858,"losses":463,"wins":213},"GB2-05":{"draws":0,"losses":739,"wins":889},"GB2-06":{"draws":33,"losses":665,"wins":848},"GB2-07":{"draws":0,"losses":686,"wins":938},"GB2-08":{"draws":230,"losses":759,"wins":637}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":246,"losses":128,"wins":156},"GB2-02":{"draws":130,"losses":52,"wins":310},"GB2-03":{"draws":52,"losses":139,"wins":323},"GB2-04":{"draws":266,"losses":105,"wins":141},"GB2-05":{"draws":0,"losses":179,"wins":365},"GB2-06":{"draws":23,"losses":104,"wins":391},"GB2-07":{"draws":0,"losses":191,"wins":349},"GB2-08":{"draws":127,"losses":348,"wins":65}},"medium":{"GB2-01":{"draws":33,"losses":246,"wins":245},"GB2-03":{"draws":274,"losses":186,"wins":56},"GB2-04":{"draws":264,"losses":209,"wins":37},"GB2-05":{"draws":0,"losses":276,"wins":268},"GB2-06":{"draws":5,"losses":227,"wins":282},"GB2-07":{"draws":0,"losses":136,"wins":408},"GB2-08":{"draws":0,"losses":73,"wins":471}},"none":{"GB2-01":{"draws":87,"losses":250,"wins":189},"GB2-02":{"draws":389,"losses":97,"wins":6},"GB2-03":{"draws":123,"losses":146,"wins":245},"GB2-04":{"draws":328,"losses":149,"wins":35},"GB2-05":{"draws":0,"losses":284,"wins":256},"GB2-06":{"draws":5,"losses":334,"wins":175},"GB2-07":{"draws":0,"losses":359,"wins":181},"GB2-08":{"draws":103,"losses":338,"wins":101}}},"per_game_raw_elo_all":{"GB2-01":1479.094734419127,"GB2-03":1518.916727637535,"GB2-04":1423.2636731950176,"GB2-05":1519.2837480210922,"GB2-06":1589.9687178651511,"GB2-07":1580.2181415102416,"GB2-08":1458.2382971473537},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1515.2154041307276,"GB2-02":1724.7807925767424,"GB2-03":1646.1941132812717,"GB2-04":1516.7539917253855,"GB2-05":1698.6915577154948,"GB2-06":1954.037936479513,"GB2-07":1661.1411098262959,"GB2-08":1097.4105025751521},"medium":{"GB2-01":1488.25089195807,"GB2-03":1352.9380358196627,"GB2-04":1352.8096930544966,"GB2-05":1440.9687418145031,"GB2-06":1572.316981666142,"GB2-07":1817.5668644126208,"GB2-08":2126.267683787642},"none":{"GB2-01":1433.8179071685827,"GB2-02":1414.0691798431617,"GB2-03":1557.6180338116708,"GB2-04":1400.2273348051701,"GB2-05":1418.190944533278,"GB2-06":1243.551235449798,"GB2-07":1261.9464502918086,"GB2-08":1151.036705079268}},"per_game_tracks":{"highest":{"GB2-01":52.89138386814176,"GB2-02":77.13462054083618,"GB2-03":70.09265117251351,"GB2-04":54.86221693747453,"GB2-05":67.39275791941763,"GB2-06":77.93331459363245,"GB2-07":65.73144509795603,"GB2-08":25.03505469705049},"medium":{"GB2-01":50.104065549072544,"GB2-03":40.101002244564384,"GB2-04":34.37095264458405,"GB2-05":49.16325610533917,"GB2-06":57.06801027954573,"GB2-07":75.23803193496164,"GB2-08":86.564244244694},"none":{"GB2-01":44.46163503366634,"GB2-02":41.97869029406207,"GB2-03":62.21843413073223,"GB2-04":40.17525320061864,"GB2-05":47.392299831917235,"GB2-06":36.52949567868078,"GB2-07":36.047989134789916,"GB2-08":29.355334167559388}},"program_outcomes":{"all":{"counted_attempts":24,"failed":1,"infra_excluded":0,"success_rate":0.9583333333333334,"too_slow":0,"worked_after_repair":3,"worked_first_time":20,"working":23},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":1,"worked_first_time":6,"working":7},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T16:30:32Z","reasoning":{"highest":61.38418060337782,"medium":49.07619537534519,"none":42.26989143400332},"reasoning_agg":{"highest":{"max":77.93331459363245,"mean":61.38418060337782,"min":25.03505469705049},"medium":{"max":86.564244244694,"mean":49.07619537534519,"min":0.0},"none":{"max":62.21843413073223,"mean":42.26989143400332,"min":29.355334167559388}},"reasoning_labels":{"highest":"High","medium":"Low","none":"None"},"reasoning_settings":{"balanced":"low","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":19.1142891693745},"working_program_strength":{"all":53.24705082211569,"highest":61.38418060337782,"medium":56.08708042896593,"none":42.26989143400332}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-6-flash:5584160e53b73374","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":4.1696877},"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":0.8934513000000002}},"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":4.169687700000001},"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":50.624100490877716,"highest":62.798152419836626,"medium":50.571628861334354,"none":38.50252019146216},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":51.96720993674691,"score":51.96720993674691},"GB2-02":{"attempts":6,"failed_attempts":1,"playable":43.283371939268534,"score":37.239079955745815},"GB2-03":{"attempts":6,"playable":55.86421264977624,"score":55.86421264977624},"GB2-04":{"attempts":6,"playable":47.85694477341675,"score":47.85694477341675},"GB2-05":{"attempts":6,"playable":64.3819086610875,"score":64.3819086610875},"GB2-06":{"attempts":6,"playable":60.80951280573394,"score":60.80951280573394},"GB2-07":{"attempts":6,"playable":47.43330900247298,"score":47.43330900247298},"GB2-08":{"attempts":6,"failed_attempts":1,"playable":50.640885003547965,"score":39.44062614204156}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":54.52400143082311,"score":54.52400143082311},"GB2-02":{"attempts":2,"playable":54.062100322843335,"score":54.062100322843335},"GB2-03":{"attempts":2,"playable":66.57712283356456,"score":66.57712283356456},"GB2-04":{"attempts":2,"playable":62.72931475420698,"score":62.72931475420698},"GB2-05":{"attempts":2,"playable":81.09445592066905,"score":81.09445592066905},"GB2-06":{"attempts":2,"playable":79.40028088285268,"score":79.40028088285268},"GB2-07":{"attempts":2,"playable":49.33236258821588,"score":49.33236258821588},"GB2-08":{"attempts":2,"playable":54.665580625517414,"score":54.665580625517414}},"medium":{"GB2-01":{"attempts":2,"playable":71.32847861908232,"score":71.32847861908232},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":36.265751901136284,"score":18.132875950568142},"GB2-03":{"attempts":2,"playable":46.64403292782249,"score":46.64403292782249},"GB2-04":{"attempts":2,"playable":39.79668464896179,"score":39.79668464896179},"GB2-05":{"attempts":2,"playable":67.23919300307631,"score":67.23919300307631},"GB2-06":{"attempts":2,"playable":80.77928867319451,"score":80.77928867319451},"GB2-07":{"attempts":2,"playable":47.05170048345006,"score":47.05170048345006},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":67.20155316903843,"score":33.60077658451922}},"none":{"GB2-01":{"attempts":2,"playable":30.049149760335304,"score":30.049149760335304},"GB2-02":{"attempts":2,"playable":39.52226359382599,"score":39.52226359382599},"GB2-03":{"attempts":2,"playable":54.37148218794168,"score":54.37148218794168},"GB2-04":{"attempts":2,"playable":41.04483491708149,"score":41.04483491708149},"GB2-05":{"attempts":2,"playable":44.812077059517115,"score":44.812077059517115},"GB2-06":{"attempts":2,"playable":22.24896886115463,"score":22.24896886115463},"GB2-07":{"attempts":2,"playable":45.915863935753016,"score":45.915863935753016},"GB2-08":{"attempts":2,"playable":30.055521216088053,"score":30.055521216088053}}},"id":"google/gemini-3.6-flash","is_recent_addition":false,"last_measured_at":"2026-11-03T07:14:48Z","match_totals_all":{"draws":4815,"losses":9216,"wins":10033},"match_totals_tracks":{"highest":{"draws":1466,"losses":2471,"wins":4425},"medium":{"draws":1365,"losses":2477,"wins":3494},"none":{"draws":1984,"losses":4268,"wins":2114}},"model_slug":"google-gemini-3-6-flash","official_rank_by_reasoning":{"highest":28,"medium":36,"none":48},"overall":{"max":81.09445592066905,"mean":50.624100490877716,"min":18.132875950568142},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":32,"overall_ranking_status":"ranked","per_game":{"GB2-01":54.52400143082311,"GB2-02":54.062100322843335,"GB2-03":66.57712283356456,"GB2-04":62.72931475420698,"GB2-05":81.09445592066905,"GB2-06":79.40028088285268,"GB2-07":49.33236258821588,"GB2-08":54.665580625517414},"per_game_all":{"GB2-01":51.96720993674691,"GB2-02":43.283371939268534,"GB2-03":55.86421264977624,"GB2-04":47.85694477341675,"GB2-05":64.3819086610875,"GB2-06":60.80951280573394,"GB2-07":47.43330900247298,"GB2-08":50.640885003547965},"per_game_match_totals_all":{"GB2-01":{"draws":720,"losses":1167,"wins":1273},"GB2-02":{"draws":1669,"losses":559,"wins":236},"GB2-03":{"draws":330,"losses":1271,"wins":1473},"GB2-04":{"draws":1762,"losses":753,"wins":541},"GB2-05":{"draws":0,"losses":1159,"wins":2099},"GB2-06":{"draws":108,"losses":1182,"wins":1802},"GB2-07":{"draws":0,"losses":1774,"wins":1470},"GB2-08":{"draws":226,"losses":1351,"wins":1139}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":260,"losses":352,"wins":442},"GB2-02":{"draws":587,"losses":171,"wins":226},"GB2-03":{"draws":60,"losses":337,"wins":627},"GB2-04":{"draws":465,"losses":160,"wins":393},"GB2-05":{"draws":0,"losses":207,"wins":879},"GB2-06":{"draws":13,"losses":209,"wins":806},"GB2-07":{"draws":0,"losses":571,"wins":511},"GB2-08":{"draws":81,"losses":464,"wins":541}},"medium":{"GB2-01":{"draws":273,"losses":167,"wins":612},"GB2-02":{"draws":339,"losses":151,"wins":4},"GB2-03":{"draws":89,"losses":529,"wins":408},"GB2-04":{"draws":609,"losses":322,"wins":87},"GB2-05":{"draws":0,"losses":354,"wins":732},"GB2-06":{"draws":36,"losses":182,"wins":814},"GB2-07":{"draws":0,"losses":596,"wins":486},"GB2-08":{"draws":19,"losses":176,"wins":351}},"none":{"GB2-01":{"draws":187,"losses":648,"wins":219},"GB2-02":{"draws":743,"losses":237,"wins":6},"GB2-03":{"draws":181,"losses":405,"wins":438},"GB2-04":{"draws":688,"losses":271,"wins":61},"GB2-05":{"draws":0,"losses":598,"wins":488},"GB2-06":{"draws":59,"losses":791,"wins":182},"GB2-07":{"draws":0,"losses":607,"wins":473},"GB2-08":{"draws":126,"losses":711,"wins":247}}},"per_game_raw_elo_all":{"GB2-01":1538.1625746754462,"GB2-02":1424.5121869283055,"GB2-03":1500.3207209159139,"GB2-04":1463.8881776882129,"GB2-05":1739.976188020859,"GB2-06":1671.958371482058,"GB2-07":1411.0226778202184,"GB2-08":1458.104809917989},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1536.1975369621114,"GB2-02":1510.4867499278078,"GB2-03":1604.7839622991883,"GB2-04":1587.5461942104257,"GB2-05":2028.560008967745,"GB2-06":1995.4487301349213,"GB2-07":1435.1912424874502,"GB2-08":1515.6889339139457},"medium":{"GB2-01":1791.0357747600578,"GB2-02":1368.4097295544436,"GB2-03":1414.1942303649166,"GB2-04":1397.0697119624592,"GB2-05":1806.6034922401218,"GB2-06":2011.6567242924093,"GB2-07":1406.3555199594282,"GB2-08":1699.3544246271692},"none":{"GB2-01":1287.2544123041694,"GB2-02":1394.6400813026644,"GB2-03":1481.9839700836371,"GB2-04":1407.0486268917543,"GB2-05":1384.7650628547103,"GB2-06":1008.7696600188435,"GB2-07":1391.521271013777,"GB2-08":1159.2710712128533}},"per_game_tracks":{"highest":{"GB2-01":54.52400143082311,"GB2-02":54.062100322843335,"GB2-03":66.57712283356456,"GB2-04":62.72931475420698,"GB2-05":81.09445592066905,"GB2-06":79.40028088285268,"GB2-07":49.33236258821588,"GB2-08":54.665580625517414},"medium":{"GB2-01":71.32847861908232,"GB2-02":36.265751901136284,"GB2-03":46.64403292782249,"GB2-04":39.79668464896179,"GB2-05":67.23919300307631,"GB2-06":80.77928867319451,"GB2-07":47.05170048345006,"GB2-08":67.20155316903843},"none":{"GB2-01":30.049149760335304,"GB2-02":39.52226359382599,"GB2-03":54.37148218794168,"GB2-04":41.04483491708149,"GB2-05":44.812077059517115,"GB2-06":22.24896886115463,"GB2-07":45.915863935753016,"GB2-08":30.055521216088053}},"program_outcomes":{"all":{"counted_attempts":48,"failed":2,"infra_excluded":5,"success_rate":0.9583333333333334,"too_slow":0,"worked_after_repair":8,"worked_first_time":38,"working":46},"highest":{"counted_attempts":16,"failed":0,"infra_excluded":5,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":12,"working":16},"medium":{"counted_attempts":16,"failed":2,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":14,"working":14},"none":{"counted_attempts":16,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":12,"working":16}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T17:05:01Z","reasoning":{"highest":62.798152419836626,"medium":50.571628861334354,"none":38.50252019146216},"reasoning_agg":{"highest":{"max":81.09445592066905,"mean":62.798152419836626,"min":49.33236258821588},"medium":{"max":80.77928867319451,"mean":50.571628861334354,"min":18.132875950568142},"none":{"max":54.37148218794168,"mean":38.50252019146216,"min":22.24896886115463}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":24.295632228374465},"working_program_strength":{"all":52.77966934650635,"highest":62.798152419836626,"medium":57.03833542822028,"none":38.50252019146216}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-ox-alpha:d7417423be731139","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":50.50526657006754,"highest":66.19471972484367,"medium":45.70889468198354,"none":39.61218530337542},"economics_best_value":{"per_model":{"medium":true,"none":true},"per_setting":{"medium":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":52.68261326309645,"score":46.02026952189227},"GB2-02":{"attempts":8,"playable":54.50783663143023,"score":54.50783663143023},"GB2-03":{"attempts":23,"failed_attempts":3,"playable":56.191126705461414,"score":50.433632938209826},"GB2-04":{"attempts":9,"playable":58.214757251807136,"score":58.214757251807136},"GB2-05":{"attempts":9,"playable":51.569316297045184,"score":51.569316297045184},"GB2-06":{"attempts":8,"playable":44.12262081856313,"score":44.12262081856313},"GB2-07":{"attempts":9,"playable":49.12208086752778,"score":49.12208086752778},"GB2-08":{"attempts":9,"failed_attempts":1,"playable":53.24866922135808,"score":50.05161823406479}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":3,"playable":57.066652061377475,"score":57.066652061377475},"GB2-02":{"attempts":2,"playable":72.54957583671495,"score":72.54957583671495},"GB2-03":{"attempts":5,"playable":68.88617438812784,"score":68.88617438812784},"GB2-04":{"attempts":3,"playable":70.3266754449726,"score":70.3266754449726},"GB2-05":{"attempts":3,"playable":59.348513497231636,"score":59.348513497231636},"GB2-06":{"attempts":3,"playable":66.55335883164355,"score":66.55335883164355},"GB2-07":{"attempts":3,"playable":64.54257408562812,"score":64.54257408562812},"GB2-08":{"attempts":3,"playable":70.28423365305316,"score":70.28423365305316}},"medium":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":59.96109367083761,"score":39.97406244722507},"GB2-02":{"attempts":3,"playable":48.82343204537232,"score":48.82343204537232},"GB2-03":{"attempts":9,"failed_attempts":2,"playable":55.76512598753643,"score":43.372875768083894},"GB2-04":{"attempts":3,"playable":56.119773237091444,"score":56.119773237091444},"GB2-05":{"attempts":3,"playable":46.4790746896731,"score":46.4790746896731},"GB2-06":{"attempts":2,"playable":25.962735978340476,"score":25.962735978340476},"GB2-07":{"attempts":3,"playable":44.250888164700505,"score":44.250888164700505},"GB2-08":{"attempts":3,"playable":60.68831512538153,"score":60.68831512538153}},"none":{"GB2-01":{"attempts":3,"playable":41.02009405707426,"score":41.02009405707426},"GB2-02":{"attempts":3,"playable":42.150502012203425,"score":42.150502012203425},"GB2-03":{"attempts":9,"failed_attempts":1,"playable":43.92207974071996,"score":39.04184865841774},"GB2-04":{"attempts":3,"playable":48.19782307335738,"score":48.19782307335738},"GB2-05":{"attempts":3,"playable":48.88036070423082,"score":48.88036070423082},"GB2-06":{"attempts":3,"playable":39.85176764570536,"score":39.85176764570536},"GB2-07":{"attempts":3,"playable":38.57278035225471,"score":38.57278035225471},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":28.773458885639535,"score":19.18230592375969}}},"id":"stealth/ox-alpha","is_recent_addition":false,"last_measured_at":"2026-11-03T08:01:57Z","match_totals_all":{"draws":8077,"losses":15963,"wins":17158},"match_totals_tracks":{"highest":{"draws":1285,"losses":3918,"wins":7865},"medium":{"draws":2769,"losses":5421,"wins":5372},"none":{"draws":4023,"losses":6624,"wins":3921}},"model_slug":"stealth-ox-alpha","official_rank_by_reasoning":{"highest":23,"medium":47,"none":44},"overall":{"max":72.54957583671495,"mean":50.50526657006754,"min":19.18230592375969},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":33,"overall_ranking_status":"ranked","per_game":{"GB2-01":57.066652061377475,"GB2-02":72.54957583671495,"GB2-03":68.88617438812784,"GB2-04":70.3266754449726,"GB2-05":59.348513497231636,"GB2-06":66.55335883164355,"GB2-07":64.54257408562812,"GB2-08":70.28423365305316},"per_game_all":{"GB2-01":52.68261326309645,"GB2-02":54.50783663143023,"GB2-03":56.191126705461414,"GB2-04":58.214757251807136,"GB2-05":51.569316297045184,"GB2-06":44.12262081856313,"GB2-07":49.12208086752778,"GB2-08":53.24866922135808},"per_game_match_totals_all":{"GB2-01":{"draws":695,"losses":1689,"wins":1820},"GB2-02":{"draws":2541,"losses":664,"wins":747},"GB2-03":{"draws":1923,"losses":3971,"wins":4352},"GB2-04":{"draws":2408,"losses":777,"wins":1413},"GB2-05":{"draws":0,"losses":2359,"wins":2519},"GB2-06":{"draws":107,"losses":2211,"wins":1798},"GB2-07":{"draws":0,"losses":2550,"wins":2314},"GB2-08":{"draws":403,"losses":1742,"wins":2195}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":75,"losses":641,"wins":858},"GB2-02":{"draws":356,"losses":103,"wins":529},"GB2-03":{"draws":146,"losses":776,"wins":1638},"GB2-04":{"draws":577,"losses":182,"wins":769},"GB2-05":{"draws":0,"losses":661,"wins":967},"GB2-06":{"draws":69,"losses":496,"wins":977},"GB2-07":{"draws":0,"losses":593,"wins":1029},"GB2-08":{"draws":62,"losses":466,"wins":1098}},"medium":{"GB2-01":{"draws":234,"losses":306,"wins":512},"GB2-02":{"draws":1067,"losses":244,"wins":171},"GB2-03":{"draws":390,"losses":1478,"wins":1716},"GB2-04":{"draws":886,"losses":251,"wins":397},"GB2-05":{"draws":0,"losses":869,"wins":757},"GB2-06":{"draws":18,"losses":769,"wins":243},"GB2-07":{"draws":0,"losses":929,"wins":693},"GB2-08":{"draws":174,"losses":575,"wins":883}},"none":{"GB2-01":{"draws":386,"losses":742,"wins":450},"GB2-02":{"draws":1118,"losses":317,"wins":47},"GB2-03":{"draws":1387,"losses":1717,"wins":998},"GB2-04":{"draws":945,"losses":344,"wins":247},"GB2-05":{"draws":0,"losses":829,"wins":795},"GB2-06":{"draws":20,"losses":946,"wins":578},"GB2-07":{"draws":0,"losses":1028,"wins":592},"GB2-08":{"draws":167,"losses":701,"wins":214}}},"per_game_raw_elo_all":{"GB2-01":1514.0495100557503,"GB2-02":1521.0876964657184,"GB2-03":1519.028902359317,"GB2-04":1555.4760878089526,"GB2-05":1475.0121860061624,"GB2-06":1360.9457091422144,"GB2-07":1428.5771508161545,"GB2-08":1503.886110698839},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1558.7991659013805,"GB2-02":1680.2303180743334,"GB2-03":1660.8621682733071,"GB2-04":1675.2128330813268,"GB2-05":1581.4539727416313,"GB2-06":1764.7949836661246,"GB2-07":1647.746355369579,"GB2-08":1776.3900461633832},"medium":{"GB2-01":1585.5244869401613,"GB2-02":1467.6386019628042,"GB2-03":1510.0072126864263,"GB2-04":1527.3909977570265,"GB2-05":1406.1443210054722,"GB2-06":1023.9991039472005,"GB2-07":1357.5569575593133,"GB2-08":1592.2108970717056},"none":{"GB2-01":1397.824877325709,"GB2-02":1415.3941693600184,"GB2-03":1386.2173261182177,"GB2-04":1463.8244325885044,"GB2-05":1437.4382642713836,"GB2-06":1294.0430398133174,"GB2-07":1280.428139519571,"GB2-08":1143.0573888614285}},"per_game_tracks":{"highest":{"GB2-01":57.066652061377475,"GB2-02":72.54957583671495,"GB2-03":68.88617438812784,"GB2-04":70.3266754449726,"GB2-05":59.348513497231636,"GB2-06":66.55335883164355,"GB2-07":64.54257408562812,"GB2-08":70.28423365305316},"medium":{"GB2-01":59.96109367083761,"GB2-02":48.82343204537232,"GB2-03":55.76512598753643,"GB2-04":56.119773237091444,"GB2-05":46.479074689673105,"GB2-06":25.962735978340476,"GB2-07":44.25088816470049,"GB2-08":60.68831512538153},"none":{"GB2-01":41.02009405707426,"GB2-02":42.150502012203425,"GB2-03":43.922079740719965,"GB2-04":48.19782307335738,"GB2-05":48.88036070423082,"GB2-06":39.85176764570536,"GB2-07":38.57278035225471,"GB2-08":28.773458885639535}},"program_outcomes":{"all":{"counted_attempts":84,"failed":5,"infra_excluded":5,"success_rate":0.9404761904761905,"too_slow":1,"worked_after_repair":17,"worked_first_time":62,"working":79},"highest":{"counted_attempts":25,"failed":0,"infra_excluded":5,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":22,"working":25},"medium":{"counted_attempts":29,"failed":3,"infra_excluded":0,"success_rate":0.896551724137931,"too_slow":1,"worked_after_repair":5,"worked_first_time":21,"working":26},"none":{"counted_attempts":30,"failed":2,"infra_excluded":0,"success_rate":0.9333333333333333,"too_slow":0,"worked_after_repair":9,"worked_first_time":19,"working":28}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T17:12:55Z","reasoning":{"highest":66.19471972484367,"medium":45.70889468198354,"none":39.61218530337542},"reasoning_agg":{"highest":{"max":72.54957583671495,"mean":66.19471972484367,"min":57.066652061377475},"medium":{"max":60.68831512538153,"mean":45.70889468198354,"min":25.962735978340476},"none":{"max":48.88036070423082,"mean":39.61218530337542,"min":19.18230592375969}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":26.582534421468246},"working_program_strength":{"all":52.45737763203618,"highest":66.19471972484367,"medium":49.756304862366676,"none":41.42110830889818}},{"canonical_public_row_identity":"publication-row.v1:overall:fireworks-ember-1:652066c0cab2100d","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":2.3911469999999997},"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":1.139997},"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":0.582672}},"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":1.1399969999999997},"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":2.3911469999999997}},"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":4.113816},"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":50.29915282041248,"highest":62.904459464956396,"medium":52.41033084264093,"none":35.582668153640135},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":58.034283992684216,"score":58.034283992684216},"GB2-02":{"attempts":3,"playable":43.24140908460901,"score":43.24140908460901},"GB2-03":{"attempts":3,"playable":58.50287586812461,"score":58.50287586812461},"GB2-04":{"attempts":3,"playable":43.549672425685706,"score":43.549672425685706},"GB2-05":{"attempts":3,"playable":41.723165654099276,"score":41.723165654099276},"GB2-06":{"attempts":3,"playable":48.903210643275315,"score":48.903210643275315},"GB2-07":{"attempts":3,"playable":57.41413816702805,"score":57.41413816702805},"GB2-08":{"attempts":3,"playable":51.02446672779373,"score":51.02446672779373}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":74.85148751742612,"score":74.85148751742612},"GB2-02":{"attempts":1,"playable":41.47623951515983,"score":41.47623951515983},"GB2-03":{"attempts":1,"playable":79.14502082529305,"score":79.14502082529305},"GB2-04":{"attempts":1,"playable":39.063105938535884,"score":39.063105938535884},"GB2-05":{"attempts":1,"playable":60.30075084949035,"score":60.30075084949035},"GB2-06":{"attempts":1,"playable":49.03237377425278,"score":49.03237377425278},"GB2-07":{"attempts":1,"playable":73.66136449687862,"score":73.66136449687862},"GB2-08":{"attempts":1,"playable":85.70533280261456,"score":85.70533280261456}},"medium":{"GB2-01":{"attempts":1,"playable":49.79278791334642,"score":49.79278791334642},"GB2-02":{"attempts":1,"playable":43.820007201965176,"score":43.820007201965176},"GB2-03":{"attempts":1,"playable":60.363119197329226,"score":60.363119197329226},"GB2-04":{"attempts":1,"playable":51.63643838395991,"score":51.63643838395991},"GB2-05":{"attempts":1,"playable":44.73240942210773,"score":44.73240942210773},"GB2-06":{"attempts":1,"playable":53.73969640017546,"score":53.73969640017546},"GB2-07":{"attempts":1,"playable":62.27683560602372,"score":62.27683560602372},"GB2-08":{"attempts":1,"playable":52.9213526162198,"score":52.9213526162198}},"none":{"GB2-01":{"attempts":1,"playable":49.458576547280096,"score":49.458576547280096},"GB2-02":{"attempts":1,"playable":44.42798053670202,"score":44.42798053670202},"GB2-03":{"attempts":1,"playable":36.00048758175156,"score":36.00048758175156},"GB2-04":{"attempts":1,"playable":39.9494729545613,"score":39.9494729545613},"GB2-05":{"attempts":1,"playable":20.136336690699753,"score":20.136336690699753},"GB2-06":{"attempts":1,"playable":43.937561755397695,"score":43.937561755397695},"GB2-07":{"attempts":1,"playable":36.30421439818182,"score":36.30421439818182},"GB2-08":{"attempts":1,"playable":14.446714764546801,"score":14.446714764546801}}},"id":"fireworks/ember-1","is_recent_addition":false,"last_measured_at":"2026-11-03T07:04:56Z","match_totals_all":{"draws":2940,"losses":4907,"wins":4703},"match_totals_tracks":{"highest":{"draws":725,"losses":1211,"wins":2250},"medium":{"draws":1042,"losses":1517,"wins":1619},"none":{"draws":1173,"losses":2179,"wins":834}},"model_slug":"fireworks-ember-1","official_rank_by_reasoning":{"highest":27,"medium":32,"none":53},"overall":{"max":85.70533280261456,"mean":50.29915282041248,"min":14.446714764546801},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":34,"overall_ranking_status":"ranked","per_game":{"GB2-01":74.85148751742612,"GB2-02":41.47623951515983,"GB2-03":79.14502082529305,"GB2-04":39.063105938535884,"GB2-05":60.30075084949035,"GB2-06":49.03237377425278,"GB2-07":73.66136449687862,"GB2-08":85.70533280261456},"per_game_all":{"GB2-01":58.034283992684216,"GB2-02":43.24140908460901,"GB2-03":58.50287586812461,"GB2-04":43.549672425685706,"GB2-05":41.723165654099276,"GB2-06":48.903210643275315,"GB2-07":57.41413816702805,"GB2-08":51.02446672779373},"per_game_match_totals_all":{"GB2-01":{"draws":476,"losses":428,"wins":674},"GB2-02":{"draws":1089,"losses":315,"wins":78},"GB2-03":{"draws":308,"losses":522,"wins":714},"GB2-04":{"draws":899,"losses":436,"wins":197},"GB2-05":{"draws":0,"losses":945,"wins":679},"GB2-06":{"draws":37,"losses":802,"wins":701},"GB2-07":{"draws":0,"losses":713,"wins":907},"GB2-08":{"draws":131,"losses":746,"wins":753}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":10,"losses":128,"wins":388},"GB2-02":{"draws":371,"losses":111,"wins":14},"GB2-03":{"draws":18,"losses":106,"wins":390},"GB2-04":{"draws":311,"losses":163,"wins":38},"GB2-05":{"draws":0,"losses":215,"wins":327},"GB2-06":{"draws":13,"losses":266,"wins":233},"GB2-07":{"draws":0,"losses":145,"wins":395},"GB2-08":{"draws":2,"losses":77,"wins":465}},"medium":{"GB2-01":{"draws":261,"losses":135,"wins":130},"GB2-02":{"draws":361,"losses":102,"wins":29},"GB2-03":{"draws":43,"losses":196,"wins":275},"GB2-04":{"draws":304,"losses":102,"wins":104},"GB2-05":{"draws":0,"losses":297,"wins":243},"GB2-06":{"draws":7,"losses":244,"wins":263},"GB2-07":{"draws":0,"losses":211,"wins":329},"GB2-08":{"draws":66,"losses":230,"wins":246}},"none":{"GB2-01":{"draws":205,"losses":165,"wins":156},"GB2-02":{"draws":357,"losses":102,"wins":35},"GB2-03":{"draws":247,"losses":220,"wins":49},"GB2-04":{"draws":284,"losses":171,"wins":55},"GB2-05":{"draws":0,"losses":433,"wins":109},"GB2-06":{"draws":17,"losses":292,"wins":205},"GB2-07":{"draws":0,"losses":357,"wins":183},"GB2-08":{"draws":63,"losses":439,"wins":42}}},"per_game_raw_elo_all":{"GB2-01":1572.9575128983354,"GB2-02":1423.958041336565,"GB2-03":1543.6074945696919,"GB2-04":1426.8621763120448,"GB2-05":1329.3188583680037,"GB2-06":1438.9212378647487,"GB2-07":1555.0163256761414,"GB2-08":1501.2946399231153},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1751.5981486482656,"GB2-02":1410.113814180713,"GB2-03":1775.9902174757603,"GB2-04":1391.30140958602,"GB2-05":1589.7483785557529,"GB2-06":1440.3766833259463,"GB2-07":1789.0375010391544,"GB2-08":2103.931568760211},"medium":{"GB2-01":1485.248447669118,"GB2-02":1428.5047226948247,"GB2-03":1538.6959067457665,"GB2-04":1490.8652588872662,"GB2-05":1383.9206507251774,"GB2-06":1516.7682026765867,"GB2-07":1610.6671894334827,"GB2-08":1454.0336730946105},"none":{"GB2-01":1482.0259423776229,"GB2-02":1433.2555871341574,"GB2-03":1316.1363594875486,"GB2-04":1398.4198604628484,"GB2-05":1014.2875458230803,"GB2-06":1359.6188275917127,"GB2-07":1265.3442865557863,"GB2-08":945.9186779145244}},"per_game_tracks":{"highest":{"GB2-01":74.85148751742612,"GB2-02":41.47623951515983,"GB2-03":79.14502082529305,"GB2-04":39.063105938535884,"GB2-05":60.30075084949035,"GB2-06":49.03237377425278,"GB2-07":73.66136449687862,"GB2-08":85.70533280261456},"medium":{"GB2-01":49.79278791334642,"GB2-02":43.820007201965176,"GB2-03":60.363119197329226,"GB2-04":51.63643838395991,"GB2-05":44.73240942210773,"GB2-06":53.73969640017546,"GB2-07":62.27683560602372,"GB2-08":52.9213526162198},"none":{"GB2-01":49.458576547280096,"GB2-02":44.42798053670202,"GB2-03":36.00048758175156,"GB2-04":39.9494729545613,"GB2-05":20.136336690699753,"GB2-06":43.937561755397695,"GB2-07":36.30421439818182,"GB2-08":14.446714764546801}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":20,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#6720FF","provider_company":"Fireworks AI","provider_key":"fireworks","provider_text_color":"#f8fafc","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T17:13:07Z","reasoning":{"highest":62.904459464956396,"medium":52.41033084264093,"none":35.582668153640135},"reasoning_agg":{"highest":{"max":85.70533280261456,"mean":62.904459464956396,"min":39.063105938535884},"medium":{"max":62.27683560602372,"mean":52.41033084264093,"min":43.820007201965176},"none":{"max":49.458576547280096,"mean":35.582668153640135,"min":14.446714764546801}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":27.32179131131626},"working_program_strength":{"all":50.29915282041248,"highest":62.904459464956396,"medium":52.41033084264093,"none":35.582668153640135}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-8:5a2ef8bbc04cd5c2","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":1.743525},"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":1.743525},"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":7.449890000000001}},"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":10.456240000000003},"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":49.57361310911697,"highest":62.364980600462125,"medium":45.419018669825014,"none":40.93684005706378},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"failed"},"none":{"GB2-03":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":53.30278844258999,"score":53.30278844258999},"GB2-02":{"attempts":3,"playable":52.62504971097618,"score":52.62504971097618},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":29.825975049308205,"score":9.941991683102735},"GB2-04":{"attempts":3,"playable":50.54369501524997,"score":50.54369501524997},"GB2-05":{"attempts":3,"playable":37.51176126229738,"score":37.51176126229738},"GB2-06":{"attempts":3,"playable":67.57632998241654,"score":67.57632998241654},"GB2-07":{"attempts":3,"playable":63.41139757642663,"score":63.41139757642663},"GB2-08":{"attempts":3,"playable":61.67589119987636,"score":61.67589119987636}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":66.99902658088797,"score":66.99902658088797},"GB2-02":{"attempts":1,"playable":78.30947046345032,"score":78.30947046345032},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":70.02707296321938,"score":70.02707296321938},"GB2-05":{"attempts":1,"playable":46.20805083377415,"score":46.20805083377415},"GB2-06":{"attempts":1,"playable":79.67969674122214,"score":79.67969674122214},"GB2-07":{"attempts":1,"playable":74.5250119791861,"score":74.5250119791861},"GB2-08":{"attempts":1,"playable":83.17151524195691,"score":83.17151524195691}},"medium":{"GB2-01":{"attempts":1,"playable":39.00092648646489,"score":39.00092648646489},"GB2-02":{"attempts":1,"playable":40.95276656352444,"score":40.95276656352444},"GB2-03":{"attempts":1,"playable":29.825975049308205,"score":29.825975049308205},"GB2-04":{"attempts":1,"playable":40.95550104809879,"score":40.95550104809879},"GB2-05":{"attempts":1,"playable":45.10162822993343,"score":45.10162822993343},"GB2-06":{"attempts":1,"playable":76.8110717948158,"score":76.8110717948158},"GB2-07":{"attempts":1,"playable":65.38664944478624,"score":65.38664944478624},"GB2-08":{"attempts":1,"playable":25.31763074166834,"score":25.31763074166834}},"none":{"GB2-01":{"attempts":1,"playable":53.90841226041713,"score":53.90841226041713},"GB2-02":{"attempts":1,"playable":38.61291210595378,"score":38.61291210595378},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.64851103443174,"score":40.64851103443174},"GB2-05":{"attempts":1,"playable":21.225604723184553,"score":21.225604723184553},"GB2-06":{"attempts":1,"playable":46.238221411211704,"score":46.238221411211704},"GB2-07":{"attempts":1,"playable":50.32253130530753,"score":50.32253130530753},"GB2-08":{"attempts":1,"playable":76.53852761600383,"score":76.53852761600383}}},"id":"claude-opus-4-8","is_recent_addition":false,"last_measured_at":"2026-11-03T07:14:24Z","match_totals_all":{"draws":2329,"losses":4221,"wins":4970},"match_totals_tracks":{"highest":{"draws":484,"losses":833,"wins":2355},"medium":{"draws":1050,"losses":1800,"wins":1332},"none":{"draws":795,"losses":1588,"wins":1283}},"model_slug":"claude-opus-4-8","official_rank_by_reasoning":{"highest":30,"medium":48,"none":38},"overall":{"max":83.17151524195691,"mean":49.57361310911697,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":35,"overall_ranking_status":"ranked","per_game":{"GB2-01":66.99902658088797,"GB2-02":78.30947046345032,"GB2-04":70.02707296321938,"GB2-05":46.20805083377415,"GB2-06":79.67969674122214,"GB2-07":74.5250119791861,"GB2-08":83.17151524195691},"per_game_all":{"GB2-01":53.30278844258999,"GB2-02":52.62504971097618,"GB2-04":50.54369501524997,"GB2-05":37.51176126229738,"GB2-06":67.57632998241654,"GB2-07":63.41139757642663,"GB2-08":61.67589119987636},"per_game_match_totals_all":{"GB2-01":{"draws":266,"losses":608,"wins":704},"GB2-02":{"draws":915,"losses":260,"wins":303},"GB2-03":{"draws":153,"losses":295,"wins":64},"GB2-04":{"draws":856,"losses":350,"wins":328},"GB2-05":{"draws":0,"losses":1016,"wins":612},"GB2-06":{"draws":38,"losses":496,"wins":1012},"GB2-07":{"draws":0,"losses":613,"wins":1009},"GB2-08":{"draws":101,"losses":583,"wins":938}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":69,"losses":140,"wins":317},"GB2-02":{"draws":188,"losses":17,"wins":287},"GB2-04":{"draws":205,"losses":57,"wins":250},"GB2-05":{"draws":0,"losses":292,"wins":252},"GB2-06":{"draws":22,"losses":95,"wins":401},"GB2-07":{"draws":0,"losses":140,"wins":400},"GB2-08":{"draws":0,"losses":92,"wins":448}},"medium":{"GB2-01":{"draws":78,"losses":285,"wins":165},"GB2-02":{"draws":386,"losses":104,"wins":2},"GB2-03":{"draws":153,"losses":295,"wins":64},"GB2-04":{"draws":326,"losses":145,"wins":39},"GB2-05":{"draws":0,"losses":298,"wins":246},"GB2-06":{"draws":7,"losses":118,"wins":389},"GB2-07":{"draws":0,"losses":193,"wins":347},"GB2-08":{"draws":100,"losses":362,"wins":80}},"none":{"GB2-01":{"draws":119,"losses":183,"wins":222},"GB2-02":{"draws":341,"losses":139,"wins":14},"GB2-04":{"draws":325,"losses":148,"wins":39},"GB2-05":{"draws":0,"losses":426,"wins":114},"GB2-06":{"draws":9,"losses":283,"wins":222},"GB2-07":{"draws":0,"losses":280,"wins":262},"GB2-08":{"draws":1,"losses":129,"wins":410}}},"per_game_raw_elo_all":{"GB2-01":1521.491730739408,"GB2-02":1510.8307722069922,"GB2-04":1487.0390025161223,"GB2-05":1275.3572526390453,"GB2-06":1772.2715783568926,"GB2-07":1636.2143497012655,"GB2-08":1677.875954350312},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1659.004789971243,"GB2-02":1739.128403468638,"GB2-04":1650.6505808600093,"GB2-05":1402.9549975318587,"GB2-06":1988.880246433608,"GB2-07":1804.4924727396103,"GB2-08":2041.2819959965727},"medium":{"GB2-01":1380.3626242842702,"GB2-02":1405.9837385039386,"GB2-03":1258.3541247208595,"GB2-04":1406.4573928473637,"GB2-05":1388.6907448689028,"GB2-06":1932.0223752461927,"GB2-07":1655.9966494065513,"GB2-08":1100.9935438065183},"none":{"GB2-01":1525.1077779627103,"GB2-02":1387.3801746483996,"GB2-04":1404.0090338409939,"GB2-05":1034.4260155163747,"GB2-06":1395.912113390877,"GB2-07":1448.1539269576344,"GB2-08":1891.3523232478447}},"per_game_tracks":{"highest":{"GB2-01":66.99902658088797,"GB2-02":78.30947046345032,"GB2-04":70.02707296321938,"GB2-05":46.20805083377415,"GB2-06":79.67969674122214,"GB2-07":74.5250119791861,"GB2-08":83.17151524195691},"medium":{"GB2-01":39.00092648646489,"GB2-02":40.95276656352444,"GB2-03":29.825975049308205,"GB2-04":40.95550104809879,"GB2-05":45.10162822993343,"GB2-06":76.8110717948158,"GB2-07":65.38664944478624,"GB2-08":25.31763074166834},"none":{"GB2-01":53.90841226041713,"GB2-02":38.61291210595378,"GB2-04":40.64851103443174,"GB2-05":21.225604723184553,"GB2-06":46.238221411211704,"GB2-07":50.32253130530753,"GB2-08":76.53852761600383}},"program_outcomes":{"all":{"counted_attempts":24,"failed":2,"infra_excluded":6,"success_rate":0.9166666666666666,"too_slow":0,"worked_after_repair":1,"worked_first_time":21,"working":22},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":6,"success_rate":0.875,"too_slow":0,"worked_after_repair":1,"worked_first_time":6,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T16:57:51Z","reasoning":{"highest":62.364980600462125,"medium":45.419018669825014,"none":40.93684005706378},"reasoning_agg":{"highest":{"max":83.17151524195691,"mean":62.364980600462125,"min":0.0},"medium":{"max":76.8110717948158,"mean":45.419018669825014,"min":25.31763074166834},"none":{"max":76.53852761600383,"mean":40.93684005706378,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":21.428140543398342},"working_program_strength":{"all":54.49274742614202,"highest":71.27426354338529,"medium":45.419018669825014,"none":46.78496006521575}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash:43de48784439f899","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":2.164549388465127},"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":1.5865090123478314},"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":1.2313580991870414}},"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":0.5341545000000001},"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":0.6972035991870417},"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":2.164549388465127}},"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":49.37618796176323,"highest":62.62871111523067,"medium":55.24022980603793,"none":30.25962296402109},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":69.44651132684233,"score":69.44651132684233},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":47.6006995419738,"score":41.1299476014583},"GB2-03":{"attempts":4,"failed_attempts":1,"playable":53.464012023227845,"score":49.640262205097024},"GB2-04":{"attempts":4,"playable":45.32613589688507,"score":45.32613589688507},"GB2-05":{"attempts":4,"playable":42.489623843099324,"score":42.489623843099324},"GB2-06":{"attempts":4,"playable":59.51516525882858,"score":59.51516525882858},"GB2-07":{"attempts":4,"playable":48.52972768903236,"score":48.52972768903236},"GB2-08":{"attempts":4,"playable":38.93212987286284,"score":38.93212987286284}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":89.94436486119334,"score":89.94436486119334},"GB2-02":{"attempts":1,"playable":61.48082027969739,"score":61.48082027969739},"GB2-03":{"attempts":1,"playable":68.99874594844829,"score":68.99874594844829},"GB2-04":{"attempts":1,"playable":41.16217150208289,"score":41.16217150208289},"GB2-05":{"attempts":1,"playable":48.79348467348524,"score":48.79348467348524},"GB2-06":{"attempts":1,"playable":70.9923097090008,"score":70.9923097090008},"GB2-07":{"attempts":1,"playable":50.646507939343074,"score":50.646507939343074},"GB2-08":{"attempts":1,"playable":69.01128400859436,"score":69.01128400859436}},"medium":{"GB2-01":{"attempts":1,"playable":71.6432828680858,"score":71.6432828680858},"GB2-02":{"attempts":1,"playable":42.49676670313098,"score":42.49676670313098},"GB2-03":{"attempts":1,"playable":68.4507912124503,"score":68.4507912124503},"GB2-04":{"attempts":1,"playable":53.73822189934258,"score":53.73822189934258},"GB2-05":{"attempts":1,"playable":64.05660123952175,"score":64.05660123952175},"GB2-06":{"attempts":1,"playable":70.53790450046571,"score":70.53790450046571},"GB2-07":{"attempts":1,"playable":51.1975847380721,"score":51.1975847380721},"GB2-08":{"attempts":1,"playable":19.800685287234167,"score":19.800685287234167}},"none":{"GB2-01":{"attempts":2,"playable":46.75188625124788,"score":46.75188625124788},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":38.82451164309305,"score":19.412255821546523},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":22.942498908784945,"score":11.471249454392472},"GB2-04":{"attempts":2,"playable":41.078014289229756,"score":41.078014289229756},"GB2-05":{"attempts":2,"playable":14.618785616290982,"score":14.618785616290982},"GB2-06":{"attempts":2,"playable":37.01528156701922,"score":37.01528156701922},"GB2-07":{"attempts":2,"playable":43.7450903896819,"score":43.7450903896819},"GB2-08":{"attempts":2,"playable":27.98442032275998,"score":27.98442032275998}}},"id":"google/gemini-3.5-flash","is_recent_addition":false,"last_measured_at":"2026-11-03T07:15:45Z","match_totals_all":{"draws":2925,"losses":6985,"wins":5830},"match_totals_tracks":{"highest":{"draws":646,"losses":1286,"wins":2256},"medium":{"draws":777,"losses":1535,"wins":1876},"none":{"draws":1502,"losses":4164,"wins":1698}},"model_slug":"google-gemini-3-5-flash","official_rank_by_reasoning":{"highest":29,"medium":28,"none":61},"overall":{"max":89.94436486119334,"mean":49.37618796176323,"min":11.471249454392472},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":36,"overall_ranking_status":"ranked","per_game":{"GB2-01":89.94436486119334,"GB2-02":61.48082027969739,"GB2-03":68.99874594844829,"GB2-04":41.16217150208289,"GB2-05":48.79348467348524,"GB2-06":70.9923097090008,"GB2-07":50.646507939343074,"GB2-08":69.01128400859436},"per_game_all":{"GB2-01":69.44651132684233,"GB2-02":47.6006995419738,"GB2-03":53.464012023227845,"GB2-04":45.32613589688507,"GB2-05":42.489623843099324,"GB2-06":59.51516525882858,"GB2-07":48.52972768903236,"GB2-08":38.93212987286284},"per_game_match_totals_all":{"GB2-01":{"draws":225,"losses":656,"wins":1225},"GB2-02":{"draws":1034,"losses":277,"wins":171},"GB2-03":{"draws":158,"losses":672,"wins":714},"GB2-04":{"draws":1197,"losses":568,"wins":279},"GB2-05":{"draws":0,"losses":1404,"wins":770},"GB2-06":{"draws":13,"losses":965,"wins":1080},"GB2-07":{"draws":0,"losses":1184,"wins":978},"GB2-08":{"draws":298,"losses":1259,"wins":613}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":42,"wins":461},"GB2-02":{"draws":262,"losses":65,"wins":167},"GB2-03":{"draws":39,"losses":152,"wins":325},"GB2-04":{"draws":278,"losses":169,"wins":65},"GB2-05":{"draws":0,"losses":278,"wins":266},"GB2-06":{"draws":3,"losses":152,"wins":361},"GB2-07":{"draws":0,"losses":277,"wins":263},"GB2-08":{"draws":43,"losses":151,"wins":348}},"medium":{"GB2-01":{"draws":14,"losses":143,"wins":369},"GB2-02":{"draws":404,"losses":88,"wins":2},"GB2-03":{"draws":47,"losses":151,"wins":318},"GB2-04":{"draws":276,"losses":105,"wins":129},"GB2-05":{"draws":0,"losses":195,"wins":347},"GB2-06":{"draws":4,"losses":154,"wins":358},"GB2-07":{"draws":0,"losses":275,"wins":267},"GB2-08":{"draws":32,"losses":424,"wins":86}},"none":{"GB2-01":{"draws":190,"losses":471,"wins":395},"GB2-02":{"draws":368,"losses":124,"wins":2},"GB2-03":{"draws":72,"losses":369,"wins":71},"GB2-04":{"draws":643,"losses":294,"wins":85},"GB2-05":{"draws":0,"losses":931,"wins":157},"GB2-06":{"draws":6,"losses":659,"wins":361},"GB2-07":{"draws":0,"losses":632,"wins":448},"GB2-08":{"draws":223,"losses":684,"wins":179}}},"per_game_raw_elo_all":{"GB2-01":1726.1352346850397,"GB2-02":1459.0119931004228,"GB2-03":1482.1516246225904,"GB2-04":1441.0449786229,"GB2-05":1327.6729457647498,"GB2-06":1627.157841517587,"GB2-07":1424.7953327793446,"GB2-08":1298.9966065445458},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2011.060933107904,"GB2-02":1569.8228907171988,"GB2-03":1632.8900803803451,"GB2-04":1408.103698278577,"GB2-05":1436.2099407250043,"GB2-06":1821.0644969186,"GB2-07":1452.4057988495051,"GB2-08":1734.9782404771101},"medium":{"GB2-01":1712.0151253183042,"GB2-02":1418.139442875138,"GB2-03":1626.3672996362136,"GB2-04":1507.6797685692095,"GB2-05":1645.2263487248263,"GB2-06":1812.5740003008395,"GB2-07":1459.6503160599873,"GB2-08":1027.835435464337},"none":{"GB2-01":1455.3296456289108,"GB2-02":1389.0736457089313,"GB2-03":1187.1974938512126,"GB2-04":1407.3514690209145,"GB2-05":901.5825478444185,"GB2-06":1247.8350273333217,"GB2-07":1362.329883428541,"GB2-08":1134.17614369219}},"per_game_tracks":{"highest":{"GB2-01":89.94436486119334,"GB2-02":61.48082027969739,"GB2-03":68.99874594844829,"GB2-04":41.16217150208289,"GB2-05":48.79348467348524,"GB2-06":70.9923097090008,"GB2-07":50.646507939343074,"GB2-08":69.01128400859436},"medium":{"GB2-01":71.6432828680858,"GB2-02":42.49676670313098,"GB2-03":68.4507912124503,"GB2-04":53.73822189934258,"GB2-05":64.05660123952175,"GB2-06":70.53790450046571,"GB2-07":51.1975847380721,"GB2-08":19.800685287234167},"none":{"GB2-01":46.75188625124788,"GB2-02":38.82451164309305,"GB2-03":22.942498908784945,"GB2-04":41.078014289229756,"GB2-05":14.618785616290982,"GB2-06":37.01528156701922,"GB2-07":43.7450903896819,"GB2-08":27.98442032275998}},"program_outcomes":{"all":{"counted_attempts":32,"failed":2,"infra_excluded":0,"success_rate":0.9375,"too_slow":0,"worked_after_repair":8,"worked_first_time":22,"working":30},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":16,"failed":2,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":11,"working":14}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T17:14:21Z","reasoning":{"highest":62.62871111523067,"medium":55.24022980603793,"none":30.259622964021087},"reasoning_agg":{"highest":{"max":89.94436486119334,"mean":62.62871111523067,"min":41.16217150208289},"medium":{"max":71.6432828680858,"mean":55.24022980603793,"min":19.800685287234167},"none":{"max":46.75188625124788,"mean":30.259622964021087,"min":11.471249454392472}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":32.36908815120958},"working_program_strength":{"all":50.66300068159402,"highest":62.62871111523067,"medium":55.24022980603793,"none":34.120061123513466}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-5:41dd219b4919f08f","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":21.885475000000003},"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":3.5428549999999994},"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":26.566349999999996},"codegen_latency_ms":{"attempt_count":26,"max_ms":1288484,"mean_ms":282342.6666666667,"min_ms":29373,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1288484,"mean_ms":693731.5,"min_ms":464667,"run_count":8},"medium":{"attempt_count":9,"max_ms":158785,"mean_ms":120076.75,"min_ms":87418,"run_count":8},"none":{"attempt_count":8,"max_ms":37405,"mean_ms":33219.75,"min_ms":29373,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":144760,"output_mean":35491.166666666664,"output_min":2821,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":144760,"output_mean":89741.375,"output_min":66963,"run_count":8},"medium":{"attempt_count":9,"output_max":16870,"output_mean":13281.625,"output_min":10218,"run_count":8},"none":{"attempt_count":8,"output_max":3990,"output_mean":3450.5,"output_min":2821,"run_count":8}},"display_name":"GPT-5.5","economics":{"all":49.013421032375625,"highest":59.706345395253656,"medium":51.16906031660392,"none":36.1648573852693},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"failed"},"none":{"GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":64.27448595252748,"score":64.27448595252748},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":47.61001698918331,"score":31.740011326122204},"GB2-03":{"attempts":3,"playable":41.641560146239435,"score":41.641560146239435},"GB2-04":{"attempts":3,"playable":38.46977507438505,"score":38.46977507438505},"GB2-05":{"attempts":3,"playable":66.19278623827942,"score":66.19278623827942},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":52.81691977592843,"score":35.21127985061896},"GB2-07":{"attempts":3,"playable":60.471089393701554,"score":60.471089393701554},"GB2-08":{"attempts":3,"playable":54.10638027713092,"score":54.10638027713092}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":79.48904928359957,"score":79.48904928359957},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":48.97008184929656,"score":48.97008184929656},"GB2-04":{"attempts":1,"playable":36.381928222487495,"score":36.381928222487495},"GB2-05":{"attempts":1,"playable":75.28384051945052,"score":75.28384051945052},"GB2-06":{"attempts":1,"playable":77.6559516738825,"score":77.6559516738825},"GB2-07":{"attempts":1,"playable":85.1053177322873,"score":85.1053177322873},"GB2-08":{"attempts":1,"playable":74.76459388102535,"score":74.76459388102535}},"medium":{"GB2-01":{"attempts":1,"playable":63.440272953650364,"score":63.440272953650364},"GB2-02":{"attempts":1,"playable":54.25208956292775,"score":54.25208956292775},"GB2-03":{"attempts":1,"playable":37.62447951039742,"score":37.62447951039742},"GB2-04":{"attempts":1,"playable":38.846322251788514,"score":38.846322251788514},"GB2-05":{"attempts":1,"playable":74.02077757611593,"score":74.02077757611593},"GB2-06":{"attempts":1,"playable":27.977887877974368,"score":27.977887877974368},"GB2-07":{"attempts":1,"playable":59.25721423359372,"score":59.25721423359372},"GB2-08":{"attempts":1,"playable":53.93343856638326,"score":53.93343856638326}},"none":{"GB2-01":{"attempts":1,"playable":49.894135620332534,"score":49.894135620332534},"GB2-02":{"attempts":1,"playable":40.96794441543886,"score":40.96794441543886},"GB2-03":{"attempts":1,"playable":38.33011907902431,"score":38.33011907902431},"GB2-04":{"attempts":1,"playable":40.18107474887915,"score":40.18107474887915},"GB2-05":{"attempts":1,"playable":49.27374061927179,"score":49.27374061927179},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":37.05073621522362,"score":37.05073621522362},"GB2-08":{"attempts":1,"playable":33.621108383984165,"score":33.621108383984165}}},"id":"gpt-5.5","is_recent_addition":false,"last_measured_at":"2026-11-03T08:03:09Z","match_totals_all":{"draws":3024,"losses":3972,"wins":4562},"match_totals_tracks":{"highest":{"draws":628,"losses":875,"wins":2189},"medium":{"draws":1122,"losses":1529,"wins":1541},"none":{"draws":1274,"losses":1568,"wins":832}},"model_slug":"gpt-5-5","official_rank_by_reasoning":{"highest":34,"medium":34,"none":52},"overall":{"max":85.1053177322873,"mean":49.013421032375625,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":37,"overall_ranking_status":"ranked","per_game":{"GB2-01":79.48904928359957,"GB2-03":48.97008184929656,"GB2-04":36.381928222487495,"GB2-05":75.28384051945052,"GB2-06":77.6559516738825,"GB2-07":85.1053177322873,"GB2-08":74.76459388102535},"per_game_all":{"GB2-01":64.27448595252748,"GB2-03":41.641560146239435,"GB2-04":38.46977507438505,"GB2-05":66.19278623827942,"GB2-07":60.471089393701554,"GB2-08":54.10638027713092},"per_game_match_totals_all":{"GB2-01":{"draws":727,"losses":207,"wins":652},"GB2-02":{"draws":703,"losses":178,"wins":107},"GB2-03":{"draws":455,"losses":713,"wins":372},"GB2-04":{"draws":873,"losses":522,"wins":129},"GB2-05":{"draws":0,"losses":554,"wins":1076},"GB2-06":{"draws":24,"losses":488,"wins":522},"GB2-07":{"draws":0,"losses":661,"wins":959},"GB2-08":{"draws":242,"losses":649,"wins":745}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":123,"losses":47,"wins":356},"GB2-03":{"draws":152,"losses":201,"wins":161},"GB2-04":{"draws":284,"losses":188,"wins":36},"GB2-05":{"draws":0,"losses":136,"wins":406},"GB2-06":{"draws":20,"losses":107,"wins":389},"GB2-07":{"draws":0,"losses":79,"wins":461},"GB2-08":{"draws":49,"losses":117,"wins":380}},"medium":{"GB2-01":{"draws":284,"losses":53,"wins":193},"GB2-02":{"draws":312,"losses":76,"wins":106},"GB2-03":{"draws":166,"losses":250,"wins":96},"GB2-04":{"draws":283,"losses":176,"wins":49},"GB2-05":{"draws":0,"losses":142,"wins":402},"GB2-06":{"draws":4,"losses":381,"wins":133},"GB2-07":{"draws":0,"losses":228,"wins":312},"GB2-08":{"draws":73,"losses":223,"wins":250}},"none":{"GB2-01":{"draws":320,"losses":107,"wins":103},"GB2-02":{"draws":391,"losses":102,"wins":1},"GB2-03":{"draws":137,"losses":262,"wins":115},"GB2-04":{"draws":306,"losses":158,"wins":44},"GB2-05":{"draws":0,"losses":276,"wins":268},"GB2-07":{"draws":0,"losses":354,"wins":186},"GB2-08":{"draws":120,"losses":309,"wins":115}}},"per_game_raw_elo_all":{"GB2-01":1640.6994231409662,"GB2-03":1366.5274466919698,"GB2-04":1386.4430064818,"GB2-05":1705.164023997824,"GB2-07":1630.6205058261974,"GB2-08":1508.430308317758},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1814.99892792584,"GB2-03":1431.635102335123,"GB2-04":1369.5006098300305,"GB2-05":1850.2336141138937,"GB2-06":1948.572305349809,"GB2-07":2048.4687175906915,"GB2-08":1853.3872241556417},"medium":{"GB2-01":1620.8734628983557,"GB2-02":1510.3278209844048,"GB2-03":1330.8080868717323,"GB2-04":1389.5544997485517,"GB2-05":1822.8672720193897,"GB2-06":1108.6134522501695,"GB2-07":1568.1769684877795,"GB2-08":1469.2658321633442},"none":{"GB2-01":1486.225878598703,"GB2-02":1406.1036299164962,"GB2-03":1337.1391508690535,"GB2-04":1400.2739098668185,"GB2-05":1442.3911858601882,"GB2-07":1275.2158314001213,"GB2-08":1202.6378686342882}},"per_game_tracks":{"highest":{"GB2-01":79.48904928359957,"GB2-03":48.97008184929656,"GB2-04":36.381928222487495,"GB2-05":75.28384051945052,"GB2-06":77.6559516738825,"GB2-07":85.1053177322873,"GB2-08":74.76459388102535},"medium":{"GB2-01":63.440272953650364,"GB2-02":54.25208956292775,"GB2-03":37.62447951039742,"GB2-04":38.846322251788514,"GB2-05":74.02077757611593,"GB2-06":27.977887877974368,"GB2-07":59.25721423359372,"GB2-08":53.93343856638326},"none":{"GB2-01":49.894135620332534,"GB2-02":40.96794441543886,"GB2-03":38.33011907902431,"GB2-04":40.18107474887915,"GB2-05":49.27374061927179,"GB2-07":37.05073621522362,"GB2-08":33.621108383984165}},"program_outcomes":{"all":{"counted_attempts":24,"failed":2,"infra_excluded":0,"success_rate":0.9166666666666666,"too_slow":0,"worked_after_repair":1,"worked_first_time":21,"working":22},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-31T17:04:19Z","reasoning":{"highest":59.706345395253656,"medium":51.16906031660392,"none":36.1648573852693},"reasoning_agg":{"highest":{"max":85.1053177322873,"mean":59.706345395253656,"min":0.0},"medium":{"max":74.02077757611593,"mean":51.16906031660392,"min":27.977887877974368},"none":{"max":49.894135620332534,"mean":36.1648573852693,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":23.541488009984356},"working_program_strength":{"all":53.57871640287672,"highest":68.23582330886133,"medium":51.16906031660392,"none":41.331265583164914}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max:5f41df3bb03edf57","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":0.9576840000000001}},"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":0.9576840000000001},"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":4.659586000000001}},"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":48.988144056253525,"highest":50.22679135913047,"medium":49.073967442527696,"none":47.6636733671024},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":33.04177500047211,"score":33.04177500047211},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":44.161055121923276,"score":35.66802734926233},"GB2-03":{"attempts":3,"playable":48.945505918194975,"score":48.945505918194975},"GB2-04":{"attempts":3,"playable":47.91913170411265,"score":47.91913170411265},"GB2-05":{"attempts":3,"playable":66.25692256486228,"score":66.25692256486228},"GB2-06":{"attempts":3,"playable":39.14427709196866,"score":39.14427709196866},"GB2-07":{"attempts":3,"playable":61.338244448053906,"score":61.338244448053906},"GB2-08":{"attempts":3,"playable":59.59126837310125,"score":59.59126837310125}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":31.805477160613293,"score":31.805477160613293},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":50.95816663596568,"score":25.47908331798284},"GB2-03":{"attempts":1,"playable":55.32397015059184,"score":55.32397015059184},"GB2-04":{"attempts":1,"playable":65.6227696617432,"score":65.6227696617432},"GB2-05":{"attempts":1,"playable":45.34697428395203,"score":45.34697428395203},"GB2-06":{"attempts":1,"playable":49.226890426580596,"score":49.226890426580596},"GB2-07":{"attempts":1,"playable":76.08076136127464,"score":76.08076136127464},"GB2-08":{"attempts":1,"playable":52.92840451030529,"score":52.92840451030529}},"medium":{"GB2-01":{"attempts":1,"playable":41.31456060972191,"score":41.31456060972191},"GB2-02":{"attempts":1,"playable":42.28577071402832,"score":42.28577071402832},"GB2-03":{"attempts":1,"playable":54.483539623883324,"score":54.483539623883324},"GB2-04":{"attempts":1,"playable":37.18265505128913,"score":37.18265505128913},"GB2-05":{"attempts":1,"playable":64.76313563432666,"score":64.76313563432666},"GB2-06":{"attempts":1,"playable":47.239736666978764,"score":47.239736666978764},"GB2-07":{"attempts":1,"playable":38.13639447998401,"score":38.13639447998401},"GB2-08":{"attempts":1,"playable":67.1859467600094,"score":67.1859467600094}},"none":{"GB2-01":{"attempts":1,"playable":26.00528723108111,"score":26.00528723108111},"GB2-02":{"attempts":1,"playable":39.23922801577583,"score":39.23922801577583},"GB2-03":{"attempts":1,"playable":37.029007980109746,"score":37.029007980109746},"GB2-04":{"attempts":1,"playable":40.9519703993056,"score":40.9519703993056},"GB2-05":{"attempts":1,"playable":88.66065777630814,"score":88.66065777630814},"GB2-06":{"attempts":1,"playable":20.96620418234662,"score":20.96620418234662},"GB2-07":{"attempts":1,"playable":69.79757750290307,"score":69.79757750290307},"GB2-08":{"attempts":1,"playable":58.65945384898906,"score":58.65945384898906}}},"id":"qwen/qwen3.8-max","is_recent_addition":false,"last_measured_at":"2026-11-03T07:15:21Z","match_totals_all":{"draws":2886,"losses":4956,"wins":4712},"match_totals_tracks":{"highest":{"draws":819,"losses":1588,"wins":1777},"medium":{"draws":1027,"losses":1669,"wins":1492},"none":{"draws":1040,"losses":1699,"wins":1443}},"model_slug":"qwen-qwen3-8-max","official_rank_by_reasoning":{"highest":45,"medium":39,"none":27},"overall":{"max":88.66065777630814,"mean":48.988144056253525,"min":20.96620418234662},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":38,"overall_ranking_status":"ranked","per_game":{"GB2-01":31.805477160613293,"GB2-02":50.95816663596568,"GB2-03":55.32397015059184,"GB2-04":65.6227696617432,"GB2-05":45.34697428395203,"GB2-06":49.226890426580596,"GB2-07":76.08076136127464,"GB2-08":52.92840451030529},"per_game_all":{"GB2-01":33.04177500047211,"GB2-02":44.161055121923276,"GB2-03":48.945505918194975,"GB2-04":47.91913170411265,"GB2-05":66.25692256486228,"GB2-06":39.14427709196866,"GB2-07":61.338244448053906,"GB2-08":59.59126837310125},"per_game_match_totals_all":{"GB2-01":{"draws":391,"losses":868,"wins":321},"GB2-02":{"draws":1085,"losses":303,"wins":92},"GB2-03":{"draws":299,"losses":677,"wins":562},"GB2-04":{"draws":844,"losses":395,"wins":291},"GB2-05":{"draws":0,"losses":548,"wins":1078},"GB2-06":{"draws":68,"losses":940,"wins":544},"GB2-07":{"draws":0,"losses":645,"wins":975},"GB2-08":{"draws":199,"losses":580,"wins":849}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":98,"losses":310,"wins":116},"GB2-02":{"draws":350,"losses":73,"wins":69},"GB2-03":{"draws":37,"losses":226,"wins":253},"GB2-04":{"draws":200,"losses":82,"wins":228},"GB2-05":{"draws":0,"losses":295,"wins":245},"GB2-06":{"draws":33,"losses":257,"wins":228},"GB2-07":{"draws":0,"losses":131,"wins":409},"GB2-08":{"draws":101,"losses":214,"wins":229}},"medium":{"GB2-01":{"draws":175,"losses":224,"wins":129},"GB2-02":{"draws":380,"losses":100,"wins":12},"GB2-03":{"draws":97,"losses":198,"wins":215},"GB2-04":{"draws":328,"losses":164,"wins":20},"GB2-05":{"draws":0,"losses":192,"wins":352},"GB2-06":{"draws":19,"losses":274,"wins":225},"GB2-07":{"draws":0,"losses":347,"wins":193},"GB2-08":{"draws":28,"losses":170,"wins":346}},"none":{"GB2-01":{"draws":118,"losses":334,"wins":76},"GB2-02":{"draws":355,"losses":130,"wins":11},"GB2-03":{"draws":165,"losses":253,"wins":94},"GB2-04":{"draws":316,"losses":149,"wins":43},"GB2-05":{"draws":0,"losses":61,"wins":481},"GB2-06":{"draws":16,"losses":409,"wins":91},"GB2-07":{"draws":0,"losses":167,"wins":373},"GB2-08":{"draws":70,"losses":196,"wins":274}}},"per_game_raw_elo_all":{"GB2-01":1317.1623928482807,"GB2-02":1431.0419188774028,"GB2-03":1432.3908227022605,"GB2-04":1463.7344289484274,"GB2-05":1765.1479116801602,"GB2-06":1282.9723300043258,"GB2-07":1615.6681923206106,"GB2-08":1565.926795063869},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1306.5545056618466,"GB2-02":1484.2573474994922,"GB2-03":1489.7994488308339,"GB2-04":1608.7147375348734,"GB2-05":1391.8573671195409,"GB2-06":1443.4924909933663,"GB2-07":1833.4241957128602,"GB2-08":1454.138780644973},"medium":{"GB2-01":1403.1814020910601,"GB2-02":1416.4826869610536,"GB2-03":1481.9270065738792,"GB2-04":1376.0592945581125,"GB2-05":1656.1726468576944,"GB2-06":1411.7921901256748,"GB2-07":1289.5050955705015,"GB2-08":1699.051042396753},"none":{"GB2-01":1241.7512707919357,"GB2-02":1392.3857221716626,"GB2-03":1325.4460127020684,"GB2-04":1406.4292547522962,"GB2-05":2247.4137210632452,"GB2-06":993.6323088939359,"GB2-07":1724.0752856784704,"GB2-08":1544.5905621498814}},"per_game_tracks":{"highest":{"GB2-01":31.805477160613293,"GB2-02":50.95816663596568,"GB2-03":55.32397015059184,"GB2-04":65.6227696617432,"GB2-05":45.34697428395203,"GB2-06":49.226890426580596,"GB2-07":76.08076136127464,"GB2-08":52.92840451030529},"medium":{"GB2-01":41.31456060972191,"GB2-02":42.28577071402832,"GB2-03":54.483539623883324,"GB2-04":37.18265505128913,"GB2-05":64.76313563432666,"GB2-06":47.239736666978764,"GB2-07":38.13639447998401,"GB2-08":67.1859467600094},"none":{"GB2-01":26.00528723108111,"GB2-02":39.23922801577583,"GB2-03":37.029007980109746,"GB2-04":40.9519703993056,"GB2-05":88.66065777630814,"GB2-06":20.96620418234662,"GB2-07":69.79757750290307,"GB2-08":58.65945384898906}},"program_outcomes":{"all":{"counted_attempts":25,"failed":1,"infra_excluded":3,"success_rate":0.96,"too_slow":1,"worked_after_repair":0,"worked_first_time":24,"working":24},"highest":{"counted_attempts":9,"failed":1,"infra_excluded":3,"success_rate":0.8888888888888888,"too_slow":1,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":-4,"rank_movement_baseline_at":"2026-10-31T17:02:38Z","reasoning":{"highest":50.22679135913047,"medium":49.073967442527696,"none":47.6636733671024},"reasoning_agg":{"highest":{"max":76.08076136127464,"mean":50.22679135913047,"min":25.47908331798284},"medium":{"max":67.1859467600094,"mean":49.073967442527696,"min":37.18265505128913},"none":{"max":88.66065777630814,"mean":47.6636733671024,"min":20.96620418234662}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":2.5631179920280758},"working_program_strength":{"all":50.04977252783615,"highest":53.41167677387833,"medium":49.073967442527696,"none":47.6636733671024}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3:5efa63052d7fe040","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":6.6471018},"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":47.20378362830461,"highest":43.840717020745814,"medium":48.01414707553999,"none":49.75648678862802},"first_seen_at":null,"game_gaps":{"highest":{"GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":41.45794606603571,"score":41.45794606603571},"GB2-02":{"attempts":3,"playable":41.42802233183523,"score":41.42802233183523},"GB2-03":{"attempts":3,"playable":62.688296893582596,"score":62.688296893582596},"GB2-04":{"attempts":3,"playable":47.500147693699695,"score":47.500147693699695},"GB2-05":{"attempts":3,"playable":53.039363807830796,"score":53.039363807830796},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":49.06928323788587,"score":32.71285549192391},"GB2-07":{"attempts":3,"playable":48.19058731827943,"score":48.19058731827943},"GB2-08":{"attempts":3,"playable":50.61304942324947,"score":50.61304942324947}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":6.160030641510229,"score":6.160030641510229},"GB2-02":{"attempts":1,"playable":41.86394448635133,"score":41.86394448635133},"GB2-03":{"attempts":1,"playable":75.95870366199722,"score":75.95870366199722},"GB2-04":{"attempts":1,"playable":51.83560573639402,"score":51.83560573639402},"GB2-05":{"attempts":1,"playable":58.98886916496993,"score":58.98886916496993},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":92.33424370500852,"score":92.33424370500852},"GB2-08":{"attempts":1,"playable":23.584338769735293,"score":23.584338769735293}},"medium":{"GB2-01":{"attempts":1,"playable":68.29777235893758,"score":68.29777235893758},"GB2-02":{"attempts":1,"playable":41.159021752334986,"score":41.159021752334986},"GB2-03":{"attempts":1,"playable":64.71085138500914,"score":64.71085138500914},"GB2-04":{"attempts":1,"playable":46.345559183332654,"score":46.345559183332654},"GB2-05":{"attempts":1,"playable":48.23902378712855,"score":48.23902378712855},"GB2-06":{"attempts":1,"playable":53.3682247678663,"score":53.3682247678663},"GB2-07":{"attempts":1,"playable":24.26323665264364,"score":24.26323665264364},"GB2-08":{"attempts":1,"playable":37.72948671706705,"score":37.72948671706705}},"none":{"GB2-01":{"attempts":1,"playable":49.91603519765931,"score":49.91603519765931},"GB2-02":{"attempts":1,"playable":41.26110075681939,"score":41.26110075681939},"GB2-03":{"attempts":1,"playable":47.39533563374144,"score":47.39533563374144},"GB2-04":{"attempts":1,"playable":44.31927816137241,"score":44.31927816137241},"GB2-05":{"attempts":1,"playable":51.8901984713939,"score":51.8901984713939},"GB2-06":{"attempts":1,"playable":44.77034170790543,"score":44.77034170790543},"GB2-07":{"attempts":1,"playable":27.974281597186135,"score":27.974281597186135},"GB2-08":{"attempts":1,"playable":90.52532278294608,"score":90.52532278294608}}},"id":"moonshotai/kimi-k3","is_recent_addition":false,"last_measured_at":"2026-11-03T07:14:30Z","match_totals_all":{"draws":2807,"losses":4832,"wins":4391},"match_totals_tracks":{"highest":{"draws":808,"losses":1445,"wins":1403},"medium":{"draws":1012,"losses":1735,"wins":1443},"none":{"draws":987,"losses":1652,"wins":1545}},"model_slug":"moonshotai-kimi-k3","official_rank_by_reasoning":{"highest":50,"medium":42,"none":21},"overall":{"max":92.33424370500852,"mean":47.20378362830461,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":39,"overall_ranking_status":"ranked","per_game":{"GB2-01":6.160030641510229,"GB2-02":41.86394448635133,"GB2-03":75.95870366199722,"GB2-04":51.83560573639402,"GB2-05":58.98886916496993,"GB2-07":92.33424370500852,"GB2-08":23.584338769735293},"per_game_all":{"GB2-01":41.45794606603571,"GB2-02":41.42802233183523,"GB2-03":62.688296893582596,"GB2-04":47.500147693699695,"GB2-05":53.039363807830796,"GB2-07":48.19058731827943,"GB2-08":50.61304942324947},"per_game_match_totals_all":{"GB2-01":{"draws":367,"losses":745,"wins":468},"GB2-02":{"draws":1080,"losses":345,"wins":53},"GB2-03":{"draws":208,"losses":506,"wins":824},"GB2-04":{"draws":819,"losses":415,"wins":296},"GB2-05":{"draws":0,"losses":763,"wins":865},"GB2-06":{"draws":40,"losses":525,"wins":465},"GB2-07":{"draws":0,"losses":865,"wins":757},"GB2-08":{"draws":293,"losses":668,"wins":663}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":490,"wins":26},"GB2-02":{"draws":339,"losses":122,"wins":29},"GB2-03":{"draws":35,"losses":115,"wins":362},"GB2-04":{"draws":250,"losses":127,"wins":131},"GB2-05":{"draws":0,"losses":222,"wins":320},"GB2-07":{"draws":0,"losses":38,"wins":502},"GB2-08":{"draws":176,"losses":331,"wins":33}},"medium":{"GB2-01":{"draws":93,"losses":122,"wins":313},"GB2-02":{"draws":360,"losses":117,"wins":17},"GB2-03":{"draws":78,"losses":155,"wins":281},"GB2-04":{"draws":343,"losses":111,"wins":60},"GB2-05":{"draws":0,"losses":281,"wins":263},"GB2-06":{"draws":21,"losses":239,"wins":254},"GB2-07":{"draws":0,"losses":424,"wins":118},"GB2-08":{"draws":117,"losses":286,"wins":137}},"none":{"GB2-01":{"draws":266,"losses":133,"wins":129},"GB2-02":{"draws":381,"losses":106,"wins":7},"GB2-03":{"draws":95,"losses":236,"wins":181},"GB2-04":{"draws":226,"losses":177,"wins":105},"GB2-05":{"draws":0,"losses":260,"wins":282},"GB2-06":{"draws":19,"losses":286,"wins":211},"GB2-07":{"draws":0,"losses":403,"wins":137},"GB2-08":{"draws":0,"losses":51,"wins":493}}},"per_game_raw_elo_all":{"GB2-01":1349.4897292154426,"GB2-02":1409.7321488515965,"GB2-03":1575.690558963199,"GB2-04":1458.205139803049,"GB2-05":1492.181830581548,"GB2-07":1529.0423119876534,"GB2-08":1523.9253859974542},"per_game_raw_elo_tracks":{"highest":{"GB2-01":888.6252751335653,"GB2-02":1413.1665996603163,"GB2-03":1725.4564628408034,"GB2-04":1492.4513038535272,"GB2-05":1571.2558534389784,"GB2-07":2340.3907994377205,"GB2-08":1078.7874446574792},"medium":{"GB2-01":1673.406812016622,"GB2-02":1407.6122299018862,"GB2-03":1584.0413353514812,"GB2-04":1449.0620221572776,"GB2-05":1429.0782242087587,"GB2-06":1510.655074318799,"GB2-07":1095.7964445951652,"GB2-08":1252.374321952068},"none":{"GB2-01":1486.4371004961408,"GB2-02":1408.4176169925875,"GB2-03":1417.5738786973125,"GB2-04":1433.1020933983414,"GB2-05":1476.2114140969074,"GB2-06":1372.730397847882,"GB2-07":1150.9396919300752,"GB2-08":2240.614391382815}},"per_game_tracks":{"highest":{"GB2-01":6.160030641510229,"GB2-02":41.86394448635133,"GB2-03":75.95870366199722,"GB2-04":51.83560573639402,"GB2-05":58.98886916496993,"GB2-07":92.33424370500852,"GB2-08":23.584338769735293},"medium":{"GB2-01":68.29777235893758,"GB2-02":41.159021752334986,"GB2-03":64.71085138500914,"GB2-04":46.345559183332654,"GB2-05":48.23902378712855,"GB2-06":53.3682247678663,"GB2-07":24.26323665264364,"GB2-08":37.72948671706705},"none":{"GB2-01":49.91603519765931,"GB2-02":41.26110075681939,"GB2-03":47.39533563374144,"GB2-04":44.31927816137241,"GB2-05":51.8901984713939,"GB2-06":44.77034170790543,"GB2-07":27.974281597186135,"GB2-08":90.52532278294608}},"program_outcomes":{"all":{"counted_attempts":24,"failed":1,"infra_excluded":0,"success_rate":0.9583333333333334,"too_slow":0,"worked_after_repair":2,"worked_first_time":21,"working":23},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":-1,"rank_movement_baseline_at":"2026-10-31T17:13:07Z","reasoning":{"highest":43.84071702074581,"medium":48.01414707553999,"none":49.75648678862802},"reasoning_agg":{"highest":{"max":92.33424370500852,"mean":43.84071702074581,"min":0.0},"medium":{"max":68.29777235893758,"mean":48.01414707553999,"min":24.26323665264364},"none":{"max":90.52532278294608,"mean":49.75648678862802,"min":27.974281597186135}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":5.91576976788221},"working_program_strength":{"all":49.2914368197687,"highest":50.103676595138076,"medium":48.01414707553999,"none":49.75648678862802}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-luna:f8c582a5decbb683","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":0.030688899999999998},"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":0.030688899999999998},"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":0.025451050000000003},"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":0.15005985},"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":47.06454773278198,"highest":55.796680772453165,"medium":41.884122735602105,"none":43.51283969029067},"economics_best_value":{"per_model":{"all":true,"highest":true,"none":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":37.72122082530183,"score":37.72122082530183},"GB2-02":{"attempts":3,"playable":49.92137195014922,"score":49.92137195014922},"GB2-03":{"attempts":3,"playable":47.42969734454656,"score":47.42969734454656},"GB2-04":{"attempts":3,"playable":52.21440423188622,"score":52.21440423188622},"GB2-05":{"attempts":3,"playable":43.901959397647055,"score":43.901959397647055},"GB2-06":{"attempts":3,"playable":61.861040936397785,"score":61.861040936397785},"GB2-07":{"attempts":3,"playable":41.17266198334466,"score":41.17266198334466},"GB2-08":{"attempts":3,"playable":42.294025192982474,"score":42.294025192982474}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":28.46719953593258,"score":28.46719953593258},"GB2-02":{"attempts":1,"playable":62.351227970895685,"score":62.351227970895685},"GB2-03":{"attempts":1,"playable":48.60456593631086,"score":48.60456593631086},"GB2-04":{"attempts":1,"playable":63.32455915221155,"score":63.32455915221155},"GB2-05":{"attempts":1,"playable":50.5857071297115,"score":50.5857071297115},"GB2-06":{"attempts":1,"playable":83.00356232619218,"score":83.00356232619218},"GB2-07":{"attempts":1,"playable":38.50617218877537,"score":38.50617218877537},"GB2-08":{"attempts":1,"playable":71.53045193959554,"score":71.53045193959554}},"medium":{"GB2-01":{"attempts":1,"playable":37.966687525556054,"score":37.966687525556054},"GB2-02":{"attempts":1,"playable":44.114470000617644,"score":44.114470000617644},"GB2-03":{"attempts":1,"playable":50.0402515567602,"score":50.0402515567602},"GB2-04":{"attempts":1,"playable":48.99261193579331,"score":48.99261193579331},"GB2-05":{"attempts":1,"playable":47.65375901252492,"score":47.65375901252492},"GB2-06":{"attempts":1,"playable":33.313207789802554,"score":33.313207789802554},"GB2-07":{"attempts":1,"playable":52.06355619706736,"score":52.06355619706736},"GB2-08":{"attempts":1,"playable":20.92843786669476,"score":20.92843786669476}},"none":{"GB2-01":{"attempts":1,"playable":46.72977541441684,"score":46.72977541441684},"GB2-02":{"attempts":1,"playable":43.29841787893435,"score":43.29841787893435},"GB2-03":{"attempts":1,"playable":43.64427454056862,"score":43.64427454056862},"GB2-04":{"attempts":1,"playable":44.326041607653785,"score":44.326041607653785},"GB2-05":{"attempts":1,"playable":33.46641205070474,"score":33.46641205070474},"GB2-06":{"attempts":1,"playable":69.26635269319864,"score":69.26635269319864},"GB2-07":{"attempts":1,"playable":32.948257564191245,"score":32.948257564191245},"GB2-08":{"attempts":1,"playable":34.42318577265713,"score":34.42318577265713}}},"id":"gpt-6-luna","is_recent_addition":false,"last_measured_at":"2026-11-03T07:02:45Z","match_totals_all":{"draws":3018,"losses":5321,"wins":4231},"match_totals_tracks":{"highest":{"draws":574,"losses":1615,"wins":1995},"medium":{"draws":1119,"losses":1941,"wins":1140},"none":{"draws":1325,"losses":1765,"wins":1096}},"model_slug":"gpt-6-luna","official_rank_by_reasoning":{"highest":39,"medium":54,"none":34},"overall":{"max":83.00356232619218,"mean":47.06454773278198,"min":20.92843786669476},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":40,"overall_ranking_status":"ranked","per_game":{"GB2-01":28.46719953593258,"GB2-02":62.351227970895685,"GB2-03":48.60456593631086,"GB2-04":63.32455915221155,"GB2-05":50.5857071297115,"GB2-06":83.00356232619218,"GB2-07":38.50617218877537,"GB2-08":71.53045193959554},"per_game_all":{"GB2-01":37.72122082530183,"GB2-02":49.92137195014922,"GB2-03":47.42969734454656,"GB2-04":52.21440423188622,"GB2-05":43.901959397647055,"GB2-06":61.861040936397785,"GB2-07":41.17266198334466,"GB2-08":42.294025192982474},"per_game_match_totals_all":{"GB2-01":{"draws":481,"losses":747,"wins":350},"GB2-02":{"draws":1071,"losses":227,"wins":186},"GB2-03":{"draws":220,"losses":744,"wins":580},"GB2-04":{"draws":848,"losses":330,"wins":356},"GB2-05":{"draws":0,"losses":912,"wins":714},"GB2-06":{"draws":67,"losses":572,"wins":909},"GB2-07":{"draws":0,"losses":993,"wins":631},"GB2-08":{"draws":331,"losses":796,"wins":505}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":3,"losses":375,"wins":146},"GB2-02":{"draws":281,"losses":51,"wins":160},"GB2-03":{"draws":27,"losses":266,"wins":223},"GB2-04":{"draws":232,"losses":78,"wins":200},"GB2-05":{"draws":0,"losses":267,"wins":275},"GB2-06":{"draws":26,"losses":75,"wins":415},"GB2-07":{"draws":0,"losses":346,"wins":194},"GB2-08":{"draws":5,"losses":157,"wins":382}},"medium":{"GB2-01":{"draws":197,"losses":231,"wins":100},"GB2-02":{"draws":399,"losses":84,"wins":13},"GB2-03":{"draws":102,"losses":221,"wins":193},"GB2-04":{"draws":290,"losses":124,"wins":100},"GB2-05":{"draws":0,"losses":284,"wins":258},"GB2-06":{"draws":21,"losses":344,"wins":151},"GB2-07":{"draws":0,"losses":270,"wins":272},"GB2-08":{"draws":110,"losses":383,"wins":53}},"none":{"GB2-01":{"draws":281,"losses":141,"wins":104},"GB2-02":{"draws":391,"losses":92,"wins":13},"GB2-03":{"draws":91,"losses":257,"wins":164},"GB2-04":{"draws":326,"losses":128,"wins":56},"GB2-05":{"draws":0,"losses":361,"wins":181},"GB2-06":{"draws":20,"losses":153,"wins":343},"GB2-07":{"draws":0,"losses":377,"wins":165},"GB2-08":{"draws":216,"losses":256,"wins":70}}},"per_game_raw_elo_all":{"GB2-01":1365.2730673173016,"GB2-02":1477.5106075117037,"GB2-03":1417.9801718699912,"GB2-04":1497.039361781199,"GB2-05":1370.870967382687,"GB2-06":1679.9901388850303,"GB2-07":1328.5944715532949,"GB2-08":1347.228506064548},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1270.0404574613162,"GB2-02":1577.3017243441284,"GB2-03":1428.36294062889,"GB2-04":1588.0446008732818,"GB2-05":1459.3107292352536,"GB2-06":2057.942811714409,"GB2-07":1294.3561922649733,"GB2-08":1785.9206422733923},"medium":{"GB2-01":1370.0513230775123,"GB2-02":1430.8064729301796,"GB2-03":1441.2501421616394,"GB2-04":1469.9180574868642,"GB2-05":1421.5528024167834,"GB2-06":1193.094008761307,"GB2-07":1471.068165906042,"GB2-08":1043.4562587705882},"none":{"GB2-01":1455.7274214130762,"GB2-02":1424.4236252608039,"GB2-03":1384.327432819444,"GB2-04":1433.1554269834514,"GB2-05":1231.7493704960243,"GB2-06":1788.9335961793745,"GB2-07":1220.359056488869,"GB2-08":1212.3086171496634}},"per_game_tracks":{"highest":{"GB2-01":28.46719953593258,"GB2-02":62.351227970895685,"GB2-03":48.60456593631086,"GB2-04":63.32455915221155,"GB2-05":50.5857071297115,"GB2-06":83.00356232619218,"GB2-07":38.50617218877537,"GB2-08":71.53045193959554},"medium":{"GB2-01":37.966687525556054,"GB2-02":44.114470000617644,"GB2-03":50.0402515567602,"GB2-04":48.99261193579331,"GB2-05":47.65375901252492,"GB2-06":33.313207789802554,"GB2-07":52.06355619706736,"GB2-08":20.92843786669476},"none":{"GB2-01":46.72977541441684,"GB2-02":43.29841787893435,"GB2-03":43.64427454056862,"GB2-04":44.326041607653785,"GB2-05":33.46641205070474,"GB2-06":69.26635269319864,"GB2-07":32.948257564191245,"GB2-08":34.42318577265713}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":23,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T16:50:37Z","reasoning":{"highest":55.796680772453165,"medium":41.884122735602105,"none":43.51283969029067},"reasoning_agg":{"highest":{"max":83.00356232619218,"mean":55.796680772453165,"min":28.46719953593258},"medium":{"max":52.06355619706736,"mean":41.884122735602105,"min":20.92843786669476},"none":{"max":69.26635269319864,"mean":43.51283969029067,"min":32.948257564191245}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":13.91255803685106},"working_program_strength":{"all":47.06454773278198,"highest":55.796680772453165,"medium":41.884122735602105,"none":43.51283969029067}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-5:970abfe5e8c98e0e","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":0.97393}},"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":0.97393},"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":4.709265},"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":11.203785},"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":47.053690768367694,"highest":48.36090532248782,"medium":46.70378515321895,"none":46.096381829396314},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":45.64802731335944,"score":45.64802731335944},"GB2-02":{"attempts":5,"playable":43.13209905025233,"score":43.13209905025233},"GB2-03":{"attempts":4,"playable":45.95141684877668,"score":45.95141684877668},"GB2-04":{"attempts":5,"playable":42.54465983670055,"score":42.54465983670055},"GB2-05":{"attempts":5,"playable":43.65586332446659,"score":43.65586332446659},"GB2-06":{"attempts":5,"playable":45.343843160553426,"score":45.343843160553426},"GB2-07":{"attempts":5,"playable":44.321092970799235,"score":44.321092970799235},"GB2-08":{"attempts":5,"playable":65.83252364203332,"score":65.83252364203332}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":48.62982611739405,"score":48.62982611739405},"GB2-02":{"attempts":2,"playable":42.54600338400381,"score":42.54600338400381},"GB2-03":{"attempts":1,"playable":48.82433175343846,"score":48.82433175343846},"GB2-04":{"attempts":2,"playable":40.40660433275826,"score":40.40660433275826},"GB2-05":{"attempts":2,"playable":44.33101024603814,"score":44.33101024603814},"GB2-06":{"attempts":2,"playable":49.201294013739215,"score":49.201294013739215},"GB2-07":{"attempts":2,"playable":53.7511868631087,"score":53.7511868631087},"GB2-08":{"attempts":2,"playable":59.19698586942188,"score":59.19698586942188}},"medium":{"GB2-01":{"attempts":2,"playable":45.585105907856516,"score":45.585105907856516},"GB2-02":{"attempts":2,"playable":43.251986601807346,"score":43.251986601807346},"GB2-03":{"attempts":2,"playable":47.573427261735205,"score":47.573427261735205},"GB2-04":{"attempts":2,"playable":40.045035371655615,"score":40.045035371655615},"GB2-05":{"attempts":2,"playable":42.46236520736754,"score":42.46236520736754},"GB2-06":{"attempts":2,"playable":44.14541287959099,"score":44.14541287959099},"GB2-07":{"attempts":2,"playable":47.863157590202604,"score":47.863157590202604},"GB2-08":{"attempts":2,"playable":62.70379040553583,"score":62.70379040553583}},"none":{"GB2-01":{"attempts":1,"playable":42.72914991482776,"score":42.72914991482776},"GB2-02":{"attempts":1,"playable":43.59830716494583,"score":43.59830716494583},"GB2-03":{"attempts":1,"playable":41.45649153115637,"score":41.45649153115637},"GB2-04":{"attempts":1,"playable":47.18233980568778,"score":47.18233980568778},"GB2-05":{"attempts":1,"playable":44.174214519994074,"score":44.174214519994074},"GB2-06":{"attempts":1,"playable":42.68482258833006,"score":42.68482258833006},"GB2-07":{"attempts":1,"playable":31.348934459086404,"score":31.348934459086404},"GB2-08":{"attempts":1,"playable":75.59679465114228,"score":75.59679465114228}}},"id":"claude-opus-4-5","is_recent_addition":false,"last_measured_at":"2026-11-03T07:14:46Z","match_totals_all":{"draws":5093,"losses":8468,"wins":6853},"match_totals_tracks":{"highest":{"draws":1781,"losses":3251,"wins":2824},"medium":{"draws":2163,"losses":3478,"wins":2723},"none":{"draws":1149,"losses":1739,"wins":1306}},"model_slug":"claude-opus-4-5","official_rank_by_reasoning":{"highest":46,"medium":44,"none":30},"overall":{"max":75.59679465114228,"mean":47.053690768367694,"min":31.348934459086404},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":41,"overall_ranking_status":"ranked","per_game":{"GB2-01":48.62982611739405,"GB2-02":42.54600338400381,"GB2-03":48.82433175343846,"GB2-04":40.40660433275826,"GB2-05":44.33101024603814,"GB2-06":49.201294013739215,"GB2-07":53.7511868631087,"GB2-08":59.19698586942188},"per_game_all":{"GB2-01":45.64802731335944,"GB2-02":43.13209905025233,"GB2-03":45.95141684877668,"GB2-04":42.54465983670055,"GB2-05":43.65586332446659,"GB2-06":45.343843160553426,"GB2-07":44.321092970799235,"GB2-08":65.83252364203332},"per_game_match_totals_all":{"GB2-01":{"draws":862,"losses":995,"wins":779},"GB2-02":{"draws":1914,"losses":482,"wins":76},"GB2-03":{"draws":492,"losses":914,"wins":650},"GB2-04":{"draws":1592,"losses":727,"wins":231},"GB2-05":{"draws":0,"losses":1529,"wins":1185},"GB2-06":{"draws":60,"losses":1413,"wins":1095},"GB2-07":{"draws":0,"losses":1490,"wins":1214},"GB2-08":{"draws":173,"losses":918,"wins":1623}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":238,"losses":426,"wins":390},"GB2-02":{"draws":764,"losses":197,"wins":25},"GB2-03":{"draws":79,"losses":239,"wins":198},"GB2-04":{"draws":595,"losses":325,"wins":102},"GB2-05":{"draws":0,"losses":602,"wins":482},"GB2-06":{"draws":24,"losses":530,"wins":474},"GB2-07":{"draws":0,"losses":519,"wins":563},"GB2-08":{"draws":81,"losses":413,"wins":590}},"medium":{"GB2-01":{"draws":381,"losses":385,"wins":286},"GB2-02":{"draws":770,"losses":189,"wins":31},"GB2-03":{"draws":239,"losses":447,"wins":340},"GB2-04":{"draws":670,"losses":289,"wins":59},"GB2-05":{"draws":0,"losses":622,"wins":462},"GB2-06":{"draws":26,"losses":583,"wins":417},"GB2-07":{"draws":0,"losses":586,"wins":496},"GB2-08":{"draws":77,"losses":377,"wins":632}},"none":{"GB2-01":{"draws":243,"losses":184,"wins":103},"GB2-02":{"draws":380,"losses":96,"wins":20},"GB2-03":{"draws":174,"losses":228,"wins":112},"GB2-04":{"draws":327,"losses":113,"wins":70},"GB2-05":{"draws":0,"losses":305,"wins":241},"GB2-06":{"draws":10,"losses":300,"wins":204},"GB2-07":{"draws":0,"losses":385,"wins":155},"GB2-08":{"draws":15,"losses":128,"wins":401}}},"per_game_raw_elo_all":{"GB2-01":1445.090596672153,"GB2-02":1423.1179259928006,"GB2-03":1404.8512172899975,"GB2-04":1418.926666667333,"GB2-05":1369.7633592622194,"GB2-06":1382.2259988521728,"GB2-07":1369.6668867803883,"GB2-08":1695.0876067157133},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1474.549172792118,"GB2-02":1418.5230255578313,"GB2-03":1430.3296520010542,"GB2-04":1402.0708971493602,"GB2-05":1378.2841175430067,"GB2-06":1443.5863238865263,"GB2-07":1494.4312741343406,"GB2-08":1583.4567025501235},"medium":{"GB2-01":1443.7245204698488,"GB2-02":1424.060032941342,"GB2-03":1419.2559109182164,"GB2-04":1399.0595734781969,"GB2-05":1354.3090656118657,"GB2-06":1363.1538966853054,"GB2-07":1416.1017393081456,"GB2-08":1630.695904332215},"none":{"GB2-01":1416.9980967544918,"GB2-02":1426.7707194792283,"GB2-03":1364.9680889507222,"GB2-04":1455.6495293744417,"GB2-05":1376.6968946317852,"GB2-06":1339.9377759846864,"GB2-07":1198.4676468986784,"GB2-08":1871.1102132648011}},"per_game_tracks":{"highest":{"GB2-01":48.62982611739405,"GB2-02":42.54600338400381,"GB2-03":48.82433175343846,"GB2-04":40.40660433275826,"GB2-05":44.33101024603814,"GB2-06":49.201294013739215,"GB2-07":53.7511868631087,"GB2-08":59.19698586942188},"medium":{"GB2-01":45.585105907856516,"GB2-02":43.251986601807346,"GB2-03":47.573427261735205,"GB2-04":40.045035371655615,"GB2-05":42.46236520736754,"GB2-06":44.14541287959099,"GB2-07":47.863157590202604,"GB2-08":62.70379040553583},"none":{"GB2-01":42.72914991482776,"GB2-02":43.59830716494583,"GB2-03":41.45649153115637,"GB2-04":47.18233980568778,"GB2-05":44.174214519994074,"GB2-06":42.68482258833006,"GB2-07":31.348934459086404,"GB2-08":75.59679465114228}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":24,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-5,"rank_movement_baseline_at":"2026-10-31T16:28:46Z","reasoning":{"highest":48.36090532248782,"medium":46.70378515321895,"none":46.096381829396314},"reasoning_agg":{"highest":{"max":59.19698586942188,"mean":48.36090532248782,"min":40.40660433275826},"medium":{"max":62.70379040553583,"mean":46.70378515321895,"min":40.045035371655615},"none":{"max":75.59679465114228,"mean":46.096381829396314,"min":31.348934459086404}},"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":2.2645234930915024},"working_program_strength":{"all":47.053690768367694,"highest":48.36090532248782,"medium":46.70378515321895,"none":46.096381829396314}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5:9d4d43e629397128","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":0.52499},"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":0.49337000000000003}},"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":0.52499},"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":0.49337},"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":2.80795}},"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":46.423927303114425,"highest":54.4081388847198,"medium":42.663154182586666,"none":42.2004888420368},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":50.71587579357538,"score":50.71587579357538},"GB2-02":{"attempts":3,"playable":42.04529843742859,"score":42.04529843742859},"GB2-03":{"attempts":3,"playable":51.329021153754546,"score":51.329021153754546},"GB2-04":{"attempts":3,"playable":45.932689949733835,"score":45.932689949733835},"GB2-05":{"attempts":3,"playable":37.596123518632076,"score":37.596123518632076},"GB2-06":{"attempts":3,"playable":35.68700895268709,"score":35.68700895268709},"GB2-07":{"attempts":3,"playable":50.07359917990552,"score":50.07359917990552},"GB2-08":{"attempts":3,"playable":58.01180143919834,"score":58.01180143919834}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":61.037830042460016,"score":61.037830042460016},"GB2-02":{"attempts":1,"playable":41.055390688585284,"score":41.055390688585284},"GB2-03":{"attempts":1,"playable":59.056901552442966,"score":59.056901552442966},"GB2-04":{"attempts":1,"playable":51.54000818058299,"score":51.54000818058299},"GB2-05":{"attempts":1,"playable":51.19882673019919,"score":51.19882673019919},"GB2-06":{"attempts":1,"playable":26.1191794557939,"score":26.1191794557939},"GB2-07":{"attempts":1,"playable":66.15915937441567,"score":66.15915937441567},"GB2-08":{"attempts":1,"playable":79.09781505327834,"score":79.09781505327834}},"medium":{"GB2-01":{"attempts":1,"playable":43.24950969908352,"score":43.24950969908352},"GB2-02":{"attempts":1,"playable":43.105740283085154,"score":43.105740283085154},"GB2-03":{"attempts":1,"playable":41.03340628928927,"score":41.03340628928927},"GB2-04":{"attempts":1,"playable":44.12073142887364,"score":44.12073142887364},"GB2-05":{"attempts":1,"playable":39.838364541303015,"score":39.838364541303015},"GB2-06":{"attempts":1,"playable":35.748138102202795,"score":35.748138102202795},"GB2-07":{"attempts":1,"playable":49.74963746384339,"score":49.74963746384339},"GB2-08":{"attempts":1,"playable":44.4597056530126,"score":44.4597056530126}},"none":{"GB2-01":{"attempts":1,"playable":47.86028763918259,"score":47.86028763918259},"GB2-02":{"attempts":1,"playable":41.97476434061533,"score":41.97476434061533},"GB2-03":{"attempts":1,"playable":53.89675561953142,"score":53.89675561953142},"GB2-04":{"attempts":1,"playable":42.13733023974489,"score":42.13733023974489},"GB2-05":{"attempts":1,"playable":21.751179284394034,"score":21.751179284394034},"GB2-06":{"attempts":1,"playable":45.193709300064576,"score":45.193709300064576},"GB2-07":{"attempts":1,"playable":34.31200070145749,"score":34.31200070145749},"GB2-08":{"attempts":1,"playable":50.47788361130407,"score":50.47788361130407}}},"id":"claude-sonnet-5","is_recent_addition":false,"last_measured_at":"2026-11-03T07:14:49Z","match_totals_all":{"draws":2872,"losses":5440,"wins":4228},"match_totals_tracks":{"highest":{"draws":842,"losses":1516,"wins":1820},"medium":{"draws":1046,"losses":1932,"wins":1204},"none":{"draws":984,"losses":1992,"wins":1204}},"model_slug":"claude-sonnet-5","official_rank_by_reasoning":{"highest":40,"medium":51,"none":36},"overall":{"max":79.09781505327834,"mean":46.423927303114425,"min":21.751179284394034},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":42,"overall_ranking_status":"ranked","per_game":{"GB2-01":61.037830042460016,"GB2-02":41.055390688585284,"GB2-03":59.056901552442966,"GB2-04":51.54000818058299,"GB2-05":51.19882673019919,"GB2-06":26.1191794557939,"GB2-07":66.15915937441567,"GB2-08":79.09781505327834},"per_game_all":{"GB2-01":50.71587579357538,"GB2-02":42.04529843742859,"GB2-03":51.329021153754546,"GB2-04":45.932689949733835,"GB2-05":37.596123518632076,"GB2-06":35.68700895268709,"GB2-07":50.07359917990552,"GB2-08":58.01180143919834},"per_game_match_totals_all":{"GB2-01":{"draws":260,"losses":655,"wins":669},"GB2-02":{"draws":1149,"losses":302,"wins":29},"GB2-03":{"draws":340,"losses":621,"wins":577},"GB2-04":{"draws":921,"losses":386,"wins":219},"GB2-05":{"draws":0,"losses":1014,"wins":614},"GB2-06":{"draws":19,"losses":1014,"wins":509},"GB2-07":{"draws":0,"losses":840,"wins":780},"GB2-08":{"draws":183,"losses":608,"wins":831}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":54,"losses":180,"wins":294},"GB2-02":{"draws":380,"losses":105,"wins":5},"GB2-03":{"draws":111,"losses":168,"wins":233},"GB2-04":{"draws":289,"losses":109,"wins":110},"GB2-05":{"draws":0,"losses":265,"wins":279},"GB2-06":{"draws":8,"losses":386,"wins":120},"GB2-07":{"draws":0,"losses":188,"wins":352},"GB2-08":{"draws":0,"losses":115,"wins":427}},"medium":{"GB2-01":{"draws":111,"losses":247,"wins":172},"GB2-02":{"draws":391,"losses":92,"wins":11},"GB2-03":{"draws":122,"losses":256,"wins":136},"GB2-04":{"draws":316,"losses":133,"wins":59},"GB2-05":{"draws":0,"losses":325,"wins":217},"GB2-06":{"draws":3,"losses":339,"wins":172},"GB2-07":{"draws":0,"losses":283,"wins":257},"GB2-08":{"draws":103,"losses":257,"wins":180}},"none":{"GB2-01":{"draws":95,"losses":228,"wins":203},"GB2-02":{"draws":378,"losses":105,"wins":13},"GB2-03":{"draws":107,"losses":197,"wins":208},"GB2-04":{"draws":316,"losses":144,"wins":50},"GB2-05":{"draws":0,"losses":424,"wins":118},"GB2-06":{"draws":8,"losses":289,"wins":217},"GB2-07":{"draws":0,"losses":369,"wins":171},"GB2-08":{"draws":80,"losses":236,"wins":224}}},"per_game_raw_elo_all":{"GB2-01":1494.903752354684,"GB2-02":1414.5823759323139,"GB2-03":1454.462863016987,"GB2-04":1445.8287860829635,"GB2-05":1277.0016331014344,"GB2-06":1229.823526435978,"GB2-07":1448.994213233231,"GB2-08":1567.5560704001389},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1596.0272335919735,"GB2-02":1406.7942074908574,"GB2-03":1525.7019293147273,"GB2-04":1490.0978308420717,"GB2-05":1467.2422740639774,"GB2-06":1078.753592014089,"GB2-07":1667.559728321949,"GB2-08":1947.4722263496383},"medium":{"GB2-01":1422.0602934810481,"GB2-02":1422.9146149176431,"GB2-03":1361.2175192871505,"GB2-04":1431.5361571758358,"GB2-05":1319.8047473249471,"GB2-06":1231.3105451013014,"GB2-07":1440.647309756332,"GB2-08":1336.759466467827},"none":{"GB2-01":1466.6237299910304,"GB2-02":1414.0383053884407,"GB2-03":1476.4691404490827,"GB2-04":1415.8523702309833,"GB2-05":1043.9578779153785,"GB2-06":1379.4064421925436,"GB2-07":1238.775601621412,"GB2-08":1418.4365183829518}},"per_game_tracks":{"highest":{"GB2-01":61.037830042460016,"GB2-02":41.055390688585284,"GB2-03":59.056901552442966,"GB2-04":51.54000818058299,"GB2-05":51.19882673019919,"GB2-06":26.1191794557939,"GB2-07":66.15915937441567,"GB2-08":79.09781505327834},"medium":{"GB2-01":43.24950969908352,"GB2-02":43.105740283085154,"GB2-03":41.03340628928927,"GB2-04":44.12073142887364,"GB2-05":39.838364541303015,"GB2-06":35.748138102202795,"GB2-07":49.74963746384339,"GB2-08":44.4597056530126},"none":{"GB2-01":47.86028763918259,"GB2-02":41.97476434061533,"GB2-03":53.89675561953142,"GB2-04":42.13733023974489,"GB2-05":21.751179284394034,"GB2-06":45.193709300064576,"GB2-07":34.31200070145749,"GB2-08":50.47788361130407}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":24,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T17:04:37Z","reasoning":{"highest":54.4081388847198,"medium":42.663154182586666,"none":42.2004888420368},"reasoning_agg":{"highest":{"max":79.09781505327834,"mean":54.4081388847198,"min":26.1191794557939},"medium":{"max":49.74963746384339,"mean":42.663154182586666,"min":35.748138102202795},"none":{"max":53.89675561953142,"mean":42.2004888420368,"min":21.751179284394034}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":12.207650042683},"working_program_strength":{"all":46.423927303114425,"highest":54.4081388847198,"medium":42.663154182586666,"none":42.2004888420368}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-terra:2dd7e8c0505d81be","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":3.0672337499999998},"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":0.77569875},"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":0.6137424999999999}},"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":0.7756987500000001},"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":4.456675},"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":45.40854382489655,"highest":53.051278249600934,"medium":48.65102461097204,"none":34.52332861411668},"first_seen_at":null,"game_gaps":{"none":{"GB2-05":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":65.52090026664492,"score":65.52090026664492},"GB2-02":{"attempts":3,"playable":48.84419264235701,"score":48.84419264235701},"GB2-03":{"attempts":3,"playable":33.47928527173709,"score":33.47928527173709},"GB2-04":{"attempts":3,"playable":42.493788786142716,"score":42.493788786142716},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":54.09951144522076,"score":36.066340963480506},"GB2-06":{"attempts":3,"playable":50.162786498859816,"score":50.162786498859816},"GB2-07":{"attempts":3,"playable":43.64685765832551,"score":43.64685765832551},"GB2-08":{"attempts":3,"playable":43.05419851162483,"score":43.05419851162483}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":68.63349190956399,"score":68.63349190956399},"GB2-02":{"attempts":1,"playable":58.10409774043583,"score":58.10409774043583},"GB2-03":{"attempts":1,"playable":35.3413305878803,"score":35.3413305878803},"GB2-04":{"attempts":1,"playable":41.34829696679952,"score":41.34829696679952},"GB2-05":{"attempts":1,"playable":52.573974793993436,"score":52.573974793993436},"GB2-06":{"attempts":1,"playable":77.08422561292774,"score":77.08422561292774},"GB2-07":{"attempts":1,"playable":42.91138804804406,"score":42.91138804804406},"GB2-08":{"attempts":1,"playable":48.41342033716262,"score":48.41342033716262}},"medium":{"GB2-01":{"attempts":1,"playable":74.92311893308332,"score":74.92311893308332},"GB2-02":{"attempts":1,"playable":45.02370235959005,"score":45.02370235959005},"GB2-03":{"attempts":1,"playable":33.152978254543314,"score":33.152978254543314},"GB2-04":{"attempts":1,"playable":42.731248970585284,"score":42.731248970585284},"GB2-05":{"attempts":1,"playable":55.62504809644809,"score":55.62504809644809},"GB2-06":{"attempts":1,"playable":39.2459979353906,"score":39.2459979353906},"GB2-07":{"attempts":1,"playable":58.81805394358748,"score":58.81805394358748},"GB2-08":{"attempts":1,"playable":39.688048394548154,"score":39.688048394548154}},"none":{"GB2-01":{"attempts":1,"playable":53.00608995728746,"score":53.00608995728746},"GB2-02":{"attempts":1,"playable":43.404777827045145,"score":43.404777827045145},"GB2-03":{"attempts":1,"playable":31.94354697278765,"score":31.94354697278765},"GB2-04":{"attempts":1,"playable":43.40182042104333,"score":43.40182042104333},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":34.15813594826111,"score":34.15813594826111},"GB2-07":{"attempts":1,"playable":29.211130983344997,"score":29.211130983344997},"GB2-08":{"attempts":1,"playable":41.061126803163724,"score":41.061126803163724}}},"id":"gpt-5.6-terra","is_recent_addition":false,"last_measured_at":"2026-11-03T07:06:54Z","match_totals_all":{"draws":3011,"losses":4978,"wins":4025},"match_totals_tracks":{"highest":{"draws":919,"losses":1560,"wins":1709},"medium":{"draws":977,"losses":1707,"wins":1498},"none":{"draws":1115,"losses":1711,"wins":818}},"model_slug":"gpt-5-6-terra","official_rank_by_reasoning":{"highest":44,"medium":40,"none":54},"overall":{"max":77.08422561292774,"mean":45.40854382489655,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":43,"overall_ranking_status":"ranked","per_game":{"GB2-01":68.63349190956399,"GB2-02":58.10409774043583,"GB2-03":35.3413305878803,"GB2-04":41.34829696679952,"GB2-05":52.573974793993436,"GB2-06":77.08422561292774,"GB2-07":42.91138804804406,"GB2-08":48.41342033716262},"per_game_all":{"GB2-01":65.52090026664492,"GB2-02":48.84419264235701,"GB2-03":33.47928527173709,"GB2-04":42.493788786142716,"GB2-06":50.162786498859816,"GB2-07":43.64685765832551,"GB2-08":43.05419851162483},"per_game_match_totals_all":{"GB2-01":{"draws":249,"losses":422,"wins":907},"GB2-02":{"draws":1068,"losses":246,"wins":174},"GB2-03":{"draws":555,"losses":784,"wins":199},"GB2-04":{"draws":911,"losses":448,"wins":177},"GB2-05":{"draws":0,"losses":497,"wins":587},"GB2-06":{"draws":57,"losses":768,"wins":719},"GB2-07":{"draws":0,"losses":948,"wins":672},"GB2-08":{"draws":171,"losses":865,"wins":590}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":71,"losses":131,"wins":326},"GB2-02":{"draws":278,"losses":75,"wins":143},"GB2-03":{"draws":153,"losses":269,"wins":92},"GB2-04":{"draws":328,"losses":144,"wins":42},"GB2-05":{"draws":0,"losses":257,"wins":285},"GB2-06":{"draws":24,"losses":108,"wins":380},"GB2-07":{"draws":0,"losses":321,"wins":219},"GB2-08":{"draws":65,"losses":255,"wins":222}},"medium":{"GB2-01":{"draws":3,"losses":131,"wins":392},"GB2-02":{"draws":392,"losses":83,"wins":21},"GB2-03":{"draws":233,"losses":240,"wins":41},"GB2-04":{"draws":250,"losses":174,"wins":86},"GB2-05":{"draws":0,"losses":240,"wins":302},"GB2-06":{"draws":31,"losses":308,"wins":175},"GB2-07":{"draws":0,"losses":231,"wins":309},"GB2-08":{"draws":68,"losses":300,"wins":172}},"none":{"GB2-01":{"draws":175,"losses":160,"wins":189},"GB2-02":{"draws":398,"losses":88,"wins":10},"GB2-03":{"draws":169,"losses":275,"wins":66},"GB2-04":{"draws":333,"losses":130,"wins":49},"GB2-06":{"draws":2,"losses":352,"wins":164},"GB2-07":{"draws":0,"losses":396,"wins":144},"GB2-08":{"draws":38,"losses":310,"wins":196}}},"per_game_raw_elo_all":{"GB2-01":1648.6747494480676,"GB2-02":1468.229428348555,"GB2-03":1292.9051960069548,"GB2-04":1418.6679822190183,"GB2-06":1476.5989173476767,"GB2-07":1360.813078383089,"GB2-08":1319.81742113203},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1677.1784985750128,"GB2-02":1541.5263279188448,"GB2-03":1310.1338219234701,"GB2-04":1409.5850522969938,"GB2-05":1485.1136937110384,"GB2-06":1937.3574261917117,"GB2-07":1351.73906375976,"GB2-08":1389.5442557625},"medium":{"GB2-01":1752.516409596868,"GB2-02":1437.9056893581926,"GB2-03":1289.9613563582463,"GB2-04":1420.5580459567414,"GB2-05":1525.3698370643128,"GB2-06":1286.0690850044548,"GB2-07":1562.1001051724807,"GB2-08":1276.4191000891885},"none":{"GB2-01":1516.3293401723215,"GB2-02":1425.2562677686276,"GB2-03":1278.6204097391483,"GB2-04":1425.86084840332,"GB2-06":1206.3702408468635,"GB2-07":1168.6000662170266,"GB2-08":1293.4889075444016}},"per_game_tracks":{"highest":{"GB2-01":68.63349190956399,"GB2-02":58.10409774043583,"GB2-03":35.3413305878803,"GB2-04":41.34829696679952,"GB2-05":52.573974793993436,"GB2-06":77.08422561292774,"GB2-07":42.91138804804406,"GB2-08":48.41342033716262},"medium":{"GB2-01":74.92311893308332,"GB2-02":45.02370235959005,"GB2-03":33.152978254543314,"GB2-04":42.731248970585284,"GB2-05":55.62504809644809,"GB2-06":39.2459979353906,"GB2-07":58.81805394358748,"GB2-08":39.688048394548154},"none":{"GB2-01":53.00608995728746,"GB2-02":43.404777827045145,"GB2-03":31.94354697278765,"GB2-04":43.40182042104333,"GB2-06":34.15813594826111,"GB2-07":29.211130983344997,"GB2-08":41.061126803163724}},"program_outcomes":{"all":{"counted_attempts":24,"failed":1,"infra_excluded":0,"success_rate":0.9583333333333334,"too_slow":0,"worked_after_repair":3,"worked_first_time":20,"working":23},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T16:37:24Z","reasoning":{"highest":53.051278249600934,"medium":48.65102461097204,"none":34.52332861411668},"reasoning_agg":{"highest":{"max":77.08422561292774,"mean":53.051278249600934,"min":35.3413305878803},"medium":{"max":74.92311893308332,"mean":48.65102461097204,"min":33.152978254543314},"none":{"max":53.00608995728746,"mean":34.52332861411668,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":18.527949635484255},"working_program_strength":{"all":47.0525118541402,"highest":53.051278249600934,"medium":48.65102461097204,"none":39.455232701847635}},{"canonical_public_row_identity":"publication-row.v1:overall:gemini-3-1-pro-preview:a324d82792c47394","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":2.592372},"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":0.642066},"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":0.3670399999999999}},"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":0.642066},"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":3.6014779999999997},"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":44.50068987624213,"highest":64.70023680131865,"medium":40.37946489545624,"none":28.4223679319515},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":48.19760486241768,"score":48.19760486241768},"GB2-02":{"attempts":3,"playable":42.421486050545354,"score":42.421486050545354},"GB2-03":{"attempts":3,"playable":51.86749069815801,"score":51.86749069815801},"GB2-04":{"attempts":3,"playable":55.50541915365923,"score":55.50541915365923},"GB2-05":{"attempts":3,"playable":37.830217799661355,"score":37.830217799661355},"GB2-06":{"attempts":3,"playable":19.675088742421305,"score":19.675088742421305},"GB2-07":{"attempts":3,"playable":55.386819368311215,"score":55.386819368311215},"GB2-08":{"attempts":3,"playable":45.1213923347629,"score":45.1213923347629}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":72.42770605628361,"score":72.42770605628361},"GB2-02":{"attempts":1,"playable":42.18341912772167,"score":42.18341912772167},"GB2-03":{"attempts":1,"playable":64.01385306205363,"score":64.01385306205363},"GB2-04":{"attempts":1,"playable":80.54963195310417,"score":80.54963195310417},"GB2-05":{"attempts":1,"playable":82.51178288104289,"score":82.51178288104289},"GB2-06":{"attempts":1,"playable":17.93770075073218,"score":17.93770075073218},"GB2-07":{"attempts":1,"playable":72.93205562331376,"score":72.93205562331376},"GB2-08":{"attempts":1,"playable":85.04574495629737,"score":85.04574495629737}},"medium":{"GB2-01":{"attempts":1,"playable":33.44573855796975,"score":33.44573855796975},"GB2-02":{"attempts":1,"playable":43.20109578613035,"score":43.20109578613035},"GB2-03":{"attempts":1,"playable":64.46175366739992,"score":64.46175366739992},"GB2-04":{"attempts":1,"playable":44.68220056823814,"score":44.68220056823814},"GB2-05":{"attempts":1,"playable":16.142754551102733,"score":16.142754551102733},"GB2-06":{"attempts":1,"playable":27.070863030365842,"score":27.070863030365842},"GB2-07":{"attempts":1,"playable":69.45108134945374,"score":69.45108134945374},"GB2-08":{"attempts":1,"playable":24.580231652989447,"score":24.580231652989447}},"none":{"GB2-01":{"attempts":1,"playable":38.71936997299969,"score":38.71936997299969},"GB2-02":{"attempts":1,"playable":41.879943237784026,"score":41.879943237784026},"GB2-03":{"attempts":1,"playable":27.126865365020493,"score":27.126865365020493},"GB2-04":{"attempts":1,"playable":41.28442493963539,"score":41.28442493963539},"GB2-05":{"attempts":1,"playable":14.836115966838454,"score":14.836115966838454},"GB2-06":{"attempts":1,"playable":14.016702446165896,"score":14.016702446165896},"GB2-07":{"attempts":1,"playable":23.777321132166136,"score":23.777321132166136},"GB2-08":{"attempts":1,"playable":25.73820039500187,"score":25.73820039500187}}},"id":"gemini-3.1-pro-preview","is_recent_addition":false,"last_measured_at":"2026-11-03T07:04:16Z","match_totals_all":{"draws":2662,"losses":5769,"wins":4117},"match_totals_tracks":{"highest":{"draws":551,"losses":1219,"wins":2412},"medium":{"draws":1054,"losses":2024,"wins":1108},"none":{"draws":1057,"losses":2526,"wins":597}},"model_slug":"gemini-3-1-pro-preview","official_rank_by_reasoning":{"highest":25,"medium":56,"none":66},"overall":{"max":85.04574495629737,"mean":44.50068987624213,"min":14.016702446165896},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":44,"overall_ranking_status":"ranked","per_game":{"GB2-01":72.42770605628361,"GB2-02":42.18341912772167,"GB2-03":64.01385306205363,"GB2-04":80.54963195310417,"GB2-05":82.51178288104289,"GB2-06":17.93770075073218,"GB2-07":72.93205562331376,"GB2-08":85.04574495629737},"per_game_all":{"GB2-01":48.19760486241768,"GB2-02":42.421486050545354,"GB2-03":51.86749069815801,"GB2-04":55.50541915365923,"GB2-05":37.830217799661355,"GB2-06":19.675088742421305,"GB2-07":55.386819368311215,"GB2-08":45.1213923347629},"per_game_match_totals_all":{"GB2-01":{"draws":281,"losses":678,"wins":613},"GB2-02":{"draws":1167,"losses":286,"wins":25},"GB2-03":{"draws":289,"losses":632,"wins":617},"GB2-04":{"draws":692,"losses":355,"wins":485},"GB2-05":{"draws":0,"losses":1019,"wins":613},"GB2-06":{"draws":14,"losses":1259,"wins":273},"GB2-07":{"draws":0,"losses":743,"wins":877},"GB2-08":{"draws":219,"losses":797,"wins":614}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":135,"wins":368},"GB2-02":{"draws":385,"losses":98,"wins":9},"GB2-03":{"draws":27,"losses":185,"wins":304},"GB2-04":{"draws":115,"losses":46,"wins":347},"GB2-05":{"draws":0,"losses":95,"wins":447},"GB2-06":{"draws":2,"losses":430,"wins":84},"GB2-07":{"draws":0,"losses":149,"wins":391},"GB2-08":{"draws":1,"losses":81,"wins":462}},"medium":{"GB2-01":{"draws":173,"losses":264,"wins":87},"GB2-02":{"draws":383,"losses":93,"wins":14},"GB2-03":{"draws":104,"losses":143,"wins":265},"GB2-04":{"draws":282,"losses":150,"wins":82},"GB2-05":{"draws":0,"losses":459,"wins":87},"GB2-06":{"draws":10,"losses":381,"wins":125},"GB2-07":{"draws":0,"losses":169,"wins":371},"GB2-08":{"draws":102,"losses":365,"wins":77}},"none":{"GB2-01":{"draws":87,"losses":279,"wins":158},"GB2-02":{"draws":399,"losses":95,"wins":2},"GB2-03":{"draws":158,"losses":304,"wins":48},"GB2-04":{"draws":295,"losses":159,"wins":56},"GB2-05":{"draws":0,"losses":465,"wins":79},"GB2-06":{"draws":2,"losses":448,"wins":64},"GB2-07":{"draws":0,"losses":425,"wins":115},"GB2-08":{"draws":116,"losses":351,"wins":75}}},"per_game_raw_elo_all":{"GB2-01":1474.2911220950798,"GB2-02":1417.5441841136346,"GB2-03":1463.1487197205242,"GB2-04":1538.5832865732575,"GB2-05":1293.751733669378,"GB2-06":967.1585758798004,"GB2-07":1527.699412153975,"GB2-08":1428.3711098259398},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1721.4341762818049,"GB2-02":1415.6785609978813,"GB2-03":1576.5246848991806,"GB2-04":1770.709900553654,"GB2-05":2038.602596651186,"GB2-06":940.8114718907951,"GB2-07":1776.2839105788448,"GB2-08":2087.196374364407},"medium":{"GB2-01":1323.8761088871079,"GB2-02":1423.66152229046,"GB2-03":1581.3429448998588,"GB2-04":1435.96312295063,"GB2-05":935.3192404744534,"GB2-06":1094.0807914119605,"GB2-07":1718.5265104867842,"GB2-08":1091.6145308799664},"none":{"GB2-01":1377.5630811163269,"GB2-02":1413.2924690525626,"GB2-03":1231.5785293625331,"GB2-04":1409.0768362154886,"GB2-05":907.3333638824947,"GB2-06":866.5834643366455,"GB2-07":1088.287815396296,"GB2-08":1106.3024242334461}},"per_game_tracks":{"highest":{"GB2-01":72.42770605628361,"GB2-02":42.18341912772167,"GB2-03":64.01385306205363,"GB2-04":80.54963195310417,"GB2-05":82.51178288104289,"GB2-06":17.93770075073218,"GB2-07":72.93205562331376,"GB2-08":85.04574495629737},"medium":{"GB2-01":33.44573855796975,"GB2-02":43.20109578613035,"GB2-03":64.46175366739992,"GB2-04":44.68220056823814,"GB2-05":16.142754551102733,"GB2-06":27.070863030365842,"GB2-07":69.45108134945374,"GB2-08":24.580231652989447},"none":{"GB2-01":38.71936997299969,"GB2-02":41.879943237784026,"GB2-03":27.126865365020493,"GB2-04":41.28442493963539,"GB2-05":14.836115966838454,"GB2-06":14.016702446165896,"GB2-07":23.777321132166136,"GB2-08":25.73820039500187}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":20,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T17:13:11Z","reasoning":{"highest":64.70023680131865,"medium":40.37946489545624,"none":28.4223679319515},"reasoning_agg":{"highest":{"max":85.04574495629737,"mean":64.70023680131865,"min":17.93770075073218},"medium":{"max":69.45108134945374,"mean":40.37946489545624,"min":16.142754551102733},"none":{"max":41.879943237784026,"mean":28.4223679319515,"min":14.016702446165896}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":36.277868869367154},"working_program_strength":{"all":44.50068987624213,"highest":64.70023680131865,"medium":40.37946489545624,"none":28.4223679319515}},{"canonical_public_row_identity":"publication-row.v1:overall:inception-mercury-3:bc6950a0d4411105","codegen_cost_by_reasoning":{"highest":{"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":0.09119202000000001,"mean":0.051659512500000004,"median":0.03605392,"min":0.02439431,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.41327610000000004},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.11405448,"mean":0.06376662999999999,"median":0.060945095000000005,"min":0.02463971,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.51013304},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0094142,"mean":0.0028034124999999997,"median":0.001882025,"min":0.0015762,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.022427299999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.11405448,"mean":0.06376662999999999,"median":0.060945095000000005,"min":0.02463971,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.51013304},"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":0.0094142,"mean":0.0028034124999999997,"median":0.001882025,"min":0.0015762,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.022427299999999997},"historical-provider-setting-intensive":{"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":0.09119202000000001,"mean":0.051659512500000004,"median":0.03605392,"min":0.02439431,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.4132761}},"codegen_cost_usd":{"admitted_cell_count":20,"cell_count":24,"cost_basis_counts":{"provider_reported":32},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.11405448,"mean":0.03940985166666667,"median":0.03513247,"min":0.0015762,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":32},"recorded_attempt_count":32,"run_count":24,"total":0.94583644},"codegen_latency_ms":{"attempt_count":30,"max_ms":377102,"mean_ms":152852.0909090909,"min_ms":3791,"run_count":22},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":319339,"mean_ms":217205.0,"min_ms":142770,"run_count":7},"medium":{"attempt_count":10,"max_ms":377102,"mean_ms":252606.2857142857,"min_ms":146739,"run_count":7},"none":{"attempt_count":9,"max_ms":30086,"mean_ms":9258.375,"min_ms":3791,"run_count":8}},"codegen_output_tokens":{"attempt_count":32,"output_max":189303,"output_mean":71566.08333333333,"output_min":2342,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":12,"output_max":127108,"output_mean":95776.5,"output_min":67386,"run_count":8},"medium":{"attempt_count":11,"output_max":189303,"output_mean":113475.0,"output_min":68315,"run_count":8},"none":{"attempt_count":9,"output_max":22506,"output_mean":5446.75,"output_min":2342,"run_count":8}},"display_name":"Mercury 3","economics":{"all":43.74811056199854,"highest":47.794519858632874,"medium":46.1942987849589,"none":37.25551304240383},"first_seen_at":null,"game_gaps":{"highest":{"GB2-04":"failed","GB2-05":"unrated","GB2-07":"infra_excluded"},"medium":{"GB2-01":"infra_excluded","GB2-03":"failed","GB2-05":"unrated"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":32,"effective_max_output_tokens":[131072],"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":32,"output_token_observations":32,"provider_post_attempt_observations":32,"provider_post_attempts":41,"reasoning_token_observations":32,"reconciliation_get_attempt_observations":32,"requested_max_output_token_observations":32,"requested_max_output_tokens":[131072],"total_output_tokens":1717586,"total_reasoning_output_tokens":1599995,"total_visible_output_tokens":117591,"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":"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":"inception","provider_model":"inception/mercury-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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":["GB2-03"],"first_pass_admitted":4,"first_pass_rate":0.5714285714285714,"game_attempts":{"GB2-01":{"infra_failures_excluded":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}},"infra_excluded_game_aliases":["GB2-01"],"infra_failures_excluded":1,"model_code_failure_rate":0.14285714285714285,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":2,"repaired_rate":0.2857142857142857},"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":6,"evaluated_cells":7,"failed_game_aliases":["GB2-04"],"first_pass_admitted":3,"first_pass_rate":0.42857142857142855,"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":{"infra_failures_excluded":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-07"],"infra_failures_excluded":1,"model_code_failure_rate":0.14285714285714285,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":3,"repaired_rate":0.42857142857142855}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":40.86304906745049,"score":40.86304906745049},"GB2-02":{"attempts":3,"playable":43.19674784164632,"score":43.19674784164632},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":46.5541271673637,"score":31.03608477824247},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":48.855371481897734,"score":32.57024765459849},"GB2-05":{"attempts":1,"playable":23.03757558877989,"score":23.03757558877989},"GB2-06":{"attempts":3,"playable":61.83135317098755,"score":61.83135317098755},"GB2-07":{"attempts":2,"playable":54.37427355825683,"score":54.37427355825683},"GB2-08":{"attempts":3,"playable":47.520498341387416,"score":47.520498341387416}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":48.62591738987319,"score":48.62591738987319},"GB2-02":{"attempts":1,"playable":42.99603971972642,"score":42.99603971972642},"GB2-03":{"attempts":1,"playable":60.65485481507936,"score":60.65485481507936},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":76.1897671086881,"score":76.1897671086881},"GB2-08":{"attempts":1,"playable":58.300540118430234,"score":58.300540118430234}},"medium":{"GB2-02":{"attempts":1,"playable":44.9298345414003,"score":44.9298345414003},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":57.83777237224106,"score":57.83777237224106},"GB2-06":{"attempts":1,"playable":46.19272702099077,"score":46.19272702099077},"GB2-07":{"attempts":1,"playable":75.91394644969456,"score":75.91394644969456},"GB2-08":{"attempts":1,"playable":52.291512325426694,"score":52.291512325426694}},"none":{"GB2-01":{"attempts":1,"playable":33.1001807450278,"score":33.1001807450278},"GB2-02":{"attempts":1,"playable":41.66436926381224,"score":41.66436926381224},"GB2-03":{"attempts":1,"playable":32.45339951964805,"score":32.45339951964805},"GB2-04":{"attempts":1,"playable":39.8729705915544,"score":39.8729705915544},"GB2-05":{"attempts":1,"playable":23.03757558877989,"score":23.03757558877989},"GB2-06":{"attempts":1,"playable":63.111565383283775,"score":63.111565383283775},"GB2-07":{"attempts":1,"playable":32.83460066681909,"score":32.83460066681909},"GB2-08":{"attempts":1,"playable":31.969442580305312,"score":31.969442580305312}}},"id":"inception/mercury-3","is_recent_addition":false,"last_measured_at":"2026-11-03T08:07:14Z","match_totals_all":{"draws":2086,"losses":3466,"wins":2827},"match_totals_tracks":{"highest":{"draws":737,"losses":761,"wins":1084},"medium":{"draws":342,"losses":525,"wins":752},"none":{"draws":1007,"losses":2180,"wins":991}},"model_slug":"inception-mercury-3","official_rank_by_reasoning":{"none":51},"overall":{"max":76.1897671086881,"mean":43.74811056199854,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete","fixed_coverage_incomplete"],"overall_official_rank":45,"overall_ranking_status":"partial","per_game":{"GB2-01":48.62591738987319,"GB2-02":42.99603971972642,"GB2-03":60.65485481507936,"GB2-06":76.1897671086881,"GB2-08":58.300540118430234},"per_game_all":{"GB2-02":43.19674784164632,"GB2-06":61.83135317098755,"GB2-08":47.520498341387416},"per_game_match_totals_all":{"GB2-01":{"draws":443,"losses":401,"wins":204},"GB2-02":{"draws":1062,"losses":328,"wins":88},"GB2-03":{"draws":234,"losses":455,"wins":333},"GB2-04":{"draws":336,"losses":152,"wins":37},"GB2-05":{"draws":0,"losses":417,"wins":125},"GB2-06":{"draws":11,"losses":328,"wins":721},"GB2-07":{"draws":0,"losses":509,"wins":573},"GB2-08":{"draws":0,"losses":876,"wins":746}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":261,"losses":140,"wins":123},"GB2-02":{"draws":350,"losses":111,"wins":29},"GB2-03":{"draws":120,"losses":155,"wins":237},"GB2-06":{"draws":6,"losses":122,"wins":388},"GB2-08":{"draws":0,"losses":233,"wins":307}},"medium":{"GB2-02":{"draws":337,"losses":110,"wins":47},"GB2-04":{"draws":5,"losses":2,"wins":4},"GB2-06":{"draws":0,"losses":13,"wins":17},"GB2-07":{"draws":0,"losses":132,"wins":410},"GB2-08":{"draws":0,"losses":268,"wins":274}},"none":{"GB2-01":{"draws":182,"losses":261,"wins":81},"GB2-02":{"draws":375,"losses":107,"wins":12},"GB2-03":{"draws":114,"losses":300,"wins":96},"GB2-04":{"draws":331,"losses":150,"wins":33},"GB2-05":{"draws":0,"losses":417,"wins":125},"GB2-06":{"draws":5,"losses":193,"wins":316},"GB2-07":{"draws":0,"losses":377,"wins":163},"GB2-08":{"draws":0,"losses":375,"wins":165}}},"per_game_raw_elo_all":{"GB2-02":1423.608032154308,"GB2-06":1664.0891297097671,"GB2-08":1388.679993153043},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1474.000906334341,"GB2-02":1422.0550867407076,"GB2-03":1541.6334655116298,"GB2-06":1919.9392079379638,"GB2-08":1538.6153453140996},"medium":{"GB2-02":1437.1732457326234,"GB2-04":1541.1390399998695,"GB2-06":1395.1920732960536,"GB2-07":1830.248515185523,"GB2-08":1444.702661206624},"none":{"GB2-01":1320.2562138692304,"GB2-02":1411.5957639895933,"GB2-03":1283.420057795924,"GB2-04":1397.8069158889004,"GB2-05":1066.8102560014017,"GB2-06":1677.136107895284,"GB2-07":1218.814419928683,"GB2-08":1182.7219729384049}},"per_game_tracks":{"highest":{"GB2-01":48.62591738987319,"GB2-02":42.99603971972642,"GB2-03":60.65485481507936,"GB2-06":76.1897671086881,"GB2-08":58.300540118430234},"medium":{"GB2-02":44.9298345414003,"GB2-04":57.83777237224106,"GB2-06":46.19272702099077,"GB2-07":75.91394644969456,"GB2-08":52.291512325426694},"none":{"GB2-01":33.1001807450278,"GB2-02":41.66436926381224,"GB2-03":32.45339951964805,"GB2-04":39.8729705915544,"GB2-05":23.03757558877989,"GB2-06":63.111565383283775,"GB2-07":32.83460066681909,"GB2-08":31.969442580305312}},"program_outcomes":{"all":{"counted_attempts":22,"failed":2,"infra_excluded":2,"success_rate":0.9090909090909091,"too_slow":0,"worked_after_repair":6,"worked_first_time":14,"working":20},"highest":{"counted_attempts":7,"failed":1,"infra_excluded":1,"success_rate":0.8571428571428571,"too_slow":0,"worked_after_repair":3,"worked_first_time":3,"working":6},"medium":{"counted_attempts":7,"failed":1,"infra_excluded":1,"success_rate":0.8571428571428571,"too_slow":0,"worked_after_repair":2,"worked_first_time":4,"working":6},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#CBD5E1","provider_company":"Inception","provider_key":"inception","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":47.794519858632874,"medium":46.1942987849589,"none":37.25551304240383},"reasoning_agg":{"highest":{"max":76.1897671086881,"mean":47.794519858632874,"min":0.0},"medium":{"max":75.91394644969456,"mean":46.1942987849589,"min":0.0},"none":{"max":63.111565383283775,"mean":37.25551304240383,"min":23.03757558877989}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.539006816229048},"working_program_strength":{"all":50.014031804904654,"highest":57.35342383035945,"medium":55.43315854195068,"none":37.25551304240383}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-2:80b09fce73ac6d39","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":0.024102434966666662,"min":0.013816857666666668,"recorded_attempt_count":37,"run_count":24,"total":0.5651094238999999}},"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":0.9754123686000001},"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":0.3591713804},"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":0.20593804349999997},"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":43.20520272913449,"highest":44.06059686336026,"medium":45.95902805559453,"none":39.59598326844867},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":39.03836683486767,"score":39.03836683486767},"GB2-02":{"attempts":6,"playable":49.281274991113854,"score":49.281274991113854},"GB2-03":{"attempts":6,"playable":34.7307230022312,"score":34.7307230022312},"GB2-04":{"attempts":6,"playable":48.75739022082027,"score":48.75739022082027},"GB2-05":{"attempts":6,"playable":46.764878084483406,"score":46.764878084483406},"GB2-06":{"attempts":6,"playable":52.75800119095962,"score":52.75800119095962},"GB2-07":{"attempts":6,"playable":37.85685190912009,"score":37.85685190912009},"GB2-08":{"attempts":6,"playable":36.45413559947979,"score":36.45413559947979}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":52.45211056591537,"score":52.45211056591537},"GB2-02":{"attempts":1,"playable":60.37371619112575,"score":60.37371619112575},"GB2-03":{"attempts":1,"playable":35.948637182340484,"score":35.948637182340484},"GB2-04":{"attempts":1,"playable":57.139646705462155,"score":57.139646705462155},"GB2-05":{"attempts":1,"playable":55.76787374532488,"score":55.76787374532488},"GB2-06":{"attempts":1,"playable":39.54527692376011,"score":39.54527692376011},"GB2-07":{"attempts":1,"playable":10.103301861040539,"score":10.103301861040539},"GB2-08":{"attempts":1,"playable":41.15421173191277,"score":41.15421173191277}},"medium":{"GB2-01":{"attempts":2,"playable":37.49318331354764,"score":37.49318331354764},"GB2-02":{"attempts":2,"playable":47.494027826174026,"score":47.494027826174026},"GB2-03":{"attempts":2,"playable":29.455113698570273,"score":29.455113698570273},"GB2-04":{"attempts":2,"playable":47.02327355653762,"score":47.02327355653762},"GB2-05":{"attempts":2,"playable":50.924344728068675,"score":50.924344728068675},"GB2-06":{"attempts":2,"playable":75.47748985748527,"score":75.47748985748527},"GB2-07":{"attempts":2,"playable":57.07111811889661,"score":57.07111811889661},"GB2-08":{"attempts":2,"playable":22.733673345476205,"score":22.733673345476205}},"none":{"GB2-01":{"attempts":3,"playable":27.169806625139994,"score":27.169806625139994},"GB2-02":{"attempts":3,"playable":39.97608095604179,"score":39.97608095604179},"GB2-03":{"attempts":3,"playable":38.78841812578285,"score":38.78841812578285},"GB2-04":{"attempts":3,"playable":42.109250400461036,"score":42.109250400461036},"GB2-05":{"attempts":3,"playable":33.60241578005668,"score":33.60241578005668},"GB2-06":{"attempts":3,"playable":43.25123679163348,"score":43.25123679163348},"GB2-07":{"attempts":3,"playable":46.39613574742312,"score":46.39613574742312},"GB2-08":{"attempts":3,"playable":45.474521721050394,"score":45.474521721050394}}},"id":"z-ai/glm-5.2","is_recent_addition":false,"last_measured_at":"2026-11-03T07:08:42Z","match_totals_all":{"draws":6273,"losses":11626,"wins":7191},"match_totals_tracks":{"highest":{"draws":965,"losses":1921,"wins":1292},"medium":{"draws":2211,"losses":3510,"wins":2645},"none":{"draws":3097,"losses":6195,"wins":3254}},"model_slug":"z-ai-glm-5-2","official_rank_by_reasoning":{"highest":49,"medium":46,"none":45},"overall":{"max":75.47748985748527,"mean":43.20520272913449,"min":10.103301861040539},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":46,"overall_ranking_status":"ranked","per_game":{"GB2-01":52.45211056591537,"GB2-02":60.37371619112575,"GB2-03":35.948637182340484,"GB2-04":57.139646705462155,"GB2-05":55.76787374532488,"GB2-06":39.54527692376011,"GB2-07":10.103301861040539,"GB2-08":41.15421173191277},"per_game_all":{"GB2-01":39.03836683486767,"GB2-02":49.281274991113854,"GB2-03":34.7307230022312,"GB2-04":48.75739022082027,"GB2-05":46.764878084483406,"GB2-06":52.75800119095962,"GB2-07":37.85685190912009,"GB2-08":36.45413559947979},"per_game_match_totals_all":{"GB2-01":{"draws":781,"losses":1683,"wins":700},"GB2-02":{"draws":2098,"losses":595,"wins":277},"GB2-03":{"draws":1107,"losses":1512,"wins":449},"GB2-04":{"draws":1700,"losses":834,"wins":520},"GB2-05":{"draws":0,"losses":1852,"wins":1400},"GB2-06":{"draws":80,"losses":1443,"wins":1559},"GB2-07":{"draws":0,"losses":1878,"wins":1364},"GB2-08":{"draws":507,"losses":1829,"wins":922}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":186,"losses":158,"wins":182},"GB2-02":{"draws":240,"losses":82,"wins":172},"GB2-03":{"draws":178,"losses":252,"wins":82},"GB2-04":{"draws":242,"losses":104,"wins":162},"GB2-05":{"draws":0,"losses":240,"wins":302},"GB2-06":{"draws":18,"losses":313,"wins":181},"GB2-07":{"draws":0,"losses":494,"wins":46},"GB2-08":{"draws":101,"losses":278,"wins":165}},"medium":{"GB2-01":{"draws":285,"losses":523,"wins":250},"GB2-02":{"draws":734,"losses":166,"wins":92},"GB2-03":{"draws":417,"losses":535,"wins":68},"GB2-04":{"draws":575,"losses":266,"wins":177},"GB2-05":{"draws":0,"losses":531,"wins":553},"GB2-06":{"draws":28,"losses":243,"wins":755},"GB2-07":{"draws":0,"losses":481,"wins":601},"GB2-08":{"draws":172,"losses":765,"wins":149}},"none":{"GB2-01":{"draws":310,"losses":1002,"wins":268},"GB2-02":{"draws":1124,"losses":347,"wins":13},"GB2-03":{"draws":512,"losses":725,"wins":299},"GB2-04":{"draws":883,"losses":464,"wins":181},"GB2-05":{"draws":0,"losses":1081,"wins":545},"GB2-06":{"draws":34,"losses":887,"wins":623},"GB2-07":{"draws":0,"losses":903,"wins":717},"GB2-08":{"draws":234,"losses":786,"wins":608}}},"per_game_raw_elo_all":{"GB2-01":1376.006615178286,"GB2-02":1471.9562729350116,"GB2-03":1303.5931432732616,"GB2-04":1468.5041850250054,"GB2-05":1400.5217675202546,"GB2-06":1519.4404771843192,"GB2-07":1253.0204233699378,"GB2-08":1258.4845641831891},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1510.9532993467599,"GB2-02":1560.4271743088962,"GB2-03":1315.6652705973975,"GB2-04":1535.3641045354836,"GB2-05":1527.2811269569095,"GB2-06":1290.7525673531072,"GB2-07":820.393204927129,"GB2-08":1294.653608117698},"medium":{"GB2-01":1362.9472787671998,"GB2-02":1457.2309653247612,"GB2-03":1254.2761652293343,"GB2-04":1454.5190044790004,"GB2-05":1463.7306206290482,"GB2-06":1910.8720424065132,"GB2-07":1540.562426382994,"GB2-08":1067.5559589987633},"none":{"GB2-01":1254.1192674208985,"GB2-02":1398.2106791713777,"GB2-03":1340.837993993053,"GB2-04":1415.6294460605325,"GB2-05":1210.5535549748058,"GB2-06":1356.696821793337,"GB2-07":1398.1056387996907,"GB2-08":1413.244125433106}},"per_game_tracks":{"highest":{"GB2-01":52.45211056591537,"GB2-02":60.37371619112575,"GB2-03":35.948637182340484,"GB2-04":57.139646705462155,"GB2-05":55.76787374532488,"GB2-06":39.54527692376011,"GB2-07":10.103301861040539,"GB2-08":41.15421173191277},"medium":{"GB2-01":37.49318331354764,"GB2-02":47.494027826174026,"GB2-03":29.455113698570273,"GB2-04":47.02327355653762,"GB2-05":50.924344728068675,"GB2-06":75.47748985748527,"GB2-07":57.07111811889661,"GB2-08":22.733673345476205},"none":{"GB2-01":27.169806625139994,"GB2-02":39.97608095604179,"GB2-03":38.78841812578285,"GB2-04":42.109250400461036,"GB2-05":33.60241578005668,"GB2-06":43.25123679163348,"GB2-07":46.39613574742312,"GB2-08":45.474521721050394}},"program_outcomes":{"all":{"counted_attempts":48,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":22,"worked_first_time":26,"working":48},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":16,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":10,"worked_first_time":6,"working":16},"none":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":11,"worked_first_time":13,"working":24}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T16:20:24Z","reasoning":{"highest":44.06059686336026,"medium":45.95902805559453,"none":39.59598326844867},"reasoning_agg":{"highest":{"max":60.37371619112575,"mean":44.06059686336026,"min":10.103301861040539},"medium":{"max":75.47748985748527,"mean":45.95902805559453,"min":22.733673345476205},"none":{"max":46.39613574742312,"mean":39.59598326844867,"min":27.169806625139994}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":6.36304478714586},"working_program_strength":{"all":43.20520272913449,"highest":44.06059686336026,"medium":45.95902805559453,"none":39.59598326844867}},{"canonical_public_row_identity":"publication-row.v1:overall:reflection-beam-1-0-501b-a23b:1c1eb87c5ea986b7","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":0.04917425,"mean":0.028458624999999998,"median":0.0242415,"min":0.016261,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.227669},"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":0.01932975,"mean":0.010711218750000001,"median":0.008422124999999999,"min":0.00683925,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.08568975000000001},"none":{"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":0.013563249999999999,"mean":0.0084324375,"median":0.007856624999999999,"min":0.0040545,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.0674595}},"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":0.01932975,"mean":0.010711218750000001,"median":0.008422124999999999,"min":0.00683925,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.08568975},"historical-provider-setting-baseline":{"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":0.013563249999999999,"mean":0.0084324375,"median":0.007856624999999999,"min":0.0040545,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.0674595},"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":0.04917425,"mean":0.028458624999999998,"median":0.0242415,"min":0.016261,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.22766899999999998}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.04917425,"mean":0.015867427083333333,"median":0.01165575,"min":0.0040545,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":36},"recorded_attempt_count":36,"run_count":24,"total":0.38081824999999997},"codegen_latency_ms":{"attempt_count":36,"max_ms":225177,"mean_ms":82986.79166666667,"min_ms":14518,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":225177,"mean_ms":159627.75,"min_ms":89322,"run_count":8},"medium":{"attempt_count":11,"max_ms":118131,"mean_ms":55222.125,"min_ms":14518,"run_count":8},"none":{"attempt_count":14,"max_ms":72565,"mean_ms":34110.5,"min_ms":18316,"run_count":8}},"codegen_output_tokens":{"attempt_count":36,"output_max":44106,"output_mean":12952.291666666666,"output_min":2213,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":44106,"output_mean":25586.0,"output_min":14383,"run_count":8},"medium":{"attempt_count":11,"output_max":15405,"output_mean":8034.75,"output_min":4457,"run_count":8},"none":{"attempt_count":14,"output_max":8725,"output_mean":5236.125,"output_min":2213,"run_count":8}},"display_name":"Beam 1.0 501B A23B","economics":{"all":42.898270385867015,"highest":53.41752229585679,"medium":35.904485312486074,"none":39.37280354925819},"first_seen_at":null,"game_gaps":{"medium":{"GB2-01":"failed"},"none":{"GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":36,"effective_max_output_tokens":[131072],"finish_reason_observations":36,"finish_reasons":["stop"],"indexed_attempts":36,"output_token_observations":36,"provider_post_attempt_observations":36,"provider_post_attempts":36,"reasoning_token_observations":36,"reconciliation_get_attempt_observations":36,"requested_max_output_token_observations":36,"requested_max_output_tokens":[131072],"total_output_tokens":310855,"total_reasoning_output_tokens":208237,"total_visible_output_tokens":102618,"visible_token_observations":36},"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":"other","provider_model":"reflection/beam-1.0-501b-a23b","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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":["GB2-01"],"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},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"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":{"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":4,"repaired_rate":0.5},"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,"failed_attempts":1,"playable":32.5578168238444,"score":21.705211215896266},"GB2-02":{"attempts":3,"playable":42.12263225951315,"score":42.12263225951315},"GB2-03":{"attempts":3,"playable":51.90602486960868,"score":51.90602486960868},"GB2-04":{"attempts":3,"playable":45.70221672625297,"score":45.70221672625297},"GB2-05":{"attempts":3,"playable":49.08685359430903,"score":49.08685359430903},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":61.92146193379209,"score":41.280974622528056},"GB2-07":{"attempts":3,"playable":26.144379400243356,"score":26.144379400243356},"GB2-08":{"attempts":3,"playable":65.23787039858462,"score":65.23787039858462}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":23.819785253908826,"score":23.819785253908826},"GB2-02":{"attempts":1,"playable":48.9659863644407,"score":48.9659863644407},"GB2-03":{"attempts":1,"playable":76.00875266579774,"score":76.00875266579774},"GB2-04":{"attempts":1,"playable":59.71783342288886,"score":59.71783342288886},"GB2-05":{"attempts":1,"playable":50.088136400919495,"score":50.088136400919495},"GB2-06":{"attempts":1,"playable":71.5912116941801,"score":71.5912116941801},"GB2-07":{"attempts":1,"playable":38.05216150279438,"score":38.05216150279438},"GB2-08":{"attempts":1,"playable":59.09631106192423,"score":59.09631106192423}},"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":32.98835818481699,"score":32.98835818481699},"GB2-03":{"attempts":1,"playable":37.59268601969362,"score":37.59268601969362},"GB2-04":{"attempts":1,"playable":38.667778565957626,"score":38.667778565957626},"GB2-05":{"attempts":1,"playable":38.5489068828315,"score":38.5489068828315},"GB2-06":{"attempts":1,"playable":52.251712173404066,"score":52.251712173404066},"GB2-07":{"attempts":1,"playable":30.355172190155766,"score":30.355172190155766},"GB2-08":{"attempts":1,"playable":56.83126848302901,"score":56.83126848302901}},"none":{"GB2-01":{"attempts":1,"playable":41.29584839377997,"score":41.29584839377997},"GB2-02":{"attempts":1,"playable":44.41355222928177,"score":44.41355222928177},"GB2-03":{"attempts":1,"playable":42.11663592333468,"score":42.11663592333468},"GB2-04":{"attempts":1,"playable":38.721038189912434,"score":38.721038189912434},"GB2-05":{"attempts":1,"playable":58.6235174991761,"score":58.6235174991761},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":10.025804507779927,"score":10.025804507779927},"GB2-08":{"attempts":1,"playable":79.78603165080064,"score":79.78603165080064}}},"id":"reflection/beam-1.0-501b-a23b","is_recent_addition":false,"last_measured_at":"2026-11-03T06:54:57Z","match_totals_all":{"draws":2530,"losses":5008,"wins":3975},"match_totals_tracks":{"highest":{"draws":737,"losses":1640,"wins":1811},"medium":{"draws":787,"losses":1816,"wins":1051},"none":{"draws":1006,"losses":1552,"wins":1113}},"model_slug":"reflection-beam-1-0-501b-a23b","official_rank_by_reasoning":{"highest":43,"medium":63,"none":47},"overall":{"max":79.78603165080064,"mean":42.898270385867015,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":47,"overall_ranking_status":"ranked","per_game":{"GB2-01":23.819785253908826,"GB2-02":48.9659863644407,"GB2-03":76.00875266579774,"GB2-04":59.71783342288886,"GB2-05":50.088136400919495,"GB2-06":71.5912116941801,"GB2-07":38.05216150279438,"GB2-08":59.09631106192423},"per_game_all":{"GB2-02":42.12263225951315,"GB2-03":51.90602486960868,"GB2-04":45.70221672625297,"GB2-05":49.08685359430903,"GB2-07":26.144379400243356,"GB2-08":65.23787039858462},"per_game_match_totals_all":{"GB2-01":{"draws":350,"losses":540,"wins":164},"GB2-02":{"draws":981,"losses":385,"wins":116},"GB2-03":{"draws":329,"losses":611,"wins":596},"GB2-04":{"draws":831,"losses":438,"wins":266},"GB2-05":{"draws":0,"losses":828,"wins":802},"GB2-06":{"draws":39,"losses":386,"wins":601},"GB2-07":{"draws":0,"losses":1235,"wins":389},"GB2-08":{"draws":0,"losses":585,"wins":1041}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":138,"losses":334,"wins":54},"GB2-02":{"draws":333,"losses":93,"wins":70},"GB2-03":{"draws":38,"losses":113,"wins":361},"GB2-04":{"draws":200,"losses":113,"wins":199},"GB2-05":{"draws":0,"losses":271,"wins":273},"GB2-06":{"draws":28,"losses":136,"wins":348},"GB2-07":{"draws":0,"losses":350,"wins":194},"GB2-08":{"draws":0,"losses":230,"wins":312}},"medium":{"GB2-02":{"draws":284,"losses":192,"wins":14},"GB2-03":{"draws":181,"losses":245,"wins":90},"GB2-04":{"draws":311,"losses":165,"wins":36},"GB2-05":{"draws":0,"losses":332,"wins":210},"GB2-06":{"draws":11,"losses":250,"wins":253},"GB2-07":{"draws":0,"losses":389,"wins":149},"GB2-08":{"draws":0,"losses":243,"wins":299}},"none":{"GB2-01":{"draws":212,"losses":206,"wins":110},"GB2-02":{"draws":364,"losses":100,"wins":32},"GB2-03":{"draws":110,"losses":253,"wins":145},"GB2-04":{"draws":320,"losses":160,"wins":31},"GB2-05":{"draws":0,"losses":225,"wins":319},"GB2-07":{"draws":0,"losses":496,"wins":46},"GB2-08":{"draws":0,"losses":112,"wins":430}}},"per_game_raw_elo_all":{"GB2-02":1414.3291745700628,"GB2-03":1475.8463107053658,"GB2-04":1444.513928790926,"GB2-05":1440.5216880905627,"GB2-07":1097.1275061395465,"GB2-08":1676.467580254249},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1215.4059082956524,"GB2-02":1468.6533054830907,"GB2-03":1726.2023881250918,"GB2-04":1556.8841158989114,"GB2-05":1452.886696634445,"GB2-06":1832.2892537198138,"GB2-07":1288.3989899284386,"GB2-08":1551.9216595399726},"medium":{"GB2-02":1341.1913118996144,"GB2-03":1330.5222647298287,"GB2-04":1388.1138765331852,"GB2-05":1302.5057863113204,"GB2-06":1492.3762712644286,"GB2-07":1184.678434040195,"GB2-08":1514.6005145369966},"none":{"GB2-01":1402.9980280121176,"GB2-02":1433.1429063274838,"GB2-03":1370.8142792611773,"GB2-04":1388.5437939406809,"GB2-05":1566.172581325923,"GB2-07":818.305094450006,"GB2-08":1962.8805666857775}},"per_game_tracks":{"highest":{"GB2-01":23.819785253908826,"GB2-02":48.9659863644407,"GB2-03":76.00875266579774,"GB2-04":59.71783342288886,"GB2-05":50.088136400919495,"GB2-06":71.5912116941801,"GB2-07":38.05216150279438,"GB2-08":59.09631106192423},"medium":{"GB2-02":32.98835818481699,"GB2-03":37.59268601969362,"GB2-04":38.667778565957626,"GB2-05":38.5489068828315,"GB2-06":52.251712173404066,"GB2-07":30.355172190155766,"GB2-08":56.83126848302901},"none":{"GB2-01":41.29584839377997,"GB2-02":44.41355222928177,"GB2-03":42.11663592333468,"GB2-04":38.721038189912434,"GB2-05":58.6235174991761,"GB2-07":10.025804507779927,"GB2-08":79.78603165080064}},"program_outcomes":{"all":{"counted_attempts":24,"failed":2,"infra_excluded":0,"success_rate":0.9166666666666666,"too_slow":0,"worked_after_repair":9,"worked_first_time":13,"working":22},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":2,"worked_first_time":5,"working":7},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":4,"worked_first_time":3,"working":7}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":-3,"rank_movement_baseline_at":"2026-10-27T23:46:14Z","reasoning":{"highest":53.41752229585679,"medium":35.904485312486074,"none":39.37280354925819},"reasoning_agg":{"highest":{"max":76.00875266579774,"mean":53.41752229585679,"min":23.819785253908826},"medium":{"max":56.83126848302901,"mean":35.904485312486074,"min":0.0},"none":{"max":79.78603165080064,"mean":39.37280354925819,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":17.513036983370718},"working_program_strength":{"all":46.48290318880722,"highest":53.41752229585679,"medium":41.033697499984086,"none":44.997489770580785}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro-0813:84c92d6f9c4c6c41","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":0.98845232184},"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":0.21636246784}},"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":0.9884523218400001},"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":1.1725616482799999}},"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":41.982275566929154,"highest":53.898256728513715,"medium":44.994507566306865,"none":27.05406240596688},"first_seen_at":null,"game_gaps":{"none":{"GB2-02":"failed","GB2-05":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":41.640006248433494,"score":41.640006248433494},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":41.68993082039853,"score":27.79328721359902},"GB2-03":{"attempts":3,"playable":46.360938192873476,"score":46.360938192873476},"GB2-04":{"attempts":3,"playable":38.97257432569176,"score":38.97257432569176},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":56.569280996907196,"score":37.71285399793813},"GB2-06":{"attempts":3,"playable":52.59925497908724,"score":52.59925497908724},"GB2-07":{"attempts":3,"playable":57.257961563490504,"score":57.257961563490504},"GB2-08":{"attempts":3,"playable":33.52132801431965,"score":33.52132801431965}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":41.63402261227026,"score":41.63402261227026},"GB2-02":{"attempts":1,"playable":43.91938501379085,"score":43.91938501379085},"GB2-03":{"attempts":1,"playable":61.919674512629896,"score":61.919674512629896},"GB2-04":{"attempts":1,"playable":41.825340045131284,"score":41.825340045131284},"GB2-05":{"attempts":1,"playable":71.35025039947664,"score":71.35025039947664},"GB2-06":{"attempts":1,"playable":62.518040127768955,"score":62.518040127768955},"GB2-07":{"attempts":1,"playable":77.2652444602042,"score":77.2652444602042},"GB2-08":{"attempts":1,"playable":30.75409665683771,"score":30.75409665683771}},"medium":{"GB2-01":{"attempts":1,"playable":49.51992283083127,"score":49.51992283083127},"GB2-02":{"attempts":1,"playable":39.4604766270062,"score":39.4604766270062},"GB2-03":{"attempts":1,"playable":41.2625054334014,"score":41.2625054334014},"GB2-04":{"attempts":1,"playable":31.977906716636166,"score":31.977906716636166},"GB2-05":{"attempts":1,"playable":41.78831159433776,"score":41.78831159433776},"GB2-06":{"attempts":1,"playable":37.08768642444839,"score":37.08768642444839},"GB2-07":{"attempts":1,"playable":71.8792437511427,"score":71.8792437511427},"GB2-08":{"attempts":1,"playable":46.98000715265109,"score":46.98000715265109}},"none":{"GB2-01":{"attempts":1,"playable":33.76607330219896,"score":33.76607330219896},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":35.90063463258913,"score":35.90063463258913},"GB2-04":{"attempts":1,"playable":43.114476215307825,"score":43.114476215307825},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":58.192038385044384,"score":58.192038385044384},"GB2-07":{"attempts":1,"playable":22.629396479124594,"score":22.629396479124594},"GB2-08":{"attempts":1,"playable":22.82988023347015,"score":22.82988023347015}}},"id":"deepseek/deepseek-v4-pro-0813","is_recent_addition":false,"last_measured_at":"2026-11-03T07:16:11Z","match_totals_all":{"draws":2421,"losses":5181,"wins":3934},"match_totals_tracks":{"highest":{"draws":737,"losses":1604,"wins":1851},"medium":{"draws":930,"losses":1882,"wins":1380},"none":{"draws":754,"losses":1695,"wins":703}},"model_slug":"deepseek-deepseek-v4-pro-0813","official_rank_by_reasoning":{"highest":42,"medium":49,"none":73},"overall":{"max":77.2652444602042,"mean":41.982275566929154,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":48,"overall_ranking_status":"ranked","per_game":{"GB2-01":41.63402261227026,"GB2-02":43.91938501379085,"GB2-03":61.919674512629896,"GB2-04":41.825340045131284,"GB2-05":71.35025039947664,"GB2-06":62.518040127768955,"GB2-07":77.2652444602042,"GB2-08":30.75409665683771},"per_game_all":{"GB2-01":41.640006248433494,"GB2-03":46.360938192873476,"GB2-04":38.97257432569176,"GB2-06":52.59925497908724,"GB2-07":57.257961563490504,"GB2-08":33.52132801431965},"per_game_match_totals_all":{"GB2-01":{"draws":413,"losses":720,"wins":447},"GB2-02":{"draws":725,"losses":228,"wins":39},"GB2-03":{"draws":302,"losses":719,"wins":525},"GB2-04":{"draws":799,"losses":557,"wins":180},"GB2-05":{"draws":0,"losses":472,"wins":614},"GB2-06":{"draws":18,"losses":749,"wins":777},"GB2-07":{"draws":0,"losses":710,"wins":910},"GB2-08":{"draws":164,"losses":1026,"wins":442}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":16,"losses":302,"wins":210},"GB2-02":{"draws":380,"losses":93,"wins":21},"GB2-03":{"draws":30,"losses":194,"wins":290},"GB2-04":{"draws":249,"losses":180,"wins":83},"GB2-05":{"draws":0,"losses":156,"wins":386},"GB2-06":{"draws":8,"losses":195,"wins":311},"GB2-07":{"draws":0,"losses":124,"wins":416},"GB2-08":{"draws":54,"losses":360,"wins":134}},"medium":{"GB2-01":{"draws":291,"losses":121,"wins":114},"GB2-02":{"draws":345,"losses":135,"wins":18},"GB2-03":{"draws":44,"losses":295,"wins":177},"GB2-04":{"draws":184,"losses":261,"wins":65},"GB2-05":{"draws":0,"losses":316,"wins":228},"GB2-06":{"draws":8,"losses":333,"wins":177},"GB2-07":{"draws":0,"losses":155,"wins":385},"GB2-08":{"draws":58,"losses":266,"wins":216}},"none":{"GB2-01":{"draws":106,"losses":297,"wins":123},"GB2-03":{"draws":228,"losses":230,"wins":58},"GB2-04":{"draws":366,"losses":116,"wins":32},"GB2-06":{"draws":2,"losses":221,"wins":289},"GB2-07":{"draws":0,"losses":431,"wins":109},"GB2-08":{"draws":52,"losses":400,"wins":92}}},"per_game_raw_elo_all":{"GB2-01":1405.3818248863156,"GB2-03":1411.0029882824576,"GB2-04":1389.805087304907,"GB2-06":1503.439351796945,"GB2-07":1561.6936761339846,"GB2-08":1202.3374695109994},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1406.3094398612639,"GB2-02":1429.281703358376,"GB2-03":1554.531127235098,"GB2-04":1413.3765256939505,"GB2-05":1769.3162591184719,"GB2-06":1666.6112389641487,"GB2-07":1856.5414757843662,"GB2-08":1168.0302786835075},"medium":{"GB2-01":1482.6173723642569,"GB2-02":1394.1490714874901,"GB2-03":1363.248856095856,"GB2-04":1332.4489717993106,"GB2-05":1345.596207912608,"GB2-06":1252.2914130332301,"GB2-07":1758.3074070889884,"GB2-08":1370.0510345001},"none":{"GB2-01":1327.2186624334265,"GB2-03":1315.228981516419,"GB2-04":1423.58976442146,"GB2-06":1591.4154033934562,"GB2-07":1070.2321455285996,"GB2-08":1068.9310953493907}},"per_game_tracks":{"highest":{"GB2-01":41.63402261227026,"GB2-02":43.91938501379085,"GB2-03":61.919674512629896,"GB2-04":41.825340045131284,"GB2-05":71.35025039947664,"GB2-06":62.518040127768955,"GB2-07":77.2652444602042,"GB2-08":30.75409665683771},"medium":{"GB2-01":49.51992283083127,"GB2-02":39.4604766270062,"GB2-03":41.2625054334014,"GB2-04":31.977906716636166,"GB2-05":41.78831159433776,"GB2-06":37.08768642444839,"GB2-07":71.8792437511427,"GB2-08":46.98000715265109},"none":{"GB2-01":33.76607330219896,"GB2-03":35.90063463258913,"GB2-04":43.114476215307825,"GB2-06":58.192038385044384,"GB2-07":22.629396479124594,"GB2-08":22.82988023347015}},"program_outcomes":{"all":{"counted_attempts":24,"failed":2,"infra_excluded":0,"success_rate":0.9166666666666666,"too_slow":0,"worked_after_repair":4,"worked_first_time":18,"working":22},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":1,"worked_first_time":5,"working":6}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T16:40:28Z","reasoning":{"highest":53.898256728513715,"medium":44.994507566306865,"none":27.054062405966885},"reasoning_agg":{"highest":{"max":77.2652444602042,"mean":53.898256728513715,"min":30.75409665683771},"medium":{"max":71.8792437511427,"mean":44.994507566306865,"min":31.977906716636166},"none":{"max":58.192038385044384,"mean":27.054062405966885,"min":0.0}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":26.84419432254683},"working_program_strength":{"all":44.98828250092547,"highest":53.898256728513715,"medium":44.994507566306865,"none":36.07208320795584}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro:201663eb3d6fa183","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":0.20237245442100002}},"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":0.9135725942490001}},"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":1.4885651789640002},"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":41.68012125206242,"highest":46.35783574969437,"medium":51.580657187573046,"none":27.10187081891985},"first_seen_at":null,"game_gaps":{"none":{"GB2-02":"failed","GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":37.761502902908916,"score":37.761502902908916},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":41.827875933891285,"score":27.88525062259419},"GB2-03":{"attempts":3,"playable":38.143032662651365,"score":38.143032662651365},"GB2-04":{"attempts":3,"playable":44.08065234628534,"score":44.08065234628534},"GB2-05":{"attempts":3,"playable":40.345666180381656,"score":40.345666180381656},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":60.608130985322454,"score":40.40542065688164},"GB2-07":{"attempts":3,"playable":65.06580496333649,"score":65.06580496333649},"GB2-08":{"attempts":3,"playable":39.75363968145979,"score":39.75363968145979}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":25.27161317756434,"score":25.27161317756434},"GB2-02":{"attempts":1,"playable":44.72909206489816,"score":44.72909206489816},"GB2-03":{"attempts":1,"playable":45.96072092425217,"score":45.96072092425217},"GB2-04":{"attempts":1,"playable":44.90625524681572,"score":44.90625524681572},"GB2-05":{"attempts":1,"playable":42.52382835459478,"score":42.52382835459478},"GB2-06":{"attempts":1,"playable":75.33373150083101,"score":75.33373150083101},"GB2-07":{"attempts":1,"playable":72.62770742990412,"score":72.62770742990412},"GB2-08":{"attempts":1,"playable":19.509737298694688,"score":19.509737298694688}},"medium":{"GB2-01":{"attempts":1,"playable":60.53506395741063,"score":60.53506395741063},"GB2-02":{"attempts":1,"playable":38.92665980288441,"score":38.92665980288441},"GB2-03":{"attempts":1,"playable":27.969698095129893,"score":27.969698095129893},"GB2-04":{"attempts":1,"playable":43.016423630667894,"score":43.016423630667894},"GB2-05":{"attempts":1,"playable":46.02357882493918,"score":46.02357882493918},"GB2-06":{"attempts":1,"playable":45.8825304698139,"score":45.8825304698139},"GB2-07":{"attempts":1,"playable":69.2778361083827,"score":69.2778361083827},"GB2-08":{"attempts":1,"playable":81.01346661135574,"score":81.01346661135574}},"none":{"GB2-01":{"attempts":1,"playable":27.477831573751786,"score":27.477831573751786},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":40.498678968572015,"score":40.498678968572015},"GB2-04":{"attempts":1,"playable":44.31927816137241,"score":44.31927816137241},"GB2-05":{"attempts":1,"playable":32.489591361611005,"score":32.489591361611005},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":53.291871351722655,"score":53.291871351722655},"GB2-08":{"attempts":1,"playable":18.73771513432894,"score":18.73771513432894}}},"id":"deepseek/deepseek-v4-pro","is_recent_addition":false,"last_measured_at":"2026-11-03T07:16:15Z","match_totals_all":{"draws":2541,"losses":5141,"wins":3866},"match_totals_tracks":{"highest":{"draws":947,"losses":1818,"wins":1421},"medium":{"draws":832,"losses":1639,"wins":1721},"none":{"draws":762,"losses":1684,"wins":724}},"model_slug":"deepseek-deepseek-v4-pro","official_rank_by_reasoning":{"highest":48,"medium":33,"none":72},"overall":{"max":81.01346661135574,"mean":41.68012125206242,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":49,"overall_ranking_status":"ranked","per_game":{"GB2-01":25.27161317756434,"GB2-02":44.72909206489816,"GB2-03":45.96072092425217,"GB2-04":44.90625524681572,"GB2-05":42.52382835459478,"GB2-06":75.33373150083101,"GB2-07":72.62770742990412,"GB2-08":19.509737298694688},"per_game_all":{"GB2-01":37.761502902908916,"GB2-03":38.143032662651365,"GB2-04":44.08065234628534,"GB2-05":40.345666180381656,"GB2-07":65.06580496333649,"GB2-08":39.75363968145979},"per_game_match_totals_all":{"GB2-01":{"draws":218,"losses":882,"wins":484},"GB2-02":{"draws":723,"losses":226,"wins":41},"GB2-03":{"draws":464,"losses":755,"wins":313},"GB2-04":{"draws":947,"losses":404,"wins":181},"GB2-05":{"draws":0,"losses":972,"wins":660},"GB2-06":{"draws":13,"losses":413,"wins":602},"GB2-07":{"draws":0,"losses":584,"wins":1038},"GB2-08":{"draws":176,"losses":905,"wins":547}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":42,"losses":376,"wins":110},"GB2-02":{"draws":366,"losses":97,"wins":33},"GB2-03":{"draws":186,"losses":198,"wins":128},"GB2-04":{"draws":298,"losses":139,"wins":73},"GB2-05":{"draws":0,"losses":312,"wins":232},"GB2-06":{"draws":8,"losses":125,"wins":379},"GB2-07":{"draws":0,"losses":151,"wins":389},"GB2-08":{"draws":47,"losses":420,"wins":77}},"medium":{"GB2-01":{"draws":39,"losses":191,"wins":300},"GB2-02":{"draws":357,"losses":129,"wins":8},"GB2-03":{"draws":114,"losses":322,"wins":74},"GB2-04":{"draws":317,"losses":141,"wins":56},"GB2-05":{"draws":0,"losses":293,"wins":251},"GB2-06":{"draws":5,"losses":288,"wins":223},"GB2-07":{"draws":0,"losses":170,"wins":370},"GB2-08":{"draws":0,"losses":105,"wins":439}},"none":{"GB2-01":{"draws":137,"losses":315,"wins":74},"GB2-03":{"draws":164,"losses":235,"wins":111},"GB2-04":{"draws":332,"losses":124,"wins":52},"GB2-05":{"draws":0,"losses":367,"wins":177},"GB2-07":{"draws":0,"losses":263,"wins":279},"GB2-08":{"draws":129,"losses":380,"wins":31}}},"per_game_raw_elo_all":{"GB2-01":1360.927032170274,"GB2-03":1333.7907539060068,"GB2-04":1431.21504872513,"GB2-05":1324.459505113469,"GB2-07":1658.048708260828,"GB2-08":1342.3953989314405},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1233.0493372011338,"GB2-02":1435.6065446228395,"GB2-03":1404.8306738863116,"GB2-04":1437.728667022418,"GB2-05":1355.229254107692,"GB2-06":1903.399381451825,"GB2-07":1771.0365553822717,"GB2-08":1023.7336966793885},"medium":{"GB2-01":1590.9023057050176,"GB2-02":1389.8902826269757,"GB2-03":1240.06967126574,"GB2-04":1422.8143857546302,"GB2-05":1400.5793203836058,"GB2-06":1390.2854304503996,"GB2-07":1715.766728541978,"GB2-08":1990.7601281970797},"none":{"GB2-01":1258.8294536046708,"GB2-03":1356.4719165659685,"GB2-04":1433.1020933983414,"GB2-05":1217.5699408491091,"GB2-07":1487.342840858235,"GB2-08":1012.6923719178528}},"per_game_tracks":{"highest":{"GB2-01":25.27161317756434,"GB2-02":44.72909206489816,"GB2-03":45.96072092425217,"GB2-04":44.90625524681572,"GB2-05":42.52382835459478,"GB2-06":75.33373150083101,"GB2-07":72.62770742990412,"GB2-08":19.509737298694688},"medium":{"GB2-01":60.53506395741063,"GB2-02":38.92665980288441,"GB2-03":27.969698095129893,"GB2-04":43.016423630667894,"GB2-05":46.02357882493918,"GB2-06":45.8825304698139,"GB2-07":69.2778361083827,"GB2-08":81.01346661135574},"none":{"GB2-01":27.477831573751786,"GB2-03":40.498678968572015,"GB2-04":44.31927816137241,"GB2-05":32.489591361611005,"GB2-07":53.291871351722655,"GB2-08":18.73771513432894}},"program_outcomes":{"all":{"counted_attempts":24,"failed":2,"infra_excluded":0,"success_rate":0.9166666666666666,"too_slow":0,"worked_after_repair":9,"worked_first_time":13,"working":22},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":4,"working":8},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":2,"worked_first_time":4,"working":6}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T16:38:21Z","reasoning":{"highest":46.35783574969437,"medium":51.580657187573046,"none":27.10187081891985},"reasoning_agg":{"highest":{"max":75.33373150083101,"mean":46.35783574969437,"min":19.509737298694688},"medium":{"max":81.01346661135574,"mean":51.580657187573046,"min":27.969698095129893},"none":{"max":53.291871351722655,"mean":27.10187081891985,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.478786368653196},"working_program_strength":{"all":44.69144023194241,"highest":46.35783574969437,"medium":51.580657187573046,"none":36.1358277585598}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5:01830fcec5780cc2","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":1.4205012499999998},"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":2.2561125000000004}},"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":4.4559187499999995},"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":41.218649442038874,"highest":46.732314657028205,"medium":37.17828784383235,"none":39.745345825256074},"first_seen_at":null,"game_gaps":{"medium":{"GB2-02":"failed"},"none":{"GB2-04":"too_slow","GB2-06":"too_slow"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":42.11611956981884,"score":42.11611956981884},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":39.543716797879114,"score":26.362477865252743},"GB2-03":{"attempts":3,"playable":27.565320476118938,"score":27.565320476118938},"GB2-04":{"attempts":2,"playable":40.14386713584646,"score":40.14386713584646},"GB2-05":{"attempts":3,"playable":58.62095821911327,"score":58.62095821911327},"GB2-06":{"attempts":2,"playable":56.185128354043215,"score":56.185128354043215},"GB2-07":{"attempts":3,"playable":50.704573903596874,"score":50.704573903596874},"GB2-08":{"attempts":3,"playable":33.663517958979874,"score":33.663517958979874}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":37.63084530303482,"score":37.63084530303482},"GB2-02":{"attempts":1,"playable":41.27644872959395,"score":41.27644872959395},"GB2-03":{"attempts":1,"playable":35.78476058303959,"score":35.78476058303959},"GB2-04":{"attempts":1,"playable":38.368805481178505,"score":38.368805481178505},"GB2-05":{"attempts":1,"playable":72.73299598611037,"score":72.73299598611037},"GB2-06":{"attempts":1,"playable":66.18008090672201,"score":66.18008090672201},"GB2-07":{"attempts":1,"playable":51.16689243516006,"score":51.16689243516006},"GB2-08":{"attempts":1,"playable":30.717687831386364,"score":30.717687831386364}},"medium":{"GB2-01":{"attempts":1,"playable":20.571364240436278,"score":20.571364240436278},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":31.69971392103312,"score":31.69971392103312},"GB2-04":{"attempts":1,"playable":41.91892879051443,"score":41.91892879051443},"GB2-05":{"attempts":1,"playable":58.40394021649804,"score":58.40394021649804},"GB2-06":{"attempts":1,"playable":46.190175801364425,"score":46.190175801364425},"GB2-07":{"attempts":1,"playable":60.81858840928365,"score":60.81858840928365},"GB2-08":{"attempts":1,"playable":37.8235913715289,"score":37.8235913715289}},"none":{"GB2-01":{"attempts":1,"playable":68.14614916598542,"score":68.14614916598542},"GB2-02":{"attempts":1,"playable":37.81098486616427,"score":37.81098486616427},"GB2-03":{"attempts":1,"playable":15.211486924284099,"score":15.211486924284099},"GB2-05":{"attempts":1,"playable":44.7259384547314,"score":44.7259384547314},"GB2-07":{"attempts":1,"playable":40.128240866346914,"score":40.128240866346914},"GB2-08":{"attempts":1,"playable":32.44927467402435,"score":32.44927467402435}}},"id":"gpt-5","is_recent_addition":false,"last_measured_at":"2026-11-03T07:15:39Z","match_totals_all":{"draws":2259,"losses":5247,"wins":3528},"match_totals_tracks":{"highest":{"draws":1055,"losses":1747,"wins":1382},"medium":{"draws":646,"losses":1839,"wins":1201},"none":{"draws":558,"losses":1661,"wins":945}},"model_slug":"gpt-5","official_rank_by_reasoning":{"highest":47,"medium":60,"none":42},"overall":{"max":72.73299598611037,"mean":41.218649442038874,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":50,"overall_ranking_status":"partial","per_game":{"GB2-01":37.63084530303482,"GB2-02":41.27644872959395,"GB2-03":35.78476058303959,"GB2-04":38.368805481178505,"GB2-05":72.73299598611037,"GB2-06":66.18008090672201,"GB2-07":51.16689243516006,"GB2-08":30.717687831386364},"per_game_all":{"GB2-01":42.11611956981884,"GB2-03":27.565320476118938,"GB2-05":58.62095821911327,"GB2-07":50.704573903596874,"GB2-08":33.663517958979874},"per_game_match_totals_all":{"GB2-01":{"draws":219,"losses":808,"wins":549},"GB2-02":{"draws":719,"losses":252,"wins":21},"GB2-03":{"draws":430,"losses":936,"wins":176},"GB2-04":{"draws":590,"losses":329,"wins":101},"GB2-05":{"draws":0,"losses":674,"wins":954},"GB2-06":{"draws":18,"losses":458,"wins":554},"GB2-07":{"draws":0,"losses":831,"wins":791},"GB2-08":{"draws":283,"losses":959,"wins":382}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":91,"losses":284,"wins":151},"GB2-02":{"draws":366,"losses":114,"wins":16},"GB2-03":{"draws":155,"losses":266,"wins":93},"GB2-04":{"draws":328,"losses":157,"wins":25},"GB2-05":{"draws":0,"losses":149,"wins":395},"GB2-06":{"draws":4,"losses":177,"wins":333},"GB2-07":{"draws":0,"losses":274,"wins":266},"GB2-08":{"draws":111,"losses":326,"wins":103}},"medium":{"GB2-01":{"draws":64,"losses":388,"wins":74},"GB2-03":{"draws":200,"losses":262,"wins":50},"GB2-04":{"draws":262,"losses":172,"wins":76},"GB2-05":{"draws":0,"losses":226,"wins":316},"GB2-06":{"draws":14,"losses":281,"wins":221},"GB2-07":{"draws":0,"losses":219,"wins":321},"GB2-08":{"draws":106,"losses":291,"wins":143}},"none":{"GB2-01":{"draws":64,"losses":136,"wins":324},"GB2-02":{"draws":353,"losses":138,"wins":5},"GB2-03":{"draws":75,"losses":408,"wins":33},"GB2-05":{"draws":0,"losses":299,"wins":243},"GB2-07":{"draws":0,"losses":338,"wins":204},"GB2-08":{"draws":66,"losses":342,"wins":136}}},"per_game_raw_elo_all":{"GB2-01":1403.9638515827298,"GB2-03":1226.6322270910766,"GB2-05":1581.1092623581005,"GB2-07":1454.9297907225837,"GB2-08":1203.2077371510625},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1366.685849804085,"GB2-02":1408.5386775781728,"GB2-03":1314.1751762940387,"GB2-04":1385.697638815819,"GB2-05":1796.360256582805,"GB2-06":1732.2983326860192,"GB2-07":1459.2464112015139,"GB2-08":1167.589284687473},"medium":{"GB2-01":1173.4955353382354,"GB2-03":1276.314815428222,"GB2-04":1414.1195157209438,"GB2-05":1563.1305348454005,"GB2-06":1395.151698332209,"GB2-07":1589.9845092028338,"GB2-08":1253.5228471116648},"none":{"GB2-01":1671.7101696058687,"GB2-02":1380.938814103395,"GB2-03":1089.4066895509688,"GB2-05":1383.8369956460954,"GB2-07":1315.5584517634031,"GB2-08":1188.51107965405}},"per_game_tracks":{"highest":{"GB2-01":37.63084530303482,"GB2-02":41.27644872959395,"GB2-03":35.78476058303959,"GB2-04":38.368805481178505,"GB2-05":72.73299598611037,"GB2-06":66.18008090672201,"GB2-07":51.16689243516006,"GB2-08":30.717687831386364},"medium":{"GB2-01":20.571364240436278,"GB2-03":31.69971392103312,"GB2-04":41.91892879051443,"GB2-05":58.40394021649804,"GB2-06":46.190175801364425,"GB2-07":60.81858840928365,"GB2-08":37.8235913715289},"none":{"GB2-01":68.14614916598542,"GB2-02":37.81098486616427,"GB2-03":15.211486924284099,"GB2-05":44.7259384547314,"GB2-07":40.128240866346914,"GB2-08":32.44927467402435}},"program_outcomes":{"all":{"counted_attempts":22,"failed":1,"infra_excluded":0,"success_rate":0.9545454545454546,"too_slow":2,"worked_after_repair":5,"worked_first_time":16,"working":21},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":1,"worked_first_time":6,"working":7},"none":{"counted_attempts":6,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":2,"worked_after_repair":2,"worked_first_time":4,"working":6}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":46.732314657028205,"medium":37.17828784383236,"none":39.745345825256074},"reasoning_agg":{"highest":{"max":72.73299598611037,"mean":46.732314657028205,"min":30.717687831386364},"medium":{"max":60.81858840928365,"mean":37.17828784383236,"min":0.0},"none":{"max":68.14614916598542,"mean":39.745345825256074,"min":15.211486924284099}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":9.554026813195847},"working_program_strength":{"all":42.98904410126898,"highest":46.732314657028205,"medium":42.489471821522685,"none":39.745345825256074}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-luna:61e59d89d21ca0b8","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":0.24666659999999999},"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":0.05054444999999999},"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":0.05054444999999999},"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":0.24666659999999999}},"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":40.1338335922781,"highest":53.950211564540226,"medium":42.14815610245931,"none":24.303133109834754},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":49.484846053250514,"score":49.484846053250514},"GB2-02":{"attempts":3,"playable":42.83383292721137,"score":42.83383292721137},"GB2-03":{"attempts":3,"playable":36.92306064331968,"score":36.92306064331968},"GB2-04":{"attempts":3,"playable":40.62125737673505,"score":40.62125737673505},"GB2-05":{"attempts":3,"playable":37.77095829937307,"score":37.77095829937307},"GB2-06":{"attempts":3,"playable":49.406425804198044,"score":49.406425804198044},"GB2-07":{"attempts":3,"playable":37.566710583334164,"score":37.566710583334164},"GB2-08":{"attempts":3,"playable":26.463577050802915,"score":26.463577050802915}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":79.3983468079422,"score":79.3983468079422},"GB2-02":{"attempts":1,"playable":43.921965509386,"score":43.921965509386},"GB2-03":{"attempts":1,"playable":40.16167676241293,"score":40.16167676241293},"GB2-04":{"attempts":1,"playable":37.75235122528156,"score":37.75235122528156},"GB2-05":{"attempts":1,"playable":48.352992819100315,"score":48.352992819100315},"GB2-06":{"attempts":1,"playable":80.67886797293676,"score":80.67886797293676},"GB2-07":{"attempts":1,"playable":70.5655023354348,"score":70.5655023354348},"GB2-08":{"attempts":1,"playable":30.769989083827255,"score":30.769989083827255}},"medium":{"GB2-01":{"attempts":1,"playable":44.123665418836175,"score":44.123665418836175},"GB2-02":{"attempts":1,"playable":42.69665276108793,"score":42.69665276108793},"GB2-03":{"attempts":1,"playable":41.925817780364845,"score":41.925817780364845},"GB2-04":{"attempts":1,"playable":46.505931601607,"score":46.505931601607},"GB2-05":{"attempts":1,"playable":41.939353461791896,"score":41.939353461791896},"GB2-06":{"attempts":1,"playable":51.22537458284066,"score":51.22537458284066},"GB2-07":{"attempts":1,"playable":27.673159445144762,"score":27.673159445144762},"GB2-08":{"attempts":1,"playable":41.0952937680013,"score":41.0952937680013}},"none":{"GB2-01":{"attempts":1,"playable":24.932525932973153,"score":24.932525932973153},"GB2-02":{"attempts":1,"playable":41.88288051116017,"score":41.88288051116017},"GB2-03":{"attempts":1,"playable":28.681687387181253,"score":28.681687387181253},"GB2-04":{"attempts":1,"playable":37.6054893033166,"score":37.6054893033166},"GB2-05":{"attempts":1,"playable":23.020528617227004,"score":23.020528617227004},"GB2-06":{"attempts":1,"playable":16.315034856816705,"score":16.315034856816705},"GB2-07":{"attempts":1,"playable":14.461469969422938,"score":14.461469969422938},"GB2-08":{"attempts":1,"playable":7.525448300580191,"score":7.525448300580191}}},"id":"gpt-5.6-luna","is_recent_addition":false,"last_measured_at":"2026-11-03T07:14:48Z","match_totals_all":{"draws":3186,"losses":6078,"wins":3288},"match_totals_tracks":{"highest":{"draws":1029,"losses":1446,"wins":1707},"medium":{"draws":1078,"losses":1947,"wins":1163},"none":{"draws":1079,"losses":2685,"wins":418}},"model_slug":"gpt-5-6-luna","official_rank_by_reasoning":{"highest":41,"medium":52,"none":79},"overall":{"max":80.67886797293676,"mean":40.1338335922781,"min":7.525448300580191},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":51,"overall_ranking_status":"ranked","per_game":{"GB2-01":79.3983468079422,"GB2-02":43.921965509386,"GB2-03":40.16167676241293,"GB2-04":37.75235122528156,"GB2-05":48.352992819100315,"GB2-06":80.67886797293676,"GB2-07":70.5655023354348,"GB2-08":30.769989083827255},"per_game_all":{"GB2-01":49.484846053250514,"GB2-02":42.83383292721137,"GB2-03":36.92306064331968,"GB2-04":40.62125737673505,"GB2-05":37.77095829937307,"GB2-06":49.406425804198044,"GB2-07":37.566710583334164,"GB2-08":26.463577050802915},"per_game_match_totals_all":{"GB2-01":{"draws":174,"losses":713,"wins":689},"GB2-02":{"draws":1149,"losses":292,"wins":43},"GB2-03":{"draws":591,"losses":714,"wins":233},"GB2-04":{"draws":965,"losses":450,"wins":123},"GB2-05":{"draws":0,"losses":1010,"wins":616},"GB2-06":{"draws":62,"losses":768,"wins":712},"GB2-07":{"draws":0,"losses":1040,"wins":584},"GB2-08":{"draws":245,"losses":1091,"wins":288}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":109,"wins":417},"GB2-02":{"draws":360,"losses":103,"wins":31},"GB2-03":{"draws":216,"losses":212,"wins":84},"GB2-04":{"draws":298,"losses":175,"wins":37},"GB2-05":{"draws":0,"losses":279,"wins":263},"GB2-06":{"draws":35,"losses":83,"wins":396},"GB2-07":{"draws":0,"losses":163,"wins":379},"GB2-08":{"draws":120,"losses":322,"wins":100}},"medium":{"GB2-01":{"draws":68,"losses":260,"wins":196},"GB2-02":{"draws":393,"losses":94,"wins":9},"GB2-03":{"draws":159,"losses":233,"wins":122},"GB2-04":{"draws":353,"losses":106,"wins":57},"GB2-05":{"draws":0,"losses":314,"wins":228},"GB2-06":{"draws":16,"losses":253,"wins":245},"GB2-07":{"draws":0,"losses":405,"wins":137},"GB2-08":{"draws":89,"losses":282,"wins":169}},"none":{"GB2-01":{"draws":106,"losses":344,"wins":76},"GB2-02":{"draws":396,"losses":95,"wins":3},"GB2-03":{"draws":216,"losses":269,"wins":27},"GB2-04":{"draws":314,"losses":169,"wins":29},"GB2-05":{"draws":0,"losses":417,"wins":125},"GB2-06":{"draws":11,"losses":432,"wins":71},"GB2-07":{"draws":0,"losses":472,"wins":68},"GB2-08":{"draws":36,"losses":487,"wins":19}}},"per_game_raw_elo_all":{"GB2-01":1491.0649385228373,"GB2-02":1420.7751010305421,"GB2-03":1323.249825251388,"GB2-04":1403.5096436970987,"GB2-05":1281.544588694721,"GB2-06":1465.333935484345,"GB2-07":1268.6931650771478,"GB2-08":1087.3606604434192},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1813.6702598575948,"GB2-02":1429.3018765248128,"GB2-03":1353.4774862406236,"GB2-04":1380.6993308480535,"GB2-05":1430.5438627060166,"GB2-06":2009.2055869379053,"GB2-07":1736.5175200344972,"GB2-08":1168.222753478902},"medium":{"GB2-01":1430.5439279708778,"GB2-02":1419.7078495343264,"GB2-03":1369.1250322329627,"GB2-04":1450.3244414892717,"GB2-05":1347.5782000678914,"GB2-06":1475.6919884167517,"GB2-07":1146.5921037817493,"GB2-08":1293.9162953113325},"none":{"GB2-01":1228.9806277400396,"GB2-02":1413.3155770324875,"GB2-03":1247.1469572805784,"GB2-04":1379.505158753971,"GB2-05":1066.5117033102545,"GB2-06":911.104231098378,"GB2-07":922.9698714151971,"GB2-08":799.942932540023}},"per_game_tracks":{"highest":{"GB2-01":79.3983468079422,"GB2-02":43.921965509386,"GB2-03":40.16167676241293,"GB2-04":37.75235122528156,"GB2-05":48.352992819100315,"GB2-06":80.67886797293676,"GB2-07":70.5655023354348,"GB2-08":30.769989083827255},"medium":{"GB2-01":44.123665418836175,"GB2-02":42.69665276108793,"GB2-03":41.925817780364845,"GB2-04":46.505931601607,"GB2-05":41.939353461791896,"GB2-06":51.22537458284066,"GB2-07":27.673159445144762,"GB2-08":41.0952937680013},"none":{"GB2-01":24.932525932973153,"GB2-02":41.88288051116017,"GB2-03":28.681687387181253,"GB2-04":37.6054893033166,"GB2-05":23.020528617227004,"GB2-06":16.315034856816705,"GB2-07":14.461469969422938,"GB2-08":7.525448300580191}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":23,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T17:01:37Z","reasoning":{"highest":53.950211564540226,"medium":42.14815610245931,"none":24.303133109834754},"reasoning_agg":{"highest":{"max":80.67886797293676,"mean":53.950211564540226,"min":30.769989083827255},"medium":{"max":51.22537458284066,"mean":42.14815610245931,"min":27.673159445144762},"none":{"max":41.88288051116017,"mean":24.303133109834754,"min":7.525448300580191}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":29.647078454705472},"working_program_strength":{"all":40.1338335922781,"highest":53.950211564540226,"medium":42.14815610245931,"none":24.303133109834754}},{"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3-1-flash:c73463359f716332","codegen_cost_by_reasoning":{"highest":{"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":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0},"medium":{"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":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0},"none":{"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-2026-10-09":11},"recorded_attempt_count":11,"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":12},"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-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0},"historical-provider-setting-baseline":{"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-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.0},"historical-provider-setting-intensive":{"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":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":35},"recorded_attempt_count":35,"run_count":24,"total":0.0},"codegen_latency_ms":{"attempt_count":35,"max_ms":926386,"mean_ms":167464.70833333334,"min_ms":7440,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":12,"max_ms":926386,"mean_ms":393879.0,"min_ms":180915,"run_count":8},"medium":{"attempt_count":12,"max_ms":181663,"mean_ms":86858.125,"min_ms":40176,"run_count":8},"none":{"attempt_count":11,"max_ms":29718,"mean_ms":21657.0,"min_ms":7440,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":73160,"output_mean":16631.416666666668,"output_min":1375,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":12,"output_max":73160,"output_mean":36727.625,"output_min":23210,"run_count":8},"medium":{"attempt_count":12,"output_max":16723,"output_mean":9745.875,"output_min":4629,"run_count":8},"none":{"attempt_count":11,"output_max":6152,"output_mean":3420.75,"output_min":1375,"run_count":8}},"display_name":"Minimax M3.1 Flash","economics":{"all":36.53205590483095,"highest":38.50536305457022,"medium":40.83895879365829,"none":30.25184586626433},"economics_best_value":{"per_model":{"all":true,"highest":true}},"first_seen_at":null,"game_gaps":{"highest":{"GB2-08":"failed"},"medium":{"GB2-02":"failed"},"none":{"GB2-08":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":35,"effective_max_output_tokens":[524288],"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,"requested_max_output_token_observations":35,"requested_max_output_tokens":[524288],"total_output_tokens":399154,"total_reasoning_output_tokens":282019,"total_visible_output_tokens":117135,"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":524288,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"minimax","provider_model":"minimax/minimax-m3.1-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":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":{"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},"baseline":{"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},"intensive":{"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}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":36.388971610601196,"score":36.388971610601196},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":40.483794170113896,"score":26.989196113409264},"GB2-03":{"attempts":3,"playable":33.59417887892669,"score":33.59417887892669},"GB2-04":{"attempts":3,"playable":38.83535559682418,"score":38.83535559682418},"GB2-05":{"attempts":3,"playable":46.375448852389354,"score":46.375448852389354},"GB2-06":{"attempts":3,"playable":48.11039706950612,"score":48.11039706950612},"GB2-07":{"attempts":3,"playable":53.01796899947241,"score":53.01796899947241},"GB2-08":{"attempts":3,"failed_attempts":2,"playable":26.8347903525551,"score":8.944930117518366}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":13.95293409060998,"score":13.95293409060998},"GB2-02":{"attempts":1,"playable":40.11485739631283,"score":40.11485739631283},"GB2-03":{"attempts":1,"playable":47.2100048249685,"score":47.2100048249685},"GB2-04":{"attempts":1,"playable":39.06154495333061,"score":39.06154495333061},"GB2-05":{"attempts":1,"playable":69.66776312412378,"score":69.66776312412378},"GB2-06":{"attempts":1,"playable":29.741198071028403,"score":29.741198071028403},"GB2-07":{"attempts":1,"playable":68.29460197618764,"score":68.29460197618764},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"medium":{"GB2-01":{"attempts":1,"playable":66.17951480087385,"score":66.17951480087385},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":30.801913814647886,"score":30.801913814647886},"GB2-04":{"attempts":1,"playable":37.78915086806535,"score":37.78915086806535},"GB2-05":{"attempts":1,"playable":47.684800657242334,"score":47.684800657242334},"GB2-06":{"attempts":1,"playable":48.31690773281683,"score":48.31690773281683},"GB2-07":{"attempts":1,"playable":69.104592123065,"score":69.104592123065},"GB2-08":{"attempts":1,"playable":26.8347903525551,"score":26.8347903525551}},"none":{"GB2-01":{"attempts":1,"playable":29.034465940319755,"score":29.034465940319755},"GB2-02":{"attempts":1,"playable":40.852730943914956,"score":40.852730943914956},"GB2-03":{"attempts":1,"playable":22.77061799716369,"score":22.77061799716369},"GB2-04":{"attempts":1,"playable":39.65537096907659,"score":39.65537096907659},"GB2-05":{"attempts":1,"playable":21.773782775801934,"score":21.773782775801934},"GB2-06":{"attempts":1,"playable":66.27308540467311,"score":66.27308540467311},"GB2-07":{"attempts":1,"playable":21.654712899164604,"score":21.654712899164604},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"minimax/minimax-m3.1-flash","is_recent_addition":false,"last_measured_at":"2026-11-03T08:05:57Z","match_totals_all":{"draws":2253,"losses":5382,"wins":3329},"match_totals_tracks":{"highest":{"draws":799,"losses":1672,"wins":1163},"medium":{"draws":519,"losses":1748,"wins":1429},"none":{"draws":935,"losses":1962,"wins":737}},"model_slug":"minimax-minimax-m3-1-flash","official_rank_by_reasoning":{"highest":53,"medium":55,"none":62},"overall":{"max":69.66776312412378,"mean":36.53205590483095,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["unknown_capability_evidence"],"overall_official_rank":52,"overall_ranking_status":"partial","per_game":{"GB2-01":13.95293409060998,"GB2-02":40.11485739631283,"GB2-03":47.2100048249685,"GB2-04":39.06154495333061,"GB2-05":69.66776312412378,"GB2-06":29.741198071028403,"GB2-07":68.29460197618764},"per_game_all":{"GB2-01":36.388971610601196,"GB2-03":33.59417887892669,"GB2-04":38.83535559682418,"GB2-05":46.375448852389354,"GB2-06":48.11039706950612,"GB2-07":53.01796899947241},"per_game_match_totals_all":{"GB2-01":{"draws":147,"losses":936,"wins":495},"GB2-02":{"draws":738,"losses":229,"wins":17},"GB2-03":{"draws":399,"losses":858,"wins":279},"GB2-04":{"draws":950,"losses":482,"wins":100},"GB2-05":{"draws":0,"losses":872,"wins":754},"GB2-06":{"draws":19,"losses":818,"wins":707},"GB2-07":{"draws":0,"losses":783,"wins":837},"GB2-08":{"draws":0,"losses":404,"wins":140}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":26,"losses":444,"wins":58},"GB2-02":{"draws":353,"losses":123,"wins":14},"GB2-03":{"draws":97,"losses":234,"wins":177},"GB2-04":{"draws":317,"losses":160,"wins":35},"GB2-05":{"draws":0,"losses":165,"wins":377},"GB2-06":{"draws":6,"losses":370,"wins":138},"GB2-07":{"draws":0,"losses":176,"wins":364}},"medium":{"GB2-01":{"draws":92,"losses":133,"wins":301},"GB2-03":{"draws":117,"losses":311,"wins":88},"GB2-04":{"draws":298,"losses":176,"wins":38},"GB2-05":{"draws":0,"losses":284,"wins":260},"GB2-06":{"draws":12,"losses":269,"wins":233},"GB2-07":{"draws":0,"losses":171,"wins":369},"GB2-08":{"draws":0,"losses":404,"wins":140}},"none":{"GB2-01":{"draws":29,"losses":359,"wins":136},"GB2-02":{"draws":385,"losses":106,"wins":3},"GB2-03":{"draws":185,"losses":313,"wins":14},"GB2-04":{"draws":335,"losses":146,"wins":27},"GB2-05":{"draws":0,"losses":423,"wins":117},"GB2-06":{"draws":1,"losses":179,"wins":336},"GB2-07":{"draws":0,"losses":436,"wins":104}}},"per_game_raw_elo_all":{"GB2-01":1332.9191120961223,"GB2-03":1289.6564959234572,"GB2-04":1389.4497417784917,"GB2-05":1401.4953703284184,"GB2-06":1433.208219074302,"GB2-07":1489.271072860621},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1072.314684934191,"GB2-02":1399.3506816286858,"GB2-03":1415.9246097717028,"GB2-04":1391.288839378522,"GB2-05":1738.168974075077,"GB2-06":1136.6946601772588,"GB2-07":1700.2786410827039},"medium":{"GB2-01":1650.0612804583811,"GB2-03":1267.7649844400698,"GB2-04":1380.9983482350592,"GB2-05":1421.951925641529,"GB2-06":1428.9411054970533,"GB2-07":1713.016445371339,"GB2-08":1120.0229980719614},"none":{"GB2-01":1276.3813708957948,"GB2-02":1405.1933262972732,"GB2-03":1185.2798935585986,"GB2-04":1396.062037721894,"GB2-05":1044.3652112686495,"GB2-06":1733.9888915485938,"GB2-07":1054.518132127821}},"per_game_tracks":{"highest":{"GB2-01":13.95293409060998,"GB2-02":40.11485739631283,"GB2-03":47.2100048249685,"GB2-04":39.06154495333061,"GB2-05":69.66776312412378,"GB2-06":29.741198071028403,"GB2-07":68.29460197618764},"medium":{"GB2-01":66.17951480087385,"GB2-03":30.801913814647886,"GB2-04":37.78915086806535,"GB2-05":47.684800657242334,"GB2-06":48.31690773281683,"GB2-07":69.104592123065,"GB2-08":26.8347903525551},"none":{"GB2-01":29.034465940319755,"GB2-02":40.852730943914956,"GB2-03":22.77061799716369,"GB2-04":39.65537096907659,"GB2-05":21.773782775801934,"GB2-06":66.27308540467311,"GB2-07":21.654712899164604}},"program_outcomes":{"all":{"counted_attempts":24,"failed":3,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":7,"worked_first_time":14,"working":21},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":2,"worked_first_time":5,"working":7},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":2,"worked_first_time":5,"working":7}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":38.50536305457022,"medium":40.838958793658286,"none":30.25184586626433},"reasoning_agg":{"highest":{"max":69.66776312412378,"mean":38.50536305457022,"min":0.0},"medium":{"max":69.104592123065,"mean":40.838958793658286,"min":0.0},"none":{"max":66.27308540467311,"mean":30.25184586626433,"min":0.0}},"reasoning_labels":{"highest":"Xhigh","medium":"Medium","none":"Low"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":10.587112927393957},"working_program_strength":{"all":41.75092103409251,"highest":44.006129205223104,"medium":46.67309576418091,"none":34.573538132873516}},{"canonical_public_row_identity":"publication-row.v1:overall:bytedance-seed-seed-2-0-code:083de56cd94240a4","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":0.40576999999999996},"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":0.428104},"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":1.0014830000000001},"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":34.88035194514441,"highest":41.40081955702935,"medium":38.864628695420926,"none":24.375607582982944},"first_seen_at":null,"game_gaps":{"medium":{"GB2-07":"failed"},"none":{"GB2-02":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":37.12565374077562,"score":37.12565374077562},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":39.84721078699704,"score":26.564807191331358},"GB2-03":{"attempts":3,"playable":40.89633213861361,"score":40.89633213861361},"GB2-04":{"attempts":3,"playable":39.52473169450781,"score":39.52473169450781},"GB2-05":{"attempts":3,"playable":35.925011567370916,"score":35.925011567370916},"GB2-06":{"attempts":3,"playable":16.051066084494018,"score":16.051066084494018},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":36.533473495956265,"score":24.355648997304176},"GB2-08":{"attempts":3,"playable":58.59956414675776,"score":58.59956414675776}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":39.74041070707327,"score":39.74041070707327},"GB2-02":{"attempts":1,"playable":40.35342088460806,"score":40.35342088460806},"GB2-03":{"attempts":1,"playable":40.134049457815124,"score":40.134049457815124},"GB2-04":{"attempts":1,"playable":37.275720047119606,"score":37.275720047119606},"GB2-05":{"attempts":1,"playable":46.77499184121805,"score":46.77499184121805},"GB2-06":{"attempts":1,"playable":18.903321181589966,"score":18.903321181589966},"GB2-07":{"attempts":1,"playable":43.97164246959579,"score":43.97164246959579},"GB2-08":{"attempts":1,"playable":64.05299986721494,"score":64.05299986721494}},"medium":{"GB2-01":{"attempts":1,"playable":48.957834732698196,"score":48.957834732698196},"GB2-02":{"attempts":1,"playable":39.341000689386014,"score":39.341000689386014},"GB2-03":{"attempts":1,"playable":38.573704272573806,"score":38.573704272573806},"GB2-04":{"attempts":1,"playable":40.2280363654063,"score":40.2280363654063},"GB2-05":{"attempts":1,"playable":45.5686854261531,"score":45.5686854261531},"GB2-06":{"attempts":1,"playable":13.293112426401683,"score":13.293112426401683},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":84.9546556507483,"score":84.9546556507483}},"none":{"GB2-01":{"attempts":1,"playable":22.678715782555393,"score":22.678715782555393},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":43.98124268545188,"score":43.98124268545188},"GB2-04":{"attempts":1,"playable":41.070438670997525,"score":41.070438670997525},"GB2-05":{"attempts":1,"playable":15.431357434741589,"score":15.431357434741589},"GB2-06":{"attempts":1,"playable":15.956764645490404,"score":15.956764645490404},"GB2-07":{"attempts":1,"playable":29.095304522316734,"score":29.095304522316734},"GB2-08":{"attempts":1,"playable":26.791036922310035,"score":26.791036922310035}}},"id":"bytedance-seed/seed-2.0-code","is_recent_addition":false,"last_measured_at":"2026-11-03T07:05:19Z","match_totals_all":{"draws":2688,"losses":5933,"wins":2915},"match_totals_tracks":{"highest":{"draws":1135,"losses":1932,"wins":1119},"medium":{"draws":858,"losses":1621,"wins":1173},"none":{"draws":695,"losses":2380,"wins":623}},"model_slug":"bytedance-seed-seed-2-0-code","official_rank_by_reasoning":{"highest":52,"medium":59,"none":78},"overall":{"max":84.9546556507483,"mean":34.88035194514441,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":53,"overall_ranking_status":"ranked","per_game":{"GB2-01":39.74041070707327,"GB2-02":40.35342088460806,"GB2-03":40.134049457815124,"GB2-04":37.275720047119606,"GB2-05":46.77499184121805,"GB2-06":18.903321181589966,"GB2-07":43.97164246959579,"GB2-08":64.05299986721494},"per_game_all":{"GB2-01":37.12565374077562,"GB2-03":40.89633213861361,"GB2-04":39.52473169450781,"GB2-05":35.925011567370916,"GB2-06":16.051066084494018,"GB2-08":58.59956414675776},"per_game_match_totals_all":{"GB2-01":{"draws":406,"losses":800,"wins":380},"GB2-02":{"draws":730,"losses":243,"wins":17},"GB2-03":{"draws":349,"losses":776,"wins":413},"GB2-04":{"draws":991,"losses":450,"wins":89},"GB2-05":{"draws":0,"losses":1043,"wins":585},"GB2-06":{"draws":7,"losses":1320,"wins":223},"GB2-07":{"draws":0,"losses":712,"wins":370},"GB2-08":{"draws":205,"losses":589,"wins":838}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":213,"losses":212,"wins":101},"GB2-02":{"draws":370,"losses":116,"wins":8},"GB2-03":{"draws":136,"losses":252,"wins":124},"GB2-04":{"draws":317,"losses":168,"wins":25},"GB2-05":{"draws":0,"losses":288,"wins":254},"GB2-06":{"draws":2,"losses":426,"wins":88},"GB2-07":{"draws":0,"losses":316,"wins":226},"GB2-08":{"draws":97,"losses":154,"wins":293}},"medium":{"GB2-01":{"draws":72,"losses":236,"wins":222},"GB2-02":{"draws":360,"losses":127,"wins":9},"GB2-03":{"draws":105,"losses":278,"wins":133},"GB2-04":{"draws":319,"losses":153,"wins":40},"GB2-05":{"draws":0,"losses":294,"wins":248},"GB2-06":{"draws":2,"losses":451,"wins":61},"GB2-08":{"draws":0,"losses":82,"wins":460}},"none":{"GB2-01":{"draws":121,"losses":352,"wins":57},"GB2-03":{"draws":108,"losses":246,"wins":156},"GB2-04":{"draws":355,"losses":129,"wins":24},"GB2-05":{"draws":0,"losses":461,"wins":83},"GB2-06":{"draws":3,"losses":443,"wins":74},"GB2-07":{"draws":0,"losses":396,"wins":144},"GB2-08":{"draws":108,"losses":353,"wins":85}}},"per_game_raw_elo_all":{"GB2-01":1355.3299558401566,"GB2-03":1359.9528786578844,"GB2-04":1394.9471511146705,"GB2-05":1241.7354755398626,"GB2-06":904.7153041917403,"GB2-08":1614.6589694212526},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1387.690371494352,"GB2-02":1401.242171911306,"GB2-03":1353.231867799296,"GB2-04":1376.8187230702547,"GB2-05":1410.251562870504,"GB2-06":957.973837976425,"GB2-07":1365.4905059810037,"GB2-08":1639.58705925951},"medium":{"GB2-01":1477.199418631405,"GB2-02":1393.1971543075897,"GB2-03":1339.319365728422,"GB2-04":1400.6495717498058,"GB2-05":1394.7170241240967,"GB2-06":851.7986189466654,"GB2-08":2084.9112025998525},"none":{"GB2-01":1201.100077394713,"GB2-03":1387.3074024459352,"GB2-04":1407.3731585239516,"GB2-05":920.237839624987,"GB2-06":904.3734556521302,"GB2-07":1166.9590341205997,"GB2-08":1119.478646404396}},"per_game_tracks":{"highest":{"GB2-01":39.74041070707327,"GB2-02":40.35342088460806,"GB2-03":40.134049457815124,"GB2-04":37.275720047119606,"GB2-05":46.77499184121805,"GB2-06":18.903321181589966,"GB2-07":43.97164246959579,"GB2-08":64.05299986721494},"medium":{"GB2-01":48.957834732698196,"GB2-02":39.341000689386014,"GB2-03":38.573704272573806,"GB2-04":40.2280363654063,"GB2-05":45.5686854261531,"GB2-06":13.293112426401683,"GB2-08":84.9546556507483},"none":{"GB2-01":22.678715782555393,"GB2-03":43.98124268545188,"GB2-04":41.070438670997525,"GB2-05":15.431357434741589,"GB2-06":15.956764645490404,"GB2-07":29.095304522316734,"GB2-08":26.791036922310035}},"program_outcomes":{"all":{"counted_attempts":24,"failed":2,"infra_excluded":0,"success_rate":0.9166666666666666,"too_slow":0,"worked_after_repair":8,"worked_first_time":14,"working":22},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":5,"worked_first_time":2,"working":7},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7}},"provider_color":"#F44336","provider_company":"ByteDance","provider_key":"bytedance-seed","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-31T16:45:39Z","reasoning":{"highest":41.40081955702935,"medium":38.864628695420926,"none":24.375607582982944},"reasoning_agg":{"highest":{"max":64.05299986721494,"mean":41.40081955702935,"min":18.903321181589966},"medium":{"max":84.9546556507483,"mean":38.864628695420926,"min":0.0},"none":{"max":43.98124268545188,"mean":24.375607582982944,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":17.025211974046407},"working_program_strength":{"all":37.89179176792555,"highest":41.40081955702935,"medium":44.41671850905249,"none":27.857837237694792}},{"canonical_public_row_identity":"publication-row.v1:overall:o3:9ca1a99e9c27624e","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":0.08840575,"min":0.07737849999999999,"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":0.390976},"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":0.3451019999999999},"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":0.08840575,"min":0.07737849999999999,"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":3.6636299999999995},"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":34.59674409915596,"highest":30.49225361113981,"medium":32.748662240499044,"none":40.54931644582903},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"too_slow","GB2-04":"failed"},"medium":{"GB2-02":"failed","GB2-03":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":43.19030289242795,"score":38.339550811138075},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":42.071365315062124,"score":21.035682657531062},"GB2-03":{"attempts":6,"failed_attempts":4,"playable":37.54373456621224,"score":16.227387486526204},"GB2-04":{"attempts":6,"failed_attempts":4,"playable":41.6402107072614,"score":27.7601404715076},"GB2-05":{"attempts":6,"playable":45.706374594727926,"score":45.706374594727926},"GB2-06":{"attempts":6,"playable":42.24320733925282,"score":42.24320733925282},"GB2-07":{"attempts":6,"playable":45.711586894928764,"score":45.711586894928764},"GB2-08":{"attempts":6,"failed_attempts":1,"playable":40.29889894308118,"score":36.59783221976567}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":58.20902497547843,"score":43.65676873160882},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":35.20707556379447,"score":8.801768890948617},"GB2-04":{"attempts":4,"failed_attempts":4,"score":0.0},"GB2-05":{"attempts":4,"playable":46.42457716230654,"score":46.42457716230654},"GB2-06":{"attempts":4,"playable":39.477957853442135,"score":39.477957853442135},"GB2-07":{"attempts":4,"playable":41.77510212983302,"score":41.77510212983302},"GB2-08":{"attempts":4,"failed_attempts":1,"playable":44.41280067978605,"score":33.30960050983954}},"medium":{"GB2-01":{"attempts":1,"playable":35.1151235146734,"score":35.1151235146734},"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":40.14229197512933,"score":40.14229197512933},"GB2-05":{"attempts":1,"playable":42.00750609938173,"score":42.00750609938173},"GB2-06":{"attempts":1,"playable":42.55409142684448,"score":42.55409142684448},"GB2-07":{"attempts":1,"playable":57.30447731812895,"score":57.30447731812895},"GB2-08":{"attempts":1,"playable":44.86580758983446,"score":44.86580758983446}},"none":{"GB2-01":{"attempts":1,"playable":36.24676018713201,"score":36.24676018713201},"GB2-02":{"attempts":1,"playable":42.071365315062124,"score":42.071365315062124},"GB2-03":{"attempts":1,"playable":39.88039356863,"score":39.88039356863},"GB2-04":{"attempts":1,"playable":43.138129439393474,"score":43.138129439393474},"GB2-05":{"attempts":1,"playable":48.68704052249551,"score":48.68704052249551},"GB2-06":{"attempts":1,"playable":44.69757273747184,"score":44.69757273747184},"GB2-07":{"attempts":1,"playable":38.055181236824325,"score":38.055181236824325},"GB2-08":{"attempts":1,"playable":31.618088559623008,"score":31.618088559623008}}},"id":"o3","is_recent_addition":false,"last_measured_at":"2026-11-03T06:21:01Z","match_totals_all":{"draws":2072,"losses":9019,"wins":6369},"match_totals_tracks":{"highest":{"draws":475,"losses":5448,"wins":4185},"medium":{"draws":487,"losses":1576,"wins":1107},"none":{"draws":1110,"losses":1995,"wins":1077}},"model_slug":"o3","official_rank_by_reasoning":{"highest":62,"medium":68,"none":39},"overall":{"max":57.30447731812895,"mean":34.59674409915596,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":54,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.20902497547843,"GB2-03":35.20707556379447,"GB2-05":46.42457716230654,"GB2-06":39.477957853442135,"GB2-07":41.77510212983302,"GB2-08":44.41280067978605},"per_game_all":{"GB2-01":43.19030289242795,"GB2-05":45.706374594727926,"GB2-06":42.24320733925282,"GB2-07":45.711586894928764,"GB2-08":40.29889894308118},"per_game_match_totals_all":{"GB2-01":{"draws":306,"losses":1191,"wins":1135},"GB2-02":{"draws":389,"losses":99,"wins":8},"GB2-03":{"draws":265,"losses":533,"wins":224},"GB2-04":{"draws":598,"losses":309,"wins":111},"GB2-05":{"draws":0,"losses":1752,"wins":1500},"GB2-06":{"draws":33,"losses":1871,"wins":1180},"GB2-07":{"draws":0,"losses":1895,"wins":1347},"GB2-08":{"draws":481,"losses":1369,"wins":864}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":164,"losses":582,"wins":834},"GB2-03":{"draws":130,"losses":280,"wins":102},"GB2-05":{"draws":0,"losses":1160,"wins":1010},"GB2-06":{"draws":10,"losses":1281,"wins":767},"GB2-07":{"draws":0,"losses":1307,"wins":853},"GB2-08":{"draws":171,"losses":838,"wins":619}},"medium":{"GB2-01":{"draws":98,"losses":294,"wins":134},"GB2-04":{"draws":332,"losses":145,"wins":31},"GB2-05":{"draws":0,"losses":313,"wins":227},"GB2-06":{"draws":18,"losses":296,"wins":198},"GB2-07":{"draws":0,"losses":239,"wins":301},"GB2-08":{"draws":39,"losses":289,"wins":216}},"none":{"GB2-01":{"draws":44,"losses":315,"wins":167},"GB2-02":{"draws":389,"losses":99,"wins":8},"GB2-03":{"draws":135,"losses":253,"wins":122},"GB2-04":{"draws":266,"losses":164,"wins":80},"GB2-05":{"draws":0,"losses":279,"wins":263},"GB2-06":{"draws":5,"losses":294,"wins":215},"GB2-07":{"draws":0,"losses":349,"wins":193},"GB2-08":{"draws":271,"losses":242,"wins":29}}},"per_game_raw_elo_all":{"GB2-01":1420.902105609445,"GB2-05":1396.0173396854889,"GB2-06":1332.585933624121,"GB2-07":1388.497102578681,"GB2-08":1298.557423214634},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1568.8234136183382,"GB2-03":1308.9074529055513,"GB2-05":1404.7396717661009,"GB2-06":1288.2877736161427,"GB2-07":1335.7242468297045,"GB2-08":1375.146077123529},"medium":{"GB2-01":1341.1656015570138,"GB2-04":1399.9636025719162,"GB2-05":1348.4718459190885,"GB2-06":1337.886373348104,"GB2-07":1541.3284103518138,"GB2-08":1342.0465956140429},"none":{"GB2-01":1352.7173016529832,"GB2-02":1414.7978575416312,"GB2-03":1350.9757316257885,"GB2-04":1423.7767776813773,"GB2-05":1434.840501371277,"GB2-06":1371.5836539081163,"GB2-07":1288.4386505545249,"GB2-08":1178.47959690633}},"per_game_tracks":{"highest":{"GB2-01":58.20902497547843,"GB2-03":35.20707556379447,"GB2-05":46.42457716230654,"GB2-06":39.477957853442135,"GB2-07":41.77510212983302,"GB2-08":44.41280067978605},"medium":{"GB2-01":35.1151235146734,"GB2-04":40.14229197512933,"GB2-05":42.00750609938173,"GB2-06":42.55409142684448,"GB2-07":57.30447731812895,"GB2-08":44.86580758983446},"none":{"GB2-01":36.24676018713201,"GB2-02":42.071365315062124,"GB2-03":39.88039356863,"GB2-04":43.138129439393474,"GB2-05":48.68704052249551,"GB2-06":44.69757273747184,"GB2-07":38.055181236824325,"GB2-08":31.618088559623008}},"program_outcomes":{"all":{"counted_attempts":44,"failed":11,"infra_excluded":0,"success_rate":0.75,"too_slow":4,"worked_after_repair":1,"worked_first_time":32,"working":33},"highest":{"counted_attempts":28,"failed":9,"infra_excluded":0,"success_rate":0.6785714285714286,"too_slow":4,"worked_after_repair":0,"worked_first_time":19,"working":19},"medium":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":0,"worked_first_time":6,"working":6},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-4,"rank_movement_baseline_at":"2026-10-31T17:14:21Z","reasoning":{"highest":30.492253611139812,"medium":32.748662240499044,"none":40.54931644582903},"reasoning_agg":{"highest":{"max":46.42457716230654,"mean":30.492253611139812,"min":0.0},"medium":{"max":57.30447731812895,"mean":32.748662240499044,"min":0.0},"none":{"max":48.68704052249551,"mean":40.54931644582903,"min":31.618088559623008}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.057062834689216},"working_program_strength":{"all":42.82176305353372,"highest":44.2510897274401,"medium":43.66488298733206,"none":40.54931644582903}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-flash:4a7f433abdec3d0b","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":0.058475471099999995},"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":0.09094043001999999},"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":0.01067159692}},"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":0.039967099359999994},"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":0.050973330659999996},"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":0.010671596920000002},"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":0.058475471099999995}},"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":33.5596515420782,"highest":36.272204503223314,"medium":33.640589100991015,"none":30.766161022020263},"first_seen_at":null,"game_gaps":{"highest":{"GB2-05":"failed"},"none":{"GB2-04":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":23.731008885078282,"score":23.731008885078282},"GB2-02":{"attempts":5,"playable":40.52693843390144,"score":40.52693843390144},"GB2-03":{"attempts":4,"playable":36.36833632562437,"score":36.36833632562437},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":40.30409358350802,"score":26.86939572233868},"GB2-05":{"attempts":5,"failed_attempts":1,"playable":33.31635820520334,"score":22.21090547013556},"GB2-06":{"attempts":5,"playable":52.32027026663217,"score":52.32027026663217},"GB2-07":{"attempts":5,"playable":27.16401574258632,"score":27.16401574258632},"GB2-08":{"attempts":5,"playable":39.286341490328745,"score":39.286341490328745}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":15.000249663574525,"score":15.000249663574525},"GB2-02":{"attempts":1,"playable":41.68813640769421,"score":41.68813640769421},"GB2-03":{"attempts":1,"playable":32.86825954965582,"score":32.86825954965582},"GB2-04":{"attempts":1,"playable":40.750324365399116,"score":40.750324365399116},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":79.39893274716044,"score":79.39893274716044},"GB2-07":{"attempts":1,"playable":37.97142991816576,"score":37.97142991816576},"GB2-08":{"attempts":1,"playable":42.500303374136614,"score":42.500303374136614}},"medium":{"GB2-01":{"attempts":3,"playable":36.36108003565934,"score":36.36108003565934},"GB2-02":{"attempts":3,"playable":38.93814211543613,"score":38.93814211543613},"GB2-03":{"attempts":2,"playable":42.67566742913436,"score":42.67566742913436},"GB2-04":{"attempts":2,"playable":39.85786280161692,"score":39.85786280161692},"GB2-05":{"attempts":3,"playable":23.840817595086445,"score":23.840817595086445},"GB2-06":{"attempts":3,"playable":24.219395767483217,"score":24.219395767483217},"GB2-07":{"attempts":3,"playable":24.832542022970284,"score":24.832542022970284},"GB2-08":{"attempts":3,"playable":38.399205040541425,"score":38.399205040541425}},"none":{"GB2-01":{"attempts":1,"playable":19.83169695600098,"score":19.83169695600098},"GB2-02":{"attempts":1,"playable":40.954536778573996,"score":40.954536778573996},"GB2-03":{"attempts":1,"playable":33.56108199808292,"score":33.56108199808292},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":42.79189881532024,"score":42.79189881532024},"GB2-06":{"attempts":1,"playable":53.34248228525284,"score":53.34248228525284},"GB2-07":{"attempts":1,"playable":18.688075286622915,"score":18.688075286622915},"GB2-08":{"attempts":1,"playable":36.95951605630819,"score":36.95951605630819}}},"id":"deepseek/deepseek-v4-flash","is_recent_addition":false,"last_measured_at":"2026-11-03T06:43:34Z","match_totals_all":{"draws":4222,"losses":10405,"wins":4217},"match_totals_tracks":{"highest":{"draws":1034,"losses":1672,"wins":940},"medium":{"draws":2483,"losses":6651,"wins":2396},"none":{"draws":705,"losses":2082,"wins":881}},"model_slug":"deepseek-deepseek-v4-flash","official_rank_by_reasoning":{"highest":54,"medium":66,"none":59},"overall":{"max":79.39893274716044,"mean":33.5596515420782,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":55,"overall_ranking_status":"ranked","per_game":{"GB2-01":15.000249663574525,"GB2-02":41.68813640769421,"GB2-03":32.86825954965582,"GB2-04":40.750324365399116,"GB2-06":79.39893274716044,"GB2-07":37.97142991816576,"GB2-08":42.500303374136614},"per_game_all":{"GB2-01":23.731008885078282,"GB2-02":40.52693843390144,"GB2-03":36.36833632562437,"GB2-06":52.32027026663217,"GB2-07":27.16401574258632,"GB2-08":39.28634149032874},"per_game_match_totals_all":{"GB2-01":{"draws":410,"losses":1679,"wins":541},"GB2-02":{"draws":1816,"losses":606,"wins":46},"GB2-03":{"draws":570,"losses":1044,"wins":440},"GB2-04":{"draws":992,"losses":444,"wins":102},"GB2-05":{"draws":0,"losses":1552,"wins":620},"GB2-06":{"draws":54,"losses":1522,"wins":994},"GB2-07":{"draws":0,"losses":2054,"wins":646},"GB2-08":{"draws":380,"losses":1504,"wins":828}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":107,"losses":396,"wins":23},"GB2-02":{"draws":353,"losses":119,"wins":24},"GB2-03":{"draws":145,"losses":284,"wins":83},"GB2-04":{"draws":296,"losses":161,"wins":53},"GB2-06":{"draws":35,"losses":90,"wins":391},"GB2-07":{"draws":0,"losses":349,"wins":191},"GB2-08":{"draws":98,"losses":273,"wins":175}},"medium":{"GB2-01":{"draws":191,"losses":915,"wins":472},"GB2-02":{"draws":1076,"losses":384,"wins":20},"GB2-03":{"draws":285,"losses":474,"wins":267},"GB2-04":{"draws":696,"losses":283,"wins":49},"GB2-05":{"draws":0,"losses":1243,"wins":387},"GB2-06":{"draws":14,"losses":1185,"wins":343},"GB2-07":{"draws":0,"losses":1254,"wins":366},"GB2-08":{"draws":221,"losses":913,"wins":492}},"none":{"GB2-01":{"draws":112,"losses":368,"wins":46},"GB2-02":{"draws":387,"losses":103,"wins":2},"GB2-03":{"draws":140,"losses":286,"wins":90},"GB2-05":{"draws":0,"losses":309,"wins":233},"GB2-06":{"draws":5,"losses":247,"wins":260},"GB2-07":{"draws":0,"losses":451,"wins":89},"GB2-08":{"draws":61,"losses":318,"wins":161}}},"per_game_raw_elo_all":{"GB2-01":1196.6256298731553,"GB2-02":1402.472908624609,"GB2-03":1318.9307857373512,"GB2-06":1507.2827695053102,"GB2-07":1125.0435536022485,"GB2-08":1275.6091307995173},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1090.2821222658854,"GB2-02":1411.7829003981722,"GB2-03":1287.3051139561987,"GB2-04":1404.8214306023438,"GB2-06":1983.2240465974733,"GB2-07":1287.3384818840752,"GB2-08":1311.6157698478025},"medium":{"GB2-01":1336.204762661055,"GB2-02":1389.6381034097951,"GB2-03":1375.7322183068354,"GB2-04":1397.6802141231046,"GB2-05":1035.023999302991,"GB2-06":1028.3922189492948,"GB2-07":1083.7027744121767,"GB2-08":1272.2133993274779},"none":{"GB2-01":1163.390004692525,"GB2-02":1405.9977220658604,"GB2-03":1293.75502494902,"GB2-05":1358.7291609783174,"GB2-06":1510.2320429691624,"GB2-07":1004.0894045104932,"GB2-08":1242.9982232232717}},"per_game_tracks":{"highest":{"GB2-01":15.000249663574525,"GB2-02":41.68813640769421,"GB2-03":32.86825954965582,"GB2-04":40.750324365399116,"GB2-06":79.39893274716044,"GB2-07":37.97142991816576,"GB2-08":42.500303374136614},"medium":{"GB2-01":36.361080035659334,"GB2-02":38.938142115436115,"GB2-03":42.67566742913436,"GB2-04":39.85786280161692,"GB2-05":23.840817595086445,"GB2-06":24.219395767483217,"GB2-07":24.832542022970284,"GB2-08":38.39920504054142},"none":{"GB2-01":19.83169695600098,"GB2-02":40.954536778573996,"GB2-03":33.56108199808292,"GB2-05":42.79189881532024,"GB2-06":53.34248228525284,"GB2-07":18.688075286622915,"GB2-08":36.95951605630819}},"program_outcomes":{"all":{"counted_attempts":38,"failed":2,"infra_excluded":2,"success_rate":0.9473684210526315,"too_slow":0,"worked_after_repair":11,"worked_first_time":25,"working":36},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7},"medium":{"counted_attempts":22,"failed":0,"infra_excluded":2,"success_rate":1.0,"too_slow":0,"worked_after_repair":7,"worked_first_time":15,"working":22},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":1,"worked_first_time":6,"working":7}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T15:55:37Z","reasoning":{"highest":36.272204503223314,"medium":33.640589100991015,"none":30.766161022020263},"reasoning_agg":{"highest":{"max":79.39893274716044,"mean":36.272204503223314,"min":0.0},"medium":{"max":42.67566742913436,"mean":33.640589100991015,"min":23.840817595086445},"none":{"max":53.34248228525284,"mean":30.766161022020263,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":5.506043481203051},"working_program_strength":{"all":36.75195466232789,"highest":41.453948003683784,"medium":33.640589100991015,"none":35.16132688230887}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-27b:9d4b0d52a83b422c","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":1.5655210449999999},"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":0.3584696499999999},"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":0.16881450499999998}},"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":0.16881450500000003},"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":2.0928052},"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":33.243434767266635,"highest":43.5913676271982,"medium":39.33051478977458,"none":16.808421884827126},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"failed","GB2-03":"failed"},"medium":{"GB2-08":"failed"},"none":{"GB2-04":"failed","GB2-05":"failed","GB2-07":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":49.382880633440486,"score":49.382880633440486},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":41.16298158248061,"score":27.441987721653742},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":44.64615441804776,"score":29.76410294536517},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":53.97648975627998,"score":35.984326504186654},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":56.18616773106855,"score":37.4574451540457},"GB2-06":{"attempts":3,"playable":37.42975347927842,"score":37.42975347927842},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":48.53140730737937,"score":32.35427153825291},"GB2-08":{"attempts":3,"failed_attempts":2,"playable":48.39813048573001,"score":16.13271016191}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":72.55463633532511,"score":72.55463633532511},"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":69.08896232502568,"score":69.08896232502568},"GB2-05":{"attempts":1,"playable":56.18616773106855,"score":56.18616773106855},"GB2-06":{"attempts":1,"playable":26.416266097498387,"score":26.416266097498387},"GB2-07":{"attempts":1,"playable":76.08677804293788,"score":76.08677804293788},"GB2-08":{"attempts":1,"playable":48.39813048573001,"score":48.39813048573001}},"medium":{"GB2-01":{"attempts":1,"playable":51.64437447714665,"score":51.64437447714665},"GB2-02":{"attempts":1,"playable":41.15406842713697,"score":41.15406842713697},"GB2-03":{"attempts":1,"playable":47.268165955567824,"score":47.268165955567824},"GB2-04":{"attempts":1,"playable":38.86401718753429,"score":38.86401718753429},"GB2-05":{"attempts":1,"playable":56.18616773106855,"score":56.18616773106855},"GB2-06":{"attempts":1,"playable":58.55128796792148,"score":58.55128796792148},"GB2-07":{"attempts":1,"playable":20.976036571820856,"score":20.976036571820856},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"playable":23.949631087849696,"score":23.949631087849696},"GB2-02":{"attempts":1,"playable":41.171894737824246,"score":41.171894737824246},"GB2-03":{"attempts":1,"playable":42.024142880527684,"score":42.024142880527684},"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":27.321706372415377,"score":27.321706372415377},"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":"2026-11-03T07:12:10Z","match_totals_all":{"draws":1913,"losses":3843,"wins":3108},"match_totals_tracks":{"highest":{"draws":235,"losses":1236,"wins":1705},"medium":{"draws":1026,"losses":1542,"wins":1076},"none":{"draws":652,"losses":1065,"wins":327}},"model_slug":"qwen-qwen3-8-27b","official_rank_by_reasoning":{"highest":51,"medium":57},"overall":{"max":76.08677804293788,"mean":33.243434767266635,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":56,"overall_ranking_status":"partial","per_game":{"GB2-01":72.55463633532511,"GB2-04":69.08896232502568,"GB2-05":56.18616773106855,"GB2-06":26.416266097498387,"GB2-07":76.08677804293788,"GB2-08":48.39813048573001},"per_game_all":{"GB2-01":49.382880633440486,"GB2-06":37.42975347927842},"per_game_match_totals_all":{"GB2-01":{"draws":278,"losses":662,"wins":636},"GB2-02":{"draws":771,"losses":208,"wins":9},"GB2-03":{"draws":288,"losses":451,"wins":285},"GB2-04":{"draws":472,"losses":248,"wins":302},"GB2-05":{"draws":0,"losses":474,"wins":610},"GB2-06":{"draws":45,"losses":970,"wins":529},"GB2-07":{"draws":0,"losses":570,"wins":512},"GB2-08":{"draws":59,"losses":260,"wins":225}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":10,"losses":140,"wins":376},"GB2-04":{"draws":153,"losses":87,"wins":268},"GB2-05":{"draws":0,"losses":237,"wins":305},"GB2-06":{"draws":13,"losses":381,"wins":120},"GB2-07":{"draws":0,"losses":131,"wins":411},"GB2-08":{"draws":59,"losses":260,"wins":225}},"medium":{"GB2-01":{"draws":121,"losses":195,"wins":210},"GB2-02":{"draws":386,"losses":104,"wins":4},"GB2-03":{"draws":180,"losses":194,"wins":138},"GB2-04":{"draws":319,"losses":161,"wins":34},"GB2-05":{"draws":0,"losses":237,"wins":305},"GB2-06":{"draws":20,"losses":212,"wins":284},"GB2-07":{"draws":0,"losses":439,"wins":101}},"none":{"GB2-01":{"draws":147,"losses":327,"wins":50},"GB2-02":{"draws":385,"losses":104,"wins":5},"GB2-03":{"draws":108,"losses":257,"wins":147},"GB2-06":{"draws":12,"losses":377,"wins":125}}},"per_game_raw_elo_all":{"GB2-01":1481.0371750987595,"GB2-06":1259.737261372254},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1722.9730383097653,"GB2-04":1641.4227435834314,"GB2-05":1532.8952907131213,"GB2-06":1083.547755989069,"GB2-07":1833.5390873741003,"GB2-08":1389.3339809825834},"medium":{"GB2-01":1503.1301847711918,"GB2-02":1407.573139323385,"GB2-03":1416.4420789719927,"GB2-04":1389.6971830730593,"GB2-05":1532.8952907131213,"GB2-06":1597.5572869738858,"GB2-07":1043.3472501853678},"none":{"GB2-01":1217.0083022153215,"GB2-02":1407.7138165447036,"GB2-03":1369.995526691472,"GB2-06":1098.1067411538072}},"per_game_tracks":{"highest":{"GB2-01":72.55463633532511,"GB2-04":69.08896232502568,"GB2-05":56.18616773106855,"GB2-06":26.416266097498387,"GB2-07":76.08677804293788,"GB2-08":48.39813048573001},"medium":{"GB2-01":51.64437447714665,"GB2-02":41.15406842713697,"GB2-03":47.268165955567824,"GB2-04":38.86401718753429,"GB2-05":56.18616773106855,"GB2-06":58.55128796792148,"GB2-07":20.976036571820856},"none":{"GB2-01":23.949631087849696,"GB2-02":41.171894737824246,"GB2-03":42.024142880527684,"GB2-06":27.321706372415377}},"program_outcomes":{"all":{"counted_attempts":24,"failed":7,"infra_excluded":0,"success_rate":0.7083333333333334,"too_slow":0,"worked_after_repair":6,"worked_first_time":11,"working":17},"highest":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":1,"worked_first_time":5,"working":6},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7},"none":{"counted_attempts":8,"failed":4,"infra_excluded":0,"success_rate":0.5,"too_slow":0,"worked_after_repair":2,"worked_first_time":2,"working":4}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":43.5913676271982,"medium":39.330514789774575,"none":16.808421884827126},"reasoning_agg":{"highest":{"max":76.08677804293788,"mean":43.5913676271982,"min":0.0},"medium":{"max":58.55128796792148,"mean":39.330514789774575,"min":0.0},"none":{"max":42.024142880527684,"mean":16.808421884827126,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":26.782945742371076},"working_program_strength":{"all":45.56260901077585,"highest":58.12182350293094,"medium":44.94915975974238,"none":33.61684376965425}},{"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:ec024dcd325d3c19","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":0.5047206500000001},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.034389,"mean":0.018099975,"median":0.0138747,"min":0.0097992,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.1447998},"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":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.034389,"mean":0.018099975,"median":0.0138747,"min":0.0097992,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.14479979999999998},"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":24,"cell_count":24,"cost_basis_counts":{"provider_reported":59},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.13485595000000003,"mean":0.027145690625,"median":0.018779375,"min":0.0097992,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":59,"run_count":33,"total":1.03871285},"codegen_latency_ms":{"attempt_count":45,"max_ms":622714,"mean_ms":75764.08333333333,"min_ms":17036,"run_count":24},"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":10,"max_ms":84713,"mean_ms":38203.875,"min_ms":17036,"run_count":8}},"codegen_output_tokens":{"attempt_count":45,"output_max":17712,"output_mean":6849.333333333333,"output_min":2187,"run_count":24},"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":10,"output_max":10037,"output_mean":4961.125,"output_min":2187,"run_count":8}},"display_name":"Nemotron 3 Ultra 550B A55B","economics":{"all":32.85288082847158,"highest":22.461867812086837,"medium":47.67966779831716,"none":28.41710687501075},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"failed","GB2-07":"failed"},"none":{"GB2-02":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[182520],"finish_reason_observations":45,"finish_reasons":["error","length","stop"],"indexed_attempts":45,"output_token_observations":45,"provider_post_attempt_observations":10,"provider_post_attempts":11,"reasoning_token_observations":10,"reconciliation_get_attempt_observations":10,"requested_max_output_token_observations":10,"requested_max_output_tokens":[182520],"total_output_tokens":164384,"total_reasoning_output_tokens":12817,"total_visible_output_tokens":26872,"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":"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":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":43.712399849124786,"score":39.69882474543477},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":41.064556318176955,"score":27.376370878784638},"GB2-03":{"attempts":4,"failed_attempts":2,"playable":40.68176248011296,"score":27.121174986741973},"GB2-04":{"attempts":3,"playable":41.949180608876354,"score":41.949180608876354},"GB2-05":{"attempts":4,"playable":57.1346386659803,"score":57.1346386659803},"GB2-06":{"attempts":3,"playable":27.452944004633604,"score":27.452944004633604},"GB2-07":{"attempts":5,"failed_attempts":3,"playable":21.045211352067074,"score":13.283543888719324},"GB2-08":{"attempts":4,"playable":28.80636884860172,"score":28.80636884860172}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":24.081450622140117,"score":12.040725311070059},"GB2-02":{"attempts":2,"playable":40.29221090564366,"score":40.29221090564366},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":1,"playable":40.13498842101576,"score":40.13498842101576},"GB2-05":{"attempts":2,"playable":28.46205067921619,"score":28.46205067921619},"GB2-06":{"attempts":1,"playable":31.99449386991976,"score":31.99449386991976},"GB2-07":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-08":{"attempts":2,"playable":26.770473309829274,"score":26.770473309829274}},"medium":{"GB2-01":{"attempts":1,"playable":54.17624856206973,"score":54.17624856206973},"GB2-02":{"attempts":1,"playable":41.83690173071026,"score":41.83690173071026},"GB2-03":{"attempts":1,"playable":52.5158095983415,"score":52.5158095983415},"GB2-04":{"attempts":1,"playable":44.57757911580546,"score":44.57757911580546},"GB2-05":{"attempts":1,"playable":84.16101207666127,"score":84.16101207666127},"GB2-06":{"attempts":1,"playable":35.30930246311465,"score":35.30930246311465},"GB2-07":{"attempts":1,"playable":37.6108406281818,"score":37.6108406281818},"GB2-08":{"attempts":1,"playable":31.24964821165265,"score":31.24964821165265}},"none":{"GB2-01":{"attempts":1,"playable":52.87950036316451,"score":52.87950036316451},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":28.84771536188442,"score":28.84771536188442},"GB2-04":{"attempts":1,"playable":41.13497428980782,"score":41.13497428980782},"GB2-05":{"attempts":1,"playable":58.78085324206344,"score":58.78085324206344},"GB2-06":{"attempts":1,"playable":15.055035680866395,"score":15.055035680866395},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":4.479582075952351,"score":2.2397910379761754},"GB2-08":{"attempts":1,"playable":28.398985024323242,"score":28.398985024323242}}},"id":"nvidia/nemotron-3-ultra-550b-a55b","is_recent_addition":false,"last_measured_at":"2026-11-03T08:07:17Z","match_totals_all":{"draws":2380,"losses":5165,"wins":2031},"match_totals_tracks":{"highest":{"draws":1419,"losses":2548,"wins":737},"medium":{"draws":260,"losses":448,"wins":472},"none":{"draws":701,"losses":2169,"wins":822}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","official_rank_by_reasoning":{"highest":64,"medium":43,"none":67},"overall":{"max":84.16101207666127,"mean":32.85288082847158,"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":{"GB2-01":24.081450622140117,"GB2-02":40.29221090564366,"GB2-04":40.13498842101576,"GB2-05":28.46205067921619,"GB2-06":31.99449386991976,"GB2-08":26.770473309829274},"per_game_all":{"GB2-01":43.712399849124786,"GB2-04":41.949180608876354,"GB2-05":57.1346386659803,"GB2-06":27.452944004633604,"GB2-08":28.80636884860172},"per_game_match_totals_all":{"GB2-01":{"draws":248,"losses":595,"wins":369},"GB2-02":{"draws":780,"losses":240,"wins":14},"GB2-03":{"draws":217,"losses":362,"wins":125},"GB2-04":{"draws":823,"losses":305,"wins":72},"GB2-05":{"draws":0,"losses":1027,"wins":791},"GB2-06":{"draws":16,"losses":817,"wins":227},"GB2-07":{"draws":0,"losses":711,"wins":131},"GB2-08":{"draws":296,"losses":1108,"wins":302}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":107,"losses":348,"wins":71},"GB2-02":{"draws":742,"losses":230,"wins":14},"GB2-04":{"draws":352,"losses":136,"wins":22},"GB2-05":{"draws":0,"losses":776,"wins":308},"GB2-06":{"draws":11,"losses":356,"wins":149},"GB2-08":{"draws":207,"losses":702,"wins":173}},"medium":{"GB2-01":{"draws":57,"losses":40,"wins":63},"GB2-02":{"draws":38,"losses":10,"wins":0},"GB2-03":{"draws":37,"losses":76,"wins":79},"GB2-04":{"draws":127,"losses":33,"wins":18},"GB2-05":{"draws":0,"losses":27,"wins":165},"GB2-06":{"draws":1,"losses":18,"wins":9},"GB2-07":{"draws":0,"losses":190,"wins":112},"GB2-08":{"draws":0,"losses":54,"wins":26}},"none":{"GB2-01":{"draws":84,"losses":207,"wins":235},"GB2-03":{"draws":180,"losses":286,"wins":46},"GB2-04":{"draws":344,"losses":136,"wins":32},"GB2-05":{"draws":0,"losses":224,"wins":318},"GB2-06":{"draws":4,"losses":443,"wins":69},"GB2-07":{"draws":0,"losses":521,"wins":19},"GB2-08":{"draws":89,"losses":352,"wins":103}}},"per_game_raw_elo_all":{"GB2-01":1420.4831090395999,"GB2-04":1414.310272895537,"GB2-05":1602.1541422466964,"GB2-06":1094.6247128119908,"GB2-08":1144.1329390153512},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1218.6299571545924,"GB2-02":1400.7156508438786,"GB2-04":1399.9051584447002,"GB2-05":1148.0426083667871,"GB2-06":1172.3312206226076,"GB2-08":1119.0312023472584},"medium":{"GB2-01":1527.719345083798,"GB2-02":1412.9538237469642,"GB2-03":1463.7379064362094,"GB2-04":1435.1385232265468,"GB2-05":2090.061531734711,"GB2-06":1224.4318359544623,"GB2-07":1282.5969963263294,"GB2-08":1174.026964886565},"none":{"GB2-01":1515.100024880409,"GB2-03":1248.7854337512981,"GB2-04":1407.8871370153643,"GB2-05":1568.3582866385916,"GB2-06":887.1110818589027,"GB2-07":619.1858268370235,"GB2-08":1139.3406498122301}},"per_game_tracks":{"highest":{"GB2-01":24.081450622140117,"GB2-02":40.29221090564366,"GB2-04":40.13498842101576,"GB2-05":28.46205067921619,"GB2-06":31.99449386991976,"GB2-08":26.770473309829274},"medium":{"GB2-01":54.17624856206973,"GB2-02":41.83690173071026,"GB2-03":52.5158095983415,"GB2-04":44.57757911580546,"GB2-05":84.16101207666127,"GB2-06":35.30930246311465,"GB2-07":37.6108406281818,"GB2-08":31.24964821165265},"none":{"GB2-01":52.87950036316451,"GB2-03":28.84771536188442,"GB2-04":41.13497428980782,"GB2-05":58.78085324206344,"GB2-06":15.055035680866395,"GB2-07":4.479582075952351,"GB2-08":28.398985024323242}},"program_outcomes":{"all":{"counted_attempts":31,"failed":7,"infra_excluded":2,"success_rate":0.7741935483870968,"too_slow":0,"worked_after_repair":11,"worked_first_time":13,"working":24},"highest":{"counted_attempts":14,"failed":5,"infra_excluded":2,"success_rate":0.6428571428571429,"too_slow":0,"worked_after_repair":7,"worked_first_time":2,"working":9},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":9,"failed":2,"infra_excluded":0,"success_rate":0.7777777777777778,"too_slow":0,"worked_after_repair":2,"worked_first_time":5,"working":7}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":22.461867812086837,"medium":47.67966779831716,"none":28.41710687501075},"reasoning_agg":{"highest":{"max":40.29221090564366,"mean":22.461867812086837,"min":0.0},"medium":{"max":84.16101207666127,"mean":47.67966779831716,"min":31.24964821165265},"none":{"max":58.78085324206344,"mean":28.41710687501075,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"medium"},"score_diagnostics":{"reasoning_variance":25.217799986230325},"working_program_strength":{"all":37.47742538422259,"highest":31.955944634627457,"medium":47.67966779831716,"none":32.79666371972316}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-space-bunny-alpha:4a1adab13c9db1f6","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":32.19270537564862,"highest":35.52175729368455,"medium":34.28723737297224,"none":26.76912146028908},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"failed","GB2-03":"failed"},"medium":{"GB2-08":"failed"},"none":{"GB2-01":"failed","GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":54.9334389854974,"score":36.62229265699827},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":40.96670024421248,"score":27.311133496141654},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":39.22623540062774,"score":26.150823600418494},"GB2-04":{"attempts":3,"playable":39.96810348470697,"score":39.96810348470697},"GB2-05":{"attempts":3,"playable":32.103495201011704,"score":32.103495201011704},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":45.626612154839506,"score":30.41774143655967},"GB2-07":{"attempts":3,"playable":44.21598522558295,"score":44.21598522558295},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":31.128101855653917,"score":20.752067903769277}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":62.78014212361902,"score":62.78014212361902},"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":37.58766527364797,"score":37.58766527364797},"GB2-05":{"attempts":1,"playable":43.15769752360819,"score":43.15769752360819},"GB2-06":{"attempts":1,"playable":35.93899889659201,"score":35.93899889659201},"GB2-07":{"attempts":1,"playable":72.26664946024567,"score":72.26664946024567},"GB2-08":{"attempts":1,"playable":32.44290507176351,"score":32.44290507176351}},"medium":{"GB2-01":{"attempts":1,"playable":47.08673584737578,"score":47.08673584737578},"GB2-02":{"attempts":1,"playable":41.67939507276384,"score":41.67939507276384},"GB2-03":{"attempts":1,"playable":43.941560798524826,"score":43.941560798524826},"GB2-04":{"attempts":1,"playable":39.85338935759843,"score":39.85338935759843},"GB2-05":{"attempts":1,"playable":11.838736928317353,"score":11.838736928317353},"GB2-06":{"attempts":1,"playable":55.314225413087,"score":55.314225413087},"GB2-07":{"attempts":1,"playable":34.58385556611069,"score":34.58385556611069},"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":40.254005415661126,"score":40.254005415661126},"GB2-03":{"attempts":1,"playable":34.510910002730654,"score":34.510910002730654},"GB2-04":{"attempts":1,"playable":42.463255822874515,"score":42.463255822874515},"GB2-05":{"attempts":1,"playable":41.31405115110956,"score":41.31405115110956},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":25.797450650392488,"score":25.797450650392488},"GB2-08":{"attempts":1,"playable":29.81329863954432,"score":29.81329863954432}}},"id":"stealth/space-bunny-alpha","is_recent_addition":false,"last_measured_at":"2026-11-03T07:14:45Z","match_totals_all":{"draws":2376,"losses":4852,"wins":2728},"match_totals_tracks":{"highest":{"draws":528,"losses":1429,"wins":1213},"medium":{"draws":920,"losses":1817,"wins":907},"none":{"draws":928,"losses":1606,"wins":608}},"model_slug":"stealth-space-bunny-alpha","official_rank_by_reasoning":{"highest":55,"medium":64,"none":74},"overall":{"max":72.26664946024567,"mean":32.19270537564862,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":58,"overall_ranking_status":"ranked","per_game":{"GB2-01":62.78014212361902,"GB2-04":37.58766527364797,"GB2-05":43.15769752360819,"GB2-06":35.93899889659201,"GB2-07":72.26664946024567,"GB2-08":32.44290507176351},"per_game_all":{"GB2-04":39.96810348470697,"GB2-05":32.103495201011704,"GB2-07":44.21598522558295},"per_game_match_totals_all":{"GB2-01":{"draws":249,"losses":354,"wins":453},"GB2-02":{"draws":766,"losses":215,"wins":11},"GB2-03":{"draws":224,"losses":536,"wins":262},"GB2-04":{"draws":944,"losses":466,"wins":118},"GB2-05":{"draws":0,"losses":1103,"wins":523},"GB2-06":{"draws":6,"losses":575,"wins":445},"GB2-07":{"draws":0,"losses":935,"wins":687},"GB2-08":{"draws":187,"losses":668,"wins":229}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":153,"losses":121,"wins":254},"GB2-04":{"draws":292,"losses":178,"wins":38},"GB2-05":{"draws":0,"losses":307,"wins":235},"GB2-06":{"draws":2,"losses":338,"wins":172},"GB2-07":{"draws":0,"losses":153,"wins":387},"GB2-08":{"draws":81,"losses":332,"wins":127}},"medium":{"GB2-01":{"draws":96,"losses":233,"wins":199},"GB2-02":{"draws":385,"losses":103,"wins":8},"GB2-03":{"draws":106,"losses":248,"wins":158},"GB2-04":{"draws":329,"losses":150,"wins":33},"GB2-05":{"draws":0,"losses":479,"wins":63},"GB2-06":{"draws":4,"losses":237,"wins":273},"GB2-07":{"draws":0,"losses":367,"wins":173}},"none":{"GB2-02":{"draws":381,"losses":112,"wins":3},"GB2-03":{"draws":118,"losses":288,"wins":104},"GB2-04":{"draws":323,"losses":138,"wins":47},"GB2-05":{"draws":0,"losses":317,"wins":225},"GB2-07":{"draws":0,"losses":415,"wins":127},"GB2-08":{"draws":106,"losses":336,"wins":102}}},"per_game_raw_elo_all":{"GB2-04":1398.481992472257,"GB2-05":1180.1197589987798,"GB2-07":1375.4406710543456},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1613.9832653359454,"GB2-04":1379.3601349531443,"GB2-05":1363.4963111821432,"GB2-06":1234.3013266875137,"GB2-07":1764.865673590421,"GB2-08":1188.4342586998962},"medium":{"GB2-01":1459.168849251975,"GB2-02":1411.714075521044,"GB2-03":1386.956462428127,"GB2-04":1397.6499869828237,"GB2-05":837.5037351274682,"GB2-06":1542.8667737158707,"GB2-07":1242.4228373762944},"none":{"GB2-02":1400.4542395495962,"GB2-03":1302.5261692124668,"GB2-04":1418.4358554808025,"GB2-05":1339.3592306867283,"GB2-07":1119.0335021963213,"GB2-08":1156.613349564109}},"per_game_tracks":{"highest":{"GB2-01":62.78014212361902,"GB2-04":37.58766527364797,"GB2-05":43.15769752360819,"GB2-06":35.93899889659201,"GB2-07":72.26664946024567,"GB2-08":32.44290507176351},"medium":{"GB2-01":47.08673584737578,"GB2-02":41.67939507276384,"GB2-03":43.941560798524826,"GB2-04":39.85338935759843,"GB2-05":11.838736928317353,"GB2-06":55.314225413087,"GB2-07":34.58385556611069},"none":{"GB2-02":40.254005415661126,"GB2-03":34.510910002730654,"GB2-04":42.463255822874515,"GB2-05":41.31405115110956,"GB2-07":25.797450650392488,"GB2-08":29.81329863954432}},"program_outcomes":{"all":{"counted_attempts":24,"failed":5,"infra_excluded":0,"success_rate":0.7916666666666666,"too_slow":0,"worked_after_repair":12,"worked_first_time":7,"working":19},"highest":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":5,"worked_first_time":1,"working":6},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":2,"worked_first_time":5,"working":7},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":5,"worked_first_time":1,"working":6}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T17:02:37Z","reasoning":{"highest":35.52175729368455,"medium":34.28723737297224,"none":26.76912146028908},"reasoning_agg":{"highest":{"max":72.26664946024567,"mean":35.52175729368455,"min":0.0},"medium":{"max":55.314225413087,"mean":34.28723737297224,"min":0.0},"none":{"max":42.463255822874515,"mean":26.76912146028908,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":8.75263583339547},"working_program_strength":{"all":40.746639715279294,"highest":47.36234305824607,"medium":39.185414140539706,"none":35.69216194705211}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash-lite:fcc83610427dff10","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":0.2715711}},"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":0.27157109999999995},"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":1.8519749},"codegen_latency_ms":{"attempt_count":132,"max_ms":115030,"mean_ms":50137.9375,"min_ms":13430,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":50,"max_ms":115030,"mean_ms":74972.3125,"min_ms":38302,"run_count":16},"medium":{"attempt_count":48,"max_ms":75176,"mean_ms":48761.1875,"min_ms":19840,"run_count":16},"none":{"attempt_count":34,"max_ms":54024,"mean_ms":26680.3125,"min_ms":13430,"run_count":16}},"codegen_output_tokens":{"attempt_count":132,"output_max":33866,"output_mean":12598.979166666666,"output_min":1476,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":50,"output_max":33866,"output_mean":21067.4375,"output_min":11641,"run_count":16},"medium":{"attempt_count":48,"output_max":19346,"output_mean":12054.5625,"output_min":4066,"run_count":16},"none":{"attempt_count":34,"output_max":9270,"output_mean":4674.9375,"output_min":1476,"run_count":16}},"display_name":"Gemini 3.5 Flash Lite","economics":{"all":31.336195834786782,"highest":31.26405423124908,"medium":25.474802777377196,"none":37.26973049573408},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":35.61017463033091,"score":30.020523245165112},"GB2-02":{"attempts":6,"failed_attempts":2,"playable":42.06924098870771,"score":27.620916985317834},"GB2-03":{"attempts":6,"failed_attempts":1,"playable":46.848665594303924,"score":38.01531601844365},"GB2-04":{"attempts":6,"playable":42.469982481145415,"score":42.469982481145415},"GB2-05":{"attempts":6,"playable":13.984524815495867,"score":13.984524815495867},"GB2-06":{"attempts":6,"playable":34.44205827770633,"score":34.44205827770633},"GB2-07":{"attempts":6,"failed_attempts":1,"playable":41.38570858542416,"score":37.93739209340473},"GB2-08":{"attempts":6,"playable":26.198852761615342,"score":26.198852761615342}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":33.537908310994794,"score":16.768954155497397},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":44.51053870794912,"score":22.25526935397456},"GB2-03":{"attempts":2,"playable":46.92891568699177,"score":46.92891568699177},"GB2-04":{"attempts":2,"playable":39.06201402844559,"score":39.06201402844559},"GB2-05":{"attempts":2,"playable":16.48881921714565,"score":16.48881921714565},"GB2-06":{"attempts":2,"playable":38.20170705091989,"score":38.20170705091989},"GB2-07":{"attempts":2,"playable":43.31759913192028,"score":43.31759913192028},"GB2-08":{"attempts":2,"playable":27.089155225097507,"score":27.089155225097507}},"medium":{"GB2-01":{"attempts":2,"playable":38.59795110731506,"score":38.59795110731506},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":42.179405312390166,"score":21.089702656195083},"GB2-03":{"attempts":2,"playable":40.616983640758356,"score":40.616983640758356},"GB2-04":{"attempts":2,"playable":41.64134552725429,"score":41.64134552725429},"GB2-05":{"attempts":2,"playable":14.617429693895549,"score":14.617429693895549},"GB2-06":{"attempts":2,"playable":11.938940585718438,"score":11.938940585718438},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":20.689898952116554,"score":10.344949476058277},"GB2-08":{"attempts":2,"playable":24.951119531822506,"score":24.951119531822506}},"none":{"GB2-01":{"attempts":2,"playable":34.694664472682874,"score":34.694664472682874},"GB2-02":{"attempts":2,"playable":39.51777894578386,"score":39.51777894578386},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":53.00009745516163,"score":26.500048727580815},"GB2-04":{"attempts":2,"playable":46.70658788773637,"score":46.70658788773637},"GB2-05":{"attempts":2,"playable":10.847325535446402,"score":10.847325535446402},"GB2-06":{"attempts":2,"playable":53.18552719648065,"score":53.18552719648065},"GB2-07":{"attempts":2,"playable":60.14962767223564,"score":60.14962767223564},"GB2-08":{"attempts":2,"playable":26.556283527926013,"score":26.556283527926013}}},"id":"google/gemini-3.5-flash-lite","is_recent_addition":false,"last_measured_at":"2026-11-03T07:16:08Z","match_totals_all":{"draws":4863,"losses":12159,"wins":4978},"match_totals_tracks":{"highest":{"draws":1324,"losses":3778,"wins":1704},"medium":{"draws":1729,"losses":4446,"wins":1167},"none":{"draws":1810,"losses":3935,"wins":2107}},"model_slug":"google-gemini-3-5-flash-lite","official_rank_by_reasoning":{"highest":59,"medium":76,"none":50},"overall":{"max":60.14962767223564,"mean":31.336195834786782,"min":10.344949476058277},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":59,"overall_ranking_status":"ranked","per_game":{"GB2-01":33.537908310994794,"GB2-02":44.51053870794912,"GB2-03":46.92891568699177,"GB2-04":39.06201402844559,"GB2-05":16.48881921714565,"GB2-06":38.20170705091989,"GB2-07":43.31759913192028,"GB2-08":27.089155225097507},"per_game_all":{"GB2-01":35.61017463033091,"GB2-02":42.06924098870771,"GB2-03":46.848665594303924,"GB2-04":42.469982481145415,"GB2-05":13.984524815495867,"GB2-06":34.44205827770633,"GB2-07":41.38570858542416,"GB2-08":26.198852761615342},"per_game_match_totals_all":{"GB2-01":{"draws":472,"losses":1455,"wins":703},"GB2-02":{"draws":1512,"losses":425,"wins":37},"GB2-03":{"draws":568,"losses":1182,"wins":818},"GB2-04":{"draws":1855,"losses":876,"wins":333},"GB2-05":{"draws":0,"losses":2807,"wins":449},"GB2-06":{"draws":23,"losses":2059,"wins":1002},"GB2-07":{"draws":0,"losses":1525,"wins":1179},"GB2-08":{"draws":433,"losses":1830,"wins":457}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":100,"losses":300,"wins":124},"GB2-02":{"draws":367,"losses":98,"wins":31},"GB2-03":{"draws":155,"losses":493,"wins":376},"GB2-04":{"draws":602,"losses":336,"wins":86},"GB2-05":{"draws":0,"losses":907,"wins":177},"GB2-06":{"draws":11,"losses":648,"wins":371},"GB2-07":{"draws":0,"losses":639,"wins":443},"GB2-08":{"draws":89,"losses":357,"wins":96}},"medium":{"GB2-01":{"draws":175,"losses":563,"wins":316},"GB2-02":{"draws":398,"losses":93,"wins":3},"GB2-03":{"draws":323,"losses":479,"wins":230},"GB2-04":{"draws":658,"losses":279,"wins":81},"GB2-05":{"draws":0,"losses":931,"wins":157},"GB2-06":{"draws":6,"losses":914,"wins":108},"GB2-07":{"draws":0,"losses":441,"wins":99},"GB2-08":{"draws":169,"losses":746,"wins":173}},"none":{"GB2-01":{"draws":197,"losses":592,"wins":263},"GB2-02":{"draws":747,"losses":234,"wins":3},"GB2-03":{"draws":90,"losses":210,"wins":212},"GB2-04":{"draws":595,"losses":261,"wins":166},"GB2-05":{"draws":0,"losses":969,"wins":115},"GB2-06":{"draws":6,"losses":497,"wins":523},"GB2-07":{"draws":0,"losses":445,"wins":637},"GB2-08":{"draws":175,"losses":727,"wins":188}}},"per_game_raw_elo_all":{"GB2-01":1345.728842518105,"GB2-02":1414.709012025157,"GB2-03":1413.5239106126458,"GB2-04":1418.3582613011847,"GB2-05":884.523942528161,"GB2-06":1199.8204152591918,"GB2-07":1327.5506720917983,"GB2-08":1111.9801878456815},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1324.8391352277176,"GB2-02":1433.9002866031594,"GB2-03":1414.8657673689268,"GB2-04":1391.2724016549887,"GB2-05":942.2516508715091,"GB2-06":1268.450268455806,"GB2-07":1356.996391165178,"GB2-08":1123.1829540393283},"medium":{"GB2-01":1376.3540757860792,"GB2-02":1415.647020230108,"GB2-03":1357.5204381742751,"GB2-04":1411.892481393329,"GB2-05":902.4919151790631,"GB2-06":822.8296825579965,"GB2-07":1038.5771264613477,"GB2-08":1096.327916772403},"none":{"GB2-01":1335.9933165405182,"GB2-02":1394.579729242204,"GB2-03":1468.185526294736,"GB2-04":1451.9099008552366,"GB2-05":808.8282615339107,"GB2-06":1508.1812947637732,"GB2-07":1587.0784986488695,"GB2-08":1116.429692725313}},"per_game_tracks":{"highest":{"GB2-01":33.537908310994794,"GB2-02":44.51053870794912,"GB2-03":46.92891568699177,"GB2-04":39.06201402844559,"GB2-05":16.48881921714565,"GB2-06":38.20170705091989,"GB2-07":43.31759913192028,"GB2-08":27.089155225097507},"medium":{"GB2-01":38.59795110731506,"GB2-02":42.179405312390166,"GB2-03":40.616983640758356,"GB2-04":41.64134552725429,"GB2-05":14.617429693895549,"GB2-06":11.938940585718438,"GB2-07":20.689898952116554,"GB2-08":24.951119531822506},"none":{"GB2-01":34.694664472682874,"GB2-02":39.51777894578386,"GB2-03":53.00009745516163,"GB2-04":46.70658788773637,"GB2-05":10.847325535446402,"GB2-06":53.18552719648065,"GB2-07":60.14962767223564,"GB2-08":26.556283527926013}},"program_outcomes":{"all":{"counted_attempts":48,"failed":5,"infra_excluded":0,"success_rate":0.8958333333333334,"too_slow":0,"worked_after_repair":7,"worked_first_time":36,"working":43},"highest":{"counted_attempts":16,"failed":2,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":1,"worked_first_time":13,"working":14},"medium":{"counted_attempts":16,"failed":2,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":14,"working":14},"none":{"counted_attempts":16,"failed":1,"infra_excluded":0,"success_rate":0.9375,"too_slow":0,"worked_after_repair":6,"worked_first_time":9,"working":15}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T17:07:30Z","reasoning":{"highest":31.26405423124908,"medium":25.474802777377196,"none":37.26973049573408},"reasoning_agg":{"highest":{"max":46.92891568699177,"mean":31.26405423124908,"min":16.48881921714565},"medium":{"max":41.64134552725429,"mean":25.474802777377196,"min":10.344949476058277},"none":{"max":60.14962767223564,"mean":37.26973049573408,"min":10.847325535446402}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":11.794927718356885},"working_program_strength":{"all":35.376151016841206,"highest":36.142082169933076,"medium":29.404134293908864,"none":40.582236586681674}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling-small:08b1f95dc978089f","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":0.38761485},"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":0.07763975000000001},"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":0.38761484999999996}},"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":29.819529412860174,"highest":33.570808841373136,"medium":27.794803578930605,"none":28.092975818276773},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":20.28510273913336,"score":20.28510273913336},"GB2-02":{"attempts":3,"playable":40.993982845812646,"score":40.993982845812646},"GB2-03":{"attempts":3,"playable":45.72589019330445,"score":45.72589019330445},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":42.48552292799439,"score":35.599935426120474},"GB2-05":{"attempts":3,"playable":17.717483018164675,"score":17.717483018164675},"GB2-06":{"attempts":5,"failed_attempts":2,"playable":27.536961441483868,"score":22.27221328977701},"GB2-07":{"attempts":3,"playable":34.24322435154564,"score":34.24322435154564},"GB2-08":{"attempts":3,"playable":21.718403439023106,"score":21.718403439023106}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":31.171265543311712,"score":31.171265543311712},"GB2-02":{"attempts":1,"playable":41.069923673119064,"score":41.069923673119064},"GB2-03":{"attempts":1,"playable":43.84248704679869,"score":43.84248704679869},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":41.31352501124347,"score":20.656762505621735},"GB2-05":{"attempts":1,"playable":39.53141491628169,"score":39.53141491628169},"GB2-06":{"attempts":1,"playable":51.02239541421044,"score":51.02239541421044},"GB2-07":{"attempts":1,"playable":18.33380663897972,"score":18.33380663897972},"GB2-08":{"attempts":1,"playable":22.938414992662032,"score":22.938414992662032}},"medium":{"GB2-01":{"attempts":1,"playable":8.993575212799765,"score":8.993575212799765},"GB2-02":{"attempts":1,"playable":41.879943237784026,"score":41.879943237784026},"GB2-03":{"attempts":1,"playable":38.01273805152664,"score":38.01273805152664},"GB2-04":{"attempts":1,"playable":43.4237594215735,"score":43.4237594215735},"GB2-05":{"attempts":1,"playable":8.961567666830286,"score":8.961567666830286},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":15.99959776290662,"score":7.99979888145331},"GB2-07":{"attempts":1,"playable":53.98412179840256,"score":53.98412179840256},"GB2-08":{"attempts":1,"playable":19.102924361074777,"score":19.102924361074777}},"none":{"GB2-01":{"attempts":1,"playable":20.690467461288602,"score":20.690467461288602},"GB2-02":{"attempts":1,"playable":40.03208162653483,"score":40.03208162653483},"GB2-03":{"attempts":1,"playable":55.32244548158805,"score":55.32244548158805},"GB2-04":{"attempts":1,"playable":42.71928435116618,"score":42.71928435116618},"GB2-05":{"attempts":1,"playable":4.65946647138205,"score":4.65946647138205},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":15.588891147334536,"score":7.794445573667268},"GB2-07":{"attempts":1,"playable":30.411744617254655,"score":30.411744617254655},"GB2-08":{"attempts":1,"playable":23.113870963332506,"score":23.113870963332506}}},"id":"thinkingmachines/inkling-small","is_recent_addition":false,"last_measured_at":"2026-11-03T07:12:30Z","match_totals_all":{"draws":3135,"losses":7256,"wins":2173},"match_totals_tracks":{"highest":{"draws":1066,"losses":2202,"wins":916},"medium":{"draws":1007,"losses":2542,"wins":641},"none":{"draws":1062,"losses":2512,"wins":616}},"model_slug":"thinkingmachines-inkling-small","official_rank_by_reasoning":{"highest":58,"medium":74,"none":69},"overall":{"max":55.32244548158805,"mean":29.819529412860174,"min":4.65946647138205},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":60,"overall_ranking_status":"ranked","per_game":{"GB2-01":31.171265543311712,"GB2-02":41.069923673119064,"GB2-03":43.84248704679869,"GB2-04":41.31352501124347,"GB2-05":39.53141491628169,"GB2-06":51.02239541421044,"GB2-07":18.33380663897972,"GB2-08":22.938414992662032},"per_game_all":{"GB2-01":20.28510273913336,"GB2-02":40.993982845812646,"GB2-03":45.72589019330445,"GB2-04":42.48552292799439,"GB2-05":17.717483018164675,"GB2-06":27.536961441483868,"GB2-07":34.24322435154564,"GB2-08":21.718403439023106},"per_game_match_totals_all":{"GB2-01":{"draws":267,"losses":1138,"wins":181},"GB2-02":{"draws":1169,"losses":308,"wins":5},"GB2-03":{"draws":458,"losses":649,"wins":433},"GB2-04":{"draws":955,"losses":425,"wins":154},"GB2-05":{"draws":0,"losses":1343,"wins":285},"GB2-06":{"draws":12,"losses":1137,"wins":397},"GB2-07":{"draws":0,"losses":1100,"wins":520},"GB2-08":{"draws":274,"losses":1156,"wins":198}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":141,"losses":295,"wins":92},"GB2-02":{"draws":392,"losses":101,"wins":1},"GB2-03":{"draws":99,"losses":252,"wins":161},"GB2-04":{"draws":312,"losses":151,"wins":49},"GB2-05":{"draws":0,"losses":327,"wins":215},"GB2-06":{"draws":11,"losses":256,"wins":249},"GB2-07":{"draws":0,"losses":453,"wins":87},"GB2-08":{"draws":111,"losses":367,"wins":62}},"medium":{"GB2-01":{"draws":62,"losses":452,"wins":14},"GB2-02":{"draws":399,"losses":95,"wins":2},"GB2-03":{"draws":133,"losses":266,"wins":115},"GB2-04":{"draws":305,"losses":143,"wins":62},"GB2-05":{"draws":0,"losses":495,"wins":47},"GB2-06":{"draws":0,"losses":441,"wins":75},"GB2-07":{"draws":0,"losses":258,"wins":282},"GB2-08":{"draws":108,"losses":392,"wins":44}},"none":{"GB2-01":{"draws":64,"losses":391,"wins":75},"GB2-02":{"draws":378,"losses":112,"wins":2},"GB2-03":{"draws":226,"losses":131,"wins":157},"GB2-04":{"draws":338,"losses":131,"wins":43},"GB2-05":{"draws":0,"losses":521,"wins":23},"GB2-06":{"draws":1,"losses":440,"wins":73},"GB2-07":{"draws":0,"losses":389,"wins":151},"GB2-08":{"draws":55,"losses":397,"wins":92}}},"per_game_raw_elo_all":{"GB2-01":1148.2575410432462,"GB2-02":1406.298404872851,"GB2-03":1403.3866267154262,"GB2-04":1418.6019713540056,"GB2-05":891.4120790087019,"GB2-06":1091.6585264876605,"GB2-07":1226.5967299704987,"GB2-08":1053.6527389591881},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1299.756711488219,"GB2-02":1406.9089490690462,"GB2-03":1386.0802908095436,"GB2-04":1409.3083965829176,"GB2-05":1315.7061126999101,"GB2-06":1472.4049004667238,"GB2-07":997.7618577771934,"GB2-08":1070.3569907022356},"medium":{"GB2-01":969.9147846466357,"GB2-02":1413.2924690525626,"GB2-03":1334.2944842519184,"GB2-04":1426.034179134129,"GB2-05":759.4699130640619,"GB2-06":905.181782285732,"GB2-07":1496.560687421097,"GB2-08":1017.9449523611554},"none":{"GB2-01":1175.1011269948838,"GB2-02":1398.693796496944,"GB2-03":1489.785105084817,"GB2-04":1420.4633383449705,"GB2-05":599.0602112621337,"GB2-06":897.3888967105257,"GB2-07":1185.4676447132056,"GB2-08":1072.6562738141727}},"per_game_tracks":{"highest":{"GB2-01":31.171265543311712,"GB2-02":41.069923673119064,"GB2-03":43.84248704679869,"GB2-04":41.31352501124347,"GB2-05":39.53141491628169,"GB2-06":51.02239541421044,"GB2-07":18.33380663897972,"GB2-08":22.938414992662032},"medium":{"GB2-01":8.993575212799765,"GB2-02":41.879943237784026,"GB2-03":38.01273805152664,"GB2-04":43.4237594215735,"GB2-05":8.961567666830286,"GB2-06":15.99959776290662,"GB2-07":53.98412179840256,"GB2-08":19.102924361074777},"none":{"GB2-01":20.690467461288602,"GB2-02":40.03208162653483,"GB2-03":55.32244548158805,"GB2-04":42.71928435116618,"GB2-05":4.65946647138205,"GB2-06":15.588891147334536,"GB2-07":30.411744617254655,"GB2-08":23.113870963332506}},"program_outcomes":{"all":{"counted_attempts":27,"failed":3,"infra_excluded":0,"success_rate":0.8888888888888888,"too_slow":1,"worked_after_repair":9,"worked_first_time":15,"working":24},"highest":{"counted_attempts":9,"failed":1,"infra_excluded":0,"success_rate":0.8888888888888888,"too_slow":1,"worked_after_repair":2,"worked_first_time":6,"working":8},"medium":{"counted_attempts":9,"failed":1,"infra_excluded":0,"success_rate":0.8888888888888888,"too_slow":0,"worked_after_repair":4,"worked_first_time":4,"working":8},"none":{"counted_attempts":9,"failed":1,"infra_excluded":0,"success_rate":0.8888888888888888,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8}},"provider_color":"#31373D","provider_company":"Thinking Machines","provider_key":"thinkingmachines","provider_text_color":"#f8fafc","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T17:05:04Z","reasoning":{"highest":33.570808841373136,"medium":27.794803578930605,"none":28.092975818276773},"reasoning_agg":{"highest":{"max":51.02239541421044,"mean":33.570808841373136,"min":18.33380663897972},"medium":{"max":53.98412179840256,"mean":27.794803578930605,"min":7.99979888145331},"none":{"max":55.32244548158805,"mean":28.092975818276773,"min":4.65946647138205}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":5.776005262442531},"working_program_strength":{"all":31.338321369557764,"highest":36.15290415457585,"medium":28.79477843911227,"none":29.06728151498518}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-glimmer-30b:812775d72ec59271","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":0.058501660000000004}},"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":0.28235539},"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":28.736932990080504,"highest":34.0269430230465,"medium":29.90726758250805,"none":22.276588364686955},"first_seen_at":null,"game_gaps":{"highest":{"GB2-06":"failed"},"none":{"GB2-02":"failed","GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":28.296643264109548,"score":28.296643264109548},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.388075210810825,"score":28.258716807207218},"GB2-03":{"attempts":3,"playable":39.45270327576574,"score":39.45270327576574},"GB2-04":{"attempts":3,"playable":44.85707616189509,"score":44.85707616189509},"GB2-05":{"attempts":3,"playable":21.55799869305697,"score":21.55799869305697},"GB2-06":{"attempts":3,"failed_attempts":2,"playable":16.082864875862086,"score":5.360954958620695},"GB2-07":{"attempts":3,"playable":36.307232334673756,"score":36.307232334673756},"GB2-08":{"attempts":3,"playable":25.804138425314978,"score":25.804138425314978}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":29.856296972809176,"score":29.856296972809176},"GB2-02":{"attempts":1,"playable":42.28577071402832,"score":42.28577071402832},"GB2-03":{"attempts":1,"playable":36.78777116739156,"score":36.78777116739156},"GB2-04":{"attempts":1,"playable":48.06206766700585,"score":48.06206766700585},"GB2-05":{"attempts":1,"playable":43.161698642240175,"score":43.161698642240175},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":46.34801185882438,"score":46.34801185882438},"GB2-08":{"attempts":1,"playable":25.71392716207251,"score":25.71392716207251}},"medium":{"GB2-01":{"attempts":1,"playable":20.544432505892242,"score":20.544432505892242},"GB2-02":{"attempts":1,"playable":42.490379707593334,"score":42.490379707593334},"GB2-03":{"attempts":1,"playable":38.03913936133595,"score":38.03913936133595},"GB2-04":{"attempts":1,"playable":44.092394413194704,"score":44.092394413194704},"GB2-05":{"attempts":1,"playable":14.343760785692627,"score":14.343760785692627},"GB2-06":{"attempts":1,"playable":16.082864875862086,"score":16.082864875862086},"GB2-07":{"attempts":1,"playable":36.30421439818182,"score":36.30421439818182},"GB2-08":{"attempts":1,"playable":27.360954612311623,"score":27.360954612311623}},"none":{"GB2-01":{"attempts":1,"playable":34.48920031362722,"score":34.48920031362722},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":43.53119929856972,"score":43.53119929856972},"GB2-04":{"attempts":1,"playable":42.416766405484715,"score":42.416766405484715},"GB2-05":{"attempts":1,"playable":7.168536651238094,"score":7.168536651238094},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":26.269470747015077,"score":26.269470747015077},"GB2-08":{"attempts":1,"playable":24.337533501560802,"score":24.337533501560802}}},"id":"meta/muse-glimmer-30b","is_recent_addition":false,"last_measured_at":"2026-11-03T07:13:00Z","match_totals_all":{"draws":2822,"losses":6178,"wins":2044},"match_totals_tracks":{"highest":{"draws":1090,"losses":1749,"wins":833},"medium":{"draws":1065,"losses":2473,"wins":654},"none":{"draws":667,"losses":1956,"wins":557}},"model_slug":"meta-muse-glimmer-30b","official_rank_by_reasoning":{"highest":56,"medium":72,"none":82},"overall":{"max":48.06206766700585,"mean":28.736932990080504,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":61,"overall_ranking_status":"ranked","per_game":{"GB2-01":29.856296972809176,"GB2-02":42.28577071402832,"GB2-03":36.78777116739156,"GB2-04":48.06206766700585,"GB2-05":43.161698642240175,"GB2-07":46.34801185882438,"GB2-08":25.71392716207251},"per_game_all":{"GB2-01":28.296643264109548,"GB2-03":39.45270327576574,"GB2-04":44.85707616189509,"GB2-05":21.55799869305697,"GB2-07":36.307232334673756,"GB2-08":25.804138425314978},"per_game_match_totals_all":{"GB2-01":{"draws":326,"losses":981,"wins":279},"GB2-02":{"draws":799,"losses":180,"wins":5},"GB2-03":{"draws":462,"losses":742,"wins":334},"GB2-04":{"draws":981,"losses":376,"wins":177},"GB2-05":{"draws":0,"losses":1281,"wins":349},"GB2-06":{"draws":0,"losses":442,"wins":76},"GB2-07":{"draws":0,"losses":1072,"wins":550},"GB2-08":{"draws":254,"losses":1104,"wins":274}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":135,"losses":305,"wins":88},"GB2-02":{"draws":396,"losses":92,"wins":4},"GB2-03":{"draws":155,"losses":261,"wins":98},"GB2-04":{"draws":286,"losses":129,"wins":95},"GB2-05":{"draws":0,"losses":307,"wins":235},"GB2-07":{"draws":0,"losses":303,"wins":239},"GB2-08":{"draws":118,"losses":352,"wins":74}},"medium":{"GB2-01":{"draws":90,"losses":377,"wins":61},"GB2-02":{"draws":403,"losses":88,"wins":1},"GB2-03":{"draws":132,"losses":265,"wins":115},"GB2-04":{"draws":342,"losses":122,"wins":48},"GB2-05":{"draws":0,"losses":469,"wins":77},"GB2-06":{"draws":0,"losses":442,"wins":76},"GB2-07":{"draws":0,"losses":357,"wins":183},"GB2-08":{"draws":98,"losses":353,"wins":93}},"none":{"GB2-01":{"draws":101,"losses":299,"wins":130},"GB2-03":{"draws":175,"losses":216,"wins":121},"GB2-04":{"draws":353,"losses":125,"wins":34},"GB2-05":{"draws":0,"losses":505,"wins":37},"GB2-07":{"draws":0,"losses":412,"wins":128},"GB2-08":{"draws":38,"losses":399,"wins":107}}},"per_game_raw_elo_all":{"GB2-01":1264.4381873205593,"GB2-03":1347.0423206836258,"GB2-04":1437.319742194064,"GB2-05":987.259308982574,"GB2-07":1262.571699380566,"GB2-08":1107.0180518512154},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1285.4630926146347,"GB2-02":1416.4826869610536,"GB2-03":1323.2681800738294,"GB2-04":1462.5790825095391,"GB2-05":1363.5484013531966,"GB2-07":1396.320108413385,"GB2-08":1105.9967707337298},"medium":{"GB2-01":1173.1316664507904,"GB2-02":1418.0893097460814,"GB2-03":1334.5312938270492,"GB2-04":1431.3126170390478,"GB2-05":896.4469792377168,"GB2-06":906.7503059558787,"GB2-07":1265.3442865557863,"GB2-08":1126.5509725575325},"none":{"GB2-01":1334.719802896253,"GB2-03":1383.3274881499985,"GB2-04":1418.0675270336055,"GB2-05":701.7825463568084,"GB2-07":1126.050703172527,"GB2-08":1088.5064122623844}},"per_game_tracks":{"highest":{"GB2-01":29.856296972809176,"GB2-02":42.28577071402832,"GB2-03":36.78777116739156,"GB2-04":48.06206766700585,"GB2-05":43.161698642240175,"GB2-07":46.34801185882438,"GB2-08":25.71392716207251},"medium":{"GB2-01":20.544432505892242,"GB2-02":42.490379707593334,"GB2-03":38.03913936133595,"GB2-04":44.092394413194704,"GB2-05":14.343760785692627,"GB2-06":16.082864875862086,"GB2-07":36.30421439818182,"GB2-08":27.360954612311623},"none":{"GB2-01":34.48920031362722,"GB2-03":43.53119929856972,"GB2-04":42.416766405484715,"GB2-05":7.168536651238094,"GB2-07":26.269470747015077,"GB2-08":24.337533501560802}},"program_outcomes":{"all":{"counted_attempts":24,"failed":3,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":7,"worked_first_time":14,"working":21},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":2,"worked_first_time":5,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":3,"worked_first_time":3,"working":6}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T11:20:56Z","reasoning":{"highest":34.0269430230465,"medium":29.90726758250805,"none":22.276588364686955},"reasoning_agg":{"highest":{"max":48.06206766700585,"mean":34.0269430230465,"min":0.0},"medium":{"max":44.092394413194704,"mean":29.90726758250805,"min":14.343760785692627},"none":{"max":43.53119929856972,"mean":22.276588364686955,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":11.750354658359544},"working_program_strength":{"all":32.83244009519079,"highest":38.88793488348171,"medium":29.90726758250805,"none":29.702117819582607}},{"canonical_public_row_identity":"publication-row.v1:overall:openai-gpt-oss-120b:1529f6ddff8e9ba9","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":0.05953976200000001},"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":0.009855891}},"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":0.009855890999999999},"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":28.61188593220675,"highest":33.839871277937576,"medium":28.94427038538898,"none":23.051516133293703},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"failed"},"none":{"GB2-04":"failed","GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":36.288769520654355,"score":24.19251301376957},"GB2-02":{"attempts":3,"playable":42.07923548456943,"score":42.07923548456943},"GB2-03":{"attempts":3,"playable":38.04532575753362,"score":38.04532575753362},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":39.329098478868616,"score":26.21939898591241},"GB2-05":{"attempts":3,"playable":28.16740367633879,"score":28.16740367633879},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":23.270105971434074,"score":15.513403980956049},"GB2-07":{"attempts":3,"playable":27.20668671222147,"score":27.20668671222147},"GB2-08":{"attempts":3,"playable":27.471119846352668,"score":27.471119846352668}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":42.79739973952104,"score":42.79739973952104},"GB2-03":{"attempts":1,"playable":44.663330193207294,"score":44.663330193207294},"GB2-04":{"attempts":1,"playable":41.07740323155408,"score":41.07740323155408},"GB2-05":{"attempts":1,"playable":55.24552028668628,"score":55.24552028668628},"GB2-06":{"attempts":1,"playable":21.84785750265215,"score":21.84785750265215},"GB2-07":{"attempts":1,"playable":32.998442220559724,"score":32.998442220559724},"GB2-08":{"attempts":1,"playable":32.08901704932005,"score":32.08901704932005}},"medium":{"GB2-01":{"attempts":1,"playable":33.987304329202985,"score":33.987304329202985},"GB2-02":{"attempts":1,"playable":41.056933771732965,"score":41.056933771732965},"GB2-03":{"attempts":1,"playable":34.387596512750804,"score":34.387596512750804},"GB2-04":{"attempts":1,"playable":37.580793726183146,"score":37.580793726183146},"GB2-05":{"attempts":1,"playable":14.538264849861212,"score":14.538264849861212},"GB2-06":{"attempts":1,"playable":24.692354440215997,"score":24.692354440215997},"GB2-07":{"attempts":1,"playable":20.275860756114202,"score":20.275860756114202},"GB2-08":{"attempts":1,"playable":25.03505469705049,"score":25.03505469705049}},"none":{"GB2-01":{"attempts":1,"playable":38.59023471210573,"score":38.59023471210573},"GB2-02":{"attempts":1,"playable":42.3833729424543,"score":42.3833729424543},"GB2-03":{"attempts":1,"playable":35.085050566642764,"score":35.085050566642764},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":14.71842589246888,"score":14.71842589246888},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":28.345757159990487,"score":28.345757159990487},"GB2-08":{"attempts":1,"playable":25.28928779268746,"score":25.28928779268746}}},"id":"openai/gpt-oss-120b","is_recent_addition":false,"last_measured_at":"2026-11-03T07:00:32Z","match_totals_all":{"draws":2644,"losses":6250,"wins":2098},"match_totals_tracks":{"highest":{"draws":893,"losses":1848,"wins":909},"medium":{"draws":1032,"losses":2520,"wins":626},"none":{"draws":719,"losses":1882,"wins":563}},"model_slug":"openai-gpt-oss-120b","official_rank_by_reasoning":{"highest":57,"medium":73,"none":81},"overall":{"max":55.24552028668628,"mean":28.61188593220675,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":62,"overall_ranking_status":"ranked","per_game":{"GB2-02":42.79739973952104,"GB2-03":44.663330193207294,"GB2-04":41.07740323155408,"GB2-05":55.24552028668628,"GB2-06":21.84785750265215,"GB2-07":32.998442220559724,"GB2-08":32.08901704932005},"per_game_all":{"GB2-02":42.07923548456943,"GB2-03":38.04532575753362,"GB2-05":28.16740367633879,"GB2-07":27.20668671222147,"GB2-08":27.471119846352668},"per_game_match_totals_all":{"GB2-01":{"draws":184,"losses":583,"wins":287},"GB2-02":{"draws":1172,"losses":290,"wins":18},"GB2-03":{"draws":368,"losses":811,"wins":361},"GB2-04":{"draws":651,"losses":305,"wins":60},"GB2-05":{"draws":0,"losses":1169,"wins":457},"GB2-06":{"draws":8,"losses":805,"wins":217},"GB2-07":{"draws":0,"losses":1219,"wins":403},"GB2-08":{"draws":261,"losses":1068,"wins":295}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":383,"losses":96,"wins":13},"GB2-03":{"draws":123,"losses":235,"wins":152},"GB2-04":{"draws":327,"losses":143,"wins":38},"GB2-05":{"draws":0,"losses":242,"wins":300},"GB2-06":{"draws":2,"losses":411,"wins":103},"GB2-07":{"draws":0,"losses":375,"wins":165},"GB2-08":{"draws":58,"losses":346,"wins":138}},"medium":{"GB2-01":{"draws":98,"losses":300,"wins":128},"GB2-02":{"draws":385,"losses":105,"wins":4},"GB2-03":{"draws":124,"losses":287,"wins":101},"GB2-04":{"draws":324,"losses":162,"wins":22},"GB2-05":{"draws":0,"losses":464,"wins":78},"GB2-06":{"draws":6,"losses":394,"wins":114},"GB2-07":{"draws":0,"losses":444,"wins":98},"GB2-08":{"draws":95,"losses":364,"wins":81}},"none":{"GB2-01":{"draws":86,"losses":283,"wins":159},"GB2-02":{"draws":404,"losses":89,"wins":1},"GB2-03":{"draws":121,"losses":289,"wins":108},"GB2-05":{"draws":0,"losses":463,"wins":79},"GB2-07":{"draws":0,"losses":400,"wins":140},"GB2-08":{"draws":108,"losses":358,"wins":76}}},"per_game_raw_elo_all":{"GB2-02":1414.8511933769112,"GB2-03":1334.1747919989205,"GB2-05":1108.6083659002984,"GB2-07":1136.308387562456,"GB2-08":1127.4034378599395},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1420.49796841202,"GB2-03":1393.340930814069,"GB2-04":1407.4286332805725,"GB2-05":1520.304367989064,"GB2-06":1008.5332169409239,"GB2-07":1221.0405784972836,"GB2-08":1184.1650566765197},"medium":{"GB2-01":1329.5199514350995,"GB2-02":1406.806390895123,"GB2-03":1301.391807045292,"GB2-04":1379.3042197921689,"GB2-05":900.7715398790152,"GB2-06":1055.5912406469479,"GB2-07":1031.6082354249825,"GB2-08":1097.4105025751521},"none":{"GB2-01":1376.2772333079809,"GB2-02":1417.24922082359,"GB2-03":1307.7916381374002,"GB2-05":904.7491898328159,"GB2-07":1156.2763487651014,"GB2-08":1100.6347543281468}},"per_game_tracks":{"highest":{"GB2-02":42.79739973952104,"GB2-03":44.663330193207294,"GB2-04":41.07740323155408,"GB2-05":55.24552028668628,"GB2-06":21.84785750265215,"GB2-07":32.998442220559724,"GB2-08":32.08901704932005},"medium":{"GB2-01":33.987304329202985,"GB2-02":41.056933771732965,"GB2-03":34.387596512750804,"GB2-04":37.580793726183146,"GB2-05":14.538264849861212,"GB2-06":24.692354440215997,"GB2-07":20.275860756114202,"GB2-08":25.03505469705049},"none":{"GB2-01":38.59023471210573,"GB2-02":42.3833729424543,"GB2-03":35.085050566642764,"GB2-05":14.71842589246888,"GB2-07":28.345757159990487,"GB2-08":25.28928779268746}},"program_outcomes":{"all":{"counted_attempts":24,"failed":3,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":5,"worked_first_time":16,"working":21},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":2,"worked_first_time":5,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":1,"worked_first_time":5,"working":6}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T17:00:51Z","reasoning":{"highest":33.839871277937576,"medium":28.94427038538898,"none":23.051516133293703},"reasoning_agg":{"highest":{"max":55.24552028668628,"mean":33.839871277937576,"min":0.0},"medium":{"max":41.056933771732965,"mean":28.94427038538898,"min":14.538264849861212},"none":{"max":42.3833729424543,"mean":23.051516133293703,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.788355144643873},"working_program_strength":{"all":32.784587944379275,"highest":38.67413860335723,"medium":28.94427038538898,"none":30.735354844391605}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling:e074e027ccf8bdfd","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":0.24908164},"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":0.5884539500000001}},"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":5.743916149999998},"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":25.376669795318055,"highest":31.151967878086154,"medium":18.401521348946336,"none":26.57652015892169},"first_seen_at":null,"game_gaps":{"medium":{"GB2-02":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":24.538424489241383,"score":24.538424489241383},"GB2-02":{"attempts":5,"failed_attempts":2,"playable":41.83351508749243,"score":20.756324147983424},"GB2-03":{"attempts":5,"playable":43.36460704374613,"score":43.36460704374613},"GB2-04":{"attempts":5,"failed_attempts":1,"playable":41.35677432922072,"score":34.22278103327929},"GB2-05":{"attempts":5,"playable":18.06435362465339,"score":18.06435362465339},"GB2-06":{"attempts":5,"failed_attempts":2,"playable":32.856091049638074,"score":20.1274045917815},"GB2-07":{"attempts":5,"failed_attempts":1,"playable":22.84818064197064,"score":19.136185571565594},"GB2-08":{"attempts":5,"failed_attempts":2,"playable":51.543616655815114,"score":22.803277860293765}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":38.01069965126685,"score":38.01069965126685},"GB2-02":{"attempts":2,"playable":40.87091471291568,"score":40.87091471291568},"GB2-03":{"attempts":2,"playable":46.522249974993294,"score":46.522249974993294},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":42.80395977564863,"score":21.401979887824314},"GB2-05":{"attempts":2,"playable":14.985027076407402,"score":14.985027076407402},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":51.481559706256284,"score":25.740779853128142},"GB2-07":{"attempts":2,"playable":27.951658018021213,"score":27.951658018021213},"GB2-08":{"attempts":2,"playable":33.732433850132345,"score":33.732433850132345}},"medium":{"GB2-01":{"attempts":1,"playable":16.706895066965117,"score":16.706895066965117},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":36.13321218290398,"score":36.13321218290398},"GB2-04":{"attempts":1,"playable":40.5828936512785,"score":40.5828936512785},"GB2-05":{"attempts":1,"playable":13.27210200318785,"score":13.27210200318785},"GB2-06":{"attempts":1,"playable":22.196154401774763,"score":22.196154401774763},"GB2-07":{"attempts":1,"playable":18.32091348546046,"score":18.32091348546046},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":2,"playable":18.897678749492187,"score":18.897678749492187},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":42.79611546206919,"score":21.398057731034594},"GB2-03":{"attempts":2,"playable":47.438358973341124,"score":47.438358973341124},"GB2-04":{"attempts":2,"playable":40.68346956073504,"score":40.68346956073504},"GB2-05":{"attempts":2,"playable":25.93593179436491,"score":25.93593179436491},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":24.890559040883183,"score":12.445279520441591},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":22.271970422430236,"score":11.135985211215118},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":69.35479946149789,"score":34.677399730748945}}},"id":"thinkingmachines/inkling","is_recent_addition":false,"last_measured_at":"2026-11-03T07:15:35Z","match_totals_all":{"draws":4102,"losses":9366,"wins":3304},"match_totals_tracks":{"highest":{"draws":1789,"losses":3955,"wins":1596},"medium":{"draws":705,"losses":2076,"wins":369},"none":{"draws":1608,"losses":3335,"wins":1339}},"model_slug":"thinkingmachines-inkling","official_rank_by_reasoning":{"highest":60,"medium":83,"none":75},"overall":{"max":47.438358973341124,"mean":25.376669795318055,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":63,"overall_ranking_status":"ranked","per_game":{"GB2-01":38.01069965126685,"GB2-02":40.87091471291568,"GB2-03":46.522249974993294,"GB2-04":42.80395977564863,"GB2-05":14.985027076407402,"GB2-06":51.481559706256284,"GB2-07":27.951658018021213,"GB2-08":33.732433850132345},"per_game_all":{"GB2-01":24.538424489241383,"GB2-03":43.36460704374613,"GB2-04":41.35677432922072,"GB2-05":18.06435362465339,"GB2-06":32.856091049638074,"GB2-07":22.84818064197064},"per_game_match_totals_all":{"GB2-01":{"draws":641,"losses":1633,"wins":356},"GB2-02":{"draws":1168,"losses":305,"wins":15},"GB2-03":{"draws":797,"losses":1081,"wins":680},"GB2-04":{"draws":1290,"losses":587,"wins":171},"GB2-05":{"draws":0,"losses":2196,"wins":514},"GB2-06":{"draws":18,"losses":1062,"wins":470},"GB2-07":{"draws":0,"losses":1695,"wins":471},"GB2-08":{"draws":188,"losses":807,"wins":627}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":288,"losses":513,"wins":253},"GB2-02":{"draws":766,"losses":216,"wins":10},"GB2-03":{"draws":224,"losses":463,"wins":335},"GB2-04":{"draws":322,"losses":139,"wins":51},"GB2-05":{"draws":0,"losses":923,"wins":161},"GB2-06":{"draws":6,"losses":255,"wins":251},"GB2-07":{"draws":0,"losses":807,"wins":275},"GB2-08":{"draws":183,"losses":639,"wins":260}},"medium":{"GB2-01":{"draws":61,"losses":410,"wins":55},"GB2-03":{"draws":308,"losses":185,"wins":17},"GB2-04":{"draws":332,"losses":145,"wins":35},"GB2-05":{"draws":0,"losses":471,"wins":71},"GB2-06":{"draws":4,"losses":409,"wins":103},"GB2-07":{"draws":0,"losses":456,"wins":88}},"none":{"GB2-01":{"draws":292,"losses":710,"wins":48},"GB2-02":{"draws":402,"losses":89,"wins":5},"GB2-03":{"draws":265,"losses":433,"wins":328},"GB2-04":{"draws":636,"losses":303,"wins":85},"GB2-05":{"draws":0,"losses":802,"wins":282},"GB2-06":{"draws":8,"losses":398,"wins":116},"GB2-07":{"draws":0,"losses":432,"wins":108},"GB2-08":{"draws":5,"losses":168,"wins":367}}},"per_game_raw_elo_all":{"GB2-01":1211.2806127712495,"GB2-03":1382.5597719343762,"GB2-04":1409.6017414136193,"GB2-05":964.911473006794,"GB2-06":1184.3477296759695,"GB2-07":1070.880076375042},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1367.1348951568689,"GB2-02":1405.3361968949062,"GB2-03":1409.8143789740307,"GB2-04":1421.1335243063813,"GB2-05":910.4337028757063,"GB2-06":1479.846496112293,"GB2-07":1150.5973471932948,"GB2-08":1198.5559062719376},"medium":{"GB2-01":1117.734119079556,"GB2-03":1317.3414260737754,"GB2-04":1403.485240356947,"GB2-05":872.0164169724594,"GB2-06":1014.3731019114284,"GB2-07":997.5301876212988},"none":{"GB2-01":1148.9728240773238,"GB2-02":1420.4878979416403,"GB2-03":1420.5235107553221,"GB2-04":1404.1864595775294,"GB2-05":1112.2842991722166,"GB2-06":1058.8235910041872,"GB2-07":1064.5126943105322,"GB2-08":1741.835615015709}},"per_game_tracks":{"highest":{"GB2-01":38.01069965126685,"GB2-02":40.87091471291568,"GB2-03":46.522249974993294,"GB2-04":42.80395977564863,"GB2-05":14.985027076407402,"GB2-06":51.481559706256284,"GB2-07":27.951658018021213,"GB2-08":33.732433850132345},"medium":{"GB2-01":16.706895066965117,"GB2-03":36.13321218290398,"GB2-04":40.5828936512785,"GB2-05":13.27210200318785,"GB2-06":22.196154401774763,"GB2-07":18.32091348546046},"none":{"GB2-01":18.897678749492187,"GB2-02":42.79611546206919,"GB2-03":47.438358973341124,"GB2-04":40.68346956073504,"GB2-05":25.93593179436491,"GB2-06":24.890559040883183,"GB2-07":22.271970422430236,"GB2-08":69.35479946149789}},"program_outcomes":{"all":{"counted_attempts":40,"failed":8,"infra_excluded":6,"success_rate":0.8,"too_slow":0,"worked_after_repair":12,"worked_first_time":20,"working":32},"highest":{"counted_attempts":16,"failed":2,"infra_excluded":6,"success_rate":0.875,"too_slow":0,"worked_after_repair":5,"worked_first_time":9,"working":14},"medium":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":2,"worked_first_time":4,"working":6},"none":{"counted_attempts":16,"failed":4,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":5,"worked_first_time":7,"working":12}},"provider_color":"#31373D","provider_company":"Thinking Machines","provider_key":"thinkingmachines","provider_text_color":"#f8fafc","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T17:13:50Z","reasoning":{"highest":31.15196787808615,"medium":18.401521348946336,"none":26.576520158921692},"reasoning_agg":{"highest":{"max":46.522249974993294,"mean":31.15196787808615,"min":14.985027076407402},"medium":{"max":40.5828936512785,"mean":18.401521348946336,"min":0.0},"none":{"max":47.438358973341124,"mean":26.576520158921692,"min":11.135985211215118}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":12.750446529139815},"working_program_strength":{"all":32.70459502580068,"highest":37.04481284570521,"medium":24.535361798595115,"none":36.533610433101714}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-3-7-flash:f2347384b860bae1","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":0.11342239999999998},"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":0.48605810000000005}},"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":0.7366195799999998},"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":22.839151407975447,"highest":13.90914932941748,"medium":25.133781659307026,"none":29.474523235201836},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"failed","GB2-03":"failed","GB2-04":"failed"},"medium":{"GB2-02":"failed","GB2-04":"failed"},"none":{"GB2-05":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":16.469296751541417,"score":16.469296751541417},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":42.584475819006784,"score":14.19482527300226},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":34.4712537589015,"score":22.980835839267666},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":39.46092048663916,"score":13.153640162213053},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":42.41823837764511,"score":28.27882558509674},"GB2-06":{"attempts":3,"playable":39.85300547689565,"score":39.85300547689565},"GB2-07":{"attempts":3,"playable":34.3263803154372,"score":34.3263803154372},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":20.18460279052437,"score":13.45640186034958}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":8.984795969844429,"score":8.984795969844429},"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":37.25806643929657,"score":37.25806643929657},"GB2-06":{"attempts":1,"playable":29.79705425956356,"score":29.79705425956356},"GB2-07":{"attempts":1,"playable":24.54431520071972,"score":24.54431520071972},"GB2-08":{"attempts":1,"playable":10.688962765915543,"score":10.688962765915543}},"medium":{"GB2-01":{"attempts":1,"playable":9.492019898034645,"score":9.492019898034645},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":32.99387033546252,"score":32.99387033546252},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":47.578410315993644,"score":47.578410315993644},"GB2-06":{"attempts":1,"playable":43.381273788472576,"score":43.381273788472576},"GB2-07":{"attempts":1,"playable":37.94443612135961,"score":37.94443612135961},"GB2-08":{"attempts":1,"playable":29.680242815133195,"score":29.680242815133195}},"none":{"GB2-01":{"attempts":1,"playable":30.931074386745177,"score":30.931074386745177},"GB2-02":{"attempts":1,"playable":42.584475819006784,"score":42.584475819006784},"GB2-03":{"attempts":1,"playable":35.948637182340484,"score":35.948637182340484},"GB2-04":{"attempts":1,"playable":39.46092048663916,"score":39.46092048663916},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":46.38068838265083,"score":46.38068838265083},"GB2-07":{"attempts":1,"playable":40.490389624232265,"score":40.490389624232265},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"stepfun/step-3.7-flash","is_recent_addition":false,"last_measured_at":"2026-11-03T06:55:50Z","match_totals_all":{"draws":1540,"losses":5428,"wins":1972},"match_totals_tracks":{"highest":{"draws":77,"losses":2070,"wins":525},"medium":{"draws":487,"losses":1913,"wins":774},"none":{"draws":976,"losses":1445,"wins":673}},"model_slug":"stepfun-step-3-7-flash","official_rank_by_reasoning":{"highest":67,"medium":77,"none":63},"overall":{"max":47.578410315993644,"mean":22.839151407975447,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":64,"overall_ranking_status":"ranked","per_game":{"GB2-01":8.984795969844429,"GB2-05":37.25806643929657,"GB2-06":29.79705425956356,"GB2-07":24.54431520071972,"GB2-08":10.688962765915543},"per_game_all":{"GB2-01":16.469296751541417,"GB2-06":39.85300547689565,"GB2-07":34.3263803154372},"per_game_match_totals_all":{"GB2-01":{"draws":194,"losses":1235,"wins":157},"GB2-02":{"draws":385,"losses":95,"wins":10},"GB2-03":{"draws":289,"losses":552,"wins":183},"GB2-04":{"draws":323,"losses":154,"wins":33},"GB2-05":{"draws":0,"losses":622,"wins":460},"GB2-06":{"draws":41,"losses":942,"wins":559},"GB2-07":{"draws":0,"losses":1103,"wins":517},"GB2-08":{"draws":308,"losses":725,"wins":53}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":28,"losses":471,"wins":31},"GB2-05":{"draws":0,"losses":339,"wins":203},"GB2-06":{"draws":3,"losses":372,"wins":141},"GB2-07":{"draws":0,"losses":421,"wins":119},"GB2-08":{"draws":46,"losses":467,"wins":31}},"medium":{"GB2-01":{"draws":69,"losses":444,"wins":13},"GB2-03":{"draws":141,"losses":285,"wins":86},"GB2-05":{"draws":0,"losses":283,"wins":257},"GB2-06":{"draws":15,"losses":295,"wins":204},"GB2-07":{"draws":0,"losses":348,"wins":192},"GB2-08":{"draws":262,"losses":258,"wins":22}},"none":{"GB2-01":{"draws":97,"losses":320,"wins":113},"GB2-02":{"draws":385,"losses":95,"wins":10},"GB2-03":{"draws":148,"losses":267,"wins":97},"GB2-04":{"draws":323,"losses":154,"wins":33},"GB2-06":{"draws":23,"losses":275,"wins":214},"GB2-07":{"draws":0,"losses":334,"wins":206}}},"per_game_raw_elo_all":{"GB2-01":1082.9426387523706,"GB2-06":1295.5407950606807,"GB2-07":1235.7890802540985},"per_game_raw_elo_tracks":{"highest":{"GB2-01":969.697814315893,"GB2-05":1284.9558998819477,"GB2-06":1137.5810401596302,"GB2-07":1100.1056900480962,"GB2-08":875.5841913667539},"medium":{"GB2-01":981.963658784497,"GB2-03":1288.4779709180275,"GB2-05":1420.5839869110532,"GB2-06":1350.8736968386168,"GB2-07":1286.9838011753188,"GB2-08":1154.9945601872294},"none":{"GB2-01":1297.166443156722,"GB2-02":1418.8277827277423,"GB2-03":1315.6652705973975,"GB2-04":1394.500923670769,"GB2-06":1398.1676481837956,"GB2-07":1320.27774953888}},"per_game_tracks":{"highest":{"GB2-01":8.984795969844429,"GB2-05":37.25806643929657,"GB2-06":29.79705425956356,"GB2-07":24.54431520071972,"GB2-08":10.688962765915543},"medium":{"GB2-01":9.492019898034645,"GB2-03":32.99387033546252,"GB2-05":47.578410315993644,"GB2-06":43.381273788472576,"GB2-07":37.94443612135961,"GB2-08":29.680242815133195},"none":{"GB2-01":30.931074386745177,"GB2-02":42.584475819006784,"GB2-03":35.948637182340484,"GB2-04":39.46092048663916,"GB2-06":46.38068838265083,"GB2-07":40.490389624232265}},"program_outcomes":{"all":{"counted_attempts":24,"failed":7,"infra_excluded":0,"success_rate":0.7083333333333334,"too_slow":0,"worked_after_repair":10,"worked_first_time":7,"working":17},"highest":{"counted_attempts":8,"failed":3,"infra_excluded":0,"success_rate":0.625,"too_slow":0,"worked_after_repair":5,"worked_first_time":0,"working":5},"medium":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":2,"worked_first_time":4,"working":6},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":3,"worked_first_time":3,"working":6}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T16:54:48Z","reasoning":{"highest":13.90914932941748,"medium":25.133781659307022,"none":29.474523235201833},"reasoning_agg":{"highest":{"max":37.25806643929657,"mean":13.90914932941748,"min":0.0},"medium":{"max":47.578410315993644,"mean":25.133781659307022,"min":0.0},"none":{"max":46.38068838265083,"mean":29.474523235201833,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low"},"score_diagnostics":{"reasoning_variance":15.565373905784353},"working_program_strength":{"all":31.68857070658215,"highest":22.254638927067965,"medium":33.51170887907603,"none":39.299364313602446}},{"canonical_public_row_identity":"publication-row.v1:overall:inception-mercury-2-5-preview:447435701832db27","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":0.007612509999999999}},"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":0.01012224},"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":0.007612509999999999},"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":0.028312970000000003},"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":21.029209931077425,"highest":20.716146288308067,"medium":19.08274195977838,"none":23.288741545145825},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"failed","GB2-05":"failed"},"medium":{"GB2-01":"failed","GB2-03":"failed"},"none":{"GB2-01":"failed","GB2-07":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":26.19185630679989,"score":8.730618768933297},"GB2-02":{"attempts":3,"playable":41.61262489585163,"score":41.61262489585163},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":44.92570311105554,"score":14.975234370351847},"GB2-04":{"attempts":3,"playable":40.54997448152611,"score":40.54997448152611},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":26.440285017736667,"score":17.626856678491112},"GB2-06":{"attempts":3,"playable":16.55976140976966,"score":16.55976140976966},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":12.163388481256474,"score":8.108925654170983},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":30.104524784287143,"score":20.069683189524763}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":26.19185630679989,"score":26.19185630679989},"GB2-02":{"attempts":1,"playable":41.18167298516684,"score":41.18167298516684},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":38.186665509736315,"score":38.186665509736315},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":14.440810185895595,"score":14.440810185895595},"GB2-07":{"attempts":1,"playable":13.66401304392685,"score":13.66401304392685},"GB2-08":{"attempts":1,"playable":32.06415227493903,"score":32.06415227493903}},"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":42.49676670313098,"score":42.49676670313098},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.05620367656769,"score":40.05620367656769},"GB2-05":{"attempts":1,"playable":15.251697417956029,"score":15.251697417956029},"GB2-06":{"attempts":1,"playable":16.049606668351007,"score":16.049606668351007},"GB2-07":{"attempts":1,"playable":10.662763918586098,"score":10.662763918586098},"GB2-08":{"attempts":1,"playable":28.144897293635257,"score":28.144897293635257}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":41.15943499925705,"score":41.15943499925705},"GB2-03":{"attempts":1,"playable":44.92570311105554,"score":44.92570311105554},"GB2-04":{"attempts":1,"playable":43.407054258274314,"score":43.407054258274314},"GB2-05":{"attempts":1,"playable":37.6288726175173,"score":37.6288726175173},"GB2-06":{"attempts":1,"playable":19.188867375062376,"score":19.188867375062376},"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":"2026-11-03T07:11:45Z","match_totals_all":{"draws":2730,"losses":4989,"wins":1135},"match_totals_tracks":{"highest":{"draws":975,"losses":1820,"wins":331},"medium":{"draws":862,"losses":1962,"wins":324},"none":{"draws":893,"losses":1207,"wins":480}},"model_slug":"inception-mercury-2-5-preview","official_rank_by_reasoning":{"highest":65,"medium":82,"none":80},"overall":{"max":44.92570311105554,"mean":21.029209931077425,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":65,"overall_ranking_status":"ranked","per_game":{"GB2-01":26.19185630679989,"GB2-02":41.18167298516684,"GB2-04":38.186665509736315,"GB2-06":14.440810185895595,"GB2-07":13.66401304392685,"GB2-08":32.06415227493903},"per_game_all":{"GB2-02":41.61262489585163,"GB2-04":40.54997448152611,"GB2-06":16.55976140976966},"per_game_match_totals_all":{"GB2-01":{"draws":124,"losses":330,"wins":74},"GB2-02":{"draws":1192,"losses":287,"wins":3},"GB2-03":{"draws":119,"losses":239,"wins":158},"GB2-04":{"draws":1070,"losses":396,"wins":66},"GB2-05":{"draws":0,"losses":797,"wins":287},"GB2-06":{"draws":6,"losses":1309,"wins":231},"GB2-07":{"draws":0,"losses":967,"wins":113},"GB2-08":{"draws":219,"losses":664,"wins":203}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":124,"losses":330,"wins":74},"GB2-02":{"draws":393,"losses":101,"wins":2},"GB2-04":{"draws":350,"losses":146,"wins":12},"GB2-06":{"draws":3,"losses":445,"wins":66},"GB2-07":{"draws":0,"losses":476,"wins":64},"GB2-08":{"draws":105,"losses":322,"wins":113}},"medium":{"GB2-02":{"draws":406,"losses":87,"wins":1},"GB2-04":{"draws":339,"losses":143,"wins":28},"GB2-05":{"draws":0,"losses":460,"wins":82},"GB2-06":{"draws":3,"losses":439,"wins":74},"GB2-07":{"draws":0,"losses":491,"wins":49},"GB2-08":{"draws":114,"losses":342,"wins":90}},"none":{"GB2-02":{"draws":393,"losses":99,"wins":0},"GB2-03":{"draws":119,"losses":239,"wins":158},"GB2-04":{"draws":381,"losses":107,"wins":26},"GB2-05":{"draws":0,"losses":337,"wins":205},"GB2-06":{"draws":0,"losses":425,"wins":91}}},"per_game_raw_elo_all":{"GB2-02":1411.181970379721,"GB2-04":1403.133304788412,"GB2-06":914.7232457657665},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1243.9428442342332,"GB2-02":1407.7909771467548,"GB2-04":1384.2231497369398,"GB2-06":875.0595098296322,"GB2-07":905.9850534310049,"GB2-08":1183.8650026380421},"medium":{"GB2-02":1418.139442875138,"GB2-04":1399.2745650427687,"GB2-05":916.3713661772232,"GB2-06":906.1242625174684,"GB2-07":835.1313644194133,"GB2-08":1136.2199604135683},"none":{"GB2-02":1407.61549111727,"GB2-03":1395.6627553095714,"GB2-04":1425.9021995855283,"GB2-05":1290.0229823627883,"GB2-06":962.9859649501988}},"per_game_tracks":{"highest":{"GB2-01":26.19185630679989,"GB2-02":41.18167298516684,"GB2-04":38.186665509736315,"GB2-06":14.440810185895595,"GB2-07":13.66401304392685,"GB2-08":32.06415227493903},"medium":{"GB2-02":42.49676670313098,"GB2-04":40.05620367656769,"GB2-05":15.251697417956029,"GB2-06":16.049606668351007,"GB2-07":10.662763918586098,"GB2-08":28.144897293635257},"none":{"GB2-02":41.15943499925705,"GB2-03":44.92570311105554,"GB2-04":43.407054258274314,"GB2-05":37.6288726175173,"GB2-06":19.188867375062376}},"program_outcomes":{"all":{"counted_attempts":24,"failed":7,"infra_excluded":0,"success_rate":0.7083333333333334,"too_slow":0,"worked_after_repair":4,"worked_first_time":13,"working":17},"highest":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":1,"worked_first_time":5,"working":6},"medium":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":0,"worked_first_time":6,"working":6},"none":{"counted_attempts":8,"failed":3,"infra_excluded":0,"success_rate":0.625,"too_slow":0,"worked_after_repair":3,"worked_first_time":2,"working":5}},"provider_color":"#CBD5E1","provider_company":"Inception","provider_key":"inception","provider_text_color":"#0b1120","rank_movement":-3,"rank_movement_baseline_at":"2026-10-31T17:07:40Z","reasoning":{"highest":20.716146288308067,"medium":19.08274195977838,"none":23.288741545145825},"reasoning_agg":{"highest":{"max":41.18167298516684,"mean":20.716146288308067,"min":0.0},"medium":{"max":42.49676670313098,"mean":19.08274195977838,"min":0.0},"none":{"max":44.92570311105554,"mean":23.288741545145825,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":4.205999585367444},"working_program_strength":{"all":30.109056934338415,"highest":27.621528384410755,"medium":25.443655946371177,"none":37.26198647223332}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-1-flash-lite:91c933b0f5011fcf","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":0.21994024999999998},"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":0.081084},"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":0.047068750000000006}},"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":0.21994025}},"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":0.34809300000000004},"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":15.236921591828578,"highest":15.741347010337952,"medium":19.23857686328134,"none":10.730840901866443},"first_seen_at":null,"game_gaps":{"all":{"GB2-03":"failed"},"highest":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed"},"medium":{"GB2-02":"failed","GB2-03":"failed"},"none":{"GB2-03":"failed","GB2-04":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":22.424410578715122,"score":14.949607052476749},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":41.88475050164298,"score":13.961583500547661},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":42.070956255056714,"score":28.04730417003781},"GB2-05":{"attempts":3,"playable":10.584998371347456,"score":10.584998371347456},"GB2-06":{"attempts":3,"playable":19.963433777534927,"score":19.963433777534927},"GB2-07":{"attempts":3,"playable":13.808762420986048,"score":13.808762420986048},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":30.86952516254698,"score":20.579683441697988}},"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":42.512979514210656,"score":42.512979514210656},"GB2-05":{"attempts":1,"playable":10.038198493080184,"score":10.038198493080184},"GB2-06":{"attempts":1,"playable":15.688894639065134,"score":15.688894639065134},"GB2-07":{"attempts":1,"playable":32.63884323820556,"score":32.63884323820556},"GB2-08":{"attempts":1,"playable":25.05186019814208,"score":25.05186019814208}},"medium":{"GB2-01":{"attempts":1,"playable":32.326157055898825,"score":32.326157055898825},"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":41.628932995902765,"score":41.628932995902765},"GB2-05":{"attempts":1,"playable":16.16065755994047,"score":16.16065755994047},"GB2-06":{"attempts":1,"playable":20.93491686208266,"score":20.93491686208266},"GB2-07":{"attempts":1,"playable":6.170760305474127,"score":6.170760305474127},"GB2-08":{"attempts":1,"playable":36.68719012695188,"score":36.68719012695188}},"none":{"GB2-01":{"attempts":1,"playable":12.522664101531417,"score":12.522664101531417},"GB2-02":{"attempts":1,"playable":41.88475050164298,"score":41.88475050164298},"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":5.556139061021713,"score":5.556139061021713},"GB2-06":{"attempts":1,"playable":23.266489831456983,"score":23.266489831456983},"GB2-07":{"attempts":1,"playable":2.6166837192784556,"score":2.6166837192784556},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"google/gemini-3.1-flash-lite","is_recent_addition":false,"last_measured_at":"2026-11-03T07:04:21Z","match_totals_all":{"draws":1585,"losses":5834,"wins":1031},"match_totals_tracks":{"highest":{"draws":449,"losses":1798,"wins":405},"medium":{"draws":658,"losses":2073,"wins":453},"none":{"draws":478,"losses":1963,"wins":173}},"model_slug":"google-gemini-3-1-flash-lite","official_rank_by_reasoning":{"highest":66,"medium":81,"none":88},"overall":{"max":42.512979514210656,"mean":15.236921591828578,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":66,"overall_ranking_status":"partial","per_game":{"GB2-04":42.512979514210656,"GB2-05":10.038198493080184,"GB2-06":15.688894639065134,"GB2-07":32.63884323820556,"GB2-08":25.05186019814208},"per_game_all":{"GB2-05":10.584998371347456,"GB2-06":19.963433777534927,"GB2-07":13.808762420986048},"per_game_match_totals_all":{"GB2-01":{"draws":338,"losses":653,"wins":63},"GB2-02":{"draws":385,"losses":101,"wins":8},"GB2-04":{"draws":707,"losses":254,"wins":65},"GB2-05":{"draws":0,"losses":1458,"wins":168},"GB2-06":{"draws":7,"losses":1255,"wins":280},"GB2-07":{"draws":0,"losses":1420,"wins":200},"GB2-08":{"draws":148,"losses":693,"wins":247}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":352,"losses":124,"wins":34},"GB2-05":{"draws":0,"losses":489,"wins":53},"GB2-06":{"draws":0,"losses":442,"wins":74},"GB2-07":{"draws":0,"losses":377,"wins":163},"GB2-08":{"draws":97,"losses":366,"wins":81}},"medium":{"GB2-01":{"draws":249,"losses":235,"wins":44},"GB2-04":{"draws":355,"losses":130,"wins":31},"GB2-05":{"draws":0,"losses":455,"wins":87},"GB2-06":{"draws":3,"losses":413,"wins":98},"GB2-07":{"draws":0,"losses":513,"wins":27},"GB2-08":{"draws":51,"losses":327,"wins":166}},"none":{"GB2-01":{"draws":89,"losses":418,"wins":19},"GB2-02":{"draws":385,"losses":101,"wins":8},"GB2-05":{"draws":0,"losses":514,"wins":28},"GB2-06":{"draws":4,"losses":400,"wins":108},"GB2-07":{"draws":0,"losses":530,"wins":10}}},"per_game_raw_elo_all":{"GB2-05":788.6411750763904,"GB2-06":974.8561637419472,"GB2-07":804.0379736766607},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1418.829746195754,"GB2-05":790.3398064001487,"GB2-06":899.2952099338196,"GB2-07":1216.1502346702027,"GB2-08":1097.623969625963},"medium":{"GB2-01":1312.0921268528061,"GB2-04":1411.8163957652298,"GB2-05":935.6942412094576,"GB2-06":993.1001866736183,"GB2-07":694.3304557081336,"GB2-08":1239.690299412782},"none":{"GB2-01":1046.105373046647,"GB2-02":1413.330288393192,"GB2-05":639.8894776195646,"GB2-06":1032.1730946184039,"GB2-07":501.6332306516457}},"per_game_tracks":{"highest":{"GB2-04":42.512979514210656,"GB2-05":10.038198493080184,"GB2-06":15.688894639065134,"GB2-07":32.63884323820556,"GB2-08":25.05186019814208},"medium":{"GB2-01":32.326157055898825,"GB2-04":41.628932995902765,"GB2-05":16.16065755994047,"GB2-06":20.93491686208266,"GB2-07":6.170760305474127,"GB2-08":36.68719012695188},"none":{"GB2-01":12.522664101531417,"GB2-02":41.88475050164298,"GB2-05":5.556139061021713,"GB2-06":23.266489831456983,"GB2-07":2.6166837192784556}},"program_outcomes":{"all":{"counted_attempts":24,"failed":8,"infra_excluded":0,"success_rate":0.6666666666666666,"too_slow":0,"worked_after_repair":11,"worked_first_time":5,"working":16},"highest":{"counted_attempts":8,"failed":3,"infra_excluded":0,"success_rate":0.625,"too_slow":0,"worked_after_repair":5,"worked_first_time":0,"working":5},"medium":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":4,"worked_first_time":2,"working":6},"none":{"counted_attempts":8,"failed":3,"infra_excluded":0,"success_rate":0.625,"too_slow":0,"worked_after_repair":2,"worked_first_time":3,"working":5}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":15.741347010337952,"medium":19.23857686328134,"none":10.730840901866443},"reasoning_agg":{"highest":{"max":42.512979514210656,"mean":15.741347010337952,"min":0.0},"medium":{"max":41.628932995902765,"mean":19.23857686328134,"min":0.0},"none":{"max":41.88475050164298,"mean":10.730840901866443,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":8.507735961414898},"working_program_strength":{"all":22.66897882574516,"highest":25.186155216540723,"medium":25.651435817708457,"none":17.16934544298631}},{"canonical_public_row_identity":"publication-row.v1:overall:upstage-solar-mini4:68d3619b194c4d1e","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":0.012156649999999998},"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":0.13069025}},"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":{"all":7.73605732043904,"highest":13.06007343593399,"medium":5.218033119017671,"none":4.930065406365456},"first_seen_at":null,"game_gaps":{"all":{"GB2-02":"failed","GB2-03":"failed","GB2-08":"failed"},"highest":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-04":"failed","GB2-08":"failed"},"medium":{"GB2-02":"infra_excluded","GB2-03":"failed","GB2-04":"failed","GB2-05":"failed","GB2-07":"failed","GB2-08":"failed"},"none":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-05":"failed","GB2-06":"failed","GB2-07":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":17.90423979877574,"score":5.968079932925247},"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":39.44052325092365,"score":13.146841083641215},"GB2-05":{"attempts":3,"failed_attempts":2,"playable":43.52168544604584,"score":14.50722848201528},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":23.68964283476689,"score":15.793095223177927},"GB2-07":{"attempts":3,"failed_attempts":2,"playable":32.201608406240254,"score":10.733869468746752},"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":43.52168544604584,"score":43.52168544604584},"GB2-06":{"attempts":1,"playable":28.75729363518582,"score":28.75729363518582},"GB2-07":{"attempts":1,"playable":32.201608406240254,"score":32.201608406240254},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"medium":{"GB2-01":{"attempts":1,"playable":17.90423979877574,"score":17.90423979877574},"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":18.621992034347958,"score":18.621992034347958},"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":39.44052325092365,"score":39.44052325092365},"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":"2026-11-03T06:44:44Z","match_totals_all":{"draws":437,"losses":2025,"wins":692},"match_totals_tracks":{"highest":{"draws":5,"losses":1065,"wins":534},"medium":{"draws":85,"losses":818,"wins":137},"none":{"draws":347,"losses":142,"wins":21}},"model_slug":"upstage-solar-mini4","overall":{"max":43.52168544604584,"mean":7.73605732043904,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold","generation_incomplete"],"overall_official_rank":67,"overall_ranking_status":"partial","per_game":{"GB2-05":43.52168544604584,"GB2-06":28.75729363518582,"GB2-07":32.201608406240254},"per_game_match_totals_all":{"GB2-01":{"draws":80,"losses":396,"wins":52},"GB2-04":{"draws":347,"losses":142,"wins":21},"GB2-05":{"draws":0,"losses":307,"wins":237},"GB2-06":{"draws":10,"losses":799,"wins":221},"GB2-07":{"draws":0,"losses":381,"wins":161}},"per_game_match_totals_tracks":{"highest":{"GB2-05":{"draws":0,"losses":307,"wins":237},"GB2-06":{"draws":5,"losses":377,"wins":136},"GB2-07":{"draws":0,"losses":381,"wins":161}},"medium":{"GB2-01":{"draws":80,"losses":396,"wins":52},"GB2-06":{"draws":5,"losses":422,"wins":85}},"none":{"GB2-04":{"draws":347,"losses":142,"wins":21}}},"per_game_raw_elo_tracks":{"highest":{"GB2-05":1368.2305736474632,"GB2-06":1121.0509159974984,"GB2-07":1210.181856165932},"medium":{"GB2-01":1135.8530443907523,"GB2-06":953.0086412132769},"none":{"GB2-04":1394.337063446179}},"per_game_tracks":{"highest":{"GB2-05":43.52168544604584,"GB2-06":28.75729363518582,"GB2-07":32.201608406240254},"medium":{"GB2-01":17.90423979877574,"GB2-06":18.621992034347958},"none":{"GB2-04":39.44052325092365}},"program_outcomes":{"all":{"counted_attempts":23,"failed":17,"infra_excluded":1,"success_rate":0.2608695652173913,"too_slow":0,"worked_after_repair":4,"worked_first_time":2,"working":6},"highest":{"counted_attempts":8,"failed":5,"infra_excluded":0,"success_rate":0.375,"too_slow":0,"worked_after_repair":3,"worked_first_time":0,"working":3},"medium":{"counted_attempts":7,"failed":5,"infra_excluded":1,"success_rate":0.2857142857142857,"too_slow":0,"worked_after_repair":1,"worked_first_time":1,"working":2},"none":{"counted_attempts":8,"failed":7,"infra_excluded":0,"success_rate":0.125,"too_slow":0,"worked_after_repair":0,"worked_first_time":1,"working":1}},"provider_color":"#805CFB","provider_company":"Upstage","provider_key":"upstage","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":13.060073435933992,"medium":5.218033119017671,"none":4.930065406365456},"reasoning_agg":{"highest":{"max":43.52168544604584,"mean":13.060073435933992,"min":0.0},"medium":{"max":18.621992034347958,"mean":5.218033119017671,"min":0.0},"none":{"max":39.44052325092365,"mean":4.930065406365456,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":8.130008029568536},"working_program_strength":{"all":30.843500554436492,"highest":34.826862495823974,"medium":18.26311591656185,"none":39.44052325092365}},{"canonical_public_row_identity":"publication-row.v1:overall:ibm-granite-granite-4-2-8b:c5eea150f8336c75","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":0.10770047999999997},"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":{"all":1.5701220195267247,"highest":0.0,"medium":4.710366058580174,"none":0.0},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-05":"failed","GB2-06":"failed","GB2-07":"failed","GB2-08":"failed"},"highest":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-04":"failed","GB2-05":"failed","GB2-06":"failed","GB2-07":"failed","GB2-08":"failed"},"medium":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-05":"failed","GB2-06":"failed","GB2-07":"failed","GB2-08":"failed"},"none":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-04":"failed","GB2-05":"failed","GB2-06":"failed","GB2-07":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":37.68292846864139,"score":12.560976156213798},"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":37.68292846864139,"score":37.68292846864139},"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":"2026-11-03T06:47:09Z","match_totals_all":{"draws":321,"losses":166,"wins":27},"match_totals_tracks":{"medium":{"draws":321,"losses":166,"wins":27}},"model_slug":"ibm-granite-granite-4-2-8b","overall":{"max":37.68292846864139,"mean":1.5701220195267247,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold","fixed_coverage_incomplete","grouped_stability_incomplete"],"overall_official_rank":68,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-04":{"draws":321,"losses":166,"wins":27}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":321,"losses":166,"wins":27}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1380.1350043679017}},"per_game_tracks":{"medium":{"GB2-04":37.68292846864139}},"program_outcomes":{"all":{"counted_attempts":24,"failed":23,"infra_excluded":0,"success_rate":0.041666666666666664,"too_slow":0,"worked_after_repair":1,"worked_first_time":0,"working":1},"highest":{"counted_attempts":8,"failed":8,"infra_excluded":0,"success_rate":0.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":0,"working":0},"medium":{"counted_attempts":8,"failed":7,"infra_excluded":0,"success_rate":0.125,"too_slow":0,"worked_after_repair":1,"worked_first_time":0,"working":1},"none":{"counted_attempts":8,"failed":8,"infra_excluded":0,"success_rate":0.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":0,"working":0}},"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":4.710366058580174,"none":0.0},"reasoning_agg":{"highest":{"max":0.0,"mean":0.0,"min":0.0},"medium":{"max":37.68292846864139,"mean":4.710366058580174,"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":4.710366058580174},"working_program_strength":{"all":37.68292846864139,"medium":37.68292846864139}},{"canonical_public_row_identity":"publication-row.v1:overall:unbiased-pareto-26-10:3f4dae3fc99a9dcb","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0450808,"mean":0.029576600000000005,"median":0.028589200000000002,"min":0.0192776,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.2366128}},"codegen_cost_by_setting":{"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":0.0450808,"mean":0.029576600000000005,"median":0.028589200000000002,"min":0.0192776,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.2366128}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0450808,"mean":0.029576600000000005,"median":0.028589200000000002,"min":0.0192776,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.2366128},"codegen_latency_ms":{"attempt_count":8,"max_ms":215199,"mean_ms":151362.125,"min_ms":97625,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":8,"max_ms":215199,"mean_ms":151362.125,"min_ms":97625,"run_count":8}},"codegen_output_tokens":{"attempt_count":8,"output_max":11980,"output_mean":7218.375,"output_min":3411,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":8,"output_max":11980,"output_mean":7218.375,"output_min":3411,"run_count":8}},"display_name":"Pareto 26.10","economics":{"all":89.6892932273046,"none":89.6892932273046},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":8,"effective_max_output_tokens":[131072],"finish_reason_observations":8,"finish_reasons":["stop"],"indexed_attempts":8,"output_token_observations":8,"provider_post_attempt_observations":8,"provider_post_attempts":8,"reasoning_token_observations":8,"reconciliation_get_attempt_observations":8,"requested_max_output_token_observations":8,"requested_max_output_tokens":[131072],"total_output_tokens":57747,"total_visible_output_tokens":57747,"visible_token_observations":8},"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","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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":90.50202364796999,"score":90.50202364796999},"GB2-02":{"attempts":1,"playable":78.60902057873324,"score":78.60902057873324},"GB2-03":{"attempts":1,"playable":95.92888382823925,"score":95.92888382823925},"GB2-04":{"attempts":1,"playable":85.2909377943891,"score":85.2909377943891},"GB2-05":{"attempts":1,"playable":90.71191840226712,"score":90.71191840226712},"GB2-06":{"attempts":1,"playable":91.79270102885849,"score":91.79270102885849},"GB2-07":{"attempts":1,"playable":94.7105866218444,"score":94.7105866218444},"GB2-08":{"attempts":1,"playable":89.9682739161352,"score":89.9682739161352}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":90.50202364796999,"score":90.50202364796999},"GB2-02":{"attempts":1,"playable":78.60902057873324,"score":78.60902057873324},"GB2-03":{"attempts":1,"playable":95.92888382823925,"score":95.92888382823925},"GB2-04":{"attempts":1,"playable":85.2909377943891,"score":85.2909377943891},"GB2-05":{"attempts":1,"playable":90.71191840226712,"score":90.71191840226712},"GB2-06":{"attempts":1,"playable":91.79270102885849,"score":91.79270102885849},"GB2-07":{"attempts":1,"playable":94.7105866218444,"score":94.7105866218444},"GB2-08":{"attempts":1,"playable":89.9682739161352,"score":89.9682739161352}}},"id":"unbiased/pareto-26.10","is_recent_addition":false,"last_measured_at":"2026-11-03T05:48:45Z","match_totals_all":{"draws":276,"losses":289,"wins":3625},"match_totals_tracks":{"none":{"draws":276,"losses":289,"wins":3625}},"model_slug":"unbiased-pareto-26-10","official_rank_by_reasoning":{"none":1},"overall":{"max":95.92888382823925,"mean":89.6892932273046,"min":78.60902057873324},"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":0,"losses":50,"wins":480},"GB2-02":{"draws":190,"losses":15,"wins":291},"GB2-03":{"draws":3,"losses":18,"wins":493},"GB2-04":{"draws":63,"losses":47,"wins":402},"GB2-05":{"draws":0,"losses":49,"wins":493},"GB2-06":{"draws":20,"losses":31,"wins":465},"GB2-07":{"draws":0,"losses":25,"wins":515},"GB2-08":{"draws":0,"losses":54,"wins":486}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":0,"losses":50,"wins":480},"GB2-02":{"draws":190,"losses":15,"wins":291},"GB2-03":{"draws":3,"losses":18,"wins":493},"GB2-04":{"draws":63,"losses":47,"wins":402},"GB2-05":{"draws":0,"losses":49,"wins":493},"GB2-06":{"draws":20,"losses":31,"wins":465},"GB2-07":{"draws":0,"losses":25,"wins":515},"GB2-08":{"draws":0,"losses":54,"wins":486}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":2025.4558432741887,"GB2-02":1742.8817524974334,"GB2-03":2289.8251203145974,"GB2-04":1841.0839843276137,"GB2-05":2329.0772235447444,"GB2-06":2282.2168137951603,"GB2-07":2469.3947584984553,"GB2-08":2223.0556985131766}},"per_game_tracks":{"none":{"GB2-01":90.50202364796999,"GB2-02":78.60902057873324,"GB2-03":95.92888382823925,"GB2-04":85.2909377943891,"GB2-05":90.71191840226712,"GB2-06":91.79270102885849,"GB2-07":94.7105866218444,"GB2-08":89.9682739161352}},"program_outcomes":{"all":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#FF563F","provider_company":"Unbiased","provider_key":"unbiased","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":89.6892932273046},"reasoning_agg":{"none":{"max":95.92888382823925,"mean":89.6892932273046,"min":78.60902057873324}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Provider default (reasoning controls unavailable)"},"reasoning_settings":{"baseline":"default"},"working_program_strength":{"all":89.6892932273046,"none":89.6892932273046}},{"canonical_public_row_identity":"publication-row.v1:overall:unbiased-pareto-26-10-preview:4e6d98f15d48c5ea","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":0.2454376}},"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":0.2454376},"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":{"all":88.42542034404784,"none":88.42542034404784},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":71.41244363822751,"score":71.41244363822751},"GB2-02":{"attempts":1,"playable":90.54050294188258,"score":90.54050294188258},"GB2-03":{"attempts":1,"playable":92.18446978979804,"score":92.18446978979804},"GB2-04":{"attempts":1,"playable":85.56295616158151,"score":85.56295616158151},"GB2-05":{"attempts":1,"playable":93.45361613363475,"score":93.45361613363475},"GB2-06":{"attempts":1,"playable":85.7604189521809,"score":85.7604189521809},"GB2-07":{"attempts":1,"playable":94.89662591140477,"score":94.89662591140477},"GB2-08":{"attempts":1,"playable":93.59232922367265,"score":93.59232922367265}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":71.41244363822751,"score":71.41244363822751},"GB2-02":{"attempts":1,"playable":90.54050294188258,"score":90.54050294188258},"GB2-03":{"attempts":1,"playable":92.18446978979804,"score":92.18446978979804},"GB2-04":{"attempts":1,"playable":85.56295616158151,"score":85.56295616158151},"GB2-05":{"attempts":1,"playable":93.45361613363475,"score":93.45361613363475},"GB2-06":{"attempts":1,"playable":85.7604189521809,"score":85.7604189521809},"GB2-07":{"attempts":1,"playable":94.89662591140477,"score":94.89662591140477},"GB2-08":{"attempts":1,"playable":93.59232922367265,"score":93.59232922367265}}},"id":"unbiased/pareto-26.10-preview","is_recent_addition":false,"last_measured_at":"2026-11-03T08:08:32Z","match_totals_all":{"draws":132,"losses":417,"wins":3645},"match_totals_tracks":{"none":{"draws":132,"losses":417,"wins":3645}},"model_slug":"unbiased-pareto-26-10-preview","official_rank_by_reasoning":{"none":2},"overall":{"max":94.89662591140477,"mean":88.42542034404784,"min":71.41244363822751},"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":17,"losses":144,"wins":369},"GB2-02":{"draws":44,"losses":26,"wins":426},"GB2-03":{"draws":7,"losses":37,"wins":470},"GB2-04":{"draws":44,"losses":55,"wins":413},"GB2-05":{"draws":0,"losses":34,"wins":510},"GB2-06":{"draws":20,"losses":63,"wins":433},"GB2-07":{"draws":0,"losses":24,"wins":516},"GB2-08":{"draws":0,"losses":34,"wins":508}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":17,"losses":144,"wins":369},"GB2-02":{"draws":44,"losses":26,"wins":426},"GB2-03":{"draws":7,"losses":37,"wins":470},"GB2-04":{"draws":44,"losses":55,"wins":413},"GB2-05":{"draws":0,"losses":34,"wins":510},"GB2-06":{"draws":20,"losses":63,"wins":433},"GB2-07":{"draws":0,"losses":24,"wins":516},"GB2-08":{"draws":0,"losses":34,"wins":508}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1709.2721847185328,"GB2-02":1947.3582320893142,"GB2-03":2104.248582859246,"GB2-04":1845.624296640834,"GB2-05":2455.1384400348616,"GB2-06":2119.4322500566354,"GB2-07":2480.5022132967406,"GB2-08":2352.073513050341}},"per_game_tracks":{"none":{"GB2-01":71.41244363822751,"GB2-02":90.54050294188258,"GB2-03":92.18446978979804,"GB2-04":85.56295616158151,"GB2-05":93.45361613363475,"GB2-06":85.7604189521809,"GB2-07":94.89662591140477,"GB2-08":93.59232922367265}},"program_outcomes":{"all":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#FF563F","provider_company":"Unbiased","provider_key":"unbiased","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":88.42542034404784},"reasoning_agg":{"none":{"max":94.89662591140477,"mean":88.42542034404784,"min":71.41244363822751}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Provider default (reasoning controls unavailable)"},"reasoning_settings":{"baseline":"default"},"working_program_strength":{"all":88.42542034404784,"none":88.42542034404784}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-pro:95e9c36e7c626276","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":0.455327115},"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":0.05751308999999999}},"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":0.512840205},"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":{"all":60.45544235642677,"medium":71.32038706103137,"none":49.59049765182218},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":44.84143604906137,"score":44.84143604906137},"GB2-02":{"attempts":2,"playable":59.23982205650693,"score":59.23982205650693},"GB2-03":{"attempts":2,"playable":63.80923031605555,"score":63.80923031605555},"GB2-04":{"attempts":2,"playable":50.046331179400326,"score":50.046331179400326},"GB2-05":{"attempts":2,"playable":63.49636547162892,"score":63.49636547162892},"GB2-06":{"attempts":2,"playable":54.00541297973587,"score":54.00541297973587},"GB2-07":{"attempts":2,"playable":64.96011662644061,"score":64.96011662644061},"GB2-08":{"attempts":2,"playable":83.24482417258466,"score":83.24482417258466}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":51.92833425428276,"score":51.92833425428276},"GB2-02":{"attempts":1,"playable":79.04236239953578,"score":79.04236239953578},"GB2-03":{"attempts":1,"playable":83.86096319888233,"score":83.86096319888233},"GB2-04":{"attempts":1,"playable":45.62139197791063,"score":45.62139197791063},"GB2-05":{"attempts":1,"playable":83.2267624677438,"score":83.2267624677438},"GB2-06":{"attempts":1,"playable":54.202992642647295,"score":54.202992642647295},"GB2-07":{"attempts":1,"playable":87.90406701496762,"score":87.90406701496762},"GB2-08":{"attempts":1,"playable":84.77622253228077,"score":84.77622253228077}},"none":{"GB2-01":{"attempts":1,"playable":37.75453784383999,"score":37.75453784383999},"GB2-02":{"attempts":1,"playable":39.437281713478086,"score":39.437281713478086},"GB2-03":{"attempts":1,"playable":43.757497433228764,"score":43.757497433228764},"GB2-04":{"attempts":1,"playable":54.47127038089001,"score":54.47127038089001},"GB2-05":{"attempts":1,"playable":43.76596847551404,"score":43.76596847551404},"GB2-06":{"attempts":1,"playable":53.80783331682445,"score":53.80783331682445},"GB2-07":{"attempts":1,"playable":42.0161662379136,"score":42.0161662379136},"GB2-08":{"attempts":1,"playable":81.71342581288854,"score":81.71342581288854}}},"id":"xiaomi/mimo-v2.6-pro","is_recent_addition":false,"last_measured_at":"2026-11-03T08:03:50Z","match_totals_all":{"draws":1425,"losses":2664,"wins":4275},"match_totals_tracks":{"medium":{"draws":394,"losses":1018,"wins":2764},"none":{"draws":1031,"losses":1646,"wins":1511}},"model_slug":"xiaomi-mimo-v2-6-pro","official_rank_by_reasoning":{"medium":12,"none":23},"overall":{"max":87.90406701496762,"mean":60.45544235642677,"min":37.75453784383999},"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":317,"losses":429,"wins":312},"GB2-02":{"draws":453,"losses":186,"wins":349},"GB2-03":{"draws":100,"losses":340,"wins":584},"GB2-04":{"draws":511,"losses":268,"wins":241},"GB2-05":{"draws":0,"losses":398,"wins":686},"GB2-06":{"draws":44,"losses":470,"wins":512},"GB2-07":{"draws":0,"losses":389,"wins":691},"GB2-08":{"draws":0,"losses":184,"wins":900}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":82,"losses":213,"wins":231},"GB2-02":{"draws":93,"losses":61,"wins":340},"GB2-03":{"draws":4,"losses":86,"wins":422},"GB2-04":{"draws":187,"losses":190,"wins":131},"GB2-05":{"draws":0,"losses":91,"wins":449},"GB2-06":{"draws":28,"losses":231,"wins":255},"GB2-07":{"draws":0,"losses":63,"wins":477},"GB2-08":{"draws":0,"losses":83,"wins":459}},"none":{"GB2-01":{"draws":235,"losses":216,"wins":81},"GB2-02":{"draws":360,"losses":125,"wins":9},"GB2-03":{"draws":96,"losses":254,"wins":162},"GB2-04":{"draws":324,"losses":78,"wins":110},"GB2-05":{"draws":0,"losses":307,"wins":237},"GB2-06":{"draws":16,"losses":239,"wins":257},"GB2-07":{"draws":0,"losses":326,"wins":214},"GB2-08":{"draws":0,"losses":101,"wins":441}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1505.8784920465182,"GB2-02":1748.3842455979861,"GB2-03":1865.4908343752304,"GB2-04":1443.3610606318002,"GB2-05":2060.512504769627,"GB2-06":1524.4155686410436,"GB2-07":2144.468420589512,"GB2-08":2080.45214659622},"none":{"GB2-01":1367.9263985675686,"GB2-02":1393.964322868096,"GB2-03":1385.3286924156016,"GB2-04":1513.5904052650533,"GB2-05":1371.4030438217258,"GB2-06":1517.8912749558024,"GB2-07":1340.1193150228262,"GB2-08":2006.9166282341005}},"per_game_tracks":{"medium":{"GB2-01":51.92833425428276,"GB2-02":79.04236239953578,"GB2-03":83.86096319888233,"GB2-04":45.62139197791063,"GB2-05":83.2267624677438,"GB2-06":54.202992642647295,"GB2-07":87.90406701496762,"GB2-08":84.77622253228077},"none":{"GB2-01":37.75453784383999,"GB2-02":39.437281713478086,"GB2-03":43.757497433228764,"GB2-04":54.47127038089001,"GB2-05":43.76596847551404,"GB2-06":53.80783331682445,"GB2-07":42.0161662379136,"GB2-08":81.71342581288854}},"program_outcomes":{"all":{"counted_attempts":16,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":14,"working":16},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":71.32038706103137,"none":49.59049765182218},"reasoning_agg":{"medium":{"max":87.90406701496762,"mean":71.32038706103137,"min":45.62139197791063},"none":{"max":81.71342581288854,"mean":49.59049765182218,"min":37.75453784383999}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":21.729889409209186},"working_program_strength":{"all":60.45544235642677,"medium":71.32038706103137,"none":49.59049765182218}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-5-preview:2cae0f4197b494f3","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":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.181248,"mean":0.181248,"median":0.181248,"min":0.181248,"recorded_attempt_count":1,"run_count":1,"total":0.181248},"none":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1905706,"mean":0.129429625,"median":0.13104325,"min":0.0897486,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":9,"total":1.1975318999999998}},"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":0.181248,"mean":0.181248,"median":0.181248,"min":0.181248,"recorded_attempt_count":1,"run_count":1,"total":0.181248},"historical-provider-setting-baseline":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1905706,"mean":0.129429625,"median":0.13104325,"min":0.0897486,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":9,"total":1.1975319},"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":9,"cell_count":10,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1905706,"mean":0.1400104,"median":0.13912960000000002,"min":0.0897486,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":13,"run_count":11,"total":1.5621989},"codegen_latency_ms":{"attempt_count":11,"max_ms":358795,"mean_ms":240510.44444444444,"min_ms":160537,"run_count":9},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":11,"max_ms":358795,"mean_ms":240510.44444444444,"min_ms":160537,"run_count":9}},"codegen_output_tokens":{"attempt_count":13,"output_max":77071,"output_mean":48934.09090909091,"output_min":30460,"run_count":11},"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":1,"output_max":64000,"output_mean":64000.0,"output_min":64000,"run_count":1},"none":{"attempt_count":11,"output_max":77071,"output_mean":45586.11111111111,"output_min":30460,"run_count":9}},"display_name":"Step 5 Preview","economics":{"all":52.16021067742903,"none":52.16021067742903},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":13,"effective_max_output_tokens":[64000],"finish_reason_observations":11,"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":[64000],"total_output_tokens":538275,"total_visible_output_tokens":538275,"visible_token_observations":13},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":9,"evaluated_cells":9,"first_pass_admitted":7,"first_pass_rate":0.7777777777777778,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":2},"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":0.2222222222222222}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":62.54568772667305,"score":62.54568772667305},"GB2-02":{"attempts":1,"playable":64.65436700687165,"score":64.65436700687165},"GB2-03":{"attempts":2,"playable":51.67171867648979,"score":51.67171867648979},"GB2-04":{"attempts":1,"playable":36.1147155392166,"score":36.1147155392166},"GB2-05":{"attempts":1,"playable":59.88071331517153,"score":59.88071331517153},"GB2-06":{"attempts":1,"playable":66.42603361365256,"score":66.42603361365256},"GB2-07":{"attempts":1,"playable":54.605502282984006,"score":54.605502282984006},"GB2-08":{"attempts":1,"playable":21.382947258373022,"score":21.382947258373022}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":62.54568772667305,"score":62.54568772667305},"GB2-02":{"attempts":1,"playable":64.65436700687165,"score":64.65436700687165},"GB2-03":{"attempts":2,"playable":51.67171867648979,"score":51.67171867648979},"GB2-04":{"attempts":1,"playable":36.1147155392166,"score":36.1147155392166},"GB2-05":{"attempts":1,"playable":59.88071331517153,"score":59.88071331517153},"GB2-06":{"attempts":1,"playable":66.42603361365256,"score":66.42603361365256},"GB2-07":{"attempts":1,"playable":54.605502282984006,"score":54.605502282984006},"GB2-08":{"attempts":1,"playable":21.382947258373022,"score":21.382947258373022}}},"id":"stepfun/step-5-preview","is_recent_addition":false,"last_measured_at":"2026-11-03T07:16:19Z","match_totals_all":{"draws":395,"losses":1276,"wins":1264},"match_totals_tracks":{"none":{"draws":395,"losses":1276,"wins":1264}},"model_slug":"stepfun-step-5-preview","official_rank_by_reasoning":{"none":18},"overall":{"max":66.42603361365256,"mean":52.16021067742903,"min":21.382947258373022},"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":3,"losses":113,"wins":200},"GB2-02":{"draws":134,"losses":56,"wins":140},"GB2-03":{"draws":82,"losses":219,"wins":204},"GB2-04":{"draws":174,"losses":169,"wins":51},"GB2-05":{"draws":0,"losses":155,"wins":211},"GB2-06":{"draws":2,"losses":112,"wins":208},"GB2-07":{"draws":0,"losses":137,"wins":169},"GB2-08":{"draws":0,"losses":315,"wins":81}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":3,"losses":113,"wins":200},"GB2-02":{"draws":134,"losses":56,"wins":140},"GB2-03":{"draws":82,"losses":219,"wins":204},"GB2-04":{"draws":174,"losses":169,"wins":51},"GB2-05":{"draws":0,"losses":155,"wins":211},"GB2-06":{"draws":2,"losses":112,"wins":208},"GB2-07":{"draws":0,"losses":137,"wins":169},"GB2-08":{"draws":0,"losses":315,"wins":81}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1611.548157034677,"GB2-02":1597.5322403110226,"GB2-03":1456.6355971436706,"GB2-04":1367.3015969503838,"GB2-05":1583.784669062475,"GB2-06":1736.7713266386386,"GB2-07":1504.865736328411,"GB2-08":1049.6370062365881}},"per_game_tracks":{"none":{"GB2-01":62.54568772667305,"GB2-02":64.65436700687165,"GB2-03":51.67171867648979,"GB2-04":36.1147155392166,"GB2-05":59.88071331517153,"GB2-06":66.42603361365256,"GB2-07":54.605502282984006,"GB2-08":21.382947258373022}},"program_outcomes":{"all":{"counted_attempts":9,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":7,"working":9},"none":{"counted_attempts":9,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":7,"working":9}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":52.16021067742903},"reasoning_agg":{"none":{"max":66.42603361365256,"mean":52.16021067742903,"min":21.382947258373022}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Low"},"reasoning_settings":{"baseline":"low"},"working_program_strength":{"all":52.16021067742903,"none":52.16021067742903}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-flash:34592c5a4472b8d3","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":0.14258062},"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":0.023437400000000004}},"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":0.14258062000000002},"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":0.0234374}},"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":{"all":48.908464917927546,"medium":58.44018969311666,"none":39.37674014273844},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-04":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":58.472248338691216,"score":58.472248338691216},"GB2-02":{"attempts":2,"playable":53.361245961372845,"score":53.361245961372845},"GB2-03":{"attempts":2,"playable":49.63269830507769,"score":49.63269830507769},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":57.669748894460994,"score":28.834874447230497},"GB2-05":{"attempts":2,"playable":53.3125902452402,"score":53.3125902452402},"GB2-06":{"attempts":2,"playable":55.042009360317095,"score":55.042009360317095},"GB2-07":{"attempts":2,"playable":60.34289398236177,"score":60.34289398236177},"GB2-08":{"attempts":2,"playable":32.269158703129094,"score":32.269158703129094}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":50.2424612489639,"score":50.2424612489639},"GB2-02":{"attempts":1,"playable":65.4606204210063,"score":65.4606204210063},"GB2-03":{"attempts":1,"playable":60.50466887221442,"score":60.50466887221442},"GB2-04":{"attempts":1,"playable":57.669748894460994,"score":57.669748894460994},"GB2-05":{"attempts":1,"playable":56.9341438395084,"score":56.9341438395084},"GB2-06":{"attempts":1,"playable":62.75222162604186,"score":62.75222162604186},"GB2-07":{"attempts":1,"playable":81.08249615635197,"score":81.08249615635197},"GB2-08":{"attempts":1,"playable":32.87515648638546,"score":32.87515648638546}},"none":{"GB2-01":{"attempts":1,"playable":66.70203542841854,"score":66.70203542841854},"GB2-02":{"attempts":1,"playable":41.2618715017394,"score":41.2618715017394},"GB2-03":{"attempts":1,"playable":38.76072773794096,"score":38.76072773794096},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":49.691036650971995,"score":49.691036650971995},"GB2-06":{"attempts":1,"playable":47.33179709459233,"score":47.33179709459233},"GB2-07":{"attempts":1,"playable":39.60329180837158,"score":39.60329180837158},"GB2-08":{"attempts":1,"playable":31.663160919872723,"score":31.663160919872723}}},"id":"xiaomi/mimo-v2.6-flash","is_recent_addition":false,"last_measured_at":"2026-11-03T07:14:40Z","match_totals_all":{"draws":1199,"losses":3258,"wins":3393},"match_totals_tracks":{"medium":{"draws":430,"losses":1571,"wins":2179},"none":{"draws":769,"losses":1687,"wins":1214}},"model_slug":"xiaomi-mimo-v2-6-flash","official_rank_by_reasoning":{"medium":25,"none":46},"overall":{"max":81.08249615635197,"mean":48.908464917927546,"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":185,"losses":346,"wins":521},"GB2-02":{"draws":574,"losses":184,"wins":226},"GB2-03":{"draws":191,"losses":447,"wins":386},"GB2-04":{"draws":52,"losses":197,"wins":261},"GB2-05":{"draws":0,"losses":507,"wins":577},"GB2-06":{"draws":32,"losses":466,"wins":532},"GB2-07":{"draws":0,"losses":442,"wins":638},"GB2-08":{"draws":165,"losses":669,"wins":252}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":20,"losses":252,"wins":252},"GB2-02":{"draws":214,"losses":69,"wins":209},"GB2-03":{"draws":37,"losses":198,"wins":279},"GB2-04":{"draws":52,"losses":197,"wins":261},"GB2-05":{"draws":0,"losses":234,"wins":308},"GB2-06":{"draws":17,"losses":190,"wins":307},"GB2-07":{"draws":0,"losses":102,"wins":438},"GB2-08":{"draws":90,"losses":329,"wins":125}},"none":{"GB2-01":{"draws":165,"losses":94,"wins":269},"GB2-02":{"draws":360,"losses":115,"wins":17},"GB2-03":{"draws":154,"losses":249,"wins":107},"GB2-05":{"draws":0,"losses":273,"wins":269},"GB2-06":{"draws":15,"losses":276,"wins":225},"GB2-07":{"draws":0,"losses":340,"wins":200},"GB2-08":{"draws":75,"losses":340,"wins":127}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1489.586180373965,"GB2-02":1604.7831622520503,"GB2-03":1540.1195245450406,"GB2-04":1539.7458252258166,"GB2-05":1542.9997722195062,"GB2-06":1670.758100269565,"GB2-07":1939.5798340560766,"GB2-08":1193.646247807482},"none":{"GB2-01":1655.7513457483708,"GB2-02":1408.4236966174744,"GB2-03":1340.991631952225,"GB2-05":1447.7665381268796,"GB2-06":1413.2548681027542,"GB2-07":1308.7091618785323,"GB2-08":1179.0240059408952}},"per_game_tracks":{"medium":{"GB2-01":50.2424612489639,"GB2-02":65.4606204210063,"GB2-03":60.50466887221442,"GB2-04":57.669748894460994,"GB2-05":56.9341438395084,"GB2-06":62.75222162604186,"GB2-07":81.08249615635197,"GB2-08":32.87515648638546},"none":{"GB2-01":66.70203542841854,"GB2-02":41.2618715017394,"GB2-03":38.76072773794096,"GB2-05":49.691036650971995,"GB2-06":47.33179709459233,"GB2-07":39.60329180837158,"GB2-08":31.663160919872723}},"program_outcomes":{"all":{"counted_attempts":16,"failed":1,"infra_excluded":0,"success_rate":0.9375,"too_slow":0,"worked_after_repair":6,"worked_first_time":9,"working":15},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":58.44018969311666,"none":39.37674014273845},"reasoning_agg":{"medium":{"max":81.08249615635197,"mean":58.44018969311666,"min":32.87515648638546},"none":{"max":66.70203542841854,"mean":39.37674014273845,"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":19.06344955037821},"working_program_strength":{"all":51.72108921383744,"medium":58.44018969311666,"none":45.00198873455822}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-flash:6c410ee360c44f11","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":0.32899823},"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":{"all":46.6492155198132,"medium":61.672097270190505,"none":31.626333769435885},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":41.52449059370673,"score":41.52449059370673},"GB2-02":{"attempts":2,"playable":49.6762473558086,"score":49.6762473558086},"GB2-03":{"attempts":2,"playable":54.60879423503004,"score":54.60879423503004},"GB2-04":{"attempts":2,"playable":43.45991584652507,"score":43.45991584652507},"GB2-05":{"attempts":2,"playable":42.24183485667709,"score":42.24183485667709},"GB2-06":{"attempts":2,"playable":64.89354629253428,"score":64.89354629253428},"GB2-07":{"attempts":2,"playable":41.48433109544872,"score":41.48433109544872},"GB2-08":{"attempts":2,"playable":35.30456388277503,"score":35.30456388277503}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":50.44079016850731,"score":50.44079016850731},"GB2-02":{"attempts":1,"playable":56.9643809849547,"score":56.9643809849547},"GB2-03":{"attempts":1,"playable":65.03614750111284,"score":65.03614750111284},"GB2-04":{"attempts":1,"playable":47.93040812072796,"score":47.93040812072796},"GB2-05":{"attempts":1,"playable":68.51141953165697,"score":68.51141953165697},"GB2-06":{"attempts":1,"playable":78.09555163365215,"score":78.09555163365215},"GB2-07":{"attempts":1,"playable":73.27834523118362,"score":73.27834523118362},"GB2-08":{"attempts":1,"playable":53.119734989728485,"score":53.119734989728485}},"none":{"GB2-01":{"attempts":1,"playable":32.60819101890615,"score":32.60819101890615},"GB2-02":{"attempts":1,"playable":42.3881137266625,"score":42.3881137266625},"GB2-03":{"attempts":1,"playable":44.18144096894724,"score":44.18144096894724},"GB2-04":{"attempts":1,"playable":38.98942357232218,"score":38.98942357232218},"GB2-05":{"attempts":1,"playable":15.97225018169721,"score":15.97225018169721},"GB2-06":{"attempts":1,"playable":51.691540951416414,"score":51.691540951416414},"GB2-07":{"attempts":1,"playable":9.690316959713808,"score":9.690316959713808},"GB2-08":{"attempts":1,"playable":17.489392775821564,"score":17.489392775821564}}},"id":"qwen/qwen3.8-flash","is_recent_addition":false,"last_measured_at":"2026-11-03T07:04:00Z","match_totals_all":{"draws":2031,"losses":3563,"wins":2780},"match_totals_tracks":{"medium":{"draws":961,"losses":1166,"wins":2061},"none":{"draws":1070,"losses":2397,"wins":719}},"model_slug":"qwen-qwen3-8-flash","official_rank_by_reasoning":{"medium":20,"none":58},"overall":{"max":78.09555163365215,"mean":46.6492155198132,"min":9.690316959713808},"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":298,"losses":472,"wins":286},"GB2-02":{"draws":649,"losses":184,"wins":153},"GB2-03":{"draws":264,"losses":362,"wins":404},"GB2-04":{"draws":629,"losses":279,"wins":118},"GB2-05":{"draws":0,"losses":629,"wins":457},"GB2-06":{"draws":36,"losses":355,"wins":635},"GB2-07":{"draws":0,"losses":643,"wins":437},"GB2-08":{"draws":155,"losses":639,"wins":290}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":184,"losses":171,"wins":173},"GB2-02":{"draws":268,"losses":85,"wins":141},"GB2-03":{"draws":134,"losses":126,"wins":256},"GB2-04":{"draws":293,"losses":127,"wins":92},"GB2-05":{"draws":0,"losses":173,"wins":371},"GB2-06":{"draws":31,"losses":99,"wins":382},"GB2-07":{"draws":0,"losses":147,"wins":393},"GB2-08":{"draws":51,"losses":238,"wins":253}},"none":{"GB2-01":{"draws":114,"losses":301,"wins":113},"GB2-02":{"draws":381,"losses":99,"wins":12},"GB2-03":{"draws":130,"losses":236,"wins":148},"GB2-04":{"draws":336,"losses":152,"wins":26},"GB2-05":{"draws":0,"losses":456,"wins":86},"GB2-06":{"draws":5,"losses":256,"wins":253},"GB2-07":{"draws":0,"losses":496,"wins":44},"GB2-08":{"draws":104,"losses":401,"wins":37}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1491.500187067927,"GB2-02":1532.1936050513664,"GB2-03":1587.585869351527,"GB2-04":1461.54158612366,"GB2-05":1717.7549937327146,"GB2-06":1957.2428777954503,"GB2-07":1782.3072131464728,"GB2-08":1456.9959644995893},"none":{"GB2-01":1315.0760780374285,"GB2-02":1417.2864464753075,"GB2-03":1389.0780149814998,"GB2-04":1390.707928173012,"GB2-05":931.7368915581628,"GB2-06":1483.2566404899121,"GB2-07":809.1265591883845,"GB2-08":994.3006651276423}},"per_game_tracks":{"medium":{"GB2-01":50.44079016850731,"GB2-02":56.9643809849547,"GB2-03":65.03614750111284,"GB2-04":47.93040812072796,"GB2-05":68.51141953165697,"GB2-06":78.09555163365215,"GB2-07":73.27834523118362,"GB2-08":53.119734989728485},"none":{"GB2-01":32.60819101890615,"GB2-02":42.3881137266625,"GB2-03":44.18144096894724,"GB2-04":38.98942357232218,"GB2-05":15.97225018169721,"GB2-06":51.691540951416414,"GB2-07":9.690316959713808,"GB2-08":17.489392775821564}},"program_outcomes":{"all":{"counted_attempts":16,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":6,"worked_first_time":10,"working":16},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":61.672097270190505,"none":31.626333769435885},"reasoning_agg":{"medium":{"max":78.09555163365215,"mean":61.672097270190505,"min":47.93040812072796},"none":{"max":51.691540951416414,"mean":31.626333769435885,"min":9.690316959713808}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":30.04576350075462},"working_program_strength":{"all":46.6492155198132,"medium":61.672097270190505,"none":31.626333769435885}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-large-4-0:2e0f5c88da762ffa","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":0.16924832999999997}},"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":1.6981897299999997},"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":{"all":45.195610684601384,"highest":56.055045981283655,"none":34.33617538791911},"first_seen_at":null,"game_gaps":{"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":45.40429207732788,"score":45.40429207732788},"GB2-02":{"attempts":2,"playable":53.532448055763155,"score":53.532448055763155},"GB2-03":{"attempts":2,"playable":35.92829319668764,"score":35.92829319668764},"GB2-04":{"attempts":2,"playable":51.585411589950155,"score":51.585411589950155},"GB2-05":{"attempts":2,"playable":53.4630547956874,"score":53.4630547956874},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":76.35613819968079,"score":38.17806909984039},"GB2-07":{"attempts":2,"playable":43.37084567902349,"score":43.37084567902349},"GB2-08":{"attempts":2,"playable":40.10247098253093,"score":40.10247098253093}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":33.141479636785164,"score":33.141479636785164},"GB2-02":{"attempts":1,"playable":64.7721388226537,"score":64.7721388226537},"GB2-03":{"attempts":1,"playable":42.24860227884937,"score":42.24860227884937},"GB2-04":{"attempts":1,"playable":65.98769920600239,"score":65.98769920600239},"GB2-05":{"attempts":1,"playable":46.4548460466474,"score":46.4548460466474},"GB2-06":{"attempts":1,"playable":76.35613819968079,"score":76.35613819968079},"GB2-07":{"attempts":1,"playable":77.2568352399559,"score":77.2568352399559},"GB2-08":{"attempts":1,"playable":42.22262841969453,"score":42.22262841969453}},"none":{"GB2-01":{"attempts":1,"playable":57.667104517870605,"score":57.667104517870605},"GB2-02":{"attempts":1,"playable":42.29275728887261,"score":42.29275728887261},"GB2-03":{"attempts":1,"playable":29.607984114525916,"score":29.607984114525916},"GB2-04":{"attempts":1,"playable":37.18312397389793,"score":37.18312397389793},"GB2-05":{"attempts":1,"playable":60.47126354472739,"score":60.47126354472739},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":9.484856118091074,"score":9.484856118091074},"GB2-08":{"attempts":1,"playable":37.98231354536733,"score":37.98231354536733}}},"id":"mistralai/mistral-large-4-0","is_recent_addition":false,"last_measured_at":"2026-11-03T08:07:20Z","match_totals_all":{"draws":2226,"losses":3050,"wins":2584},"match_totals_tracks":{"highest":{"draws":1008,"losses":1386,"wins":1798},"none":{"draws":1218,"losses":1664,"wins":786}},"model_slug":"mistralai-mistral-large-4-0","official_rank_by_reasoning":{"highest":38,"none":56},"overall":{"max":77.2568352399559,"mean":45.195610684601384,"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":33.141479636785164,"GB2-02":64.7721388226537,"GB2-03":42.24860227884937,"GB2-04":65.98769920600239,"GB2-05":46.4548460466474,"GB2-06":76.35613819968079,"GB2-07":77.2568352399559,"GB2-08":42.22262841969453},"per_game_match_totals_all":{"GB2-01":{"draws":132,"losses":512,"wins":408},"GB2-02":{"draws":673,"losses":136,"wins":183},"GB2-03":{"draws":350,"losses":511,"wins":169},"GB2-04":{"draws":531,"losses":242,"wins":249},"GB2-05":{"draws":0,"losses":506,"wins":578},"GB2-06":{"draws":36,"losses":106,"wins":372},"GB2-07":{"draws":0,"losses":621,"wins":459},"GB2-08":{"draws":504,"losses":416,"wins":166}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":22,"losses":344,"wins":162},"GB2-02":{"draws":278,"losses":42,"wins":178},"GB2-03":{"draws":182,"losses":221,"wins":113},"GB2-04":{"draws":239,"losses":61,"wins":212},"GB2-05":{"draws":0,"losses":291,"wins":251},"GB2-06":{"draws":36,"losses":106,"wins":372},"GB2-07":{"draws":0,"losses":124,"wins":416},"GB2-08":{"draws":251,"losses":197,"wins":94}},"none":{"GB2-01":{"draws":110,"losses":168,"wins":246},"GB2-02":{"draws":395,"losses":94,"wins":5},"GB2-03":{"draws":168,"losses":290,"wins":56},"GB2-04":{"draws":292,"losses":181,"wins":37},"GB2-05":{"draws":0,"losses":215,"wins":327},"GB2-07":{"draws":0,"losses":497,"wins":43},"GB2-08":{"draws":253,"losses":219,"wins":72}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1320.6896291155135,"GB2-02":1598.5855773580597,"GB2-03":1371.9822808591996,"GB2-04":1612.0655671076192,"GB2-05":1406.1320413719166,"GB2-06":1923.1680018451646,"GB2-07":1856.3736419962468,"GB2-08":1308.0976308464908},"none":{"GB2-01":1562.0766563739373,"GB2-02":1416.5375660447883,"GB2-03":1256.2341245041098,"GB2-04":1376.063122499792,"GB2-05":1592.1814620337536,"GB2-07":803.3891887850668,"GB2-08":1255.4613949551783}},"per_game_tracks":{"highest":{"GB2-01":33.141479636785164,"GB2-02":64.7721388226537,"GB2-03":42.24860227884937,"GB2-04":65.98769920600239,"GB2-05":46.4548460466474,"GB2-06":76.35613819968079,"GB2-07":77.2568352399559,"GB2-08":42.22262841969453},"none":{"GB2-01":57.667104517870605,"GB2-02":42.29275728887261,"GB2-03":29.607984114525916,"GB2-04":37.18312397389793,"GB2-05":60.47126354472739,"GB2-07":9.484856118091074,"GB2-08":37.98231354536733}},"program_outcomes":{"all":{"counted_attempts":16,"failed":1,"infra_excluded":0,"success_rate":0.9375,"too_slow":0,"worked_after_repair":4,"worked_first_time":11,"working":15},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":56.055045981283655,"none":34.33617538791911},"reasoning_agg":{"highest":{"max":77.2568352399559,"mean":56.055045981283655,"min":33.141479636785164},"none":{"max":60.47126354472739,"mean":34.33617538791911,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":21.718870593364542},"working_program_strength":{"all":47.64819464088132,"highest":56.055045981283655,"none":39.24134330047899}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-1-flash:1c5b561ce24b9b78","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":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0247314,"mean":0.007667503125,"median":0.0038676375,"min":0.00127815,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.061340025}},"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":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0247314,"mean":0.007667503125,"median":0.0038676375,"min":0.00127815,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.061340025000000006}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":9,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0247314,"mean":0.006815558333333333,"median":0.0033986249999999997,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":15,"run_count":9,"total":0.061340025},"codegen_latency_ms":{"attempt_count":14,"max_ms":935199,"mean_ms":264027.375,"min_ms":25587,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":14,"max_ms":935199,"mean_ms":264027.375,"min_ms":25587,"run_count":8}},"codegen_output_tokens":{"attempt_count":15,"output_max":102151,"output_mean":29500.333333333332,"output_min":3161,"run_count":9},"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":14,"output_max":102151,"output_mean":29091.875,"output_min":3161,"run_count":8}},"display_name":"Ling 3.1 Flash","economics":{"all":43.514995701124704,"none":43.514995701124704},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":15,"effective_max_output_tokens":[32768,262144],"finish_reason_observations":14,"finish_reasons":["stop"],"indexed_attempts":15,"output_token_observations":15,"provider_post_attempt_observations":15,"provider_post_attempts":16,"reasoning_token_observations":15,"reconciliation_get_attempt_observations":15,"requested_max_output_token_observations":15,"requested_max_output_tokens":[32768,262144],"total_output_tokens":265503,"total_reasoning_output_tokens":30791,"total_visible_output_tokens":234712,"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":"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-3.1-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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":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":{"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":5,"repaired_rate":0.625}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":46.88594575220492,"score":46.88594575220492},"GB2-02":{"attempts":1,"playable":43.866682960092156,"score":43.866682960092156},"GB2-03":{"attempts":1,"playable":38.889360494836765,"score":38.889360494836765},"GB2-04":{"attempts":1,"playable":43.03187493012393,"score":43.03187493012393},"GB2-05":{"attempts":1,"playable":59.11299589039325,"score":59.11299589039325},"GB2-06":{"attempts":1,"playable":24.607890813898024,"score":24.607890813898024},"GB2-07":{"attempts":1,"playable":23.17332094718862,"score":23.17332094718862},"GB2-08":{"attempts":1,"playable":68.55189382025989,"score":68.55189382025989}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":46.88594575220492,"score":46.88594575220492},"GB2-02":{"attempts":1,"playable":43.866682960092156,"score":43.866682960092156},"GB2-03":{"attempts":1,"playable":38.889360494836765,"score":38.889360494836765},"GB2-04":{"attempts":1,"playable":43.03187493012393,"score":43.03187493012393},"GB2-05":{"attempts":1,"playable":59.11299589039325,"score":59.11299589039325},"GB2-06":{"attempts":1,"playable":24.607890813898024,"score":24.607890813898024},"GB2-07":{"attempts":1,"playable":23.17332094718862,"score":23.17332094718862},"GB2-08":{"attempts":1,"playable":68.55189382025989,"score":68.55189382025989}}},"id":"inclusionai/ling-3.1-flash","is_recent_addition":false,"last_measured_at":"2026-11-03T08:08:32Z","match_totals_all":{"draws":658,"losses":882,"wins":502},"match_totals_tracks":{"none":{"draws":658,"losses":882,"wins":502}},"model_slug":"inclusionai-ling-3-1-flash","official_rank_by_reasoning":{"none":33},"overall":{"max":68.55189382025989,"mean":43.514995701124704,"min":23.17332094718862},"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":130,"losses":127,"wins":115},"GB2-02":{"draws":163,"losses":49,"wins":8},"GB2-03":{"draws":146,"losses":98,"wins":26},"GB2-04":{"draws":214,"losses":67,"wins":25},"GB2-05":{"draws":0,"losses":112,"wins":126},"GB2-06":{"draws":5,"losses":140,"wins":43},"GB2-07":{"draws":0,"losses":245,"wins":61},"GB2-08":{"draws":0,"losses":44,"wins":98}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":130,"losses":127,"wins":115},"GB2-02":{"draws":163,"losses":49,"wins":8},"GB2-03":{"draws":146,"losses":98,"wins":26},"GB2-04":{"draws":214,"losses":67,"wins":25},"GB2-05":{"draws":0,"losses":112,"wins":126},"GB2-06":{"draws":5,"losses":140,"wins":43},"GB2-07":{"draws":0,"losses":245,"wins":61},"GB2-08":{"draws":0,"losses":44,"wins":98}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1457.233184975437,"GB2-02":1428.869676669695,"GB2-03":1342.1409800247943,"GB2-04":1422.9365853386978,"GB2-05":1572.9892012573455,"GB2-06":1054.2122189627185,"GB2-07":1078.8452090052506,"GB2-08":1725.8541247796384}},"per_game_tracks":{"none":{"GB2-01":46.88594575220492,"GB2-02":43.866682960092156,"GB2-03":38.889360494836765,"GB2-04":43.03187493012393,"GB2-05":59.11299589039325,"GB2-06":24.607890813898024,"GB2-07":23.17332094718862,"GB2-08":68.55189382025989}},"program_outcomes":{"all":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":5,"worked_first_time":3,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":5,"worked_first_time":3,"working":8}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#000000","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":43.514995701124704},"reasoning_agg":{"none":{"max":68.55189382025989,"mean":43.514995701124704,"min":23.17332094718862}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning disabled"},"reasoning_settings":{"baseline":"none"},"working_program_strength":{"all":43.514995701124704,"none":43.514995701124704}},{"canonical_public_row_identity":"publication-row.v1:overall:elorian-glimpse:b4b918abe4735ef0","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.224169,"mean":0.1412031,"median":0.16102650000000002,"min":0.0567792,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.1296248},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0395322,"mean":0.023054325,"median":0.0214521,"min":0.0107334,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.18443459999999998}},"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":0.224169,"mean":0.1412031,"median":0.16102650000000002,"min":0.0567792,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.1296248},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0395322,"mean":0.023054325,"median":0.0214521,"min":0.0107334,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.18443460000000003}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.224169,"mean":0.0821287125,"median":0.0481557,"min":0.0107334,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":23},"recorded_attempt_count":23,"run_count":16,"total":1.3140593999999999},"codegen_latency_ms":{"attempt_count":23,"max_ms":561371,"mean_ms":157083.3125,"min_ms":8331,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":10,"max_ms":561371,"mean_ms":286804.25,"min_ms":88263,"run_count":8},"none":{"attempt_count":13,"max_ms":43454,"mean_ms":27362.375,"min_ms":8331,"run_count":8}},"codegen_output_tokens":{"attempt_count":23,"output_max":73204,"output_mean":25017.0625,"output_min":2066,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":10,"output_max":73204,"output_mean":44953.5,"output_min":17269,"run_count":8},"none":{"attempt_count":13,"output_max":8678,"output_mean":5080.625,"output_min":2066,"run_count":8}},"display_name":"Glimpse","economics":{"all":41.37376781753075,"medium":64.07970324247144,"none":18.667832392590064},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-02":"failed","GB2-05":"failed","GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":23,"effective_max_output_tokens":[235929],"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":[235929],"total_output_tokens":400273,"total_reasoning_output_tokens":316594,"total_visible_output_tokens":83679,"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":235929,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"elorian/glimpse","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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":5,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-05","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":{"model_code_failures":1},"GB2-06":{"model_code_failures":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":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":46.8920836949234,"score":46.8920836949234},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":42.997011170890296,"score":21.498505585445148},"GB2-03":{"attempts":2,"playable":44.084165826190016,"score":44.084165826190016},"GB2-04":{"attempts":2,"playable":46.86665194423755,"score":46.86665194423755},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":55.61945502637064,"score":27.80972751318532},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":81.7427537148249,"score":40.87137685741245},"GB2-07":{"attempts":2,"playable":44.65961097319807,"score":44.65961097319807},"GB2-08":{"attempts":2,"playable":58.30802014565405,"score":58.30802014565405}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":81.99149370946253,"score":81.99149370946253},"GB2-02":{"attempts":1,"playable":42.997011170890296,"score":42.997011170890296},"GB2-03":{"attempts":1,"playable":35.52476681881556,"score":35.52476681881556},"GB2-04":{"attempts":1,"playable":54.259500463614195,"score":54.259500463614195},"GB2-05":{"attempts":1,"playable":55.61945502637064,"score":55.61945502637064},"GB2-06":{"attempts":1,"playable":81.7427537148249,"score":81.7427537148249},"GB2-07":{"attempts":1,"playable":73.14337634897771,"score":73.14337634897771},"GB2-08":{"attempts":1,"playable":87.35926868681568,"score":87.35926868681568}},"none":{"GB2-01":{"attempts":1,"playable":11.792673680384262,"score":11.792673680384262},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":52.64356483356448,"score":52.64356483356448},"GB2-04":{"attempts":1,"playable":39.47380342486091,"score":39.47380342486091},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":16.175845597418427,"score":16.175845597418427},"GB2-08":{"attempts":1,"playable":29.256771604492414,"score":29.256771604492414}}},"id":"elorian/glimpse","is_recent_addition":false,"last_measured_at":"2026-11-03T06:52:14Z","match_totals_all":{"draws":1363,"losses":2736,"wins":2723},"match_totals_tracks":{"medium":{"draws":946,"losses":1045,"wins":2191},"none":{"draws":417,"losses":1691,"wins":532}},"model_slug":"elorian-glimpse","official_rank_by_reasoning":{"medium":19,"none":85},"overall":{"max":87.35926868681568,"mean":41.37376781753075,"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":54,"losses":533,"wins":465},"GB2-02":{"draws":387,"losses":93,"wins":12},"GB2-03":{"draws":286,"losses":458,"wins":282},"GB2-04":{"draws":617,"losses":248,"wins":157},"GB2-05":{"draws":0,"losses":240,"wins":302},"GB2-06":{"draws":19,"losses":85,"wins":410},"GB2-07":{"draws":0,"losses":615,"wins":469},"GB2-08":{"draws":0,"losses":464,"wins":626}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":21,"losses":85,"wins":422},"GB2-02":{"draws":387,"losses":93,"wins":12},"GB2-03":{"draws":217,"losses":235,"wins":60},"GB2-04":{"draws":302,"losses":90,"wins":120},"GB2-05":{"draws":0,"losses":240,"wins":302},"GB2-06":{"draws":19,"losses":85,"wins":410},"GB2-07":{"draws":0,"losses":148,"wins":392},"GB2-08":{"draws":0,"losses":69,"wins":473}},"none":{"GB2-01":{"draws":33,"losses":448,"wins":43},"GB2-03":{"draws":69,"losses":223,"wins":222},"GB2-04":{"draws":315,"losses":158,"wins":37},"GB2-07":{"draws":0,"losses":467,"wins":77},"GB2-08":{"draws":0,"losses":395,"wins":153}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1853.4210582408805,"GB2-02":1422.0626995104974,"GB2-03":1311.8073210688763,"GB2-04":1511.8801096675331,"GB2-05":1525.2950477083127,"GB2-06":2031.2299172236185,"GB2-07":1779.9527692317006,"GB2-08":2147.5704230875704},"none":{"GB2-01":1031.8545717656016,"GB2-03":1464.909478438237,"GB2-04":1394.6044078349896,"GB2-07":957.4879348428673,"GB2-08":1149.834610869629}},"per_game_tracks":{"medium":{"GB2-01":81.99149370946253,"GB2-02":42.997011170890296,"GB2-03":35.52476681881556,"GB2-04":54.259500463614195,"GB2-05":55.61945502637064,"GB2-06":81.7427537148249,"GB2-07":73.14337634897771,"GB2-08":87.35926868681568},"none":{"GB2-01":11.792673680384262,"GB2-03":52.64356483356448,"GB2-04":39.47380342486091,"GB2-07":16.175845597418427,"GB2-08":29.256771604492414}},"program_outcomes":{"all":{"counted_attempts":16,"failed":3,"infra_excluded":0,"success_rate":0.8125,"too_slow":0,"worked_after_repair":3,"worked_first_time":10,"working":13},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":3,"infra_excluded":0,"success_rate":0.625,"too_slow":0,"worked_after_repair":1,"worked_first_time":4,"working":5}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":64.07970324247144,"none":18.667832392590064},"reasoning_agg":{"medium":{"max":87.35926868681568,"mean":64.07970324247144,"min":35.52476681881556},"none":{"max":52.64356483356448,"mean":18.667832392590064,"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":45.411870849881375},"working_program_strength":{"all":46.97411753530777,"medium":64.07970324247144,"none":29.868531828144103}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1:c98700024fdd7cc7","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":0.457564}},"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":{"all":41.12651805599547,"none":41.12651805599547},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":59.19053074729083,"score":59.19053074729083},"GB2-02":{"attempts":1,"playable":42.09115662585098,"score":42.09115662585098},"GB2-03":{"attempts":1,"playable":37.40705629131404,"score":37.40705629131404},"GB2-04":{"attempts":1,"playable":37.38212260580418,"score":37.38212260580418},"GB2-05":{"attempts":1,"playable":12.552600974472877,"score":12.552600974472877},"GB2-06":{"attempts":1,"playable":46.855568373710085,"score":46.855568373710085},"GB2-07":{"attempts":1,"playable":46.4528288215314,"score":46.4528288215314},"GB2-08":{"attempts":1,"playable":47.08028000798937,"score":47.08028000798937}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":59.19053074729083,"score":59.19053074729083},"GB2-02":{"attempts":1,"playable":42.09115662585098,"score":42.09115662585098},"GB2-03":{"attempts":1,"playable":37.40705629131404,"score":37.40705629131404},"GB2-04":{"attempts":1,"playable":37.38212260580418,"score":37.38212260580418},"GB2-05":{"attempts":1,"playable":12.552600974472877,"score":12.552600974472877},"GB2-06":{"attempts":1,"playable":46.855568373710085,"score":46.855568373710085},"GB2-07":{"attempts":1,"playable":46.4528288215314,"score":46.4528288215314},"GB2-08":{"attempts":1,"playable":47.08028000798937,"score":47.08028000798937}}},"id":"gpt-4.1","is_recent_addition":false,"last_measured_at":"2026-11-03T07:12:45Z","match_totals_all":{"draws":999,"losses":2032,"wins":1163},"match_totals_tracks":{"none":{"draws":999,"losses":2032,"wins":1163}},"model_slug":"gpt-4-1","official_rank_by_reasoning":{"none":37},"overall":{"max":59.19053074729083,"mean":41.12651805599547,"min":12.552600974472877},"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":38,"losses":198,"wins":292},"GB2-02":{"draws":395,"losses":97,"wins":6},"GB2-03":{"draws":122,"losses":274,"wins":118},"GB2-04":{"draws":324,"losses":165,"wins":23},"GB2-05":{"draws":0,"losses":477,"wins":67},"GB2-06":{"draws":5,"losses":280,"wins":227},"GB2-07":{"draws":0,"losses":302,"wins":240},"GB2-08":{"draws":115,"losses":239,"wins":190}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":38,"losses":198,"wins":292},"GB2-02":{"draws":395,"losses":97,"wins":6},"GB2-03":{"draws":122,"losses":274,"wins":118},"GB2-04":{"draws":324,"losses":165,"wins":23},"GB2-05":{"draws":0,"losses":477,"wins":67},"GB2-06":{"draws":5,"losses":280,"wins":227},"GB2-07":{"draws":0,"losses":302,"wins":240},"GB2-08":{"draws":115,"losses":239,"wins":190}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1577.3073815293433,"GB2-02":1414.9534374259308,"GB2-03":1328.8524258684938,"GB2-04":1377.686290023533,"GB2-05":854.9805203569308,"GB2-06":1405.6939866391604,"GB2-07":1397.6814377472817,"GB2-08":1371.4006281747907}},"per_game_tracks":{"none":{"GB2-01":59.19053074729083,"GB2-02":42.09115662585098,"GB2-03":37.40705629131404,"GB2-04":37.38212260580418,"GB2-05":12.552600974472877,"GB2-06":46.855568373710085,"GB2-07":46.4528288215314,"GB2-08":47.08028000798937}},"program_outcomes":{"all":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":41.12651805599547},"reasoning_agg":{"none":{"max":59.19053074729083,"mean":41.12651805599547,"min":12.552600974472877}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"working_program_strength":{"all":41.12651805599547,"none":41.12651805599547}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-mini:44a91940833966cb","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":0.14705250000000003},"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":5.1688104},"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":{"all":37.012374451523854,"medium":46.346366240592836,"none":27.678382662454876},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":50.30725746506931,"score":50.30725746506931},"GB2-02":{"attempts":2,"playable":40.91676160209354,"score":40.91676160209354},"GB2-03":{"attempts":2,"playable":43.47496302732134,"score":43.47496302732134},"GB2-04":{"attempts":2,"playable":42.279571574240585,"score":42.279571574240585},"GB2-05":{"attempts":2,"playable":27.683636663933694,"score":27.683636663933694},"GB2-06":{"attempts":2,"playable":36.93636657750176,"score":36.93636657750176},"GB2-07":{"attempts":2,"playable":25.322965396520438,"score":25.322965396520438},"GB2-08":{"attempts":2,"playable":29.177473305510137,"score":29.177473305510137}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":68.61083274024124,"score":68.61083274024124},"GB2-02":{"attempts":1,"playable":40.77653311755532,"score":40.77653311755532},"GB2-03":{"attempts":1,"playable":42.7660702225988,"score":42.7660702225988},"GB2-04":{"attempts":1,"playable":43.028074374127954,"score":43.028074374127954},"GB2-05":{"attempts":1,"playable":45.249565512874284,"score":45.249565512874284},"GB2-06":{"attempts":1,"playable":44.717784333627414,"score":44.717784333627414},"GB2-07":{"attempts":1,"playable":44.69547905062318,"score":44.69547905062318},"GB2-08":{"attempts":1,"playable":40.92659057309446,"score":40.92659057309446}},"none":{"GB2-01":{"attempts":1,"playable":32.00368218989739,"score":32.00368218989739},"GB2-02":{"attempts":1,"playable":41.05699008663176,"score":41.05699008663176},"GB2-03":{"attempts":1,"playable":44.18385583204388,"score":44.18385583204388},"GB2-04":{"attempts":1,"playable":41.531068774353216,"score":41.531068774353216},"GB2-05":{"attempts":1,"playable":10.117707814993103,"score":10.117707814993103},"GB2-06":{"attempts":1,"playable":29.15494882137611,"score":29.15494882137611},"GB2-07":{"attempts":1,"playable":5.950451742417698,"score":5.950451742417698},"GB2-08":{"attempts":1,"playable":17.428356037925816,"score":17.428356037925816}}},"id":"gpt-5.4-mini","is_recent_addition":false,"last_measured_at":"2026-11-03T06:57:03Z","match_totals_all":{"draws":2311,"losses":4252,"wins":1817},"match_totals_tracks":{"medium":{"draws":958,"losses":1828,"wins":1404},"none":{"draws":1353,"losses":2424,"wins":413}},"model_slug":"gpt-5-4-mini","official_rank_by_reasoning":{"medium":45,"none":70},"overall":{"max":68.61083274024124,"mean":37.012374451523854,"min":5.950451742417698},"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":197,"losses":427,"wins":428},"GB2-02":{"draws":766,"losses":214,"wins":10},"GB2-03":{"draws":562,"losses":331,"wins":139},"GB2-04":{"draws":609,"losses":298,"wins":113},"GB2-05":{"draws":0,"losses":788,"wins":298},"GB2-06":{"draws":17,"losses":662,"wins":349},"GB2-07":{"draws":0,"losses":827,"wins":255},"GB2-08":{"draws":160,"losses":705,"wins":225}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":36,"losses":148,"wins":342},"GB2-02":{"draws":376,"losses":113,"wins":9},"GB2-03":{"draws":169,"losses":225,"wins":122},"GB2-04":{"draws":321,"losses":136,"wins":51},"GB2-05":{"draws":0,"losses":297,"wins":245},"GB2-06":{"draws":9,"losses":291,"wins":214},"GB2-07":{"draws":0,"losses":311,"wins":229},"GB2-08":{"draws":47,"losses":307,"wins":192}},"none":{"GB2-01":{"draws":161,"losses":279,"wins":86},"GB2-02":{"draws":390,"losses":101,"wins":1},"GB2-03":{"draws":393,"losses":106,"wins":17},"GB2-04":{"draws":288,"losses":162,"wins":62},"GB2-05":{"draws":0,"losses":491,"wins":53},"GB2-06":{"draws":8,"losses":371,"wins":135},"GB2-07":{"draws":0,"losses":516,"wins":26},"GB2-08":{"draws":113,"losses":398,"wins":33}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1676.9232708052075,"GB2-02":1404.591003710977,"GB2-03":1376.5606658290399,"GB2-04":1422.9065283996588,"GB2-05":1390.6004137889133,"GB2-06":1371.9021410912842,"GB2-07":1374.8770294994913,"GB2-08":1291.8073311719634},"none":{"GB2-01":1308.666971470951,"GB2-02":1406.8068355274077,"GB2-03":1389.0993738379002,"GB2-04":1411.0385690749708,"GB2-05":792.5309635071118,"GB2-06":1127.3806419588059,"GB2-07":685.5694270954638,"GB2-08":993.3826438603846}},"per_game_tracks":{"medium":{"GB2-01":68.61083274024124,"GB2-02":40.77653311755532,"GB2-03":42.7660702225988,"GB2-04":43.028074374127954,"GB2-05":45.249565512874284,"GB2-06":44.717784333627414,"GB2-07":44.69547905062318,"GB2-08":40.92659057309446},"none":{"GB2-01":32.00368218989739,"GB2-02":41.05699008663176,"GB2-03":44.18385583204388,"GB2-04":41.531068774353216,"GB2-05":10.117707814993103,"GB2-06":29.15494882137611,"GB2-07":5.950451742417698,"GB2-08":17.428356037925816}},"program_outcomes":{"all":{"counted_attempts":16,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":13,"working":16},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":46.346366240592836,"none":27.678382662454876},"reasoning_agg":{"medium":{"max":68.61083274024124,"mean":46.346366240592836,"min":40.77653311755532},"none":{"max":44.18385583204388,"mean":27.678382662454876,"min":5.950451742417698}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":18.66798357813796},"working_program_strength":{"all":37.012374451523854,"medium":46.346366240592836,"none":27.678382662454876}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-max:f83bb28d1f66f75b","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":0.7288237499999999},"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":0.9112224999999998},"codegen_latency_ms":{"attempt_count":24,"max_ms":500731,"mean_ms":212687.25,"min_ms":38716,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":500731,"mean_ms":358367.875,"min_ms":131800,"run_count":8},"none":{"attempt_count":9,"max_ms":115558,"mean_ms":67006.625,"min_ms":38716,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27099,"output_mean":11144.8125,"output_min":1575,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":27099,"output_mean":19189.625,"output_min":6698,"run_count":8},"none":{"attempt_count":9,"output_max":5506,"output_mean":3100.0,"output_min":1575,"run_count":8}},"display_name":"Qwen3.7 Max","economics":{"all":35.8513364989863,"medium":39.02167631563344,"none":32.68099668233916},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"failed"},"none":{"GB2-04":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":40.633419228966,"score":40.633419228966},"GB2-02":{"attempts":2,"playable":44.272976447432896,"score":44.272976447432896},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":28.048864646340473,"score":14.024432323170236},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":42.76846073724155,"score":21.384230368620774},"GB2-05":{"attempts":2,"playable":35.630373002596656,"score":35.630373002596656},"GB2-06":{"attempts":2,"playable":35.8153449631059,"score":35.8153449631059},"GB2-07":{"attempts":2,"playable":66.59260279888449,"score":66.59260279888449},"GB2-08":{"attempts":2,"playable":28.4573128591135,"score":28.4573128591135}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":17.692808762790836,"score":17.692808762790836},"GB2-02":{"attempts":1,"playable":43.41265632348345,"score":43.41265632348345},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":42.76846073724155,"score":42.76846073724155},"GB2-05":{"attempts":1,"playable":36.89344743584181,"score":36.89344743584181},"GB2-06":{"attempts":1,"playable":57.4871641303838,"score":57.4871641303838},"GB2-07":{"attempts":1,"playable":74.14431261975015,"score":74.14431261975015},"GB2-08":{"attempts":1,"playable":39.77456051557594,"score":39.77456051557594}},"none":{"GB2-01":{"attempts":1,"playable":63.57402969514116,"score":63.57402969514116},"GB2-02":{"attempts":1,"playable":45.133296571382346,"score":45.133296571382346},"GB2-03":{"attempts":1,"playable":28.048864646340473,"score":28.048864646340473},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":34.3672985693515,"score":34.3672985693515},"GB2-06":{"attempts":1,"playable":14.143525795828,"score":14.143525795828},"GB2-07":{"attempts":1,"playable":59.04089297801881,"score":59.04089297801881},"GB2-08":{"attempts":1,"playable":17.140065202651055,"score":17.140065202651055}}},"id":"qwen/qwen3.7-max","is_recent_addition":false,"last_measured_at":"2026-11-03T08:06:23Z","match_totals_all":{"draws":1635,"losses":3590,"wins":2123},"match_totals_tracks":{"medium":{"draws":862,"losses":1638,"wins":1176},"none":{"draws":773,"losses":1952,"wins":947}},"model_slug":"qwen-qwen3-7-max","official_rank_by_reasoning":{"medium":58,"none":57},"overall":{"max":74.14431261975015,"mean":35.8513364989863,"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":228,"losses":517,"wins":309},"GB2-02":{"draws":704,"losses":212,"wins":74},"GB2-03":{"draws":194,"losses":286,"wins":36},"GB2-04":{"draws":276,"losses":160,"wins":72},"GB2-05":{"draws":0,"losses":696,"wins":388},"GB2-06":{"draws":33,"losses":656,"wins":339},"GB2-07":{"draws":0,"losses":371,"wins":709},"GB2-08":{"draws":200,"losses":692,"wins":196}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":70,"losses":404,"wins":56},"GB2-02":{"draws":369,"losses":102,"wins":25},"GB2-04":{"draws":276,"losses":160,"wins":72},"GB2-05":{"draws":0,"losses":341,"wins":201},"GB2-06":{"draws":29,"losses":212,"wins":275},"GB2-07":{"draws":0,"losses":142,"wins":398},"GB2-08":{"draws":118,"losses":277,"wins":149}},"none":{"GB2-01":{"draws":158,"losses":113,"wins":253},"GB2-02":{"draws":335,"losses":110,"wins":49},"GB2-03":{"draws":194,"losses":286,"wins":36},"GB2-05":{"draws":0,"losses":355,"wins":187},"GB2-06":{"draws":4,"losses":444,"wins":64},"GB2-07":{"draws":0,"losses":229,"wins":311},"GB2-08":{"draws":82,"losses":415,"wins":47}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1132.7146850999259,"GB2-02":1425.3179353651003,"GB2-04":1420.8525787637848,"GB2-05":1279.9520293586177,"GB2-06":1579.418014139546,"GB2-07":1797.6305539037382,"GB2-08":1277.4888652422446},"none":{"GB2-01":1622.275852628928,"GB2-02":1438.7607331720692,"GB2-03":1240.8607919361962,"GB2-05":1244.6426383911935,"GB2-06":869.1320622774997,"GB2-07":1565.1806736683902,"GB2-08":989.0211789210157}},"per_game_tracks":{"medium":{"GB2-01":17.692808762790836,"GB2-02":43.41265632348345,"GB2-04":42.76846073724155,"GB2-05":36.89344743584181,"GB2-06":57.4871641303838,"GB2-07":74.14431261975015,"GB2-08":39.77456051557594},"none":{"GB2-01":63.57402969514116,"GB2-02":45.133296571382346,"GB2-03":28.048864646340473,"GB2-05":34.3672985693515,"GB2-06":14.143525795828,"GB2-07":59.04089297801881,"GB2-08":17.140065202651055}},"program_outcomes":{"all":{"counted_attempts":16,"failed":2,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":6,"worked_first_time":8,"working":14},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":6,"worked_first_time":1,"working":7},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":39.02167631563344,"none":32.68099668233916},"reasoning_agg":{"medium":{"max":74.14431261975015,"mean":39.02167631563344,"min":0.0},"none":{"max":63.57402969514116,"mean":32.68099668233916,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":6.340679633294279},"working_program_strength":{"all":40.972955998841485,"medium":44.59620150358108,"none":37.3497104941019}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k2-7-code:ce08b7c528aec083","codegen_cost_by_reasoning":{"medium":{"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":0.1537476,"mean":0.099387675,"median":0.09342906000000001,"min":0.0605136,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.7951014000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.1537476,"mean":0.099387675,"median":0.09342906000000001,"min":0.0605136,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.7951014000000001}},"codegen_cost_usd":{"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":0.1537476,"mean":0.099387675,"median":0.09342906000000001,"min":0.0605136,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.7951014000000001},"codegen_latency_ms":{"attempt_count":14,"max_ms":1100381,"mean_ms":515239.875,"min_ms":290806,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":14,"max_ms":1100381,"mean_ms":515239.875,"min_ms":290806,"run_count":8}},"codegen_output_tokens":{"attempt_count":14,"output_max":47856,"output_mean":30393.25,"output_min":18166,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":14,"output_max":47856,"output_mean":30393.25,"output_min":18166,"run_count":8}},"display_name":"Kimi K2.7 Code","economics":{"all":34.09517226623859,"medium":34.09517226623859},"first_seen_at":null,"game_gaps":{"all":{"GB2-03":"failed","GB2-05":"failed","GB2-07":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"failed","GB2-05":"failed","GB2-07":"failed"},"none":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":14,"effective_max_output_tokens":[235929],"finish_reason_observations":14,"finish_reasons":["stop"],"indexed_attempts":14,"output_token_observations":14,"provider_post_attempt_observations":14,"provider_post_attempts":14,"reasoning_token_observations":14,"reconciliation_get_attempt_observations":14,"requested_max_output_token_observations":14,"requested_max_output_tokens":[235929],"total_output_tokens":243146,"total_reasoning_output_tokens":207636,"total_visible_output_tokens":35510,"visible_token_observations":14},"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":235929,"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-05","GB2-07"],"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":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":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":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":63.40375388190238,"score":63.40375388190238},"GB2-02":{"attempts":1,"playable":43.30346631602694,"score":43.30346631602694},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":38.89036817689621,"score":38.89036817689621},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":48.63306916230925,"score":48.63306916230925},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":78.53072059277395,"score":78.53072059277395}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":63.40375388190238,"score":63.40375388190238},"GB2-02":{"attempts":1,"playable":43.30346631602694,"score":43.30346631602694},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":38.89036817689621,"score":38.89036817689621},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":48.63306916230925,"score":48.63306916230925},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":78.53072059277395,"score":78.53072059277395}}},"id":"moonshotai/kimi-k2.7-code","is_recent_addition":false,"last_measured_at":"2026-11-03T08:03:32Z","match_totals_all":{"draws":318,"losses":249,"wins":347},"match_totals_tracks":{"medium":{"draws":318,"losses":249,"wins":347}},"model_slug":"moonshotai-kimi-k2-7-code","official_rank_by_reasoning":{"medium":65},"overall":{"max":78.53072059277395,"mean":34.09517226623859,"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":104,"losses":22,"wins":70},"GB2-02":{"draws":106,"losses":30,"wins":12},"GB2-04":{"draws":104,"losses":68,"wins":20},"GB2-06":{"draws":4,"losses":94,"wins":94},"GB2-08":{"draws":0,"losses":35,"wins":151}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":104,"losses":22,"wins":70},"GB2-02":{"draws":106,"losses":30,"wins":12},"GB2-04":{"draws":104,"losses":68,"wins":20},"GB2-06":{"draws":4,"losses":94,"wins":94},"GB2-08":{"draws":0,"losses":35,"wins":151}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1620.4909490891146,"GB2-02":1424.4631525765494,"GB2-04":1389.9096339890714,"GB2-06":1433.9897262753573,"GB2-08":1934.8841735641788}},"per_game_tracks":{"medium":{"GB2-01":63.40375388190238,"GB2-02":43.30346631602694,"GB2-04":38.89036817689621,"GB2-06":48.63306916230925,"GB2-08":78.53072059277395}},"program_outcomes":{"all":{"counted_attempts":8,"failed":3,"infra_excluded":0,"success_rate":0.625,"too_slow":0,"worked_after_repair":2,"worked_first_time":3,"working":5},"medium":{"counted_attempts":8,"failed":3,"infra_excluded":0,"success_rate":0.625,"too_slow":0,"worked_after_repair":2,"worked_first_time":3,"working":5}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":34.09517226623859},"reasoning_agg":{"medium":{"max":78.53072059277395,"mean":34.09517226623859,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{"balanced":"enabled"},"working_program_strength":{"all":54.55227562598175,"medium":54.55227562598175}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-build-0-1:a7cc431cc0a41ac7","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":0.4852846}},"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":{"all":33.36127440060654,"medium":33.36127440060654},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":35.61253827343055,"score":35.61253827343055},"GB2-02":{"attempts":1,"playable":42.999039084898335,"score":42.999039084898335},"GB2-03":{"attempts":1,"playable":27.960907533552888,"score":27.960907533552888},"GB2-04":{"attempts":1,"playable":39.461008403522506,"score":39.461008403522506},"GB2-05":{"attempts":1,"playable":48.05425620960328,"score":48.05425620960328},"GB2-06":{"attempts":1,"playable":30.86138868526904,"score":30.86138868526904},"GB2-07":{"attempts":1,"playable":14.732315718973688,"score":14.732315718973688},"GB2-08":{"attempts":1,"playable":27.208741295602046,"score":27.208741295602046}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":35.61253827343055,"score":35.61253827343055},"GB2-02":{"attempts":1,"playable":42.999039084898335,"score":42.999039084898335},"GB2-03":{"attempts":1,"playable":27.960907533552888,"score":27.960907533552888},"GB2-04":{"attempts":1,"playable":39.461008403522506,"score":39.461008403522506},"GB2-05":{"attempts":1,"playable":48.05425620960328,"score":48.05425620960328},"GB2-06":{"attempts":1,"playable":30.86138868526904,"score":30.86138868526904},"GB2-07":{"attempts":1,"playable":14.732315718973688,"score":14.732315718973688},"GB2-08":{"attempts":1,"playable":27.208741295602046,"score":27.208741295602046}}},"id":"x-ai/grok-build-0.1","is_recent_addition":false,"last_measured_at":"2026-11-03T06:54:27Z","match_totals_all":{"draws":1073,"losses":2322,"wins":805},"match_totals_tracks":{"medium":{"draws":1073,"losses":2322,"wins":805}},"model_slug":"x-ai-grok-build-0-1","official_rank_by_reasoning":{"medium":67},"overall":{"max":48.05425620960328,"mean":33.36127440060654,"min":14.732315718973688},"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":105,"losses":291,"wins":134},"GB2-02":{"draws":394,"losses":92,"wins":10},"GB2-03":{"draws":134,"losses":318,"wins":66},"GB2-04":{"draws":341,"losses":147,"wins":26},"GB2-05":{"draws":0,"losses":282,"wins":262},"GB2-06":{"draws":3,"losses":365,"wins":146},"GB2-07":{"draws":0,"losses":471,"wins":69},"GB2-08":{"draws":96,"losses":356,"wins":92}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":105,"losses":291,"wins":134},"GB2-02":{"draws":394,"losses":92,"wins":10},"GB2-03":{"draws":134,"losses":318,"wins":66},"GB2-04":{"draws":341,"losses":147,"wins":26},"GB2-05":{"draws":0,"losses":282,"wins":262},"GB2-06":{"draws":3,"losses":365,"wins":146},"GB2-07":{"draws":0,"losses":471,"wins":69},"GB2-08":{"draws":96,"losses":356,"wins":92}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1346.258750906256,"GB2-02":1422.0785911716132,"GB2-03":1239.9817598211184,"GB2-04":1394.5016299035462,"GB2-05":1426.7023199841135,"GB2-06":1154.4398563015757,"GB2-07":928.5956896142807,"GB2-08":1124.6658712610667}},"per_game_tracks":{"medium":{"GB2-01":35.61253827343055,"GB2-02":42.999039084898335,"GB2-03":27.960907533552888,"GB2-04":39.461008403522506,"GB2-05":48.05425620960328,"GB2-06":30.86138868526904,"GB2-07":14.732315718973688,"GB2-08":27.208741295602046}},"program_outcomes":{"all":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":8,"worked_first_time":0,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":8,"worked_first_time":0,"working":8}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":33.36127440060654},"reasoning_agg":{"medium":{"max":48.05425620960328,"mean":33.36127440060654,"min":14.732315718973688}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"working_program_strength":{"all":33.36127440060654,"medium":33.36127440060654}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5-pro:dfe6567492f18ae7","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.013987023000000001,"mean":0.007770620325,"median":0.006556245299999999,"min":0.005627394,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.0621649626},"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":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.013987023000000001,"mean":0.007770620325,"median":0.006556245299999999,"min":0.005627394,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.062164962600000005},"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":15,"cell_count":16,"cost_basis_counts":{"provider_reported":21},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.0197353528625,"median":0.0065649564,"min":0.005627394,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":21,"run_count":16,"total":0.3157656458},"codegen_latency_ms":{"attempt_count":21,"max_ms":886851,"mean_ms":120417.0625,"min_ms":8215,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":10,"max_ms":34657,"mean_ms":17617.5,"min_ms":8215,"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":21,"output_max":42691,"output_mean":7236.9375,"output_min":2239,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":10,"output_max":7415,"output_mean":3602.75,"output_min":2239,"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":{"all":32.635471394718635,"medium":36.94589771845848,"none":28.325045070978785},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-04":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[131072],"finish_reason_observations":21,"finish_reasons":["stop"],"indexed_attempts":21,"output_token_observations":21,"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":[131072],"total_output_tokens":115791,"total_visible_output_tokens":28822,"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":"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":"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":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":44.99705484963049,"score":44.99705484963049},"GB2-02":{"attempts":2,"playable":39.68666972508105,"score":39.68666972508105},"GB2-03":{"attempts":2,"playable":43.178128166191414,"score":43.178128166191414},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":38.55032176041392,"score":19.27516088020696},"GB2-05":{"attempts":2,"playable":18.79844066213517,"score":18.79844066213517},"GB2-06":{"attempts":2,"playable":29.86814699486248,"score":29.86814699486248},"GB2-07":{"attempts":2,"playable":43.48166338465846,"score":43.48166338465846},"GB2-08":{"attempts":2,"playable":21.798506494983066,"score":21.798506494983066}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":54.692943437203986,"score":54.692943437203986},"GB2-02":{"attempts":1,"playable":41.39916787138037,"score":41.39916787138037},"GB2-03":{"attempts":1,"playable":53.090728691026456,"score":53.090728691026456},"GB2-04":{"attempts":1,"playable":38.55032176041392,"score":38.55032176041392},"GB2-05":{"attempts":1,"playable":19.48566916943243,"score":19.48566916943243},"GB2-06":{"attempts":1,"playable":24.88182459737415,"score":24.88182459737415},"GB2-07":{"attempts":1,"playable":39.09944056477113,"score":39.09944056477113},"GB2-08":{"attempts":1,"playable":24.36708565606548,"score":24.36708565606548}},"none":{"GB2-01":{"attempts":1,"playable":35.301166262056995,"score":35.301166262056995},"GB2-02":{"attempts":1,"playable":37.974171578781736,"score":37.974171578781736},"GB2-03":{"attempts":1,"playable":33.265527641356364,"score":33.265527641356364},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":18.111212154837915,"score":18.111212154837915},"GB2-06":{"attempts":1,"playable":34.854469392350815,"score":34.854469392350815},"GB2-07":{"attempts":1,"playable":47.863886204545786,"score":47.863886204545786},"GB2-08":{"attempts":1,"playable":19.229927333900655,"score":19.229927333900655}}},"id":"xiaomi/mimo-v2.5-pro","is_recent_addition":false,"last_measured_at":"2026-11-03T07:15:45Z","match_totals_all":{"draws":1311,"losses":3626,"wins":1391},"match_totals_tracks":{"medium":{"draws":550,"losses":1467,"wins":637},"none":{"draws":761,"losses":2159,"wins":754}},"model_slug":"xiaomi-mimo-v2-5-pro","official_rank_by_reasoning":{"medium":61,"none":68},"overall":{"max":54.692943437203986,"mean":32.635471394718635,"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":164,"losses":350,"wins":198},"GB2-02":{"draws":604,"losses":208,"wins":20},"GB2-03":{"draws":275,"losses":400,"wins":211},"GB2-04":{"draws":124,"losses":60,"wins":8},"GB2-05":{"draws":0,"losses":776,"wins":188},"GB2-06":{"draws":28,"losses":621,"wins":255},"GB2-07":{"draws":0,"losses":494,"wins":364},"GB2-08":{"draws":116,"losses":717,"wins":147}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":29,"losses":74,"wins":81},"GB2-02":{"draws":283,"losses":57,"wins":0},"GB2-03":{"draws":89,"losses":137,"wins":146},"GB2-04":{"draws":124,"losses":60,"wins":8},"GB2-05":{"draws":0,"losses":331,"wins":91},"GB2-06":{"draws":25,"losses":278,"wins":89},"GB2-07":{"draws":0,"losses":200,"wins":116},"GB2-08":{"draws":0,"losses":330,"wins":106}},"none":{"GB2-01":{"draws":135,"losses":276,"wins":117},"GB2-02":{"draws":321,"losses":151,"wins":20},"GB2-03":{"draws":186,"losses":263,"wins":65},"GB2-05":{"draws":0,"losses":445,"wins":97},"GB2-06":{"draws":3,"losses":343,"wins":166},"GB2-07":{"draws":0,"losses":294,"wins":248},"GB2-08":{"draws":116,"losses":387,"wins":41}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1532.765828323847,"GB2-02":1409.5063519803737,"GB2-03":1469.019860835356,"GB2-04":1387.1652062556275,"GB2-05":1001.9978042212388,"GB2-06":1058.6812559925816,"GB2-07":1302.1245200129845,"GB2-08":1088.8854627795222},"none":{"GB2-01":1343.073488887175,"GB2-02":1382.252706378875,"GB2-03":1291.0091809673734,"GB2-05":975.3437794219058,"GB2-06":1217.298801848373,"GB2-07":1416.0309191937206,"GB2-08":1019.7590215958498}},"per_game_tracks":{"medium":{"GB2-01":54.692943437203986,"GB2-02":41.39916787138037,"GB2-03":53.090728691026456,"GB2-04":38.55032176041392,"GB2-05":19.48566916943243,"GB2-06":24.88182459737415,"GB2-07":39.09944056477113,"GB2-08":24.36708565606548},"none":{"GB2-01":35.301166262056995,"GB2-02":37.974171578781736,"GB2-03":33.265527641356364,"GB2-05":18.111212154837915,"GB2-06":34.854469392350815,"GB2-07":47.863886204545786,"GB2-08":19.229927333900655}},"program_outcomes":{"all":{"counted_attempts":16,"failed":1,"infra_excluded":0,"success_rate":0.9375,"too_slow":0,"worked_after_repair":5,"worked_first_time":10,"working":15},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":36.94589771845848,"none":28.325045070978785},"reasoning_agg":{"medium":{"max":54.692943437203986,"mean":36.94589771845848,"min":19.48566916943243},"none":{"max":47.863886204545786,"mean":28.325045070978785,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled"},"score_diagnostics":{"reasoning_variance":8.620852647479698},"working_program_strength":{"all":34.658688899788544,"medium":36.94589771845848,"none":32.37148008111861}},{"canonical_public_row_identity":"publication-row.v1:overall:poolside-laguna-s-2-1:ecc8f58110ed6507","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":0.04176386000000001}},"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":0.04917795999999999},"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":0.09094181999999999},"codegen_latency_ms":{"attempt_count":68,"max_ms":490920,"mean_ms":122427.25,"min_ms":29915,"run_count":28},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":35,"max_ms":490920,"mean_ms":129686.92857142857,"min_ms":29915,"run_count":14},"none":{"attempt_count":33,"max_ms":199208,"mean_ms":115167.57142857143,"min_ms":46525,"run_count":14}},"codegen_output_tokens":{"attempt_count":68,"output_max":42038,"output_mean":8274.82142857143,"output_min":1701,"run_count":28},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":35,"output_max":42038,"output_mean":9630.357142857143,"output_min":1701,"run_count":14},"none":{"attempt_count":33,"output_max":12644,"output_mean":6919.285714285715,"output_min":2544,"run_count":14}},"display_name":"Laguna S 2.1","economics":{"all":30.33552415515183,"medium":30.201195663813028,"none":30.469852646490637},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-07":"too_slow"},"none":{"GB2-04":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":43.51953222610562,"score":33.828640293737465},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":41.0422931842091,"score":31.02985201434494},"GB2-03":{"attempts":4,"playable":38.15864245174651,"score":38.15864245174651},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":39.35582940809733,"score":19.677914704048664},"GB2-05":{"attempts":4,"playable":36.390421481854816,"score":36.390421481854816},"GB2-06":{"attempts":2,"playable":18.61956962678557,"score":18.61956962678557},"GB2-07":{"attempts":2,"playable":43.90041419104564,"score":43.90041419104564},"GB2-08":{"attempts":4,"playable":27.928347741267377,"score":27.928347741267377}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":38.76356772947261,"score":19.381783864736306},"GB2-02":{"attempts":2,"playable":42.03482168896156,"score":42.03482168896156},"GB2-03":{"attempts":2,"playable":38.07513621241883,"score":38.07513621241883},"GB2-04":{"attempts":1,"playable":39.35582940809733,"score":39.35582940809733},"GB2-05":{"attempts":2,"playable":26.263742559960995,"score":26.263742559960995},"GB2-06":{"attempts":1,"playable":18.310646153163653,"score":18.310646153163653},"GB2-08":{"attempts":2,"playable":27.986409759352526,"score":27.986409759352526}},"none":{"GB2-01":{"attempts":2,"playable":48.27549672273862,"score":48.27549672273862},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.049764679456636,"score":20.024882339728318},"GB2-03":{"attempts":2,"playable":38.242148691074185,"score":38.242148691074185},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":2,"playable":46.51710040374863,"score":46.51710040374863},"GB2-06":{"attempts":1,"playable":18.928493100407483,"score":18.928493100407483},"GB2-07":{"attempts":2,"playable":43.90041419104564,"score":43.90041419104564},"GB2-08":{"attempts":2,"playable":27.870285723182228,"score":27.870285723182228}}},"id":"poolside/laguna-s-2.1","is_recent_addition":false,"last_measured_at":"2026-11-03T08:03:31Z","match_totals_all":{"draws":2820,"losses":6436,"wins":2812},"match_totals_tracks":{"medium":{"draws":1730,"losses":3045,"wins":963},"none":{"draws":1090,"losses":3391,"wins":1849}},"model_slug":"poolside-laguna-s-2-1","official_rank_by_reasoning":{"medium":71,"none":60},"overall":{"max":48.27549672273862,"mean":30.33552415515183,"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":264,"losses":741,"wins":577},"GB2-02":{"draws":1150,"losses":312,"wins":20},"GB2-03":{"draws":675,"losses":984,"wins":391},"GB2-04":{"draws":300,"losses":168,"wins":46},"GB2-05":{"draws":0,"losses":1378,"wins":788},"GB2-06":{"draws":4,"losses":849,"wins":173},"GB2-07":{"draws":0,"losses":630,"wins":452},"GB2-08":{"draws":427,"losses":1374,"wins":365}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":91,"losses":281,"wins":158},"GB2-02":{"draws":802,"losses":184,"wins":2},"GB2-03":{"draws":320,"losses":502,"wins":204},"GB2-04":{"draws":300,"losses":168,"wins":46},"GB2-05":{"draws":0,"losses":799,"wins":285},"GB2-06":{"draws":2,"losses":425,"wins":85},"GB2-08":{"draws":215,"losses":686,"wins":183}},"none":{"GB2-01":{"draws":173,"losses":460,"wins":419},"GB2-02":{"draws":348,"losses":128,"wins":18},"GB2-03":{"draws":355,"losses":482,"wins":187},"GB2-05":{"draws":0,"losses":579,"wins":503},"GB2-06":{"draws":2,"losses":424,"wins":88},"GB2-07":{"draws":0,"losses":630,"wins":452},"GB2-08":{"draws":212,"losses":688,"wins":182}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1378.0029056849999,"GB2-02":1414.508545338405,"GB2-03":1334.5780350663044,"GB2-04":1393.6564641295154,"GB2-05":1099.3620577231538,"GB2-06":947.4808221549213,"GB2-08":1134.2453348081476},"none":{"GB2-01":1470.638497493747,"GB2-02":1398.8341499070036,"GB2-03":1336.0695980440958,"GB2-05":1409.5872477006637,"GB2-06":958.416770019076,"GB2-07":1364.2677798253571,"GB2-08":1132.77158137184}},"per_game_tracks":{"medium":{"GB2-01":38.76356772947261,"GB2-02":42.03482168896156,"GB2-03":38.07513621241883,"GB2-04":39.35582940809733,"GB2-05":26.263742559960995,"GB2-06":18.310646153163653,"GB2-08":27.986409759352526},"none":{"GB2-01":48.27549672273862,"GB2-02":40.049764679456636,"GB2-03":38.242148691074185,"GB2-05":46.51710040374863,"GB2-06":18.928493100407483,"GB2-07":43.90041419104564,"GB2-08":27.870285723182228}},"program_outcomes":{"all":{"counted_attempts":26,"failed":3,"infra_excluded":5,"success_rate":0.8846153846153846,"too_slow":1,"worked_after_repair":9,"worked_first_time":14,"working":23},"medium":{"counted_attempts":12,"failed":1,"infra_excluded":3,"success_rate":0.9166666666666666,"too_slow":1,"worked_after_repair":4,"worked_first_time":7,"working":11},"none":{"counted_attempts":14,"failed":2,"infra_excluded":2,"success_rate":0.8571428571428571,"too_slow":0,"worked_after_repair":5,"worked_first_time":7,"working":12}},"provider_color":"#4137FF","provider_company":"Poolside","provider_key":"poolside","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.201195663813028,"none":30.469852646490637},"reasoning_agg":{"medium":{"max":42.03482168896156,"mean":30.201195663813028,"min":18.310646153163653},"none":{"max":48.27549672273862,"mean":30.469852646490637,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":0.2686569826776086},"working_program_strength":{"all":35.32670407307721,"medium":32.97002193020393,"none":37.683386215950485}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy3-preview:e6c2b0dc7e43b018","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":0.031586439},"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":{"all":29.982719237339055,"highest":31.12477793241367,"none":28.840660542264438},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"failed"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-06":"failed","GB2-07":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":69.83785795026043,"score":69.83785795026043},"GB2-02":{"attempts":2,"playable":37.03390759540194,"score":37.03390759540194},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":30.801913814647886,"score":15.400956907323943},"GB2-04":{"attempts":2,"playable":44.39672868456807,"score":44.39672868456807},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":35.62911663149306,"score":21.310701995409662},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":12.575066766375622,"score":6.287533383187811},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":25.145004952747502,"score":12.572502476373751},"GB2-08":{"attempts":2,"playable":33.02156490618684,"score":33.02156490618684}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":63.11246044613853,"score":63.11246044613853},"GB2-02":{"attempts":1,"playable":37.99019623710896,"score":37.99019623710896},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":42.59710289312251,"score":42.59710289312251},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":57.273658544333614,"score":28.636829272166807},"GB2-06":{"attempts":1,"playable":12.575066766375622,"score":12.575066766375622},"GB2-07":{"attempts":1,"playable":25.145004952747502,"score":25.145004952747502},"GB2-08":{"attempts":1,"playable":38.94156289164942,"score":38.94156289164942}},"none":{"GB2-01":{"attempts":1,"playable":76.56325545438231,"score":76.56325545438231},"GB2-02":{"attempts":1,"playable":36.077618953694916,"score":36.077618953694916},"GB2-03":{"attempts":1,"playable":30.801913814647886,"score":30.801913814647886},"GB2-04":{"attempts":1,"playable":46.196354476013624,"score":46.196354476013624},"GB2-05":{"attempts":1,"playable":13.984574718652516,"score":13.984574718652516},"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":27.101566920724256,"score":27.101566920724256}}},"id":"tencent/hy3-preview","is_recent_addition":false,"last_measured_at":"2026-11-03T06:51:59Z","match_totals_all":{"draws":1871,"losses":3289,"wins":1652},"match_totals_tracks":{"highest":{"draws":866,"losses":1818,"wins":988},"none":{"draws":1005,"losses":1471,"wins":664}},"model_slug":"tencent-hy3-preview","official_rank_by_reasoning":{"highest":61,"none":65},"overall":{"max":76.56325545438231,"mean":29.982719237339055,"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":63.11246044613853,"GB2-02":37.99019623710896,"GB2-04":42.59710289312251,"GB2-05":57.273658544333614,"GB2-06":12.575066766375622,"GB2-07":25.145004952747502,"GB2-08":38.94156289164942},"per_game_match_totals_all":{"GB2-01":{"draws":170,"losses":235,"wins":649},"GB2-02":{"draws":693,"losses":289,"wins":8},"GB2-03":{"draws":123,"losses":308,"wins":85},"GB2-04":{"draws":662,"losses":252,"wins":110},"GB2-05":{"draws":0,"losses":701,"wins":385},"GB2-06":{"draws":5,"losses":451,"wins":56},"GB2-07":{"draws":0,"losses":417,"wins":123},"GB2-08":{"draws":218,"losses":636,"wins":236}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":88,"losses":152,"wins":288},"GB2-02":{"draws":347,"losses":139,"wins":8},"GB2-04":{"draws":365,"losses":119,"wins":30},"GB2-05":{"draws":0,"losses":232,"wins":310},"GB2-06":{"draws":5,"losses":451,"wins":56},"GB2-07":{"draws":0,"losses":417,"wins":123},"GB2-08":{"draws":61,"losses":308,"wins":173}},"none":{"GB2-01":{"draws":82,"losses":83,"wins":361},"GB2-02":{"draws":346,"losses":150,"wins":0},"GB2-03":{"draws":123,"losses":308,"wins":85},"GB2-04":{"draws":297,"losses":133,"wins":80},"GB2-05":{"draws":0,"losses":469,"wins":75},"GB2-08":{"draws":157,"losses":328,"wins":63}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1617.4455184305427,"GB2-02":1382.3816399731427,"GB2-04":1419.4959926738102,"GB2-05":1547.6159614006565,"GB2-06":836.6760459615593,"GB2-07":1109.2349103020626,"GB2-08":1267.2172638466384},"none":{"GB2-01":1774.0178201903009,"GB2-02":1366.8725775706682,"GB2-03":1267.7649844400698,"GB2-04":1447.8875079643087,"GB2-05":888.3755058529752,"GB2-08":1123.3369429594795}},"per_game_tracks":{"highest":{"GB2-01":63.11246044613853,"GB2-02":37.99019623710896,"GB2-04":42.59710289312251,"GB2-05":57.273658544333614,"GB2-06":12.575066766375622,"GB2-07":25.145004952747502,"GB2-08":38.94156289164942},"none":{"GB2-01":76.56325545438231,"GB2-02":36.077618953694916,"GB2-03":30.801913814647886,"GB2-04":46.196354476013624,"GB2-05":13.984574718652516,"GB2-08":27.101566920724256}},"program_outcomes":{"all":{"counted_attempts":17,"failed":4,"infra_excluded":0,"success_rate":0.7647058823529411,"too_slow":0,"worked_after_repair":4,"worked_first_time":9,"working":13},"highest":{"counted_attempts":9,"failed":2,"infra_excluded":0,"success_rate":0.7777777777777778,"too_slow":0,"worked_after_repair":2,"worked_first_time":5,"working":7},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":2,"worked_first_time":4,"working":6}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":31.12477793241367,"none":28.84066054226444},"reasoning_agg":{"highest":{"max":63.11246044613853,"mean":31.12477793241367,"min":0.0},"none":{"max":76.56325545438231,"mean":28.84066054226444,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":2.2841173901492304},"working_program_strength":{"all":39.05818222328173,"highest":39.662150390210876,"none":38.45421405635258}},{"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-5-super-vl:d4bad1e12af20a2e","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":0.017223799999999997,"mean":0.011684275,"median":0.01118885,"min":0.0072799,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.0934742},"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":0.0053376,"mean":0.0035628175,"median":0.00344317,"min":0.0016103,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":15,"run_count":8,"total":0.028502539999999996}},"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":0.017223799999999997,"mean":0.011684275,"median":0.01118885,"min":0.0072799,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.09347420000000001},"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":0.0053376,"mean":0.0035628175,"median":0.00344317,"min":0.0016103,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":15,"run_count":8,"total":0.02850254}},"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":16,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.017223799999999997,"mean":0.00762354625,"median":0.00630875,"min":0.0016103,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":26},"recorded_attempt_count":26,"run_count":16,"total":0.12197674000000001},"codegen_latency_ms":{"attempt_count":26,"max_ms":256073,"mean_ms":74799.75,"min_ms":5868,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":11,"max_ms":256073,"mean_ms":129205.75,"min_ms":48724,"run_count":8},"none":{"attempt_count":15,"max_ms":35513,"mean_ms":20393.75,"min_ms":5868,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":39370,"output_mean":15837.375,"output_min":2130,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":11,"output_max":39370,"output_mean":26486.125,"output_min":16576,"run_count":8},"none":{"attempt_count":15,"output_max":9122,"output_mean":5188.625,"output_min":2130,"run_count":8}},"display_name":"Nemotron 3.5 Super Vl","economics":{"all":29.661772265069086,"medium":48.05299861856464,"none":11.270545911573533},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-05":"failed","GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":26,"effective_max_output_tokens":[235929],"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":[235929],"total_output_tokens":253398,"total_reasoning_output_tokens":186412,"total_visible_output_tokens":66986,"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":235929,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nvidia","provider_model":"nvidia/nemotron-3.5-super-vl","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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-05","GB2-06"],"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":{"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":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":64.0056060641035,"score":32.00280303205175},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.70514591693035,"score":21.852572958465174},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":34.68647430399471,"score":17.343237151997354},"GB2-04":{"attempts":2,"playable":41.07488542226986,"score":41.07488542226986},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":55.20362733991935,"score":27.601813669959675},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":43.535001966023856,"score":21.767500983011928},"GB2-07":{"attempts":2,"playable":39.061325866756526,"score":39.061325866756526},"GB2-08":{"attempts":2,"playable":36.59003903604039,"score":36.59003903604039}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":64.0056060641035,"score":64.0056060641035},"GB2-02":{"attempts":1,"playable":43.70514591693035,"score":43.70514591693035},"GB2-03":{"attempts":1,"playable":34.68647430399471,"score":34.68647430399471},"GB2-04":{"attempts":1,"playable":40.028680972350244,"score":40.028680972350244},"GB2-05":{"attempts":1,"playable":55.20362733991935,"score":55.20362733991935},"GB2-06":{"attempts":1,"playable":43.535001966023856,"score":43.535001966023856},"GB2-07":{"attempts":1,"playable":55.378816395034214,"score":55.378816395034214},"GB2-08":{"attempts":1,"playable":47.880635990160826,"score":47.880635990160826}},"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":42.12108987218948,"score":42.12108987218948},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":22.743835338478842,"score":22.743835338478842},"GB2-08":{"attempts":1,"playable":25.29944208191995,"score":25.29944208191995}}},"id":"nvidia/nemotron-3.5-super-vl","is_recent_addition":false,"last_measured_at":"2026-11-03T08:04:35Z","match_totals_all":{"draws":1336,"losses":2703,"wins":1747},"match_totals_tracks":{"medium":{"draws":984,"losses":1738,"wins":1474},"none":{"draws":352,"losses":965,"wins":273}},"model_slug":"nvidia-nemotron-3-5-super-vl","official_rank_by_reasoning":{"medium":41},"overall":{"max":64.0056060641035,"mean":29.661772265069086,"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":{"GB2-01":{"draws":72,"losses":156,"wins":302},"GB2-02":{"draws":381,"losses":93,"wins":18},"GB2-03":{"draws":187,"losses":258,"wins":73},"GB2-04":{"draws":684,"losses":276,"wins":66},"GB2-05":{"draws":0,"losses":243,"wins":299},"GB2-06":{"draws":12,"losses":296,"wins":208},"GB2-07":{"draws":0,"losses":679,"wins":401},"GB2-08":{"draws":0,"losses":702,"wins":380}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":72,"losses":156,"wins":302},"GB2-02":{"draws":381,"losses":93,"wins":18},"GB2-03":{"draws":187,"losses":258,"wins":73},"GB2-04":{"draws":332,"losses":149,"wins":33},"GB2-05":{"draws":0,"losses":243,"wins":299},"GB2-06":{"draws":12,"losses":296,"wins":208},"GB2-07":{"draws":0,"losses":251,"wins":291},"GB2-08":{"draws":0,"losses":292,"wins":250}},"none":{"GB2-04":{"draws":352,"losses":127,"wins":33},"GB2-07":{"draws":0,"losses":428,"wins":110},"GB2-08":{"draws":0,"losses":410,"wins":130}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1626.8157546478144,"GB2-02":1427.606462760092,"GB2-03":1304.1390455493447,"GB2-04":1399.054209745604,"GB2-05":1519.7463897566438,"GB2-06":1353.289419448743,"GB2-07":1515.2453559560156,"GB2-08":1382.2475280406945},"none":{"GB2-04":1415.7235623546262,"GB2-07":1072.0532323176128,"GB2-08":1100.7633111536966}},"per_game_tracks":{"medium":{"GB2-01":64.0056060641035,"GB2-02":43.70514591693035,"GB2-03":34.68647430399471,"GB2-04":40.028680972350244,"GB2-05":55.20362733991935,"GB2-06":43.535001966023856,"GB2-07":55.378816395034214,"GB2-08":47.880635990160826},"none":{"GB2-04":42.12108987218948,"GB2-07":22.743835338478842,"GB2-08":25.29944208191995}},"program_outcomes":{"all":{"counted_attempts":16,"failed":5,"infra_excluded":0,"success_rate":0.6875,"too_slow":0,"worked_after_repair":5,"worked_first_time":6,"working":11},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"none":{"counted_attempts":8,"failed":5,"infra_excluded":0,"success_rate":0.375,"too_slow":0,"worked_after_repair":2,"worked_first_time":1,"working":3}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":48.05299861856464,"none":11.270545911573533},"reasoning_agg":{"medium":{"max":64.0056060641035,"mean":48.05299861856464,"min":34.68647430399471},"none":{"max":42.12108987218948,"mean":11.270545911573533,"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":36.7824527069911},"working_program_strength":{"all":39.05389385804703,"medium":48.05299861856464,"none":30.054789097529422}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5:37c5cd9d362c0a6b","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":0.486187507},"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":0.0689052158}},"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":0.27207317540000003},"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":0.21411433159999999},"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":0.0306854728},"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":0.7524538072},"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":29.262375726582977,"highest":33.5694938636817,"medium":28.877065223249218,"none":25.340568092818017},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"infra_excluded","GB2-05":"infra_excluded","GB2-07":"infra_excluded"},"medium":{"GB2-03":"infra_excluded"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":30.628851622799022,"score":30.628851622799022},"GB2-02":{"attempts":7,"failed_attempts":2,"playable":41.61858012562602,"score":32.6058311904841},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":44.522005781681415,"score":14.840668593893804},"GB2-04":{"attempts":6,"playable":39.085095008693706,"score":39.085095008693706},"GB2-05":{"attempts":5,"playable":24.48182560977716,"score":24.48182560977716},"GB2-06":{"attempts":5,"playable":31.781136235838506,"score":31.781136235838506},"GB2-07":{"attempts":5,"failed_attempts":1,"playable":25.318244257519382,"score":21.89152582300781},"GB2-08":{"attempts":7,"failed_attempts":2,"playable":28.474990452540215,"score":20.940452330262477}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":22.988592572595227,"score":22.988592572595227},"GB2-02":{"attempts":1,"playable":43.100487355847264,"score":43.100487355847264},"GB2-04":{"attempts":1,"playable":38.475347608725116,"score":38.475347608725116},"GB2-06":{"attempts":1,"playable":45.668913524119844,"score":45.668913524119844},"GB2-08":{"attempts":1,"playable":17.614128257121042,"score":17.614128257121042}},"medium":{"GB2-01":{"attempts":2,"playable":28.17961662686202,"score":28.17961662686202},"GB2-02":{"attempts":3,"playable":41.19788281289216,"score":41.19788281289216},"GB2-04":{"attempts":3,"playable":38.03886054221376,"score":38.03886054221376},"GB2-05":{"attempts":2,"playable":22.95384923047283,"score":22.95384923047283},"GB2-06":{"attempts":1,"playable":18.90332118158996,"score":18.90332118158996},"GB2-07":{"attempts":2,"playable":30.076177907969353,"score":30.076177907969353},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":34.18462239111669,"score":22.78974826074446}},"none":{"GB2-01":{"attempts":3,"playable":40.71834566893981,"score":40.71834566893981},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":40.557370208138636,"score":13.519123402712879},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":44.522005781681415,"score":14.840668593893804},"GB2-04":{"attempts":2,"playable":40.74107687514222,"score":40.74107687514222},"GB2-05":{"attempts":3,"playable":26.00980198908149,"score":26.00980198908149},"GB2-06":{"attempts":3,"playable":30.771174001805722,"score":30.771174001805722},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":20.560310607069407,"score":13.706873738046271},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":33.62622070938291,"score":22.41748047292194}}},"id":"xiaomi/mimo-v2.5","is_recent_addition":false,"last_measured_at":"2026-11-03T07:12:30Z","match_totals_all":{"draws":5035,"losses":10699,"wins":3628},"match_totals_tracks":{"highest":{"draws":1035,"losses":1244,"wins":313},"medium":{"draws":2319,"losses":4227,"wins":1282},"none":{"draws":1681,"losses":5228,"wins":2033}},"model_slug":"xiaomi-mimo-v2-5","official_rank_by_reasoning":{"none":76},"overall":{"max":45.668913524119844,"mean":29.262375726582977,"min":13.519123402712879},"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":22.988592572595227,"GB2-02":43.100487355847264,"GB2-04":38.475347608725116,"GB2-06":45.668913524119844,"GB2-08":17.614128257121042},"per_game_all":{"GB2-01":30.628851622799022,"GB2-02":41.61858012562602,"GB2-04":39.085095008693706,"GB2-06":31.781136235838506,"GB2-08":28.474990452540215},"per_game_match_totals_all":{"GB2-01":{"draws":660,"losses":1776,"wins":718},"GB2-02":{"draws":1887,"losses":532,"wins":49},"GB2-03":{"draws":187,"losses":205,"wins":120},"GB2-04":{"draws":1861,"losses":982,"wins":229},"GB2-05":{"draws":0,"losses":2039,"wins":671},"GB2-06":{"draws":17,"losses":1797,"wins":758},"GB2-07":{"draws":0,"losses":1664,"wins":498},"GB2-08":{"draws":423,"losses":1704,"wins":585}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":225,"losses":295,"wins":6},"GB2-02":{"draws":393,"losses":92,"wins":11},"GB2-04":{"draws":307,"losses":168,"wins":37},"GB2-06":{"draws":5,"losses":288,"wins":221},"GB2-08":{"draws":105,"losses":401,"wins":38}},"medium":{"GB2-01":{"draws":134,"losses":691,"wins":225},"GB2-02":{"draws":1117,"losses":329,"wins":32},"GB2-04":{"draws":940,"losses":501,"wins":95},"GB2-05":{"draws":0,"losses":831,"wins":249},"GB2-06":{"draws":6,"losses":424,"wins":86},"GB2-07":{"draws":0,"losses":783,"wins":299},"GB2-08":{"draws":122,"losses":668,"wins":296}},"none":{"GB2-01":{"draws":301,"losses":790,"wins":487},"GB2-02":{"draws":377,"losses":111,"wins":6},"GB2-03":{"draws":187,"losses":205,"wins":120},"GB2-04":{"draws":614,"losses":313,"wins":97},"GB2-05":{"draws":0,"losses":1208,"wins":422},"GB2-06":{"draws":6,"losses":1085,"wins":451},"GB2-07":{"draws":0,"losses":881,"wins":199},"GB2-08":{"draws":196,"losses":635,"wins":251}}},"per_game_raw_elo_all":{"GB2-01":1288.864333957331,"GB2-02":1411.2099169363528,"GB2-04":1391.4326467829735,"GB2-06":1164.0431797250912,"GB2-08":1136.123812104899},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1205.0261347918624,"GB2-02":1422.8734634215145,"GB2-04":1386.5592602865781,"GB2-06":1386.9092580650668,"GB2-08":996.1710211602335},"medium":{"GB2-01":1266.2646029745044,"GB2-02":1407.8989906144973,"GB2-04":1382.9912111716096,"GB2-05":1063.138761876176,"GB2-06":957.9738379764249,"GB2-07":1176.2368576261201,"GB2-08":1209.49302688752},"none":{"GB2-01":1395.3022641056257,"GB2-02":1402.8572967730468,"GB2-03":1392.0905657796131,"GB2-04":1404.7474688907337,"GB2-05":1082.224357359238,"GB2-06":1147.246443133782,"GB2-07":1020.7642833671594,"GB2-08":1202.7073882669429}},"per_game_tracks":{"highest":{"GB2-01":22.988592572595227,"GB2-02":43.100487355847264,"GB2-04":38.475347608725116,"GB2-06":45.668913524119844,"GB2-08":17.614128257121042},"medium":{"GB2-01":28.17961662686202,"GB2-02":41.19788281289216,"GB2-04":38.03886054221376,"GB2-05":22.95384923047283,"GB2-06":18.90332118158996,"GB2-07":30.076177907969353,"GB2-08":34.18462239111669},"none":{"GB2-01":40.71834566893981,"GB2-02":40.557370208138636,"GB2-03":44.522005781681415,"GB2-04":40.74107687514222,"GB2-05":26.00980198908149,"GB2-06":30.771174001805722,"GB2-07":20.560310607069407,"GB2-08":33.62622070938291}},"program_outcomes":{"all":{"counted_attempts":44,"failed":7,"infra_excluded":12,"success_rate":0.8409090909090909,"too_slow":0,"worked_after_repair":24,"worked_first_time":13,"working":37},"highest":{"counted_attempts":5,"failed":0,"infra_excluded":3,"success_rate":1.0,"too_slow":0,"worked_after_repair":5,"worked_first_time":0,"working":5},"medium":{"counted_attempts":16,"failed":1,"infra_excluded":8,"success_rate":0.9375,"too_slow":0,"worked_after_repair":14,"worked_first_time":1,"working":15},"none":{"counted_attempts":23,"failed":6,"infra_excluded":1,"success_rate":0.7391304347826086,"too_slow":0,"worked_after_repair":5,"worked_first_time":12,"working":17}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":33.5694938636817,"medium":28.877065223249215,"none":25.340568092818017},"reasoning_agg":{"highest":{"max":45.668913524119844,"mean":33.5694938636817,"min":17.614128257121042},"medium":{"max":41.19788281289216,"mean":28.877065223249215,"min":18.90332118158996},"none":{"max":40.74107687514222,"mean":25.340568092818017,"min":13.519123402712879}},"reasoning_labels":{"highest":"High","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":8.228925770863682},"working_program_strength":{"all":32.920895492855955,"highest":33.5694938636817,"medium":30.504904384730967,"none":34.6882882301552}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-nano:f2f3aae2a18b47b3","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":0.39544915},"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":0.39544915},"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":1.0821379},"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":{"all":28.083585287182245,"medium":30.988693093296916,"none":25.178477481067578},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"failed"},"none":{"GB2-04":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":29.758369835077314,"score":29.758369835077314},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":39.268283522078775,"score":29.542351018343446},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":32.68645796231143,"score":8.171614490577857},"GB2-04":{"attempts":4,"failed_attempts":3,"playable":50.17515273929614,"score":12.543788184824034},"GB2-05":{"attempts":4,"playable":28.069216320215162,"score":28.069216320215162},"GB2-06":{"attempts":4,"playable":47.805166432319936,"score":47.805166432319936},"GB2-07":{"attempts":4,"failed_attempts":1,"playable":27.446506289619514,"score":22.263935587561164},"GB2-08":{"attempts":4,"playable":46.51424042853906,"score":46.51424042853906}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"playable":15.196709888174674,"score":15.196709888174674},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":38.9037300149413,"score":19.45186500747065},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":50.17515273929614,"score":25.08757636964807},"GB2-05":{"attempts":2,"playable":48.43229730676257,"score":48.43229730676257},"GB2-06":{"attempts":2,"playable":56.49818638765654,"score":56.49818638765654},"GB2-07":{"attempts":2,"playable":34.16272977100562,"score":34.16272977100562},"GB2-08":{"attempts":2,"playable":49.080180015657206,"score":49.080180015657206}},"none":{"GB2-01":{"attempts":2,"playable":44.320029781979954,"score":44.320029781979954},"GB2-02":{"attempts":2,"playable":39.63283702921624,"score":39.63283702921624},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":32.68645796231143,"score":16.343228981155715},"GB2-04":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-05":{"attempts":2,"playable":7.706135333667749,"score":7.706135333667749},"GB2-06":{"attempts":2,"playable":39.11214647698333,"score":39.11214647698333},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":20.730282808233405,"score":10.365141404116702},"GB2-08":{"attempts":2,"playable":43.94830084142092,"score":43.94830084142092}}},"id":"gpt-5.4-nano","is_recent_addition":false,"last_measured_at":"2026-11-03T07:16:19Z","match_totals_all":{"draws":2091,"losses":7000,"wins":3541},"match_totals_tracks":{"medium":{"draws":875,"losses":3341,"wins":2116},"none":{"draws":1216,"losses":3659,"wins":1425}},"model_slug":"gpt-5-4-nano","official_rank_by_reasoning":{"medium":70,"none":77},"overall":{"max":56.49818638765654,"mean":28.083585287182245,"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":392,"losses":1289,"wins":423},"GB2-02":{"draws":1102,"losses":364,"wins":14},"GB2-03":{"draws":145,"losses":286,"wins":83},"GB2-04":{"draws":236,"losses":144,"wins":132},"GB2-05":{"draws":0,"losses":1568,"wins":604},"GB2-06":{"draws":24,"losses":1095,"wins":941},"GB2-07":{"draws":0,"losses":1168,"wins":452},"GB2-08":{"draws":192,"losses":1086,"wins":892}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":163,"losses":815,"wins":74},"GB2-02":{"draws":367,"losses":123,"wins":2},"GB2-04":{"draws":236,"losses":144,"wins":132},"GB2-05":{"draws":0,"losses":560,"wins":524},"GB2-06":{"draws":21,"losses":453,"wins":554},"GB2-07":{"draws":0,"losses":728,"wins":352},"GB2-08":{"draws":88,"losses":518,"wins":478}},"none":{"GB2-01":{"draws":229,"losses":474,"wins":349},"GB2-02":{"draws":735,"losses":241,"wins":12},"GB2-03":{"draws":145,"losses":286,"wins":83},"GB2-05":{"draws":0,"losses":1008,"wins":80},"GB2-06":{"draws":3,"losses":642,"wins":387},"GB2-07":{"draws":0,"losses":440,"wins":100},"GB2-08":{"draws":104,"losses":568,"wins":414}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1054.3672328946552,"GB2-02":1389.7070162587138,"GB2-04":1479.2659662550452,"GB2-05":1458.3357264321207,"GB2-06":1563.6776474050139,"GB2-07":1184.2444446804438,"GB2-08":1458.651916421938},"none":{"GB2-01":1432.0338750905034,"GB2-02":1395.5211057534175,"GB2-03":1285.6047723269064,"GB2-05":720.069970521196,"GB2-06":1284.0170819951502,"GB2-07":1039.2525968250322,"GB2-08":1379.313353414208}},"per_game_tracks":{"medium":{"GB2-01":15.196709888174674,"GB2-02":38.9037300149413,"GB2-04":50.17515273929614,"GB2-05":48.43229730676257,"GB2-06":56.49818638765654,"GB2-07":34.16272977100562,"GB2-08":49.080180015657206},"none":{"GB2-01":44.320029781979954,"GB2-02":39.63283702921624,"GB2-03":32.68645796231143,"GB2-05":7.706135333667749,"GB2-06":39.11214647698333,"GB2-07":20.730282808233405,"GB2-08":43.94830084142092}},"program_outcomes":{"all":{"counted_attempts":32,"failed":8,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":14,"worked_first_time":10,"working":24},"medium":{"counted_attempts":16,"failed":4,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":7,"worked_first_time":5,"working":12},"none":{"counted_attempts":16,"failed":4,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":7,"worked_first_time":5,"working":12}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.988693093296916,"none":25.178477481067578},"reasoning_agg":{"medium":{"max":56.49818638765654,"mean":30.988693093296916,"min":0.0},"none":{"max":44.320029781979954,"mean":25.178477481067578,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":5.810215612229339},"working_program_strength":{"all":37.18465545409336,"medium":41.77842658907058,"none":32.59088431911615}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemma-4-31b-it:dac3a348339f0ac2","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":0.01492467}},"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":0.03073979},"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":0.014924670000000001}},"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":{"all":27.903025580275997,"medium":36.279501910336904,"none":19.52654925021509},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"failed","GB2-03":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":20.92272929154496,"score":10.46136464577248},"GB2-02":{"attempts":2,"playable":40.90970722945614,"score":40.90970722945614},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":41.34492060724577,"score":20.672460303622884},"GB2-04":{"attempts":2,"playable":43.31589639421554,"score":43.31589639421554},"GB2-05":{"attempts":2,"playable":42.50072757458745,"score":42.50072757458745},"GB2-06":{"attempts":2,"playable":20.218278995291918,"score":20.218278995291918},"GB2-07":{"attempts":2,"playable":13.7195170056211,"score":13.7195170056211},"GB2-08":{"attempts":2,"playable":31.42625249364051,"score":31.42625249364051}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":20.92272929154496,"score":20.92272929154496},"GB2-02":{"attempts":1,"playable":42.601581762720286,"score":42.601581762720286},"GB2-03":{"attempts":1,"playable":41.34492060724577,"score":41.34492060724577},"GB2-04":{"attempts":1,"playable":41.951110633242514,"score":41.951110633242514},"GB2-05":{"attempts":1,"playable":69.02967705272938,"score":69.02967705272938},"GB2-06":{"attempts":1,"playable":25.16210740944454,"score":25.16210740944454},"GB2-07":{"attempts":1,"playable":17.543461835711224,"score":17.543461835711224},"GB2-08":{"attempts":1,"playable":31.680426690056624,"score":31.680426690056624}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":39.21783269619199,"score":39.21783269619199},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":44.68068215518856,"score":44.68068215518856},"GB2-05":{"attempts":1,"playable":15.971778096445524,"score":15.971778096445524},"GB2-06":{"attempts":1,"playable":15.274450581139298,"score":15.274450581139298},"GB2-07":{"attempts":1,"playable":9.895572175530976,"score":9.895572175530976},"GB2-08":{"attempts":1,"playable":31.172078297224402,"score":31.172078297224402}}},"id":"google/gemma-4-31b-it","is_recent_addition":false,"last_measured_at":"2026-11-03T08:03:50Z","match_totals_all":{"draws":2202,"losses":4007,"wins":1131},"match_totals_tracks":{"medium":{"draws":1254,"losses":2105,"wins":831},"none":{"draws":948,"losses":1902,"wins":300}},"model_slug":"google-gemma-4-31b-it","official_rank_by_reasoning":{"medium":62,"none":84},"overall":{"max":69.02967705272938,"mean":27.903025580275997,"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":130,"losses":355,"wins":43},"GB2-02":{"draws":752,"losses":219,"wins":15},"GB2-03":{"draws":119,"losses":257,"wins":140},"GB2-04":{"draws":638,"losses":276,"wins":112},"GB2-05":{"draws":0,"losses":627,"wins":459},"GB2-06":{"draws":30,"losses":823,"wins":175},"GB2-07":{"draws":0,"losses":955,"wins":129},"GB2-08":{"draws":533,"losses":495,"wins":58}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":130,"losses":355,"wins":43},"GB2-02":{"draws":383,"losses":97,"wins":12},"GB2-03":{"draws":119,"losses":257,"wins":140},"GB2-04":{"draws":328,"losses":140,"wins":44},"GB2-05":{"draws":0,"losses":169,"wins":373},"GB2-06":{"draws":29,"losses":381,"wins":104},"GB2-07":{"draws":0,"losses":460,"wins":84},"GB2-08":{"draws":265,"losses":246,"wins":31}},"none":{"GB2-02":{"draws":369,"losses":122,"wins":3},"GB2-04":{"draws":310,"losses":136,"wins":68},"GB2-05":{"draws":0,"losses":458,"wins":86},"GB2-06":{"draws":1,"losses":442,"wins":71},"GB2-07":{"draws":0,"losses":495,"wins":45},"GB2-08":{"draws":268,"losses":249,"wins":27}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1178.2155649185934,"GB2-02":1418.962006042096,"GB2-03":1363.979356032531,"GB2-04":1414.3749427645175,"GB2-05":1726.810850407298,"GB2-06":1063.2438759706838,"GB2-07":983.3723762697506,"GB2-08":1179.2325358807318},"none":{"GB2-02":1392.2150706726982,"GB2-04":1435.9511560894864,"GB2-05":931.726945251939,"GB2-06":891.3563899819092,"GB2-07":814.769289058982,"GB2-08":1173.0889301915115}},"per_game_tracks":{"medium":{"GB2-01":20.92272929154496,"GB2-02":42.601581762720286,"GB2-03":41.34492060724577,"GB2-04":41.951110633242514,"GB2-05":69.02967705272938,"GB2-06":25.16210740944454,"GB2-07":17.543461835711224,"GB2-08":31.680426690056624},"none":{"GB2-02":39.21783269619199,"GB2-04":44.68068215518856,"GB2-05":15.971778096445524,"GB2-06":15.274450581139298,"GB2-07":9.895572175530976,"GB2-08":31.172078297224402}},"program_outcomes":{"all":{"counted_attempts":16,"failed":2,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":11,"working":14},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":0,"worked_first_time":6,"working":6}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":36.279501910336904,"none":19.52654925021509},"reasoning_agg":{"medium":{"max":69.02967705272938,"mean":36.279501910336904,"min":17.543461835711224},"none":{"max":44.68068215518856,"mean":19.52654925021509,"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":16.752952660121814},"working_program_strength":{"all":31.157450455311846,"medium":36.279501910336904,"none":26.035399000286787}},{"canonical_public_row_identity":"publication-row.v1:overall:meituan-longcat-2-0:67b72b073a6b634c","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":0.214047204}},"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":1.60040646},"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":{"all":27.10648905228803,"medium":26.612994770626937,"none":27.599983333949123},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":41.22639348459185,"score":20.613196742295926},"GB2-02":{"attempts":4,"failed_attempts":2,"playable":40.964891902437415,"score":20.482445951218708},"GB2-03":{"attempts":4,"failed_attempts":1,"playable":36.10052897728778,"score":26.47803008918077},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":41.41763800927554,"score":30.11144102126596},"GB2-05":{"attempts":4,"playable":21.304851705612787,"score":21.304851705612787},"GB2-06":{"attempts":4,"playable":28.017369181967922,"score":28.017369181967922},"GB2-07":{"attempts":4,"playable":35.59117674484523,"score":35.59117674484523},"GB2-08":{"attempts":4,"playable":34.25340098191693,"score":34.25340098191693}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":42.28607639408971,"score":21.143038197044856},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":38.48999555242802,"score":19.24499777621401},"GB2-04":{"attempts":2,"playable":37.610488066512765,"score":37.610488066512765},"GB2-05":{"attempts":2,"playable":31.405108447353953,"score":31.405108447353953},"GB2-06":{"attempts":2,"playable":22.420157038369915,"score":22.420157038369915},"GB2-07":{"attempts":2,"playable":36.668386844707584,"score":36.668386844707584},"GB2-08":{"attempts":2,"playable":44.41178179481242,"score":44.41178179481242}},"none":{"GB2-01":{"attempts":2,"playable":41.22639348459185,"score":41.22639348459185},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":39.643707410785126,"score":19.821853705392563},"GB2-03":{"attempts":2,"playable":33.71106240214753,"score":33.71106240214753},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":45.22478795203832,"score":22.61239397601916},"GB2-05":{"attempts":2,"playable":11.204594963871621,"score":11.204594963871621},"GB2-06":{"attempts":2,"playable":33.61458132556593,"score":33.61458132556593},"GB2-07":{"attempts":2,"playable":34.51396664498288,"score":34.51396664498288},"GB2-08":{"attempts":2,"playable":24.095020169021446,"score":24.095020169021446}}},"id":"meituan/longcat-2.0","is_recent_addition":false,"last_measured_at":"2026-11-03T06:54:15Z","match_totals_all":{"draws":2602,"losses":8014,"wins":3060},"match_totals_tracks":{"medium":{"draws":1210,"losses":3546,"wins":1550},"none":{"draws":1392,"losses":4468,"wins":1510}},"model_slug":"meituan-longcat-2-0","official_rank_by_reasoning":{"medium":75,"none":71},"overall":{"max":44.41178179481242,"mean":27.10648905228803,"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":255,"losses":498,"wins":305},"GB2-02":{"draws":784,"losses":206,"wins":2},"GB2-03":{"draws":453,"losses":810,"wins":279},"GB2-04":{"draws":828,"losses":519,"wins":177},"GB2-05":{"draws":0,"losses":1711,"wins":459},"GB2-06":{"draws":36,"losses":1502,"wins":520},"GB2-07":{"draws":0,"losses":1437,"wins":725},"GB2-08":{"draws":246,"losses":1331,"wins":593}},"per_game_match_totals_tracks":{"medium":{"GB2-02":{"draws":405,"losses":90,"wins":1},"GB2-03":{"draws":154,"losses":254,"wins":108},"GB2-04":{"draws":543,"losses":376,"wins":97},"GB2-05":{"draws":0,"losses":744,"wins":340},"GB2-06":{"draws":24,"losses":805,"wins":201},"GB2-07":{"draws":0,"losses":702,"wins":378},"GB2-08":{"draws":84,"losses":575,"wins":425}},"none":{"GB2-01":{"draws":255,"losses":498,"wins":305},"GB2-02":{"draws":379,"losses":116,"wins":1},"GB2-03":{"draws":299,"losses":556,"wins":171},"GB2-04":{"draws":285,"losses":143,"wins":80},"GB2-05":{"draws":0,"losses":967,"wins":119},"GB2-06":{"draws":12,"losses":697,"wins":319},"GB2-07":{"draws":0,"losses":735,"wins":347},"GB2-08":{"draws":162,"losses":756,"wins":168}}},"per_game_raw_elo_tracks":{"medium":{"GB2-02":1416.4850880868755,"GB2-03":1338.5704154550167,"GB2-04":1379.2087172321842,"GB2-05":1168.1603917653738,"GB2-06":1017.1825221617371,"GB2-07":1239.5547599488068,"GB2-08":1352.7692797293219},"none":{"GB2-01":1402.306458318909,"GB2-02":1395.6075896394448,"GB2-03":1293.2797599290461,"GB2-04":1440.2378836999542,"GB2-05":818.3424914236404,"GB2-06":1196.5064122853469,"GB2-07":1240.1239601333855,"GB2-08":1085.3276214551524}},"per_game_tracks":{"medium":{"GB2-02":42.28607639408971,"GB2-03":38.48999555242802,"GB2-04":37.610488066512765,"GB2-05":31.405108447353953,"GB2-06":22.420157038369915,"GB2-07":36.668386844707584,"GB2-08":44.41178179481242},"none":{"GB2-01":41.22639348459185,"GB2-02":39.643707410785126,"GB2-03":33.71106240214753,"GB2-04":45.22478795203832,"GB2-05":11.204594963871621,"GB2-06":33.61458132556593,"GB2-07":34.51396664498288,"GB2-08":24.095020169021446}},"program_outcomes":{"all":{"counted_attempts":32,"failed":6,"infra_excluded":0,"success_rate":0.8125,"too_slow":0,"worked_after_repair":9,"worked_first_time":17,"working":26},"medium":{"counted_attempts":16,"failed":4,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":3,"worked_first_time":9,"working":12},"none":{"counted_attempts":16,"failed":2,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":6,"worked_first_time":8,"working":14}},"provider_color":"#29E154","provider_company":"Meituan","provider_key":"meituan","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":26.612994770626937,"none":27.599983333949123},"reasoning_agg":{"medium":{"max":44.41178179481242,"mean":26.612994770626937,"min":0.0},"none":{"max":41.22639348459185,"mean":27.599983333949123,"min":11.204594963871621}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":0.9869885633221855},"working_program_strength":{"all":34.544417442653824,"medium":36.18457059118206,"none":32.90426429412559}},{"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-pro:25328172d378693d","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":0.8197712500000001},"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":2.586028}},"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":0.81977125},"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":2.586028}},"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":{"all":25.960993868817805,"medium":14.963820721482392,"none":36.95816701615322},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"infra_excluded"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"infra_excluded","GB2-02":"infra_excluded","GB2-04":"failed"},"none":{"GB2-01":"infra_excluded"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":35.56986386705331,"score":35.56986386705331},"GB2-03":{"attempts":2,"playable":32.07094896441558,"score":32.07094896441558},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":40.74185887305207,"score":20.370929436526033},"GB2-05":{"attempts":2,"playable":19.778987622142537,"score":19.778987622142537},"GB2-06":{"attempts":2,"playable":12.22937861923602,"score":12.22937861923602},"GB2-07":{"attempts":2,"playable":42.74298378311742,"score":42.74298378311742},"GB2-08":{"attempts":2,"playable":29.266886362019214,"score":29.266886362019214}},"headline_games_tracks":{"medium":{"GB2-03":{"attempts":1,"playable":29.641388440359762,"score":29.641388440359762},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":11.11494421181499,"score":11.11494421181499},"GB2-06":{"attempts":1,"playable":13.677144489718934,"score":13.677144489718934},"GB2-07":{"attempts":1,"playable":23.01665776725942,"score":23.01665776725942},"GB2-08":{"attempts":1,"playable":12.33278941974124,"score":12.33278941974124}},"none":{"GB2-02":{"attempts":1,"playable":35.56986386705331,"score":35.56986386705331},"GB2-03":{"attempts":1,"playable":34.50050948847139,"score":34.50050948847139},"GB2-04":{"attempts":1,"playable":40.74185887305207,"score":40.74185887305207},"GB2-05":{"attempts":1,"playable":28.44303103247009,"score":28.44303103247009},"GB2-06":{"attempts":1,"playable":10.781612748753105,"score":10.781612748753105},"GB2-07":{"attempts":1,"playable":62.46930979897542,"score":62.46930979897542},"GB2-08":{"attempts":1,"playable":46.20098330429719,"score":46.20098330429719}}},"id":"nex-agi/nex-n2-pro","is_recent_addition":false,"last_measured_at":"2026-11-03T08:07:17Z","match_totals_all":{"draws":1163,"losses":3992,"wins":1175},"match_totals_tracks":{"medium":{"draws":190,"losses":2127,"wins":343},"none":{"draws":973,"losses":1865,"wins":832}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":62.46930979897542,"mean":25.960993868817805,"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":331,"losses":160,"wins":5},"GB2-03":{"draws":412,"losses":519,"wins":99},"GB2-04":{"draws":360,"losses":130,"wins":22},"GB2-05":{"draws":0,"losses":874,"wins":214},"GB2-06":{"draws":12,"losses":912,"wins":108},"GB2-07":{"draws":0,"losses":640,"wins":444},"GB2-08":{"draws":48,"losses":757,"wins":283}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":164,"losses":292,"wins":58},"GB2-05":{"draws":0,"losses":485,"wins":59},"GB2-06":{"draws":8,"losses":448,"wins":60},"GB2-07":{"draws":0,"losses":430,"wins":112},"GB2-08":{"draws":18,"losses":472,"wins":54}},"none":{"GB2-02":{"draws":331,"losses":160,"wins":5},"GB2-03":{"draws":248,"losses":227,"wins":41},"GB2-04":{"draws":360,"losses":130,"wins":22},"GB2-05":{"draws":0,"losses":389,"wins":155},"GB2-06":{"draws":4,"losses":464,"wins":48},"GB2-07":{"draws":0,"losses":210,"wins":332},"GB2-08":{"draws":30,"losses":285,"wins":229}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1256.5594302808474,"GB2-05":819.1229760751127,"GB2-06":859.6985115328253,"GB2-07":1076.3753774938914,"GB2-08":908.2206182392054},"none":{"GB2-02":1362.7100375830412,"GB2-03":1302.430543092622,"GB2-04":1404.7538973482929,"GB2-05":1156.315960064693,"GB2-06":796.4942597905942,"GB2-07":1613.4220877246285,"GB2-08":1359.6342077895374}},"per_game_tracks":{"medium":{"GB2-03":29.641388440359762,"GB2-05":11.11494421181499,"GB2-06":13.677144489718934,"GB2-07":23.01665776725942,"GB2-08":12.33278941974124},"none":{"GB2-02":35.56986386705331,"GB2-03":34.50050948847139,"GB2-04":40.74185887305207,"GB2-05":28.44303103247009,"GB2-06":10.781612748753105,"GB2-07":62.46930979897542,"GB2-08":46.20098330429719}},"program_outcomes":{"all":{"counted_attempts":13,"failed":1,"infra_excluded":11,"success_rate":0.9230769230769231,"too_slow":0,"worked_after_repair":12,"worked_first_time":0,"working":12},"medium":{"counted_attempts":6,"failed":1,"infra_excluded":2,"success_rate":0.8333333333333334,"too_slow":0,"worked_after_repair":5,"worked_first_time":0,"working":5},"none":{"counted_attempts":7,"failed":0,"infra_excluded":9,"success_rate":1.0,"too_slow":0,"worked_after_repair":7,"worked_first_time":0,"working":7}},"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":14.963820721482392,"none":36.95816701615322},"reasoning_agg":{"medium":{"max":29.641388440359762,"mean":14.963820721482392,"min":0.0},"none":{"max":62.46930979897542,"mean":36.95816701615322,"min":10.781612748753105}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":21.994346294670827},"working_program_strength":{"all":27.457375940966045,"medium":17.956584865778872,"none":36.95816701615322}},{"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3:77ef69bca80e8838","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":0.58451034},"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":0.20304798000000002}},"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":{"all":25.378394721638372,"medium":21.721488059745557,"none":29.03530138353119},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"failed"},"none":{"GB2-04":"failed","GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":36.930408343542865,"score":36.930408343542865},"GB2-02":{"attempts":2,"playable":38.86059362095422,"score":38.86059362095422},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":38.261461056410674,"score":19.130730528205337},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":39.18327615239837,"score":19.591638076199185},"GB2-05":{"attempts":2,"playable":14.586468176707013,"score":14.586468176707013},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":16.10134029818734,"score":8.05067014909367},"GB2-07":{"attempts":2,"playable":31.732735317266766,"score":31.732735317266766},"GB2-08":{"attempts":2,"playable":34.143913561137936,"score":34.143913561137936}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":17.358487330395896,"score":17.358487330395896},"GB2-02":{"attempts":1,"playable":38.41084272056079,"score":38.41084272056079},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":39.18327615239837,"score":39.18327615239837},"GB2-05":{"attempts":1,"playable":1.9754749862267365,"score":1.9754749862267365},"GB2-06":{"attempts":1,"playable":16.10134029818734,"score":16.10134029818734},"GB2-07":{"attempts":1,"playable":41.036592471079096,"score":41.036592471079096},"GB2-08":{"attempts":1,"playable":19.705890519116217,"score":19.705890519116217}},"none":{"GB2-01":{"attempts":1,"playable":56.50232935668983,"score":56.50232935668983},"GB2-02":{"attempts":1,"playable":39.31034452134766,"score":39.31034452134766},"GB2-03":{"attempts":1,"playable":38.261461056410674,"score":38.261461056410674},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":27.19746136718729,"score":27.19746136718729},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":22.42887816345443,"score":22.42887816345443},"GB2-08":{"attempts":1,"playable":48.58193660315966,"score":48.58193660315966}}},"id":"minimax/minimax-m3","is_recent_addition":false,"last_measured_at":"2026-11-03T08:03:29Z","match_totals_all":{"draws":1328,"losses":4141,"wins":1377},"match_totals_tracks":{"medium":{"draws":761,"losses":2438,"wins":481},"none":{"draws":567,"losses":1703,"wins":896}},"model_slug":"minimax-minimax-m3","official_rank_by_reasoning":{"medium":80,"none":64},"overall":{"max":56.50232935668983,"mean":25.378394721638372,"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":108,"losses":615,"wins":333},"GB2-02":{"draws":731,"losses":250,"wins":5},"GB2-03":{"draws":107,"losses":280,"wins":131},"GB2-04":{"draws":324,"losses":158,"wins":34},"GB2-05":{"draws":0,"losses":932,"wins":156},"GB2-06":{"draws":3,"losses":439,"wins":74},"GB2-07":{"draws":0,"losses":764,"wins":316},"GB2-08":{"draws":55,"losses":703,"wins":328}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":22,"losses":426,"wins":78},"GB2-02":{"draws":365,"losses":128,"wins":1},"GB2-04":{"draws":324,"losses":158,"wins":34},"GB2-05":{"draws":0,"losses":538,"wins":8},"GB2-06":{"draws":3,"losses":439,"wins":74},"GB2-07":{"draws":0,"losses":332,"wins":208},"GB2-08":{"draws":47,"losses":417,"wins":78}},"none":{"GB2-01":{"draws":86,"losses":189,"wins":255},"GB2-02":{"draws":366,"losses":122,"wins":4},"GB2-03":{"draws":107,"losses":280,"wins":131},"GB2-05":{"draws":0,"losses":394,"wins":148},"GB2-07":{"draws":0,"losses":432,"wins":108},"GB2-08":{"draws":8,"losses":286,"wins":250}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1127.7000811195326,"GB2-02":1385.7606378674504,"GB2-04":1392.268737007318,"GB2-05":415.08762984288387,"GB2-06":907.097825220776,"GB2-07":1327.387634728189,"GB2-08":1026.5024469551622},"none":{"GB2-01":1550.5381972889168,"GB2-02":1392.9527881910565,"GB2-03":1336.5241592655686,"GB2-05":1136.5418056442968,"GB2-07":1067.0294685012461,"GB2-08":1391.865258532389}},"per_game_tracks":{"medium":{"GB2-01":17.358487330395896,"GB2-02":38.41084272056079,"GB2-04":39.18327615239837,"GB2-05":1.9754749862267365,"GB2-06":16.10134029818734,"GB2-07":41.036592471079096,"GB2-08":19.705890519116217},"none":{"GB2-01":56.50232935668983,"GB2-02":39.31034452134766,"GB2-03":38.261461056410674,"GB2-05":27.19746136718729,"GB2-07":22.42887816345443,"GB2-08":48.58193660315966}},"program_outcomes":{"all":{"counted_attempts":16,"failed":3,"infra_excluded":0,"success_rate":0.8125,"too_slow":0,"worked_after_repair":9,"worked_first_time":4,"working":13},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":7,"worked_first_time":0,"working":7},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":2,"worked_first_time":4,"working":6}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":21.721488059745557,"none":29.03530138353119},"reasoning_agg":{"medium":{"max":41.036592471079096,"mean":21.721488059745557,"min":0.0},"none":{"max":56.50232935668983,"mean":29.03530138353119,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":7.313813323785634},"working_program_strength":{"all":31.76914648030397,"medium":24.82455778256635,"none":38.71373517804159}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-medium-3-5:db598f876bca3856","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":0.5409853360167188},"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":1.3975426639832813}},"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":{"all":24.487906043029486,"highest":27.01092377367869,"none":21.964888312380282},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"failed"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-07":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":11.199101146744084,"score":5.599550573372042},"GB2-02":{"attempts":2,"playable":42.29240519770384,"score":42.29240519770384},"GB2-03":{"attempts":2,"playable":34.51080792435177,"score":34.51080792435177},"GB2-04":{"attempts":2,"playable":35.986302693836805,"score":35.986302693836805},"GB2-05":{"attempts":2,"playable":23.444373170293147,"score":23.444373170293147},"GB2-06":{"attempts":2,"playable":20.16927689232694,"score":20.16927689232694},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":13.025628885684895,"score":6.512814442842448},"GB2-08":{"attempts":2,"playable":27.387717449508887,"score":27.387717449508887}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":44.12744102299191,"score":44.12744102299191},"GB2-03":{"attempts":1,"playable":35.93327573502171,"score":35.93327573502171},"GB2-04":{"attempts":1,"playable":38.64681698376744,"score":38.64681698376744},"GB2-05":{"attempts":1,"playable":34.69036969239769,"score":34.69036969239769},"GB2-06":{"attempts":1,"playable":23.771902500558188,"score":23.771902500558188},"GB2-07":{"attempts":1,"playable":13.025628885684895,"score":13.025628885684895},"GB2-08":{"attempts":1,"playable":25.891955369007675,"score":25.891955369007675}},"none":{"GB2-01":{"attempts":1,"playable":11.199101146744084,"score":11.199101146744084},"GB2-02":{"attempts":1,"playable":40.45736937241578,"score":40.45736937241578},"GB2-03":{"attempts":1,"playable":33.08834011368182,"score":33.08834011368182},"GB2-04":{"attempts":1,"playable":33.325788403906174,"score":33.325788403906174},"GB2-05":{"attempts":1,"playable":12.19837664818861,"score":12.19837664818861},"GB2-06":{"attempts":1,"playable":16.5666512840957,"score":16.5666512840957},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":28.8834795300101,"score":28.8834795300101}}},"id":"mistralai/mistral-medium-3-5","is_recent_addition":false,"last_measured_at":"2026-11-03T01:51:08Z","match_totals_all":{"draws":1841,"losses":4445,"wins":1012},"match_totals_tracks":{"highest":{"draws":948,"losses":2109,"wins":593},"none":{"draws":893,"losses":2336,"wins":419}},"model_slug":"mistralai-mistral-medium-3-5","official_rank_by_reasoning":{"highest":63,"none":83},"overall":{"max":44.12744102299191,"mean":24.487906043029486,"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":44.12744102299191,"GB2-03":35.93327573502171,"GB2-04":38.64681698376744,"GB2-05":34.69036969239769,"GB2-06":23.771902500558188,"GB2-07":13.025628885684895,"GB2-08":25.891955369007675},"per_game_match_totals_all":{"GB2-01":{"draws":47,"losses":446,"wins":33},"GB2-02":{"draws":767,"losses":200,"wins":23},"GB2-03":{"draws":238,"losses":578,"wins":208},"GB2-04":{"draws":560,"losses":386,"wins":74},"GB2-05":{"draws":0,"losses":830,"wins":254},"GB2-06":{"draws":3,"losses":838,"wins":189},"GB2-07":{"draws":0,"losses":481,"wins":61},"GB2-08":{"draws":226,"losses":686,"wins":170}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":380,"losses":92,"wins":22},"GB2-03":{"draws":130,"losses":275,"wins":105},"GB2-04":{"draws":327,"losses":155,"wins":26},"GB2-05":{"draws":0,"losses":353,"wins":189},"GB2-06":{"draws":3,"losses":400,"wins":111},"GB2-07":{"draws":0,"losses":481,"wins":61},"GB2-08":{"draws":108,"losses":353,"wins":79}},"none":{"GB2-01":{"draws":47,"losses":446,"wins":33},"GB2-02":{"draws":387,"losses":108,"wins":1},"GB2-03":{"draws":108,"losses":303,"wins":103},"GB2-04":{"draws":233,"losses":231,"wins":48},"GB2-05":{"draws":0,"losses":477,"wins":65},"GB2-06":{"draws":0,"losses":438,"wins":78},"GB2-08":{"draws":118,"losses":333,"wins":91}}},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1430.907831227477,"GB2-03":1315.5256691452337,"GB2-04":1387.9446302019278,"GB2-05":1249.225574663259,"GB2-06":1040.5091213190956,"GB2-07":891.8975393015204,"GB2-08":1108.2364734994273},"none":{"GB2-01":1019.7626569249821,"GB2-02":1402.065582421301,"GB2-03":1289.35902544602,"GB2-04":1343.9913152448034,"GB2-05":846.3842746696713,"GB2-06":915.7913913138924,"GB2-08":1145.275222169313}},"per_game_tracks":{"highest":{"GB2-02":44.12744102299191,"GB2-03":35.93327573502171,"GB2-04":38.64681698376744,"GB2-05":34.69036969239769,"GB2-06":23.771902500558188,"GB2-07":13.025628885684895,"GB2-08":25.891955369007675},"none":{"GB2-01":11.199101146744084,"GB2-02":40.45736937241578,"GB2-03":33.08834011368182,"GB2-04":33.325788403906174,"GB2-05":12.19837664818861,"GB2-06":16.5666512840957,"GB2-08":28.8834795300101}},"program_outcomes":{"all":{"counted_attempts":16,"failed":2,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":7,"worked_first_time":7,"working":14},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":4,"worked_first_time":3,"working":7},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":27.01092377367869,"none":21.964888312380282},"reasoning_agg":{"highest":{"max":44.12744102299191,"mean":27.01092377367869,"min":0.0},"none":{"max":40.45736937241578,"mean":21.964888312380282,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":5.046035461298409},"working_program_strength":{"all":27.986178334890845,"highest":30.869627169918505,"none":25.10272949986318}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-plus:48cad3280fe927da","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":0.43500896},"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":0.08145696000000001}},"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":{"all":24.44588994261821,"medium":31.252533398504777,"none":17.63924648673164},"first_seen_at":null,"game_gaps":{"all":{"GB2-03":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"failed","GB2-04":"failed"},"none":{"GB2-03":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":33.78348359681672,"score":29.29894788078498},"GB2-02":{"attempts":2,"playable":39.85891772379925,"score":39.85891772379925},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":42.571734661723085,"score":21.285867330861542},"GB2-05":{"attempts":2,"playable":36.189078210087146,"score":36.189078210087146},"GB2-06":{"attempts":2,"playable":39.81723168326587,"score":39.81723168326587},"GB2-07":{"attempts":2,"playable":15.957613025572464,"score":15.957613025572464},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":26.318927373148824,"score":13.159463686574412}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":49.628824329506465,"score":49.628824329506465},"GB2-02":{"attempts":1,"playable":42.08190140143401,"score":42.08190140143401},"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":42.047432497615276,"score":42.047432497615276},"GB2-06":{"attempts":1,"playable":66.22519369501187,"score":66.22519369501187},"GB2-07":{"attempts":1,"playable":23.71798789132176,"score":23.71798789132176},"GB2-08":{"attempts":1,"playable":26.318927373148824,"score":26.318927373148824}},"none":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":17.938142864126988,"score":8.969071432063494},"GB2-02":{"attempts":1,"playable":37.635934046164486,"score":37.635934046164486},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":42.571734661723085,"score":42.571734661723085},"GB2-05":{"attempts":1,"playable":30.330723922559024,"score":30.330723922559024},"GB2-06":{"attempts":1,"playable":13.40926967151986,"score":13.40926967151986},"GB2-07":{"attempts":1,"playable":8.197238159823167,"score":8.197238159823167},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"qwen/qwen3.7-plus","is_recent_addition":false,"last_measured_at":"2026-11-03T08:01:54Z","match_totals_all":{"draws":1445,"losses":3549,"wins":1306},"match_totals_tracks":{"medium":{"draws":637,"losses":1571,"wins":962},"none":{"draws":808,"losses":1978,"wins":344}},"model_slug":"qwen-qwen3-7-plus","official_rank_by_reasoning":{"medium":69,"none":87},"overall":{"max":66.22519369501187,"mean":24.44588994261821,"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":206,"losses":596,"wins":248},"GB2-02":{"draws":758,"losses":232,"wins":6},"GB2-04":{"draws":336,"losses":132,"wins":42},"GB2-05":{"draws":0,"losses":692,"wins":394},"GB2-06":{"draws":24,"losses":619,"wins":387},"GB2-07":{"draws":0,"losses":929,"wins":153},"GB2-08":{"draws":121,"losses":349,"wins":76}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":96,"losses":217,"wins":211},"GB2-02":{"draws":401,"losses":94,"wins":3},"GB2-05":{"draws":0,"losses":315,"wins":229},"GB2-06":{"draws":19,"losses":170,"wins":327},"GB2-07":{"draws":0,"losses":426,"wins":116},"GB2-08":{"draws":121,"losses":349,"wins":76}},"none":{"GB2-01":{"draws":110,"losses":379,"wins":37},"GB2-02":{"draws":357,"losses":138,"wins":3},"GB2-04":{"draws":336,"losses":132,"wins":42},"GB2-05":{"draws":0,"losses":377,"wins":165},"GB2-06":{"draws":5,"losses":449,"wins":60},"GB2-07":{"draws":0,"losses":503,"wins":37}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1483.6673578842942,"GB2-02":1414.8806833863482,"GB2-05":1348.99518898505,"GB2-06":1733.1182249367,"GB2-07":1087.3656969597678,"GB2-08":1113.5891835296104},"none":{"GB2-01":1136.353958606509,"GB2-02":1379.5275467180627,"GB2-04":1419.2950984400843,"GB2-05":1185.4268588965856,"GB2-06":854.2012175246173,"GB2-07":765.1460840719104}},"per_game_tracks":{"medium":{"GB2-01":49.628824329506465,"GB2-02":42.08190140143401,"GB2-05":42.047432497615276,"GB2-06":66.22519369501187,"GB2-07":23.71798789132176,"GB2-08":26.318927373148824},"none":{"GB2-01":17.938142864126988,"GB2-02":37.635934046164486,"GB2-04":42.571734661723085,"GB2-05":30.330723922559024,"GB2-06":13.40926967151986,"GB2-07":8.197238159823167}},"program_outcomes":{"all":{"counted_attempts":17,"failed":5,"infra_excluded":0,"success_rate":0.7058823529411765,"too_slow":0,"worked_after_repair":7,"worked_first_time":5,"working":12},"medium":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":5,"worked_first_time":1,"working":6},"none":{"counted_attempts":9,"failed":3,"infra_excluded":0,"success_rate":0.6666666666666666,"too_slow":0,"worked_after_repair":2,"worked_first_time":4,"working":6}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":31.252533398504777,"none":17.63924648673164},"reasoning_agg":{"medium":{"max":66.22519369501187,"mean":31.252533398504777,"min":0.0},"none":{"max":42.571734661723085,"mean":17.63924648673164,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":13.613286911773137},"working_program_strength":{"all":33.34194254282957,"medium":41.670044531339705,"none":25.01384055431944}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-0-flash:432d200d01d8da23","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":{"all":23.72103513083328,"medium":29.52596115253386,"none":17.916109109132694},"first_seen_at":null,"game_gaps":{"all":{"GB2-05":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"infra_excluded","GB2-05":"infra_excluded","GB2-08":"infra_excluded"},"none":{"GB2-05":"failed","GB2-07":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":25.91403206255726,"score":25.91403206255726},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":38.034715690066434,"score":28.150745092400058},"GB2-03":{"attempts":2,"playable":27.989448166961164,"score":27.989448166961164},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":41.47855694998484,"score":30.504664713325074},"GB2-05":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-06":{"attempts":3,"playable":13.535300760943215,"score":13.535300760943215},"GB2-07":{"attempts":4,"failed_attempts":2,"playable":35.18096295298573,"score":17.590481476492865},"GB2-08":{"attempts":3,"playable":31.578782257332744,"score":31.578782257332744}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":18.280776253732327,"score":18.280776253732327},"GB2-02":{"attempts":1,"playable":36.53354898946738,"score":36.53354898946738},"GB2-04":{"attempts":1,"playable":39.06154495333061,"score":39.06154495333061},"GB2-06":{"attempts":1,"playable":18.572972613153244,"score":18.572972613153244},"GB2-07":{"attempts":2,"playable":35.18096295298573,"score":35.18096295298573}},"none":{"GB2-01":{"attempts":2,"playable":33.547287871382196,"score":33.547287871382196},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":39.535882390665485,"score":19.767941195332742},"GB2-03":{"attempts":2,"playable":27.989448166961164,"score":27.989448166961164},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.895568946639074,"score":21.947784473319537},"GB2-05":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-06":{"attempts":2,"playable":8.497628908733187,"score":8.497628908733187},"GB2-07":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-08":{"attempts":3,"playable":31.578782257332744,"score":31.578782257332744}}},"id":"inclusionai/ling-3.0-flash","is_recent_addition":false,"last_measured_at":"2026-11-03T07:07:05Z","match_totals_all":{"draws":2547,"losses":5105,"wins":1220},"match_totals_tracks":{"medium":{"draws":812,"losses":1822,"wins":496},"none":{"draws":1735,"losses":3283,"wins":724}},"model_slug":"inclusionai-ling-3-0-flash","official_rank_by_reasoning":{"none":86},"overall":{"max":39.06154495333061,"mean":23.72103513083328,"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":332,"losses":971,"wins":277},"GB2-02":{"draws":707,"losses":270,"wins":9},"GB2-03":{"draws":320,"losses":602,"wins":104},"GB2-04":{"draws":707,"losses":259,"wins":58},"GB2-06":{"draws":5,"losses":1376,"wins":163},"GB2-07":{"draws":0,"losses":729,"wins":353},"GB2-08":{"draws":476,"losses":898,"wins":256}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":132,"losses":368,"wins":28},"GB2-02":{"draws":333,"losses":152,"wins":7},"GB2-04":{"draws":345,"losses":146,"wins":21},"GB2-06":{"draws":2,"losses":427,"wins":87},"GB2-07":{"draws":0,"losses":729,"wins":353}},"none":{"GB2-01":{"draws":200,"losses":603,"wins":249},"GB2-02":{"draws":374,"losses":118,"wins":2},"GB2-03":{"draws":320,"losses":602,"wins":104},"GB2-04":{"draws":362,"losses":113,"wins":37},"GB2-06":{"draws":3,"losses":949,"wins":76},"GB2-08":{"draws":476,"losses":898,"wins":256}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1141.3811043915052,"GB2-02":1370.5931603066501,"GB2-04":1391.288839378522,"GB2-06":952.1406515325592,"GB2-07":1250.1384250175167},"none":{"GB2-01":1323.224158104074,"GB2-02":1394.7494994168158,"GB2-03":1238.910455437432,"GB2-04":1429.7595939549005,"GB2-06":619.4921935825275,"GB2-08":1177.8932250535602}},"per_game_tracks":{"medium":{"GB2-01":18.280776253732327,"GB2-02":36.53354898946738,"GB2-04":39.06154495333061,"GB2-06":18.572972613153244,"GB2-07":35.18096295298573},"none":{"GB2-01":33.547287871382196,"GB2-02":39.535882390665485,"GB2-03":27.989448166961164,"GB2-04":43.895568946639074,"GB2-06":8.497628908733187,"GB2-08":31.578782257332744}},"program_outcomes":{"all":{"counted_attempts":23,"failed":6,"infra_excluded":10,"success_rate":0.7391304347826086,"too_slow":0,"worked_after_repair":9,"worked_first_time":8,"working":17},"medium":{"counted_attempts":6,"failed":0,"infra_excluded":10,"success_rate":1.0,"too_slow":0,"worked_after_repair":5,"worked_first_time":1,"working":6},"none":{"counted_attempts":17,"failed":6,"infra_excluded":0,"success_rate":0.6470588235294118,"too_slow":0,"worked_after_repair":4,"worked_first_time":7,"working":11}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#000000","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":29.525961152533863,"none":17.916109109132694},"reasoning_agg":{"medium":{"max":39.06154495333061,"mean":29.525961152533863,"min":18.280776253732327},"none":{"max":33.547287871382196,"mean":17.916109109132694,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":11.609852043401169},"working_program_strength":{"all":30.183363788076417,"medium":29.52596115253386,"none":30.840766423618973}},{"canonical_public_row_identity":"publication-row.v1:overall:recursive-flint-v1-0:d9c69a116ed62ccb","codegen_cost_by_reasoning":{"medium":{"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":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"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":12},"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-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0}},"codegen_cost_usd":{"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":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0},"codegen_latency_ms":{"attempt_count":12,"max_ms":304042,"mean_ms":184222.375,"min_ms":109335,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":12,"max_ms":304042,"mean_ms":184222.375,"min_ms":109335,"run_count":8}},"codegen_output_tokens":{"attempt_count":12,"output_max":45150,"output_mean":24220.375,"output_min":14107,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":12,"output_max":45150,"output_mean":24220.375,"output_min":14107,"run_count":8}},"display_name":"Flint V1.0","economics":{"all":22.526369740347643,"medium":22.526369740347643},"first_seen_at":null,"game_gaps":{"all":{"GB2-03":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"failed"},"none":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":12,"effective_max_output_tokens":[235929],"finish_reason_observations":12,"finish_reasons":["stop"],"indexed_attempts":12,"output_token_observations":12,"provider_post_attempt_observations":12,"provider_post_attempts":12,"reasoning_token_observations":12,"reconciliation_get_attempt_observations":12,"requested_max_output_token_observations":12,"requested_max_output_tokens":[235929],"total_output_tokens":193763,"total_reasoning_output_tokens":181158,"total_visible_output_tokens":12944,"visible_token_observations":12},"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":235929,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"recursive/flint-v1.0","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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":4,"first_pass_rate":0.5,"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":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":42.51922753078504,"score":42.51922753078504},"GB2-02":{"attempts":1,"playable":33.83346796437536,"score":33.83346796437536},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":38.86545763094499,"score":38.86545763094499},"GB2-05":{"attempts":1,"playable":12.911779464694975,"score":12.911779464694975},"GB2-06":{"attempts":1,"playable":15.373199482534622,"score":15.373199482534622},"GB2-07":{"attempts":1,"playable":10.255892841012738,"score":10.255892841012738},"GB2-08":{"attempts":1,"playable":26.451933008433436,"score":26.451933008433436}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":42.51922753078504,"score":42.51922753078504},"GB2-02":{"attempts":1,"playable":33.83346796437536,"score":33.83346796437536},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":38.86545763094499,"score":38.86545763094499},"GB2-05":{"attempts":1,"playable":12.911779464694975,"score":12.911779464694975},"GB2-06":{"attempts":1,"playable":15.373199482534622,"score":15.373199482534622},"GB2-07":{"attempts":1,"playable":10.255892841012738,"score":10.255892841012738},"GB2-08":{"attempts":1,"playable":26.451933008433436,"score":26.451933008433436}}},"id":"recursive/flint-v1.0","is_recent_addition":false,"last_measured_at":"2026-11-03T07:10:18Z","match_totals_all":{"draws":740,"losses":2407,"wins":531},"match_totals_tracks":{"medium":{"draws":740,"losses":2407,"wins":531}},"model_slug":"recursive-flint-v1-0","official_rank_by_reasoning":{"medium":78},"overall":{"max":42.51922753078504,"mean":22.526369740347643,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","unknown_capability_evidence","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":77,"losses":267,"wins":184},"GB2-02":{"draws":324,"losses":172,"wins":0},"GB2-04":{"draws":337,"losses":151,"wins":24},"GB2-05":{"draws":0,"losses":475,"wins":69},"GB2-06":{"draws":2,"losses":443,"wins":71},"GB2-07":{"draws":0,"losses":493,"wins":47},"GB2-08":{"draws":0,"losses":406,"wins":136}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":77,"losses":267,"wins":184},"GB2-02":{"draws":324,"losses":172,"wins":0},"GB2-04":{"draws":337,"losses":151,"wins":24},"GB2-05":{"draws":0,"losses":475,"wins":69},"GB2-06":{"draws":2,"losses":443,"wins":71},"GB2-07":{"draws":0,"losses":493,"wins":47},"GB2-08":{"draws":0,"losses":406,"wins":136}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1414.953054377501,"GB2-02":1348.3068854782011,"GB2-04":1389.7087973780106,"GB2-05":863.5533527486572,"GB2-06":893.2572801400232,"GB2-07":824.4706894618226,"GB2-08":1115.25139098103}},"per_game_tracks":{"medium":{"GB2-01":42.51922753078504,"GB2-02":33.83346796437536,"GB2-04":38.86545763094499,"GB2-05":12.911779464694975,"GB2-06":15.373199482534622,"GB2-07":10.255892841012738,"GB2-08":26.451933008433436}},"program_outcomes":{"all":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":22.526369740347643},"reasoning_agg":{"medium":{"max":42.51922753078504,"mean":22.526369740347643,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"Setting not tested"},"reasoning_settings":{},"working_program_strength":{"all":25.744422560397307,"medium":25.744422560397307}},{"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-5-pro:9145cdfa46fd7b2f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02555855,"mean":0.00555063125,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":4},"recorded_attempt_count":11,"run_count":9,"total":0.04440505},"medium":{"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.020746485000000002,"mean":0.0054863575000000005,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":5},"recorded_attempt_count":12,"run_count":9,"total":0.043890860000000004},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007327775,"mean":0.0040270015625,"median":0.0034028549999999998,"min":0.0009412025,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":15,"run_count":9,"total":0.033157215000000004}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.020746485000000002,"mean":0.0054863575000000005,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":5},"recorded_attempt_count":11,"run_count":8,"total":0.043890860000000004},"historical-provider-setting-balanced-variant-2":{"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-variant-1":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007327775,"mean":0.0041446518750000005,"median":0.0034028549999999998,"min":0.001882405,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.033157215000000004},"historical-provider-setting-baseline-variant-2":{"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-intensive-variant-1":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02555855,"mean":0.00555063125,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":4},"recorded_attempt_count":10,"run_count":8,"total":0.04440505},"historical-provider-setting-intensive-variant-2":{"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}},"codegen_cost_usd":{"admitted_cell_count":5,"cell_count":24,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.02555855,"mean":0.0050213301041666675,"median":0.00152996375,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":23},"recorded_attempt_count":38,"run_count":27,"total":0.12145312500000001},"codegen_latency_ms":{"attempt_count":23,"max_ms":2441104,"mean_ms":798480.3076923077,"min_ms":99802,"run_count":13},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":4,"max_ms":2441104,"mean_ms":2103669.0,"min_ms":1766234,"run_count":2},"medium":{"attempt_count":5,"max_ms":1803928,"mean_ms":1240602.3333333333,"min_ms":254972,"run_count":3},"none":{"attempt_count":14,"max_ms":535646,"mean_ms":306387.375,"min_ms":99802,"run_count":8}},"codegen_output_tokens":{"attempt_count":38,"output_max":170673,"output_mean":49682.0,"output_min":3766,"run_count":27},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":91928,"output_mean":64861.0,"output_min":10319,"run_count":9},"medium":{"attempt_count":12,"output_max":170673,"output_mean":72901.44444444444,"output_min":9244,"run_count":9},"none":{"attempt_count":15,"output_max":20225,"output_mean":11283.555555555555,"output_min":3766,"run_count":9}},"display_name":"Nex N2.5 Pro","economics":{"all":19.167244138742205,"highest":20.28884415409627,"none":18.045644123388143},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"failed","GB2-04":"failed","GB2-05":"failed","GB2-06":"failed"},"highest":{"GB2-01":"infra_excluded","GB2-02":"infra_excluded","GB2-03":"failed","GB2-04":"infra_excluded","GB2-05":"infra_excluded","GB2-06":"infra_excluded","GB2-08":"infra_excluded"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"failed","GB2-04":"failed","GB2-05":"failed","GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":38,"effective_max_output_tokens":[235929],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":38,"output_token_observations":38,"provider_post_attempt_observations":38,"provider_post_attempts":40,"reasoning_token_observations":38,"reconciliation_get_attempt_observations":38,"requested_max_output_token_observations":38,"requested_max_output_tokens":[235929],"total_output_tokens":1341414,"total_reasoning_output_tokens":1137994,"total_visible_output_tokens":203420,"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":"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":235929,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nex-agi","provider_model":"nex-agi/nex-n2.5-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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-04","GB2-05","GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"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":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":1,"evaluated_cells":2,"failed_game_aliases":["GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"infra_failures_excluded":1},"GB2-02":{"infra_failures_excluded":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"infra_failures_excluded":1},"GB2-05":{"infra_failures_excluded":1},"GB2-06":{"infra_failures_excluded":1},"GB2-07":{"admitted":1},"GB2-08":{"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-04","GB2-05","GB2-06","GB2-08"],"infra_failures_excluded":6,"model_code_failure_rate":0.5,"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}}},"headline_games_all":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":36.746310805283656,"score":36.746310805283656},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":44.785271079374695,"score":22.392635539687348},"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":2,"playable":37.3353578251582,"score":37.3353578251582},"GB2-08":{"attempts":1,"playable":28.74054376032295,"score":28.74054376032295}},"headline_games_tracks":{"highest":{"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":40.57768830819254,"score":40.57768830819254}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":36.746310805283656,"score":36.746310805283656},"GB2-03":{"attempts":1,"playable":44.785271079374695,"score":44.785271079374695},"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,"playable":34.09302734212386,"score":34.09302734212386},"GB2-08":{"attempts":1,"playable":28.74054376032295,"score":28.74054376032295}}},"id":"nex-agi/nex-n2.5-pro","is_recent_addition":false,"last_measured_at":"2026-11-03T07:13:06Z","match_totals_all":{"draws":514,"losses":1462,"wins":662},"match_totals_tracks":{"highest":{"draws":0,"losses":335,"wins":207},"none":{"draws":514,"losses":1127,"wins":455}},"model_slug":"nex-agi-nex-n2-5-pro","overall":{"max":44.785271079374695,"mean":19.167244138742205,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality","below_generation_quality_threshold","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-07":40.57768830819254},"per_game_match_totals_all":{"GB2-02":{"draws":352,"losses":146,"wins":2},"GB2-03":{"draws":162,"losses":218,"wins":136},"GB2-07":{"draws":0,"losses":704,"wins":376},"GB2-08":{"draws":0,"losses":394,"wins":148}},"per_game_match_totals_tracks":{"highest":{"GB2-07":{"draws":0,"losses":335,"wins":207}},"none":{"GB2-02":{"draws":352,"losses":146,"wins":2},"GB2-03":{"draws":162,"losses":218,"wins":136},"GB2-07":{"draws":0,"losses":369,"wins":169},"GB2-08":{"draws":0,"losses":394,"wins":148}}},"per_game_raw_elo_tracks":{"highest":{"GB2-07":1321.4147191344084},"none":{"GB2-02":1372.3241038106378,"GB2-03":1394.4199415427292,"GB2-07":1235.8323159818003,"GB2-08":1143.5264793816054}},"per_game_tracks":{"highest":{"GB2-07":40.57768830819254},"none":{"GB2-02":36.746310805283656,"GB2-03":44.785271079374695,"GB2-07":34.09302734212386,"GB2-08":28.74054376032295}},"program_outcomes":{"all":{"counted_attempts":10,"failed":5,"infra_excluded":6,"success_rate":0.5,"too_slow":0,"worked_after_repair":0,"worked_first_time":5,"working":5},"highest":{"counted_attempts":2,"failed":1,"infra_excluded":6,"success_rate":0.5,"too_slow":0,"worked_after_repair":0,"worked_first_time":1,"working":1},"none":{"counted_attempts":8,"failed":4,"infra_excluded":0,"success_rate":0.5,"too_slow":0,"worked_after_repair":0,"worked_first_time":4,"working":4}},"provider_color":"#111827","provider_company":"Nex AGI","provider_key":"nex-agi","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":20.28884415409627,"none":18.045644123388143},"reasoning_agg":{"highest":{"max":40.57768830819254,"mean":20.28884415409627,"min":0.0},"none":{"max":44.785271079374695,"mean":18.045644123388143,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":2.2432000307081275},"working_program_strength":{"all":38.33448827748441,"highest":40.57768830819254,"none":36.09128824677629}},{"canonical_public_row_identity":"publication-row.v1:overall:cohere-north-mini-code:1234cb5692bc501c","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":{"all":14.368340137605314,"medium":22.427700587591346,"none":6.308979687619281},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"failed","GB2-02":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"failed","GB2-02":"failed"},"none":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-04":"failed","GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":20.692353410175134,"score":10.346176705087567},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":40.56250224655172,"score":20.28125112327586},"GB2-05":{"attempts":2,"playable":30.924802903833356,"score":30.924802903833356},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":15.278855885838052,"score":7.639427942919026},"GB2-07":{"attempts":2,"playable":15.800728505511069,"score":15.800728505511069},"GB2-08":{"attempts":2,"playable":29.954333920215632,"score":29.954333920215632}},"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":20.692353410175134,"score":20.692353410175134},"GB2-04":{"attempts":1,"playable":40.56250224655172,"score":40.56250224655172},"GB2-05":{"attempts":1,"playable":43.34084044724628,"score":43.34084044724628},"GB2-06":{"attempts":1,"playable":15.278855885838052,"score":15.278855885838052},"GB2-07":{"attempts":1,"playable":29.617017442031806,"score":29.617017442031806},"GB2-08":{"attempts":1,"playable":29.930035268887778,"score":29.930035268887778}},"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":18.508765360420433,"score":18.508765360420433},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":1.9844395689903316,"score":1.9844395689903316},"GB2-08":{"attempts":1,"playable":29.978632571543486,"score":29.978632571543486}}},"id":"cohere/north-mini-code","is_recent_addition":false,"last_measured_at":"2026-08-05T05:19:01Z","match_totals_all":{"draws":750,"losses":3249,"wins":797},"match_totals_tracks":{"medium":{"draws":475,"losses":2026,"wins":673},"none":{"draws":275,"losses":1223,"wins":124}},"model_slug":"cohere-north-mini-code","official_rank_by_reasoning":{"medium":79},"overall":{"max":43.34084044724628,"mean":14.368340137605314,"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":114,"losses":362,"wins":40},"GB2-04":{"draws":312,"losses":156,"wins":46},"GB2-05":{"draws":0,"losses":748,"wins":336},"GB2-06":{"draws":2,"losses":441,"wins":71},"GB2-07":{"draws":0,"losses":930,"wins":154},"GB2-08":{"draws":322,"losses":612,"wins":150}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":114,"losses":362,"wins":40},"GB2-04":{"draws":312,"losses":156,"wins":46},"GB2-05":{"draws":0,"losses":308,"wins":236},"GB2-06":{"draws":2,"losses":441,"wins":71},"GB2-07":{"draws":0,"losses":395,"wins":147},"GB2-08":{"draws":47,"losses":364,"wins":133}},"none":{"GB2-05":{"draws":0,"losses":440,"wins":100},"GB2-07":{"draws":0,"losses":535,"wins":7},"GB2-08":{"draws":275,"losses":248,"wins":17}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1161.356936387442,"GB2-04":1403.3224305200897,"GB2-05":1365.8794991724112,"GB2-06":891.4413180751501,"GB2-07":1174.3310008654535,"GB2-08":1158.0326817112025},"none":{"GB2-05":983.1545203947578,"GB2-07":444.41792448869364,"GB2-08":1158.623303571901}},"per_game_tracks":{"medium":{"GB2-03":20.692353410175134,"GB2-04":40.56250224655172,"GB2-05":43.34084044724628,"GB2-06":15.278855885838052,"GB2-07":29.617017442031806,"GB2-08":29.930035268887778},"none":{"GB2-05":18.508765360420433,"GB2-07":1.9844395689903316,"GB2-08":29.978632571543486}},"program_outcomes":{"all":{"counted_attempts":16,"failed":7,"infra_excluded":0,"success_rate":0.5625,"too_slow":0,"worked_after_repair":4,"worked_first_time":5,"working":9},"medium":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":3,"worked_first_time":3,"working":6},"none":{"counted_attempts":8,"failed":5,"infra_excluded":0,"success_rate":0.375,"too_slow":0,"worked_after_repair":1,"worked_first_time":2,"working":3}},"provider_color":"#FF7759","provider_company":"Cohere","provider_key":"cohere","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":22.427700587591346,"none":6.308979687619281},"reasoning_agg":{"medium":{"max":43.34084044724628,"mean":22.427700587591346,"min":0.0},"none":{"max":29.978632571543486,"mean":6.308979687619281,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":16.118720899972065},"working_program_strength":{"all":23.363773308553274,"medium":29.90360078345513,"none":16.82394583365142}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1-nano:e3821806f8f4f3d0","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":{"all":11.25225953344901,"none":11.25225953344901},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"failed","GB2-04":"failed","GB2-05":"failed","GB2-07":"failed","GB2-08":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"failed","GB2-04":"failed","GB2-05":"failed","GB2-07":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":40.353335801136616,"score":40.353335801136616},"GB2-03":{"attempts":1,"playable":34.06304853957962,"score":34.06304853957962},"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":15.60169192687585,"score":15.60169192687585},"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":40.353335801136616,"score":40.353335801136616},"GB2-03":{"attempts":1,"playable":34.06304853957962,"score":34.06304853957962},"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":15.60169192687585,"score":15.60169192687585},"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":"2026-11-03T07:15:32Z","match_totals_all":{"draws":691,"losses":751,"wins":84},"match_totals_tracks":{"none":{"draws":691,"losses":751,"wins":84}},"model_slug":"gpt-4-1-nano","overall":{"max":40.353335801136616,"mean":11.25225953344901,"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":382,"losses":111,"wins":3},"GB2-03":{"draws":307,"losses":200,"wins":9},"GB2-06":{"draws":2,"losses":440,"wins":72}},"per_game_match_totals_tracks":{"none":{"GB2-02":{"draws":382,"losses":111,"wins":3},"GB2-03":{"draws":307,"losses":200,"wins":9},"GB2-06":{"draws":2,"losses":440,"wins":72}}},"per_game_raw_elo_tracks":{"none":{"GB2-02":1401.2414977499543,"GB2-03":1298.4001887505624,"GB2-06":897.6332348441964}},"per_game_tracks":{"none":{"GB2-02":40.353335801136616,"GB2-03":34.06304853957962,"GB2-06":15.60169192687585}},"program_outcomes":{"all":{"counted_attempts":8,"failed":5,"infra_excluded":0,"success_rate":0.375,"too_slow":0,"worked_after_repair":0,"worked_first_time":3,"working":3},"none":{"counted_attempts":8,"failed":5,"infra_excluded":0,"success_rate":0.375,"too_slow":0,"worked_after_repair":0,"worked_first_time":3,"working":3}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":11.252259533449012},"reasoning_agg":{"none":{"max":40.353335801136616,"mean":11.252259533449012,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning field omitted"},"reasoning_settings":{"baseline":"none"},"working_program_strength":{"all":30.006025422530694,"none":30.006025422530694}}],"public_release_id":"gb2-20261103-09b2218cbd85","rating_method":{"bootstrap_iterations":0,"first_player_advantage":true,"method":"bradley_terry_newton","reference_field":{"manifest_sha256":"deff14cfd9a37b714d23fcf8bc0b4174fa1a1485d4572b44e05c910f050acfb9","population_revision":"cd13f51dae0f40d277054b3e1dc13c563075320817f9a81be9bf5295a13d93f8","rule":"model_balanced_common_field_v1","source":"frozen_manifest","version":"v2"}},"results_cut_id":"gb2-20261103-09b2218cbd85","schema_version":2,"snapshot_id":"20261103_094507","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-11-03 09:45 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":17,"losses":98,"wins":17},"claude-fable-5-1":{"draws":7,"losses":133,"wins":8},"claude-haiku-5-5":{"draws":28,"losses":73,"wins":25},"claude-opus-4-5":{"draws":67,"losses":93,"wins":54},"claude-opus-4-8":{"draws":29,"losses":70,"wins":21},"claude-opus-5":{"draws":29,"losses":174,"wins":23},"claude-opus-5-5":{"draws":6,"losses":131,"wins":7},"claude-sonnet-5":{"draws":36,"losses":71,"wins":25},"claude-sonnet-5-5":{"draws":28,"losses":80,"wins":24},"cohere/north-mini-code":{"draws":13,"losses":14,"wins":23},"deepseek/deepseek-v4-flash":{"draws":55,"losses":68,"wins":73},"deepseek/deepseek-v4-pro":{"draws":30,"losses":61,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":53,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":67,"wins":34},"deepseek/deepseek-v4.1-flash-1017":{"draws":23,"losses":89,"wins":20},"elorian/glimpse":{"draws":16,"losses":34,"wins":22},"fireworks/ember-1":{"draws":35,"losses":70,"wins":27},"gemini-3.1-pro-preview":{"draws":32,"losses":62,"wins":38},"gemini-4-argon":{"draws":3,"losses":123,"wins":6},"google/gemini-3.1-flash-lite":{"draws":22,"losses":19,"wins":47},"google/gemini-3.5-flash":{"draws":35,"losses":85,"wins":46},"google/gemini-3.5-flash-lite":{"draws":71,"losses":76,"wins":87},"google/gemini-3.6-flash":{"draws":53,"losses":142,"wins":59},"google/gemini-3.8-flash":{"draws":25,"losses":84,"wins":23},"google/gemma-4-31b-it":{"draws":27,"losses":24,"wins":25},"gpt-4.1":{"draws":14,"losses":19,"wins":11},"gpt-4.1-nano":{"draws":8,"losses":4,"wins":4},"gpt-5":{"draws":32,"losses":43,"wins":41},"gpt-5.4":{"draws":29,"losses":70,"wins":29},"gpt-5.4-mini":{"draws":29,"losses":26,"wins":33},"gpt-5.4-nano":{"draws":26,"losses":48,"wins":58},"gpt-5.5":{"draws":41,"losses":57,"wins":24},"gpt-5.6-luna":{"draws":39,"losses":46,"wins":47},"gpt-5.6-sol":{"draws":22,"losses":97,"wins":13},"gpt-5.6-terra":{"draws":31,"losses":69,"wins":26},"gpt-6-astra":{"draws":6,"losses":120,"wins":6},"gpt-6-luna":{"draws":40,"losses":53,"wins":39},"gpt-6-sol":{"draws":15,"losses":102,"wins":15},"gpt-6.1-sol":{"draws":10,"losses":113,"wins":9},"gpt-6.1-terra":{"draws":18,"losses":104,"wins":10},"gpt-6.1-terra-pro":{"draws":15,"losses":108,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":33,"losses":24,"wins":35},"inception/mercury-3":{"draws":25,"losses":36,"wins":27},"inclusionai/ling-3.0-flash":{"draws":36,"losses":16,"wins":42},"inclusionai/ling-3.1-flash":{"draws":15,"losses":7,"wins":4},"meituan/longcat-2.0":{"draws":34,"losses":45,"wins":65},"meta/muse-glimmer-30b":{"draws":35,"losses":37,"wins":44},"meta/muse-spark-1.2":{"draws":32,"losses":63,"wins":31},"meta/muse-spark-1.3":{"draws":27,"losses":82,"wins":23},"meta/muse-spark-open":{"draws":29,"losses":76,"wins":27},"meta/muse-wonder":{"draws":30,"losses":86,"wins":16},"minimax/minimax-m3":{"draws":16,"losses":14,"wins":40},"minimax/minimax-m3.1-flash":{"draws":26,"losses":47,"wins":43},"mistralai/mistral-large-4-0":{"draws":25,"losses":33,"wins":24},"mistralai/mistral-medium-3-5":{"draws":30,"losses":19,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":3},"moonshotai/kimi-k3":{"draws":34,"losses":60,"wins":32},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":105,"wins":8},"nex-agi/nex-n2-pro":{"draws":14,"losses":16,"wins":36},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":9,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":37,"wins":37},"nvidia/nemotron-3.5-super-vl":{"draws":22,"losses":22,"wins":16},"o3":{"draws":38,"losses":90,"wins":56},"openai/gpt-oss-120b":{"draws":32,"losses":35,"wins":47},"poolside/laguna-s-2.1":{"draws":41,"losses":40,"wins":47},"qwen/qwen3.7-max":{"draws":21,"losses":29,"wins":26},"qwen/qwen3.7-plus":{"draws":18,"losses":21,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":63,"wins":30},"qwen/qwen3.8-27b":{"draws":22,"losses":48,"wins":24},"qwen/qwen3.8-flash":{"draws":26,"losses":40,"wins":22},"qwen/qwen3.8-max":{"draws":41,"losses":53,"wins":38},"qwen/qwen3.8-max-0902":{"draws":31,"losses":77,"wins":24},"recursive/flint-v1.0":{"draws":8,"losses":9,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":32,"losses":57,"wins":31},"stealth/ox-alpha":{"draws":92,"losses":259,"wins":89},"stealth/space-bunny-alpha":{"draws":34,"losses":40,"wins":30},"stepfun/step-3.7-flash":{"draws":23,"losses":33,"wins":38},"stepfun/step-5-preview":{"draws":6,"losses":17,"wins":9},"tencent/hy3-preview":{"draws":20,"losses":25,"wins":27},"tencent/hy4-preview":{"draws":35,"losses":75,"wins":18},"thinkingmachines/inkling":{"draws":57,"losses":48,"wins":73},"thinkingmachines/inkling-small":{"draws":42,"losses":30,"wins":60},"unbiased/pareto-26.10":{"draws":2,"losses":42,"wins":0},"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":85,"wins":17},"x-ai/grok-4.6":{"draws":30,"losses":85,"wins":17},"x-ai/grok-4.7":{"draws":6,"losses":93,"wins":15},"x-ai/grok-build-0.1":{"draws":12,"losses":11,"wins":21},"xiaomi/mimo-v2.5":{"draws":64,"losses":57,"wins":83},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":17,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":51,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":57,"wins":18},"z-ai/glm-5.2":{"draws":88,"losses":99,"wins":77},"z-ai/glm-5.3":{"draws":22,"losses":88,"wins":16},"z-ai/glm-5.3-flash":{"draws":28,"losses":74,"wins":30},"z-ai/glm-5.3-flashx":{"draws":20,"losses":86,"wins":26}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":17,"wins":98},"claude-fable-5":{"draws":14,"losses":41,"wins":41},"claude-fable-5-1":{"draws":10,"losses":133,"wins":19},"claude-haiku-5-5":{"draws":26,"losses":38,"wins":74},"claude-opus-4-5":{"draws":36,"losses":40,"wins":158},"claude-opus-4-8":{"draws":22,"losses":37,"wins":73},"claude-opus-5":{"draws":33,"losses":141,"wins":72},"claude-opus-5-5":{"draws":12,"losses":123,"wins":21},"claude-sonnet-5":{"draws":23,"losses":27,"wins":94},"claude-sonnet-5-5":{"draws":25,"losses":59,"wins":60},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":44},"deepseek/deepseek-v4-flash":{"draws":35,"losses":14,"wins":167},"deepseek/deepseek-v4-pro":{"draws":24,"losses":27,"wins":81},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":26,"wins":88},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":37,"wins":74},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":53,"wins":65},"elorian/glimpse":{"draws":11,"losses":28,"wins":39},"fireworks/ember-1":{"draws":30,"losses":22,"wins":92},"gemini-3.1-pro-preview":{"draws":29,"losses":29,"wins":86},"gemini-4-argon":{"draws":13,"losses":101,"wins":30},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":83},"google/gemini-3.5-flash":{"draws":28,"losses":33,"wins":119},"google/gemini-3.5-flash-lite":{"draws":38,"losses":28,"wins":186},"google/gemini-3.6-flash":{"draws":41,"losses":79,"wins":156},"google/gemini-3.8-flash":{"draws":19,"losses":56,"wins":69},"google/gemma-4-31b-it":{"draws":21,"losses":7,"wins":56},"gpt-4.1":{"draws":8,"losses":12,"wins":28},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":20,"losses":21,"wins":85},"gpt-5.4":{"draws":31,"losses":40,"wins":67},"gpt-5.4-mini":{"draws":19,"losses":11,"wins":66},"gpt-5.4-nano":{"draws":16,"losses":14,"wins":114},"gpt-5.5":{"draws":30,"losses":39,"wins":63},"gpt-5.6-luna":{"draws":27,"losses":18,"wins":99},"gpt-5.6-sol":{"draws":16,"losses":65,"wins":63},"gpt-5.6-terra":{"draws":31,"losses":20,"wins":87},"gpt-6-astra":{"draws":11,"losses":112,"wins":21},"gpt-6-luna":{"draws":28,"losses":28,"wins":88},"gpt-6-sol":{"draws":18,"losses":83,"wins":43},"gpt-6.1-sol":{"draws":9,"losses":101,"wins":34},"gpt-6.1-terra":{"draws":18,"losses":89,"wins":37},"gpt-6.1-terra-pro":{"draws":11,"losses":102,"wins":31},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":26,"losses":5,"wins":71},"inception/mercury-3":{"draws":24,"losses":13,"wins":61},"inclusionai/ling-3.0-flash":{"draws":18,"losses":4,"wins":80},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":12},"meituan/longcat-2.0":{"draws":14,"losses":20,"wins":122},"meta/muse-glimmer-30b":{"draws":22,"losses":7,"wins":97},"meta/muse-spark-1.2":{"draws":17,"losses":31,"wins":90},"meta/muse-spark-1.3":{"draws":22,"losses":42,"wins":80},"meta/muse-spark-open":{"draws":23,"losses":32,"wins":89},"meta/muse-wonder":{"draws":27,"losses":57,"wins":60},"minimax/minimax-m3":{"draws":18,"losses":6,"wins":54},"minimax/minimax-m3.1-flash":{"draws":23,"losses":20,"wins":83},"mistralai/mistral-large-4-0":{"draws":20,"losses":20,"wins":50},"mistralai/mistral-medium-3-5":{"draws":17,"losses":6,"wins":61},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":24,"losses":28,"wins":86},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":98,"wins":35},"nex-agi/nex-n2-pro":{"draws":12,"losses":2,"wins":58},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":6,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":11,"wins":75},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":4,"wins":49},"o3":{"draws":17,"losses":30,"wins":151},"openai/gpt-oss-120b":{"draws":26,"losses":11,"wins":89},"poolside/laguna-s-2.1":{"draws":20,"losses":20,"wins":98},"qwen/qwen3.7-max":{"draws":11,"losses":13,"wins":60},"qwen/qwen3.7-plus":{"draws":10,"losses":8,"wins":54},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":36,"wins":76},"qwen/qwen3.8-27b":{"draws":21,"losses":16,"wins":65},"qwen/qwen3.8-flash":{"draws":18,"losses":22,"wins":56},"qwen/qwen3.8-max":{"draws":24,"losses":36,"wins":84},"qwen/qwen3.8-max-0902":{"draws":28,"losses":34,"wins":82},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":39},"reflection/beam-1.0-501b-a23b":{"draws":25,"losses":26,"wins":81},"stealth/ox-alpha":{"draws":75,"losses":122,"wins":277},"stealth/space-bunny-alpha":{"draws":28,"losses":15,"wins":71},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":84},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":20},"tencent/hy3-preview":{"draws":21,"losses":12,"wins":45},"tencent/hy4-preview":{"draws":18,"losses":30,"wins":90},"thinkingmachines/inkling":{"draws":37,"losses":12,"wins":143},"thinkingmachines/inkling-small":{"draws":23,"losses":14,"wins":107},"unbiased/pareto-26.10":{"draws":1,"losses":43,"wins":4},"unbiased/pareto-26.10-preview":{"draws":5,"losses":32,"wins":11},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":29},"x-ai/grok-4.5":{"draws":24,"losses":47,"wins":73},"x-ai/grok-4.6":{"draws":31,"losses":49,"wins":64},"x-ai/grok-4.7":{"draws":7,"losses":78,"wins":41},"x-ai/grok-build-0.1":{"draws":8,"losses":6,"wins":34},"xiaomi/mimo-v2.5":{"draws":38,"losses":7,"wins":177},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":8,"wins":61},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":21,"wins":53},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":40,"wins":48},"z-ai/glm-5.2":{"draws":58,"losses":43,"wins":187},"z-ai/glm-5.3":{"draws":21,"losses":63,"wins":54},"z-ai/glm-5.3-flash":{"draws":22,"losses":46,"wins":76},"z-ai/glm-5.3-flashx":{"draws":22,"losses":43,"wins":79}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":8,"wins":133},"claude-fable-5":{"draws":10,"losses":19,"wins":133},"claude-fable-5-1":{"draws":8,"losses":62,"wins":62},"claude-haiku-5-5":{"draws":8,"losses":11,"wins":135},"claude-opus-4-5":{"draws":10,"losses":11,"wins":241},"claude-opus-4-8":{"draws":8,"losses":13,"wins":125},"claude-opus-5":{"draws":23,"losses":76,"wins":179},"claude-opus-5-5":{"draws":14,"losses":88,"wins":72},"claude-sonnet-5":{"draws":6,"losses":6,"wins":150},"claude-sonnet-5-5":{"draws":8,"losses":37,"wins":117},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":60},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":232},"deepseek/deepseek-v4-pro":{"draws":9,"losses":5,"wins":136},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":3,"wins":144},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":13,"wins":136},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":20,"wins":133},"elorian/glimpse":{"draws":7,"losses":9,"wins":74},"fireworks/ember-1":{"draws":5,"losses":10,"wins":147},"gemini-3.1-pro-preview":{"draws":8,"losses":6,"wins":148},"gemini-4-argon":{"draws":14,"losses":53,"wins":95},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":99},"google/gemini-3.5-flash":{"draws":11,"losses":7,"wins":184},"google/gemini-3.5-flash-lite":{"draws":16,"losses":3,"wins":265},"google/gemini-3.6-flash":{"draws":16,"losses":19,"wins":277},"google/gemini-3.8-flash":{"draws":11,"losses":13,"wins":138},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":88},"gpt-4.1":{"draws":5,"losses":2,"wins":47},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":20},"gpt-5":{"draws":3,"losses":0,"wins":139},"gpt-5.4":{"draws":9,"losses":15,"wins":132},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":102},"gpt-5.4-nano":{"draws":2,"losses":1,"wins":151},"gpt-5.5":{"draws":6,"losses":16,"wins":128},"gpt-5.6-luna":{"draws":10,"losses":6,"wins":146},"gpt-5.6-sol":{"draws":13,"losses":19,"wins":130},"gpt-5.6-terra":{"draws":7,"losses":6,"wins":143},"gpt-6-astra":{"draws":15,"losses":82,"wins":65},"gpt-6-luna":{"draws":12,"losses":6,"wins":144},"gpt-6-sol":{"draws":12,"losses":42,"wins":108},"gpt-6.1-sol":{"draws":10,"losses":80,"wins":72},"gpt-6.1-terra":{"draws":17,"losses":58,"wins":87},"gpt-6.1-terra-pro":{"draws":22,"losses":64,"wins":76},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":106},"inception/mercury-3":{"draws":4,"losses":1,"wins":101},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":106},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":22},"meituan/longcat-2.0":{"draws":4,"losses":7,"wins":165},"meta/muse-glimmer-30b":{"draws":8,"losses":0,"wins":136},"meta/muse-spark-1.2":{"draws":8,"losses":9,"wins":139},"meta/muse-spark-1.3":{"draws":9,"losses":16,"wins":137},"meta/muse-spark-open":{"draws":6,"losses":15,"wins":141},"meta/muse-wonder":{"draws":12,"losses":32,"wins":118},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":83},"minimax/minimax-m3.1-flash":{"draws":8,"losses":5,"wins":131},"mistralai/mistral-large-4-0":{"draws":6,"losses":8,"wins":88},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":87},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":7,"losses":11,"wins":138},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":43,"wins":104},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":77},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":35},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":2,"wins":103},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":1,"wins":71},"o3":{"draws":3,"losses":10,"wins":205},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":137},"poolside/laguna-s-2.1":{"draws":5,"losses":3,"wins":144},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":89},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":74},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":7,"wins":147},"qwen/qwen3.8-27b":{"draws":8,"losses":1,"wins":105},"qwen/qwen3.8-flash":{"draws":7,"losses":5,"wins":96},"qwen/qwen3.8-max":{"draws":8,"losses":5,"wins":149},"qwen/qwen3.8-max-0902":{"draws":10,"losses":17,"wins":135},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":44},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":2,"wins":141},"stealth/ox-alpha":{"draws":26,"losses":26,"wins":498},"stealth/space-bunny-alpha":{"draws":3,"losses":2,"wins":125},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":111},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":38},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":76},"tencent/hy4-preview":{"draws":10,"losses":13,"wins":133},"thinkingmachines/inkling":{"draws":8,"losses":1,"wins":209},"thinkingmachines/inkling-small":{"draws":13,"losses":0,"wins":149},"unbiased/pareto-26.10":{"draws":7,"losses":26,"wins":21},"unbiased/pareto-26.10-preview":{"draws":0,"losses":30,"wins":24},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":38},"x-ai/grok-4.5":{"draws":12,"losses":11,"wins":139},"x-ai/grok-4.6":{"draws":9,"losses":25,"wins":128},"x-ai/grok-4.7":{"draws":7,"losses":33,"wins":100},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":51},"xiaomi/mimo-v2.5":{"draws":12,"losses":6,"wins":226},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":80},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":8,"wins":87},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":11,"wins":84},"z-ai/glm-5.2":{"draws":16,"losses":5,"wins":303},"z-ai/glm-5.3":{"draws":13,"losses":21,"wins":122},"z-ai/glm-5.3-flash":{"draws":9,"losses":12,"wins":141},"z-ai/glm-5.3-flashx":{"draws":10,"losses":14,"wins":138}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":25,"wins":73},"claude-fable-5":{"draws":26,"losses":74,"wins":38},"claude-fable-5-1":{"draws":8,"losses":135,"wins":11},"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":27,"losses":57,"wins":46},"claude-opus-5":{"draws":41,"losses":156,"wins":37},"claude-opus-5-5":{"draws":16,"losses":125,"wins":9},"claude-sonnet-5":{"draws":35,"losses":40,"wins":63},"claude-sonnet-5-5":{"draws":24,"losses":71,"wins":43},"cohere/north-mini-code":{"draws":10,"losses":9,"wins":33},"deepseek/deepseek-v4-flash":{"draws":58,"losses":29,"wins":121},"deepseek/deepseek-v4-pro":{"draws":34,"losses":41,"wins":51},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":29,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":40,"wins":57},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":61,"wins":52},"elorian/glimpse":{"draws":11,"losses":29,"wins":34},"fireworks/ember-1":{"draws":37,"losses":38,"wins":63},"gemini-3.1-pro-preview":{"draws":34,"losses":46,"wins":58},"gemini-4-argon":{"draws":14,"losses":98,"wins":26},"google/gemini-3.1-flash-lite":{"draws":20,"losses":8,"wins":68},"google/gemini-3.5-flash":{"draws":36,"losses":59,"wins":79},"google/gemini-3.5-flash-lite":{"draws":51,"losses":40,"wins":151},"google/gemini-3.6-flash":{"draws":62,"losses":100,"wins":102},"google/gemini-3.8-flash":{"draws":34,"losses":61,"wins":43},"google/gemma-4-31b-it":{"draws":22,"losses":9,"wins":51},"gpt-4.1":{"draws":14,"losses":8,"wins":24},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":9},"gpt-5":{"draws":31,"losses":26,"wins":63},"gpt-5.4":{"draws":31,"losses":52,"wins":49},"gpt-5.4-mini":{"draws":27,"losses":12,"wins":53},"gpt-5.4-nano":{"draws":29,"losses":39,"wins":74},"gpt-5.5":{"draws":46,"losses":35,"wins":45},"gpt-5.6-luna":{"draws":40,"losses":24,"wins":74},"gpt-5.6-sol":{"draws":20,"losses":77,"wins":41},"gpt-5.6-terra":{"draws":39,"losses":37,"wins":56},"gpt-6-astra":{"draws":7,"losses":123,"wins":8},"gpt-6-luna":{"draws":35,"losses":39,"wins":64},"gpt-6-sol":{"draws":25,"losses":85,"wins":28},"gpt-6.1-sol":{"draws":13,"losses":114,"wins":11},"gpt-6.1-terra":{"draws":18,"losses":101,"wins":19},"gpt-6.1-terra-pro":{"draws":15,"losses":111,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":4,"wins":66},"inception/mercury-3":{"draws":23,"losses":29,"wins":40},"inclusionai/ling-3.0-flash":{"draws":29,"losses":5,"wins":64},"inclusionai/ling-3.1-flash":{"draws":3,"losses":5,"wins":4},"meituan/longcat-2.0":{"draws":32,"losses":21,"wins":97},"meta/muse-glimmer-30b":{"draws":36,"losses":15,"wins":69},"meta/muse-spark-1.2":{"draws":28,"losses":40,"wins":64},"meta/muse-spark-1.3":{"draws":27,"losses":51,"wins":60},"meta/muse-spark-open":{"draws":23,"losses":55,"wins":60},"meta/muse-wonder":{"draws":30,"losses":79,"wins":29},"minimax/minimax-m3":{"draws":8,"losses":15,"wins":53},"minimax/minimax-m3.1-flash":{"draws":24,"losses":28,"wins":68},"mistralai/mistral-large-4-0":{"draws":29,"losses":28,"wins":29},"mistralai/mistral-medium-3-5":{"draws":21,"losses":4,"wins":55},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":9},"moonshotai/kimi-k3":{"draws":34,"losses":39,"wins":59},"moonshotai/kimi-k3.1-pro":{"draws":16,"losses":99,"wins":23},"nex-agi/nex-n2-pro":{"draws":14,"losses":10,"wins":44},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":6,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":20,"wins":53},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":20,"wins":33},"o3":{"draws":32,"losses":61,"wins":101},"openai/gpt-oss-120b":{"draws":29,"losses":12,"wins":79},"poolside/laguna-s-2.1":{"draws":33,"losses":36,"wins":61},"qwen/qwen3.7-max":{"draws":28,"losses":20,"wins":34},"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":30,"wins":46},"qwen/qwen3.8-flash":{"draws":27,"losses":18,"wins":47},"qwen/qwen3.8-max":{"draws":34,"losses":37,"wins":67},"qwen/qwen3.8-max-0902":{"draws":40,"losses":47,"wins":51},"recursive/flint-v1.0":{"draws":9,"losses":8,"wins":25},"reflection/beam-1.0-501b-a23b":{"draws":25,"losses":35,"wins":66},"stealth/ox-alpha":{"draws":94,"losses":165,"wins":175},"stealth/space-bunny-alpha":{"draws":30,"losses":23,"wins":57},"stepfun/step-3.7-flash":{"draws":15,"losses":16,"wins":67},"stepfun/step-5-preview":{"draws":7,"losses":15,"wins":12},"tencent/hy3-preview":{"draws":25,"losses":20,"wins":31},"tencent/hy4-preview":{"draws":30,"losses":54,"wins":48},"thinkingmachines/inkling":{"draws":50,"losses":23,"wins":109},"thinkingmachines/inkling-small":{"draws":33,"losses":13,"wins":92},"unbiased/pareto-26.10":{"draws":4,"losses":38,"wins":4},"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":59,"wins":49},"x-ai/grok-4.6":{"draws":36,"losses":60,"wins":42},"x-ai/grok-4.7":{"draws":12,"losses":92,"wins":18},"x-ai/grok-build-0.1":{"draws":12,"losses":4,"wins":30},"xiaomi/mimo-v2.5":{"draws":57,"losses":31,"wins":132},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":10,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":27,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":43,"wins":32},"z-ai/glm-5.2":{"draws":64,"losses":65,"wins":147},"z-ai/glm-5.3":{"draws":23,"losses":76,"wins":33},"z-ai/glm-5.3-flash":{"draws":27,"losses":56,"wins":55},"z-ai/glm-5.3-flashx":{"draws":29,"losses":52,"wins":57}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":34,"wins":63},"claude-fable-5":{"draws":23,"losses":92,"wins":29},"claude-fable-5-1":{"draws":9,"losses":145,"wins":8},"claude-haiku-5-5":{"draws":40,"losses":55,"wins":43},"claude-opus-4-5":{"draws":61,"losses":53,"wins":72},"claude-opus-4-8":{"draws":35,"losses":57,"wins":40},"claude-opus-5":{"draws":37,"losses":185,"wins":24},"claude-opus-5-5":{"draws":12,"losses":135,"wins":9},"claude-sonnet-5":{"draws":49,"losses":44,"wins":51},"claude-sonnet-5-5":{"draws":29,"losses":72,"wins":43},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":43},"deepseek/deepseek-v4-flash":{"draws":54,"losses":44,"wins":118},"deepseek/deepseek-v4-pro":{"draws":34,"losses":47,"wins":51},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":49,"wins":50},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":61,"wins":45},"deepseek/deepseek-v4.1-flash-1017":{"draws":27,"losses":84,"wins":33},"elorian/glimpse":{"draws":19,"losses":35,"wins":24},"fireworks/ember-1":{"draws":48,"losses":56,"wins":40},"gemini-3.1-pro-preview":{"draws":33,"losses":45,"wins":66},"gemini-4-argon":{"draws":6,"losses":129,"wins":9},"google/gemini-3.1-flash-lite":{"draws":20,"losses":2,"wins":74},"google/gemini-3.5-flash":{"draws":39,"losses":74,"wins":67},"google/gemini-3.5-flash-lite":{"draws":76,"losses":50,"wins":126},"google/gemini-3.6-flash":{"draws":67,"losses":128,"wins":81},"google/gemini-3.8-flash":{"draws":37,"losses":75,"wins":32},"google/gemma-4-31b-it":{"draws":28,"losses":10,"wins":46},"gpt-4.1":{"draws":18,"losses":12,"wins":18},"gpt-4.1-nano":{"draws":12,"losses":0,"wins":6},"gpt-5":{"draws":34,"losses":41,"wins":51},"gpt-5.4":{"draws":35,"losses":68,"wins":35},"gpt-5.4-mini":{"draws":36,"losses":18,"wins":42},"gpt-5.4-nano":{"draws":36,"losses":33,"wins":75},"gpt-5.5":{"draws":53,"losses":53,"wins":26},"gpt-5.6-luna":{"draws":51,"losses":30,"wins":63},"gpt-5.6-sol":{"draws":22,"losses":96,"wins":26},"gpt-5.6-terra":{"draws":49,"losses":41,"wins":48},"gpt-6-astra":{"draws":9,"losses":128,"wins":7},"gpt-6-luna":{"draws":43,"losses":49,"wins":52},"gpt-6-sol":{"draws":23,"losses":106,"wins":15},"gpt-6.1-sol":{"draws":11,"losses":121,"wins":12},"gpt-6.1-terra":{"draws":21,"losses":116,"wins":7},"gpt-6.1-terra-pro":{"draws":18,"losses":114,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":42,"losses":6,"wins":54},"inception/mercury-3":{"draws":27,"losses":33,"wins":36},"inclusionai/ling-3.0-flash":{"draws":37,"losses":10,"wins":55},"inclusionai/ling-3.1-flash":{"draws":10,"losses":4,"wins":10},"meituan/longcat-2.0":{"draws":35,"losses":24,"wins":97},"meta/muse-glimmer-30b":{"draws":39,"losses":18,"wins":69},"meta/muse-spark-1.2":{"draws":34,"losses":65,"wins":39},"meta/muse-spark-1.3":{"draws":29,"losses":81,"wins":34},"meta/muse-spark-open":{"draws":42,"losses":60,"wins":42},"meta/muse-wonder":{"draws":27,"losses":87,"wins":30},"minimax/minimax-m3":{"draws":20,"losses":9,"wins":49},"minimax/minimax-m3.1-flash":{"draws":31,"losses":37,"wins":58},"mistralai/mistral-large-4-0":{"draws":30,"losses":27,"wins":33},"mistralai/mistral-medium-3-5":{"draws":23,"losses":8,"wins":53},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":47,"losses":48,"wins":43},"moonshotai/kimi-k3.1-pro":{"draws":17,"losses":114,"wins":13},"nex-agi/nex-n2-pro":{"draws":18,"losses":9,"wins":45},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":7,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":23,"wins":64},"nvidia/nemotron-3.5-super-vl":{"draws":23,"losses":21,"wins":22},"o3":{"draws":22,"losses":56,"wins":120},"openai/gpt-oss-120b":{"draws":36,"losses":22,"wins":68},"poolside/laguna-s-2.1":{"draws":41,"losses":20,"wins":77},"qwen/qwen3.7-max":{"draws":20,"losses":21,"wins":43},"qwen/qwen3.7-plus":{"draws":20,"losses":14,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":46,"losses":60,"wins":38},"qwen/qwen3.8-27b":{"draws":29,"losses":37,"wins":36},"qwen/qwen3.8-flash":{"draws":30,"losses":33,"wins":33},"qwen/qwen3.8-max":{"draws":36,"losses":64,"wins":44},"qwen/qwen3.8-max-0902":{"draws":36,"losses":58,"wins":50},"recursive/flint-v1.0":{"draws":12,"losses":1,"wins":29},"reflection/beam-1.0-501b-a23b":{"draws":44,"losses":42,"wins":46},"stealth/ox-alpha":{"draws":122,"losses":200,"wins":152},"stealth/space-bunny-alpha":{"draws":33,"losses":27,"wins":54},"stepfun/step-3.7-flash":{"draws":13,"losses":21,"wins":68},"stepfun/step-5-preview":{"draws":8,"losses":7,"wins":13},"tencent/hy3-preview":{"draws":26,"losses":17,"wins":35},"tencent/hy4-preview":{"draws":32,"losses":63,"wins":43},"thinkingmachines/inkling":{"draws":58,"losses":30,"wins":104},"thinkingmachines/inkling-small":{"draws":42,"losses":18,"wins":84},"unbiased/pareto-26.10":{"draws":5,"losses":43,"wins":0},"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":40,"losses":62,"wins":42},"x-ai/grok-4.6":{"draws":34,"losses":76,"wins":34},"x-ai/grok-4.7":{"draws":11,"losses":89,"wins":26},"x-ai/grok-build-0.1":{"draws":15,"losses":7,"wins":26},"xiaomi/mimo-v2.5":{"draws":69,"losses":33,"wins":120},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":21,"wins":38},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":43,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":52,"wins":20},"z-ai/glm-5.2":{"draws":82,"losses":80,"wins":126},"z-ai/glm-5.3":{"draws":32,"losses":83,"wins":23},"z-ai/glm-5.3-flash":{"draws":29,"losses":76,"wins":39},"z-ai/glm-5.3-flashx":{"draws":36,"losses":75,"wins":33}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":21,"wins":70},"claude-fable-5":{"draws":22,"losses":73,"wins":37},"claude-fable-5-1":{"draws":8,"losses":125,"wins":13},"claude-haiku-5-5":{"draws":27,"losses":46,"wins":57},"claude-opus-4-5":{"draws":59,"losses":56,"wins":103},"claude-opus-4-8":{"draws":16,"losses":34,"wins":34},"claude-opus-5":{"draws":32,"losses":157,"wins":33},"claude-opus-5-5":{"draws":10,"losses":115,"wins":19},"claude-sonnet-5":{"draws":33,"losses":40,"wins":59},"claude-sonnet-5-5":{"draws":26,"losses":63,"wins":43},"cohere/north-mini-code":{"draws":10,"losses":3,"wins":37},"deepseek/deepseek-v4-flash":{"draws":43,"losses":31,"wins":126},"deepseek/deepseek-v4-pro":{"draws":25,"losses":38,"wins":57},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":40,"wins":52},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":58,"wins":49},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":66,"wins":42},"elorian/glimpse":{"draws":14,"losses":29,"wins":27},"fireworks/ember-1":{"draws":41,"losses":37,"wins":54},"gemini-3.1-pro-preview":{"draws":29,"losses":38,"wins":65},"gemini-4-argon":{"draws":9,"losses":98,"wins":25},"google/gemini-3.1-flash-lite":{"draws":19,"losses":7,"wins":70},"google/gemini-3.5-flash":{"draws":36,"losses":51,"wins":81},"google/gemini-3.5-flash-lite":{"draws":53,"losses":28,"wins":151},"google/gemini-3.6-flash":{"draws":52,"losses":106,"wins":94},"google/gemini-3.8-flash":{"draws":26,"losses":62,"wins":44},"google/gemma-4-31b-it":{"draws":23,"losses":10,"wins":47},"gpt-4.1":{"draws":10,"losses":7,"wins":27},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":7},"gpt-5":{"draws":25,"losses":32,"wins":57},"gpt-5.4":{"draws":28,"losses":57,"wins":41},"gpt-5.4-mini":{"draws":20,"losses":24,"wins":44},"gpt-5.4-nano":{"draws":25,"losses":31,"wins":84},"gpt-5.5":{"draws":34,"losses":50,"wins":36},"gpt-5.6-luna":{"draws":34,"losses":33,"wins":65},"gpt-5.6-sol":{"draws":21,"losses":73,"wins":38},"gpt-5.6-terra":{"draws":28,"losses":40,"wins":58},"gpt-6-astra":{"draws":8,"losses":114,"wins":10},"gpt-6-luna":{"draws":29,"losses":39,"wins":64},"gpt-6-sol":{"draws":17,"losses":80,"wins":35},"gpt-6.1-sol":{"draws":6,"losses":110,"wins":16},"gpt-6.1-terra":{"draws":9,"losses":105,"wins":18},"gpt-6.1-terra-pro":{"draws":13,"losses":104,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":29,"losses":11,"wins":58},"inception/mercury-3":{"draws":24,"losses":20,"wins":44},"inclusionai/ling-3.0-flash":{"draws":30,"losses":0,"wins":64},"inclusionai/ling-3.1-flash":{"draws":2,"losses":4,"wins":8},"meituan/longcat-2.0":{"draws":28,"losses":24,"wins":92},"meta/muse-glimmer-30b":{"draws":24,"losses":19,"wins":71},"meta/muse-spark-1.2":{"draws":27,"losses":47,"wins":52},"meta/muse-spark-1.3":{"draws":23,"losses":55,"wins":54},"meta/muse-spark-open":{"draws":32,"losses":47,"wins":53},"meta/muse-wonder":{"draws":26,"losses":62,"wins":44},"minimax/minimax-m3":{"draws":15,"losses":11,"wins":48},"minimax/minimax-m3.1-flash":{"draws":26,"losses":28,"wins":60},"mistralai/mistral-large-4-0":{"draws":18,"losses":33,"wins":31},"mistralai/mistral-medium-3-5":{"draws":21,"losses":6,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":34,"losses":43,"wins":49},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":106,"wins":13},"nex-agi/nex-n2-pro":{"draws":13,"losses":5,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":22,"wins":61},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":12,"wins":35},"o3":{"draws":25,"losses":55,"wins":110},"openai/gpt-oss-120b":{"draws":31,"losses":15,"wins":68},"poolside/laguna-s-2.1":{"draws":33,"losses":18,"wins":71},"qwen/qwen3.7-max":{"draws":21,"losses":22,"wins":37},"qwen/qwen3.7-plus":{"draws":18,"losses":11,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":50,"wins":42},"qwen/qwen3.8-27b":{"draws":20,"losses":31,"wins":43},"qwen/qwen3.8-flash":{"draws":26,"losses":20,"wins":42},"qwen/qwen3.8-max":{"draws":25,"losses":47,"wins":60},"qwen/qwen3.8-max-0902":{"draws":29,"losses":52,"wins":51},"recursive/flint-v1.0":{"draws":11,"losses":2,"wins":29},"reflection/beam-1.0-501b-a23b":{"draws":26,"losses":32,"wins":62},"stealth/ox-alpha":{"draws":72,"losses":163,"wins":159},"stealth/space-bunny-alpha":{"draws":25,"losses":27,"wins":54},"stepfun/step-3.7-flash":{"draws":13,"losses":19,"wins":62},"stepfun/step-5-preview":{"draws":4,"losses":15,"wins":15},"tencent/hy3-preview":{"draws":17,"losses":17,"wins":40},"tencent/hy4-preview":{"draws":28,"losses":50,"wins":48},"thinkingmachines/inkling":{"draws":42,"losses":22,"wins":108},"thinkingmachines/inkling-small":{"draws":34,"losses":13,"wins":85},"unbiased/pareto-26.10":{"draws":4,"losses":36,"wins":4},"unbiased/pareto-26.10-preview":{"draws":1,"losses":41,"wins":2},"upstage/solar-mini4":{"draws":6,"losses":3,"wins":27},"x-ai/grok-4.5":{"draws":36,"losses":52,"wins":44},"x-ai/grok-4.6":{"draws":31,"losses":57,"wins":44},"x-ai/grok-4.7":{"draws":15,"losses":71,"wins":32},"x-ai/grok-build-0.1":{"draws":9,"losses":7,"wins":28},"xiaomi/mimo-v2.5":{"draws":57,"losses":32,"wins":129},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":12,"wins":39},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":42,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":42,"wins":37},"z-ai/glm-5.2":{"draws":69,"losses":61,"wins":134},"z-ai/glm-5.3":{"draws":20,"losses":76,"wins":30},"z-ai/glm-5.3-flash":{"draws":19,"losses":63,"wins":50},"z-ai/glm-5.3-flashx":{"draws":21,"losses":53,"wins":58}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":23,"wins":174},"claude-fable-5":{"draws":33,"losses":72,"wins":141},"claude-fable-5-1":{"draws":23,"losses":179,"wins":76},"claude-haiku-5-5":{"draws":41,"losses":37,"wins":156},"claude-opus-4-5":{"draws":69,"losses":36,"wins":293},"claude-opus-4-8":{"draws":32,"losses":33,"wins":157},"claude-opus-5":{"draws":52,"losses":166,"wins":166},"claude-opus-5-5":{"draws":24,"losses":168,"wins":78},"claude-sonnet-5":{"draws":36,"losses":33,"wins":177},"claude-sonnet-5-5":{"draws":26,"losses":81,"wins":139},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":80},"deepseek/deepseek-v4-flash":{"draws":44,"losses":21,"wins":297},"deepseek/deepseek-v4-pro":{"draws":25,"losses":33,"wins":174},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":26,"wins":177},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":37,"wins":169},"deepseek/deepseek-v4.1-flash-1017":{"draws":35,"losses":53,"wins":158},"elorian/glimpse":{"draws":19,"losses":28,"wins":91},"fireworks/ember-1":{"draws":27,"losses":40,"wins":179},"gemini-3.1-pro-preview":{"draws":26,"losses":31,"wins":189},"gemini-4-argon":{"draws":30,"losses":114,"wins":102},"google/gemini-3.1-flash-lite":{"draws":18,"losses":5,"wins":127},"google/gemini-3.5-flash":{"draws":35,"losses":34,"wins":235},"google/gemini-3.5-flash-lite":{"draws":51,"losses":34,"wins":339},"google/gemini-3.6-flash":{"draws":59,"losses":93,"wins":316},"google/gemini-3.8-flash":{"draws":26,"losses":53,"wins":167},"google/gemma-4-31b-it":{"draws":19,"losses":10,"wins":111},"gpt-4.1":{"draws":11,"losses":4,"wins":67},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":20},"gpt-5":{"draws":26,"losses":17,"wins":177},"gpt-5.4":{"draws":29,"losses":35,"wins":170},"gpt-5.4-mini":{"draws":30,"losses":13,"wins":121},"gpt-5.4-nano":{"draws":22,"losses":15,"wins":199},"gpt-5.5":{"draws":30,"losses":47,"wins":155},"gpt-5.6-luna":{"draws":28,"losses":24,"wins":194},"gpt-5.6-sol":{"draws":30,"losses":66,"wins":150},"gpt-5.6-terra":{"draws":25,"losses":23,"wins":186},"gpt-6-astra":{"draws":22,"losses":168,"wins":56},"gpt-6-luna":{"draws":40,"losses":26,"wins":180},"gpt-6-sol":{"draws":38,"losses":89,"wins":119},"gpt-6.1-sol":{"draws":32,"losses":140,"wins":74},"gpt-6.1-terra":{"draws":28,"losses":124,"wins":94},"gpt-6.1-terra-pro":{"draws":29,"losses":125,"wins":92},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":2,"wins":6},"inception/mercury-2.5-preview":{"draws":31,"losses":7,"wins":128},"inception/mercury-3":{"draws":18,"losses":18,"wins":128},"inclusionai/ling-3.0-flash":{"draws":26,"losses":7,"wins":133},"inclusionai/ling-3.1-flash":{"draws":8,"losses":2,"wins":28},"meituan/longcat-2.0":{"draws":22,"losses":21,"wins":213},"meta/muse-glimmer-30b":{"draws":15,"losses":22,"wins":193},"meta/muse-spark-1.2":{"draws":33,"losses":36,"wins":175},"meta/muse-spark-1.3":{"draws":30,"losses":51,"wins":165},"meta/muse-spark-open":{"draws":27,"losses":42,"wins":177},"meta/muse-wonder":{"draws":29,"losses":77,"wins":140},"minimax/minimax-m3":{"draws":17,"losses":6,"wins":115},"minimax/minimax-m3.1-flash":{"draws":29,"losses":21,"wins":160},"mistralai/mistral-large-4-0":{"draws":26,"losses":19,"wins":117},"mistralai/mistral-medium-3-5":{"draws":23,"losses":12,"wins":109},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":37,"losses":40,"wins":167},"moonshotai/kimi-k3.1-pro":{"draws":26,"losses":111,"wins":109},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":109},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":46},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":9,"wins":157},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":15,"wins":81},"o3":{"draws":24,"losses":23,"wins":265},"openai/gpt-oss-120b":{"draws":26,"losses":11,"wins":183},"poolside/laguna-s-2.1":{"draws":24,"losses":13,"wins":211},"qwen/qwen3.7-max":{"draws":17,"losses":12,"wins":111},"qwen/qwen3.7-plus":{"draws":15,"losses":8,"wins":93},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":42,"wins":173},"qwen/qwen3.8-27b":{"draws":29,"losses":13,"wins":124},"qwen/qwen3.8-flash":{"draws":24,"losses":14,"wins":126},"qwen/qwen3.8-max":{"draws":36,"losses":31,"wins":179},"qwen/qwen3.8-max-0902":{"draws":36,"losses":41,"wins":169},"recursive/flint-v1.0":{"draws":7,"losses":1,"wins":62},"reflection/beam-1.0-501b-a23b":{"draws":29,"losses":23,"wins":180},"stealth/ox-alpha":{"draws":133,"losses":121,"wins":578},"stealth/space-bunny-alpha":{"draws":30,"losses":15,"wins":151},"stepfun/step-3.7-flash":{"draws":14,"losses":7,"wins":141},"stepfun/step-5-preview":{"draws":6,"losses":5,"wins":47},"tencent/hy3-preview":{"draws":24,"losses":12,"wins":106},"tencent/hy4-preview":{"draws":21,"losses":36,"wins":177},"thinkingmachines/inkling":{"draws":47,"losses":30,"wins":261},"thinkingmachines/inkling-small":{"draws":40,"losses":11,"wins":195},"unbiased/pareto-26.10":{"draws":7,"losses":51,"wins":24},"unbiased/pareto-26.10-preview":{"draws":5,"losses":47,"wins":30},"upstage/solar-mini4":{"draws":6,"losses":1,"wins":41},"x-ai/grok-4.5":{"draws":38,"losses":52,"wins":156},"x-ai/grok-4.6":{"draws":37,"losses":48,"wins":161},"x-ai/grok-4.7":{"draws":21,"losses":97,"wins":102},"x-ai/grok-build-0.1":{"draws":15,"losses":3,"wins":64},"xiaomi/mimo-v2.5":{"draws":56,"losses":23,"wins":299},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":6,"wins":113},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":17,"wins":120},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":41,"wins":98},"z-ai/glm-5.2":{"draws":74,"losses":34,"wins":384},"z-ai/glm-5.3":{"draws":29,"losses":64,"wins":141},"z-ai/glm-5.3-flash":{"draws":35,"losses":46,"wins":165},"z-ai/glm-5.3-flashx":{"draws":40,"losses":41,"wins":165}},"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":14,"losses":72,"wins":88},"claude-haiku-5-5":{"draws":16,"losses":9,"wins":125},"claude-opus-4-5":{"draws":19,"losses":15,"wins":220},"claude-opus-4-8":{"draws":10,"losses":19,"wins":115},"claude-opus-5":{"draws":24,"losses":78,"wins":168},"claude-opus-5-5":{"draws":8,"losses":58,"wins":58},"claude-sonnet-5":{"draws":10,"losses":9,"wins":137},"claude-sonnet-5-5":{"draws":14,"losses":31,"wins":111},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":60},"deepseek/deepseek-v4-flash":{"draws":12,"losses":6,"wins":218},"deepseek/deepseek-v4-pro":{"draws":11,"losses":5,"wins":128},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":4,"wins":133},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":14,"wins":132},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":18,"wins":128},"elorian/glimpse":{"draws":7,"losses":7,"wins":72},"fireworks/ember-1":{"draws":8,"losses":12,"wins":136},"gemini-3.1-pro-preview":{"draws":9,"losses":9,"wins":138},"gemini-4-argon":{"draws":9,"losses":47,"wins":100},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":96},"google/gemini-3.5-flash":{"draws":11,"losses":9,"wins":176},"google/gemini-3.5-flash-lite":{"draws":17,"losses":1,"wins":254},"google/gemini-3.6-flash":{"draws":20,"losses":25,"wins":251},"google/gemini-3.8-flash":{"draws":13,"losses":20,"wins":123},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":87},"gpt-4.1":{"draws":3,"losses":1,"wins":48},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":8,"losses":2,"wins":128},"gpt-5.4":{"draws":9,"losses":12,"wins":129},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":96},"gpt-5.4-nano":{"draws":6,"losses":1,"wins":153},"gpt-5.5":{"draws":13,"losses":15,"wins":116},"gpt-5.6-luna":{"draws":16,"losses":4,"wins":136},"gpt-5.6-sol":{"draws":11,"losses":20,"wins":125},"gpt-5.6-terra":{"draws":8,"losses":3,"wins":139},"gpt-6-astra":{"draws":15,"losses":72,"wins":69},"gpt-6-luna":{"draws":12,"losses":3,"wins":141},"gpt-6-sol":{"draws":14,"losses":39,"wins":103},"gpt-6.1-sol":{"draws":16,"losses":66,"wins":74},"gpt-6.1-terra":{"draws":12,"losses":53,"wins":91},"gpt-6.1-terra-pro":{"draws":13,"losses":55,"wins":88},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":102},"inception/mercury-3":{"draws":5,"losses":1,"wins":102},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":106},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":24},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":155},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":131},"meta/muse-spark-1.2":{"draws":13,"losses":10,"wins":127},"meta/muse-spark-1.3":{"draws":10,"losses":14,"wins":132},"meta/muse-spark-open":{"draws":10,"losses":15,"wins":131},"meta/muse-wonder":{"draws":9,"losses":30,"wins":117},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":83},"minimax/minimax-m3.1-flash":{"draws":7,"losses":2,"wins":121},"mistralai/mistral-large-4-0":{"draws":15,"losses":4,"wins":79},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":85},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":5,"losses":10,"wins":135},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":50,"wins":94},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":74},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":31},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":4,"wins":114},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":4,"wins":66},"o3":{"draws":11,"losses":3,"wins":204},"openai/gpt-oss-120b":{"draws":9,"losses":0,"wins":129},"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":4,"losses":0,"wins":72},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":17,"wins":129},"qwen/qwen3.8-27b":{"draws":5,"losses":3,"wins":98},"qwen/qwen3.8-flash":{"draws":10,"losses":3,"wins":91},"qwen/qwen3.8-max":{"draws":13,"losses":13,"wins":130},"qwen/qwen3.8-max-0902":{"draws":13,"losses":11,"wins":132},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":43},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":4,"wins":126},"stealth/ox-alpha":{"draws":45,"losses":27,"wins":434},"stealth/space-bunny-alpha":{"draws":6,"losses":2,"wins":114},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":106},"stepfun/step-5-preview":{"draws":4,"losses":3,"wins":33},"tencent/hy3-preview":{"draws":8,"losses":0,"wins":78},"tencent/hy4-preview":{"draws":10,"losses":15,"wins":125},"thinkingmachines/inkling":{"draws":19,"losses":0,"wins":185},"thinkingmachines/inkling-small":{"draws":10,"losses":0,"wins":146},"unbiased/pareto-26.10":{"draws":4,"losses":21,"wins":27},"unbiased/pareto-26.10-preview":{"draws":1,"losses":26,"wins":25},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":34},"x-ai/grok-4.5":{"draws":18,"losses":18,"wins":120},"x-ai/grok-4.6":{"draws":16,"losses":14,"wins":126},"x-ai/grok-4.7":{"draws":10,"losses":30,"wins":98},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":51},"xiaomi/mimo-v2.5":{"draws":13,"losses":4,"wins":225},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":59},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":2,"wins":89},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":14,"wins":80},"z-ai/glm-5.2":{"draws":17,"losses":12,"wins":283},"z-ai/glm-5.3":{"draws":11,"losses":27,"wins":112},"z-ai/glm-5.3-flash":{"draws":11,"losses":11,"wins":134},"z-ai/glm-5.3-flashx":{"draws":15,"losses":9,"wins":132}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":25,"wins":71},"claude-fable-5":{"draws":23,"losses":94,"wins":27},"claude-fable-5-1":{"draws":6,"losses":150,"wins":6},"claude-haiku-5-5":{"draws":35,"losses":63,"wins":40},"claude-opus-4-5":{"draws":74,"losses":78,"wins":82},"claude-opus-4-8":{"draws":33,"losses":59,"wins":40},"claude-opus-5":{"draws":36,"losses":177,"wins":33},"claude-opus-5-5":{"draws":10,"losses":137,"wins":9},"claude-sonnet-5":{"draws":24,"losses":36,"wins":36},"claude-sonnet-5-5":{"draws":24,"losses":83,"wins":37},"cohere/north-mini-code":{"draws":8,"losses":8,"wins":38},"deepseek/deepseek-v4-flash":{"draws":54,"losses":45,"wins":117},"deepseek/deepseek-v4-pro":{"draws":38,"losses":47,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":50,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":58,"wins":50},"deepseek/deepseek-v4.1-flash-1017":{"draws":31,"losses":81,"wins":32},"elorian/glimpse":{"draws":18,"losses":31,"wins":29},"fireworks/ember-1":{"draws":37,"losses":62,"wins":45},"gemini-3.1-pro-preview":{"draws":36,"losses":50,"wins":58},"gemini-4-argon":{"draws":12,"losses":124,"wins":8},"google/gemini-3.1-flash-lite":{"draws":26,"losses":5,"wins":65},"google/gemini-3.5-flash":{"draws":44,"losses":79,"wins":57},"google/gemini-3.5-flash-lite":{"draws":61,"losses":56,"wins":135},"google/gemini-3.6-flash":{"draws":64,"losses":121,"wins":91},"google/gemini-3.8-flash":{"draws":30,"losses":78,"wins":36},"google/gemma-4-31b-it":{"draws":27,"losses":12,"wins":45},"gpt-4.1":{"draws":12,"losses":15,"wins":21},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":33,"losses":38,"wins":55},"gpt-5.4":{"draws":33,"losses":73,"wins":32},"gpt-5.4-mini":{"draws":38,"losses":28,"wins":30},"gpt-5.4-nano":{"draws":33,"losses":41,"wins":70},"gpt-5.5":{"draws":43,"losses":58,"wins":31},"gpt-5.6-luna":{"draws":36,"losses":43,"wins":65},"gpt-5.6-sol":{"draws":20,"losses":105,"wins":19},"gpt-5.6-terra":{"draws":46,"losses":46,"wins":46},"gpt-6-astra":{"draws":6,"losses":132,"wins":6},"gpt-6-luna":{"draws":36,"losses":54,"wins":54},"gpt-6-sol":{"draws":23,"losses":102,"wins":19},"gpt-6.1-sol":{"draws":6,"losses":130,"wins":8},"gpt-6.1-terra":{"draws":16,"losses":119,"wins":9},"gpt-6.1-terra-pro":{"draws":13,"losses":122,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":34,"losses":11,"wins":57},"inception/mercury-3":{"draws":31,"losses":33,"wins":32},"inclusionai/ling-3.0-flash":{"draws":34,"losses":8,"wins":60},"inclusionai/ling-3.1-flash":{"draws":5,"losses":8,"wins":5},"meituan/longcat-2.0":{"draws":34,"losses":33,"wins":89},"meta/muse-glimmer-30b":{"draws":37,"losses":19,"wins":70},"meta/muse-spark-1.2":{"draws":37,"losses":64,"wins":37},"meta/muse-spark-1.3":{"draws":32,"losses":77,"wins":35},"meta/muse-spark-open":{"draws":38,"losses":74,"wins":32},"meta/muse-wonder":{"draws":31,"losses":85,"wins":28},"minimax/minimax-m3":{"draws":18,"losses":15,"wins":45},"minimax/minimax-m3.1-flash":{"draws":32,"losses":37,"wins":57},"mistralai/mistral-large-4-0":{"draws":27,"losses":24,"wins":39},"mistralai/mistral-medium-3-5":{"draws":26,"losses":11,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":38,"losses":58,"wins":42},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":118,"wins":11},"nex-agi/nex-n2-pro":{"draws":20,"losses":10,"wins":42},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":7,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":21,"wins":52},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":17,"wins":31},"o3":{"draws":26,"losses":83,"wins":89},"openai/gpt-oss-120b":{"draws":34,"losses":17,"wins":75},"poolside/laguna-s-2.1":{"draws":40,"losses":27,"wins":71},"qwen/qwen3.7-max":{"draws":23,"losses":21,"wins":40},"qwen/qwen3.7-plus":{"draws":20,"losses":16,"wins":36},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":62,"wins":37},"qwen/qwen3.8-27b":{"draws":24,"losses":40,"wins":38},"qwen/qwen3.8-flash":{"draws":29,"losses":33,"wins":34},"qwen/qwen3.8-max":{"draws":44,"losses":59,"wins":41},"qwen/qwen3.8-max-0902":{"draws":35,"losses":70,"wins":39},"recursive/flint-v1.0":{"draws":12,"losses":3,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":39,"losses":46,"wins":47},"stealth/ox-alpha":{"draws":99,"losses":241,"wins":134},"stealth/space-bunny-alpha":{"draws":24,"losses":40,"wins":50},"stepfun/step-3.7-flash":{"draws":21,"losses":27,"wins":54},"stepfun/step-5-preview":{"draws":6,"losses":15,"wins":15},"tencent/hy3-preview":{"draws":22,"losses":21,"wins":35},"tencent/hy4-preview":{"draws":35,"losses":64,"wins":39},"thinkingmachines/inkling":{"draws":61,"losses":28,"wins":103},"thinkingmachines/inkling-small":{"draws":41,"losses":24,"wins":79},"unbiased/pareto-26.10":{"draws":4,"losses":43,"wins":1},"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":38,"losses":73,"wins":33},"x-ai/grok-4.6":{"draws":36,"losses":74,"wins":34},"x-ai/grok-4.7":{"draws":12,"losses":88,"wins":26},"x-ai/grok-build-0.1":{"draws":17,"losses":4,"wins":27},"xiaomi/mimo-v2.5":{"draws":68,"losses":45,"wins":109},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":20,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":50,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":56,"wins":25},"z-ai/glm-5.2":{"draws":75,"losses":94,"wins":119},"z-ai/glm-5.3":{"draws":25,"losses":94,"wins":19},"z-ai/glm-5.3-flash":{"draws":23,"losses":81,"wins":40},"z-ai/glm-5.3-flashx":{"draws":31,"losses":78,"wins":35}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":24,"wins":80},"claude-fable-5":{"draws":25,"losses":60,"wins":59},"claude-fable-5-1":{"draws":8,"losses":117,"wins":37},"claude-haiku-5-5":{"draws":24,"losses":43,"wins":71},"claude-opus-4-5":{"draws":47,"losses":61,"wins":126},"claude-opus-4-8":{"draws":26,"losses":43,"wins":63},"claude-opus-5":{"draws":26,"losses":139,"wins":81},"claude-opus-5-5":{"draws":14,"losses":111,"wins":31},"claude-sonnet-5":{"draws":24,"losses":37,"wins":83},"claude-sonnet-5-5":{"draws":8,"losses":44,"wins":44},"cohere/north-mini-code":{"draws":6,"losses":8,"wins":40},"deepseek/deepseek-v4-flash":{"draws":43,"losses":31,"wins":142},"deepseek/deepseek-v4-pro":{"draws":29,"losses":34,"wins":69},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":33,"wins":78},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":40,"wins":75},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":60,"wins":60},"elorian/glimpse":{"draws":16,"losses":19,"wins":43},"fireworks/ember-1":{"draws":28,"losses":44,"wins":72},"gemini-3.1-pro-preview":{"draws":21,"losses":42,"wins":81},"gemini-4-argon":{"draws":12,"losses":88,"wins":44},"google/gemini-3.1-flash-lite":{"draws":15,"losses":12,"wins":69},"google/gemini-3.5-flash":{"draws":32,"losses":47,"wins":101},"google/gemini-3.5-flash-lite":{"draws":47,"losses":39,"wins":166},"google/gemini-3.6-flash":{"draws":52,"losses":94,"wins":130},"google/gemini-3.8-flash":{"draws":19,"losses":55,"wins":70},"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":26,"losses":26,"wins":74},"gpt-5.4":{"draws":32,"losses":42,"wins":64},"gpt-5.4-mini":{"draws":17,"losses":17,"wins":62},"gpt-5.4-nano":{"draws":20,"losses":19,"wins":105},"gpt-5.5":{"draws":29,"losses":42,"wins":61},"gpt-5.6-luna":{"draws":33,"losses":27,"wins":84},"gpt-5.6-sol":{"draws":14,"losses":74,"wins":56},"gpt-5.6-terra":{"draws":31,"losses":31,"wins":76},"gpt-6-astra":{"draws":11,"losses":100,"wins":33},"gpt-6-luna":{"draws":32,"losses":44,"wins":68},"gpt-6-sol":{"draws":11,"losses":82,"wins":51},"gpt-6.1-sol":{"draws":3,"losses":106,"wins":35},"gpt-6.1-terra":{"draws":18,"losses":88,"wins":38},"gpt-6.1-terra-pro":{"draws":12,"losses":91,"wins":41},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":25,"losses":12,"wins":65},"inception/mercury-3":{"draws":21,"losses":22,"wins":53},"inclusionai/ling-3.0-flash":{"draws":26,"losses":7,"wins":69},"inclusionai/ling-3.1-flash":{"draws":5,"losses":3,"wins":12},"meituan/longcat-2.0":{"draws":19,"losses":31,"wins":106},"meta/muse-glimmer-30b":{"draws":21,"losses":21,"wins":84},"meta/muse-spark-1.2":{"draws":28,"losses":42,"wins":68},"meta/muse-spark-1.3":{"draws":21,"losses":54,"wins":69},"meta/muse-spark-open":{"draws":26,"losses":52,"wins":64},"meta/muse-wonder":{"draws":22,"losses":54,"wins":68},"minimax/minimax-m3":{"draws":13,"losses":13,"wins":52},"minimax/minimax-m3.1-flash":{"draws":25,"losses":22,"wins":79},"mistralai/mistral-large-4-0":{"draws":23,"losses":24,"wins":43},"mistralai/mistral-medium-3-5":{"draws":18,"losses":8,"wins":58},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":28,"losses":46,"wins":64},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":90,"wins":40},"nex-agi/nex-n2-pro":{"draws":14,"losses":10,"wins":48},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":5,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":18,"wins":72},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":11,"wins":39},"o3":{"draws":17,"losses":46,"wins":135},"openai/gpt-oss-120b":{"draws":25,"losses":18,"wins":83},"poolside/laguna-s-2.1":{"draws":26,"losses":26,"wins":86},"qwen/qwen3.7-max":{"draws":18,"losses":22,"wins":44},"qwen/qwen3.7-plus":{"draws":15,"losses":13,"wins":44},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":50,"wins":63},"qwen/qwen3.8-27b":{"draws":17,"losses":26,"wins":59},"qwen/qwen3.8-flash":{"draws":17,"losses":30,"wins":49},"qwen/qwen3.8-max":{"draws":20,"losses":42,"wins":82},"qwen/qwen3.8-max-0902":{"draws":26,"losses":53,"wins":65},"recursive/flint-v1.0":{"draws":7,"losses":4,"wins":31},"reflection/beam-1.0-501b-a23b":{"draws":31,"losses":34,"wins":67},"stealth/ox-alpha":{"draws":77,"losses":162,"wins":235},"stealth/space-bunny-alpha":{"draws":21,"losses":24,"wins":69},"stepfun/step-3.7-flash":{"draws":11,"losses":26,"wins":65},"stepfun/step-5-preview":{"draws":2,"losses":11,"wins":21},"tencent/hy3-preview":{"draws":19,"losses":10,"wins":49},"tencent/hy4-preview":{"draws":22,"losses":48,"wins":68},"thinkingmachines/inkling":{"draws":41,"losses":40,"wins":111},"thinkingmachines/inkling-small":{"draws":31,"losses":21,"wins":92},"unbiased/pareto-26.10":{"draws":4,"losses":36,"wins":8},"unbiased/pareto-26.10-preview":{"draws":3,"losses":35,"wins":10},"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":22,"losses":61,"wins":61},"x-ai/grok-4.7":{"draws":14,"losses":64,"wins":48},"x-ai/grok-build-0.1":{"draws":9,"losses":6,"wins":33},"xiaomi/mimo-v2.5":{"draws":47,"losses":29,"wins":146},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":10,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":33,"wins":47},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":37,"wins":46},"z-ai/glm-5.2":{"draws":55,"losses":65,"wins":168},"z-ai/glm-5.3":{"draws":21,"losses":63,"wins":54},"z-ai/glm-5.3-flash":{"draws":19,"losses":55,"wins":70},"z-ai/glm-5.3-flashx":{"draws":24,"losses":54,"wins":66}},"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":1,"losses":60,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":33,"wins":9},"claude-opus-4-5":{"draws":9,"losses":71,"wins":8},"claude-opus-4-8":{"draws":10,"losses":37,"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":8,"losses":38,"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":18,"losses":37,"wins":25},"deepseek/deepseek-v4-pro":{"draws":10,"losses":28,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":33,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":35,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":47,"wins":1},"elorian/glimpse":{"draws":3,"losses":21,"wins":6},"fireworks/ember-1":{"draws":8,"losses":37,"wins":9},"gemini-3.1-pro-preview":{"draws":10,"losses":26,"wins":18},"gemini-4-argon":{"draws":0,"losses":52,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":14,"wins":22},"google/gemini-3.5-flash":{"draws":14,"losses":44,"wins":12},"google/gemini-3.5-flash-lite":{"draws":28,"losses":35,"wins":35},"google/gemini-3.6-flash":{"draws":17,"losses":79,"wins":8},"google/gemini-3.8-flash":{"draws":8,"losses":40,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":18,"wins":6},"gpt-4.1":{"draws":5,"losses":10,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":34,"wins":6},"gpt-5.4":{"draws":9,"losses":35,"wins":10},"gpt-5.4-mini":{"draws":7,"losses":17,"wins":12},"gpt-5.4-nano":{"draws":7,"losses":36,"wins":13},"gpt-5.5":{"draws":12,"losses":36,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":30,"wins":12},"gpt-5.6-sol":{"draws":2,"losses":47,"wins":5},"gpt-5.6-terra":{"draws":9,"losses":33,"wins":8},"gpt-6-astra":{"draws":2,"losses":52,"wins":0},"gpt-6-luna":{"draws":12,"losses":33,"wins":9},"gpt-6-sol":{"draws":4,"losses":49,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":52,"wins":0},"gpt-6.1-terra":{"draws":1,"losses":53,"wins":0},"gpt-6.1-terra-pro":{"draws":0,"losses":54,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":15,"wins":13},"inception/mercury-3":{"draws":2,"losses":26,"wins":6},"inclusionai/ling-3.0-flash":{"draws":12,"losses":13,"wins":9},"inclusionai/ling-3.1-flash":{"draws":3,"losses":5,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":40,"wins":16},"meta/muse-glimmer-30b":{"draws":16,"losses":17,"wins":17},"meta/muse-spark-1.2":{"draws":4,"losses":39,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":47,"wins":2},"meta/muse-spark-open":{"draws":6,"losses":41,"wins":7},"meta/muse-wonder":{"draws":3,"losses":47,"wins":4},"minimax/minimax-m3":{"draws":3,"losses":17,"wins":10},"minimax/minimax-m3.1-flash":{"draws":8,"losses":27,"wins":11},"mistralai/mistral-large-4-0":{"draws":9,"losses":20,"wins":5},"mistralai/mistral-medium-3-5":{"draws":9,"losses":11,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":35,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":53,"wins":1},"nex-agi/nex-n2-pro":{"draws":5,"losses":17,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":9,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":26,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":22,"wins":3},"o3":{"draws":13,"losses":61,"wins":14},"openai/gpt-oss-120b":{"draws":13,"losses":20,"wins":17},"poolside/laguna-s-2.1":{"draws":13,"losses":19,"wins":22},"qwen/qwen3.7-max":{"draws":9,"losses":17,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":14,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":45,"wins":3},"qwen/qwen3.8-27b":{"draws":3,"losses":25,"wins":6},"qwen/qwen3.8-flash":{"draws":7,"losses":18,"wins":11},"qwen/qwen3.8-max":{"draws":9,"losses":42,"wins":3},"qwen/qwen3.8-max-0902":{"draws":8,"losses":41,"wins":5},"recursive/flint-v1.0":{"draws":2,"losses":7,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":39,"wins":9},"stealth/ox-alpha":{"draws":24,"losses":132,"wins":22},"stealth/space-bunny-alpha":{"draws":9,"losses":29,"wins":8},"stepfun/step-3.7-flash":{"draws":8,"losses":25,"wins":7},"stepfun/step-5-preview":{"draws":3,"losses":11,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":13,"wins":8},"tencent/hy4-preview":{"draws":12,"losses":36,"wins":6},"thinkingmachines/inkling":{"draws":16,"losses":33,"wins":23},"thinkingmachines/inkling-small":{"draws":15,"losses":22,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":18,"wins":0},"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":7,"losses":44,"wins":3},"x-ai/grok-4.6":{"draws":9,"losses":43,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":45,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":9,"wins":5},"xiaomi/mimo-v2.5":{"draws":17,"losses":31,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":12,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":24,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":31,"wins":5},"z-ai/glm-5.2":{"draws":28,"losses":62,"wins":18},"z-ai/glm-5.3":{"draws":8,"losses":44,"wins":2},"z-ai/glm-5.3-flash":{"draws":6,"losses":36,"wins":12},"z-ai/glm-5.3-flashx":{"draws":9,"losses":40,"wins":5}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":55,"losses":73,"wins":68},"claude-fable-5":{"draws":35,"losses":167,"wins":14},"claude-fable-5-1":{"draws":6,"losses":232,"wins":2},"claude-haiku-5-5":{"draws":58,"losses":121,"wins":29},"claude-opus-4-5":{"draws":95,"losses":187,"wins":70},"claude-opus-4-8":{"draws":43,"losses":126,"wins":31},"claude-opus-5":{"draws":44,"losses":297,"wins":21},"claude-opus-5-5":{"draws":12,"losses":218,"wins":6},"claude-sonnet-5":{"draws":54,"losses":117,"wins":45},"claude-sonnet-5-5":{"draws":43,"losses":142,"wins":31},"cohere/north-mini-code":{"draws":18,"losses":25,"wins":37},"deepseek/deepseek-v4-flash":{"draws":70,"losses":95,"wins":95},"deepseek/deepseek-v4-pro":{"draws":49,"losses":100,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":48,"losses":92,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":57,"losses":123,"wins":36},"deepseek/deepseek-v4.1-flash-1017":{"draws":40,"losses":150,"wins":26},"elorian/glimpse":{"draws":25,"losses":61,"wins":30},"fireworks/ember-1":{"draws":60,"losses":107,"wins":49},"gemini-3.1-pro-preview":{"draws":56,"losses":97,"wins":63},"gemini-4-argon":{"draws":13,"losses":199,"wins":4},"google/gemini-3.1-flash-lite":{"draws":32,"losses":30,"wins":84},"google/gemini-3.5-flash":{"draws":55,"losses":144,"wins":71},"google/gemini-3.5-flash-lite":{"draws":87,"losses":134,"wins":153},"google/gemini-3.6-flash":{"draws":88,"losses":256,"wins":68},"google/gemini-3.8-flash":{"draws":40,"losses":155,"wins":21},"google/gemma-4-31b-it":{"draws":58,"losses":22,"wins":46},"gpt-4.1":{"draws":18,"losses":37,"wins":17},"gpt-4.1-nano":{"draws":17,"losses":3,"wins":8},"gpt-5":{"draws":44,"losses":98,"wins":48},"gpt-5.4":{"draws":51,"losses":123,"wins":32},"gpt-5.4-mini":{"draws":51,"losses":51,"wins":42},"gpt-5.4-nano":{"draws":48,"losses":96,"wins":82},"gpt-5.5":{"draws":58,"losses":112,"wins":26},"gpt-5.6-luna":{"draws":70,"losses":84,"wins":62},"gpt-5.6-sol":{"draws":29,"losses":168,"wins":19},"gpt-5.6-terra":{"draws":55,"losses":115,"wins":38},"gpt-6-astra":{"draws":10,"losses":201,"wins":5},"gpt-6-luna":{"draws":59,"losses":106,"wins":51},"gpt-6-sol":{"draws":32,"losses":169,"wins":15},"gpt-6.1-sol":{"draws":14,"losses":196,"wins":6},"gpt-6.1-terra":{"draws":20,"losses":194,"wins":2},"gpt-6.1-terra-pro":{"draws":13,"losses":195,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":53,"losses":29,"wins":70},"inception/mercury-3":{"draws":43,"losses":72,"wins":39},"inclusionai/ling-3.0-flash":{"draws":59,"losses":43,"wins":56},"inclusionai/ling-3.1-flash":{"draws":16,"losses":6,"wins":4},"meituan/longcat-2.0":{"draws":50,"losses":81,"wins":103},"meta/muse-glimmer-30b":{"draws":65,"losses":47,"wins":74},"meta/muse-spark-1.2":{"draws":52,"losses":121,"wins":33},"meta/muse-spark-1.3":{"draws":37,"losses":151,"wins":28},"meta/muse-spark-open":{"draws":47,"losses":138,"wins":31},"meta/muse-wonder":{"draws":38,"losses":146,"wins":32},"minimax/minimax-m3":{"draws":27,"losses":46,"wins":47},"minimax/minimax-m3.1-flash":{"draws":39,"losses":86,"wins":61},"mistralai/mistral-large-4-0":{"draws":43,"losses":71,"wins":20},"mistralai/mistral-medium-3-5":{"draws":46,"losses":30,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":59,"losses":106,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":188,"wins":9},"nex-agi/nex-n2-pro":{"draws":21,"losses":33,"wins":54},"nex-agi/nex-n2.5-pro":{"draws":10,"losses":23,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":48,"wins":71},"nvidia/nemotron-3.5-super-vl":{"draws":22,"losses":44,"wins":32},"o3":{"draws":38,"losses":183,"wins":85},"openai/gpt-oss-120b":{"draws":57,"losses":65,"wins":68},"poolside/laguna-s-2.1":{"draws":62,"losses":74,"wins":74},"qwen/qwen3.7-max":{"draws":39,"losses":52,"wins":39},"qwen/qwen3.7-plus":{"draws":31,"losses":38,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":65,"losses":120,"wins":31},"qwen/qwen3.8-27b":{"draws":38,"losses":81,"wins":35},"qwen/qwen3.8-flash":{"draws":38,"losses":74,"wins":32},"qwen/qwen3.8-max":{"draws":58,"losses":120,"wins":38},"qwen/qwen3.8-max-0902":{"draws":53,"losses":126,"wins":37},"recursive/flint-v1.0":{"draws":12,"losses":16,"wins":36},"reflection/beam-1.0-501b-a23b":{"draws":42,"losses":112,"wins":42},"stealth/ox-alpha":{"draws":156,"losses":403,"wins":137},"stealth/space-bunny-alpha":{"draws":48,"losses":69,"wins":51},"stepfun/step-3.7-flash":{"draws":30,"losses":58,"wins":70},"stepfun/step-5-preview":{"draws":6,"losses":39,"wins":15},"tencent/hy3-preview":{"draws":33,"losses":42,"wins":41},"tencent/hy4-preview":{"draws":46,"losses":119,"wins":41},"thinkingmachines/inkling":{"draws":83,"losses":99,"wins":102},"thinkingmachines/inkling-small":{"draws":78,"losses":48,"wins":90},"unbiased/pareto-26.10":{"draws":4,"losses":68,"wins":0},"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":37,"losses":146,"wins":33},"x-ai/grok-4.6":{"draws":50,"losses":141,"wins":25},"x-ai/grok-4.7":{"draws":18,"losses":159,"wins":15},"x-ai/grok-build-0.1":{"draws":20,"losses":20,"wins":32},"xiaomi/mimo-v2.5":{"draws":104,"losses":112,"wins":118},"xiaomi/mimo-v2.5-pro":{"draws":31,"losses":34,"wins":45},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":86,"wins":34},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":95,"wins":24},"z-ai/glm-5.2":{"draws":134,"losses":185,"wins":113},"z-ai/glm-5.3":{"draws":38,"losses":152,"wins":16},"z-ai/glm-5.3-flash":{"draws":48,"losses":120,"wins":48},"z-ai/glm-5.3-flashx":{"draws":42,"losses":131,"wins":43}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":31,"wins":61},"claude-fable-5":{"draws":24,"losses":81,"wins":27},"claude-fable-5-1":{"draws":9,"losses":136,"wins":5},"claude-haiku-5-5":{"draws":34,"losses":51,"wins":41},"claude-opus-4-5":{"draws":58,"losses":80,"wins":76},"claude-opus-4-8":{"draws":25,"losses":57,"wins":38},"claude-opus-5":{"draws":25,"losses":174,"wins":33},"claude-opus-5-5":{"draws":11,"losses":128,"wins":5},"claude-sonnet-5":{"draws":38,"losses":47,"wins":47},"claude-sonnet-5-5":{"draws":29,"losses":69,"wins":34},"cohere/north-mini-code":{"draws":10,"losses":14,"wins":28},"deepseek/deepseek-v4-flash":{"draws":49,"losses":47,"wins":100},"deepseek/deepseek-v4-pro":{"draws":24,"losses":28,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":47,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":54,"wins":43},"deepseek/deepseek-v4.1-flash-1017":{"draws":28,"losses":79,"wins":25},"elorian/glimpse":{"draws":20,"losses":37,"wins":17},"fireworks/ember-1":{"draws":35,"losses":57,"wins":40},"gemini-3.1-pro-preview":{"draws":30,"losses":54,"wins":48},"gemini-4-argon":{"draws":14,"losses":104,"wins":14},"google/gemini-3.1-flash-lite":{"draws":23,"losses":5,"wins":60},"google/gemini-3.5-flash":{"draws":37,"losses":72,"wins":57},"google/gemini-3.5-flash-lite":{"draws":55,"losses":72,"wins":105},"google/gemini-3.6-flash":{"draws":61,"losses":110,"wins":83},"google/gemini-3.8-flash":{"draws":25,"losses":74,"wins":33},"google/gemma-4-31b-it":{"draws":28,"losses":14,"wins":34},"gpt-4.1":{"draws":12,"losses":9,"wins":23},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":4},"gpt-5":{"draws":26,"losses":40,"wins":52},"gpt-5.4":{"draws":28,"losses":63,"wins":37},"gpt-5.4-mini":{"draws":27,"losses":27,"wins":34},"gpt-5.4-nano":{"draws":15,"losses":48,"wins":67},"gpt-5.5":{"draws":36,"losses":61,"wins":27},"gpt-5.6-luna":{"draws":40,"losses":38,"wins":54},"gpt-5.6-sol":{"draws":16,"losses":87,"wins":29},"gpt-5.6-terra":{"draws":38,"losses":46,"wins":42},"gpt-6-astra":{"draws":11,"losses":114,"wins":7},"gpt-6-luna":{"draws":34,"losses":56,"wins":42},"gpt-6-sol":{"draws":12,"losses":98,"wins":22},"gpt-6.1-sol":{"draws":7,"losses":117,"wins":8},"gpt-6.1-terra":{"draws":17,"losses":108,"wins":7},"gpt-6.1-terra-pro":{"draws":10,"losses":112,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":35,"losses":9,"wins":46},"inception/mercury-3":{"draws":24,"losses":31,"wins":31},"inclusionai/ling-3.0-flash":{"draws":32,"losses":18,"wins":42},"inclusionai/ling-3.1-flash":{"draws":12,"losses":5,"wins":9},"meituan/longcat-2.0":{"draws":27,"losses":31,"wins":86},"meta/muse-glimmer-30b":{"draws":33,"losses":31,"wins":56},"meta/muse-spark-1.2":{"draws":23,"losses":59,"wins":46},"meta/muse-spark-1.3":{"draws":18,"losses":79,"wins":35},"meta/muse-spark-open":{"draws":31,"losses":71,"wins":30},"meta/muse-wonder":{"draws":21,"losses":80,"wins":31},"minimax/minimax-m3":{"draws":11,"losses":14,"wins":47},"minimax/minimax-m3.1-flash":{"draws":32,"losses":29,"wins":55},"mistralai/mistral-large-4-0":{"draws":26,"losses":32,"wins":26},"mistralai/mistral-medium-3-5":{"draws":19,"losses":11,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":28,"losses":60,"wins":40},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":103,"wins":16},"nex-agi/nex-n2-pro":{"draws":15,"losses":14,"wins":37},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":5,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":23,"wins":43},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":20,"wins":25},"o3":{"draws":20,"losses":72,"wins":92},"openai/gpt-oss-120b":{"draws":30,"losses":28,"wins":58},"poolside/laguna-s-2.1":{"draws":28,"losses":50,"wins":50},"qwen/qwen3.7-max":{"draws":18,"losses":19,"wins":39},"qwen/qwen3.7-plus":{"draws":14,"losses":15,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":62,"wins":37},"qwen/qwen3.8-27b":{"draws":26,"losses":34,"wins":32},"qwen/qwen3.8-flash":{"draws":17,"losses":41,"wins":30},"qwen/qwen3.8-max":{"draws":37,"losses":59,"wins":36},"qwen/qwen3.8-max-0902":{"draws":34,"losses":62,"wins":36},"recursive/flint-v1.0":{"draws":8,"losses":9,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":30,"losses":47,"wins":45},"stealth/ox-alpha":{"draws":102,"losses":209,"wins":131},"stealth/space-bunny-alpha":{"draws":28,"losses":31,"wins":47},"stepfun/step-3.7-flash":{"draws":17,"losses":22,"wins":55},"stepfun/step-5-preview":{"draws":3,"losses":18,"wins":9},"tencent/hy3-preview":{"draws":24,"losses":19,"wins":29},"tencent/hy4-preview":{"draws":26,"losses":63,"wins":39},"thinkingmachines/inkling":{"draws":56,"losses":31,"wins":93},"thinkingmachines/inkling-small":{"draws":41,"losses":20,"wins":71},"unbiased/pareto-26.10":{"draws":1,"losses":42,"wins":1},"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":62,"wins":36},"x-ai/grok-4.6":{"draws":31,"losses":74,"wins":27},"x-ai/grok-4.7":{"draws":10,"losses":86,"wins":20},"x-ai/grok-build-0.1":{"draws":15,"losses":11,"wins":18},"xiaomi/mimo-v2.5":{"draws":67,"losses":36,"wins":99},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":13,"wins":41},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":38,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":47,"wins":25},"z-ai/glm-5.2":{"draws":76,"losses":88,"wins":100},"z-ai/glm-5.3":{"draws":22,"losses":77,"wins":27},"z-ai/glm-5.3-flash":{"draws":20,"losses":73,"wins":39},"z-ai/glm-5.3-flashx":{"draws":31,"losses":60,"wins":41}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":33,"losses":36,"wins":53},"claude-fable-5":{"draws":18,"losses":88,"wins":26},"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":55,"losses":79,"wins":80},"claude-opus-4-8":{"draws":28,"losses":52,"wins":40},"claude-opus-5":{"draws":19,"losses":177,"wins":26},"claude-opus-5-5":{"draws":7,"losses":133,"wins":4},"claude-sonnet-5":{"draws":36,"losses":46,"wins":50},"claude-sonnet-5-5":{"draws":21,"losses":78,"wins":33},"cohere/north-mini-code":{"draws":8,"losses":9,"wins":33},"deepseek/deepseek-v4-flash":{"draws":48,"losses":58,"wins":92},"deepseek/deepseek-v4-pro":{"draws":33,"losses":42,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":34,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":66,"wins":33},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":76,"wins":32},"elorian/glimpse":{"draws":15,"losses":31,"wins":28},"fireworks/ember-1":{"draws":30,"losses":59,"wins":43},"gemini-3.1-pro-preview":{"draws":35,"losses":46,"wins":51},"gemini-4-argon":{"draws":13,"losses":111,"wins":8},"google/gemini-3.1-flash-lite":{"draws":20,"losses":12,"wins":56},"google/gemini-3.5-flash":{"draws":37,"losses":76,"wins":53},"google/gemini-3.5-flash-lite":{"draws":63,"losses":50,"wins":119},"google/gemini-3.6-flash":{"draws":48,"losses":124,"wins":82},"google/gemini-3.8-flash":{"draws":28,"losses":70,"wins":34},"google/gemma-4-31b-it":{"draws":32,"losses":6,"wins":38},"gpt-4.1":{"draws":11,"losses":13,"wins":20},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":8},"gpt-5":{"draws":24,"losses":46,"wins":46},"gpt-5.4":{"draws":24,"losses":67,"wins":37},"gpt-5.4-mini":{"draws":30,"losses":18,"wins":40},"gpt-5.4-nano":{"draws":24,"losses":42,"wins":64},"gpt-5.5":{"draws":29,"losses":55,"wins":38},"gpt-5.6-luna":{"draws":38,"losses":38,"wins":56},"gpt-5.6-sol":{"draws":15,"losses":90,"wins":27},"gpt-5.6-terra":{"draws":32,"losses":54,"wins":42},"gpt-6-astra":{"draws":8,"losses":123,"wins":1},"gpt-6-luna":{"draws":33,"losses":51,"wins":48},"gpt-6-sol":{"draws":13,"losses":99,"wins":20},"gpt-6.1-sol":{"draws":7,"losses":123,"wins":2},"gpt-6.1-terra":{"draws":17,"losses":110,"wins":5},"gpt-6.1-terra-pro":{"draws":11,"losses":113,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":30,"losses":16,"wins":46},"inception/mercury-3":{"draws":22,"losses":38,"wins":28},"inclusionai/ling-3.0-flash":{"draws":35,"losses":19,"wins":44},"inclusionai/ling-3.1-flash":{"draws":11,"losses":7,"wins":8},"meituan/longcat-2.0":{"draws":33,"losses":39,"wins":72},"meta/muse-glimmer-30b":{"draws":30,"losses":21,"wins":65},"meta/muse-spark-1.2":{"draws":22,"losses":67,"wins":37},"meta/muse-spark-1.3":{"draws":26,"losses":68,"wins":38},"meta/muse-spark-open":{"draws":23,"losses":74,"wins":35},"meta/muse-wonder":{"draws":24,"losses":79,"wins":29},"minimax/minimax-m3":{"draws":15,"losses":15,"wins":40},"minimax/minimax-m3.1-flash":{"draws":20,"losses":41,"wins":55},"mistralai/mistral-large-4-0":{"draws":30,"losses":24,"wins":28},"mistralai/mistral-medium-3-5":{"draws":18,"losses":13,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":8,"wins":3},"moonshotai/kimi-k3":{"draws":33,"losses":42,"wins":51},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":105,"wins":15},"nex-agi/nex-n2-pro":{"draws":11,"losses":16,"wins":39},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":17,"wins":50},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":23,"wins":23},"o3":{"draws":27,"losses":56,"wins":101},"openai/gpt-oss-120b":{"draws":30,"losses":31,"wins":53},"poolside/laguna-s-2.1":{"draws":25,"losses":35,"wins":64},"qwen/qwen3.7-max":{"draws":21,"losses":18,"wins":37},"qwen/qwen3.7-plus":{"draws":13,"losses":22,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":58,"wins":45},"qwen/qwen3.8-27b":{"draws":25,"losses":39,"wins":30},"qwen/qwen3.8-flash":{"draws":21,"losses":37,"wins":30},"qwen/qwen3.8-max":{"draws":35,"losses":58,"wins":39},"qwen/qwen3.8-max-0902":{"draws":35,"losses":58,"wins":39},"recursive/flint-v1.0":{"draws":10,"losses":6,"wins":22},"reflection/beam-1.0-501b-a23b":{"draws":30,"losses":51,"wins":39},"stealth/ox-alpha":{"draws":99,"losses":190,"wins":151},"stealth/space-bunny-alpha":{"draws":27,"losses":30,"wins":47},"stepfun/step-3.7-flash":{"draws":17,"losses":21,"wins":58},"stepfun/step-5-preview":{"draws":3,"losses":20,"wins":7},"tencent/hy3-preview":{"draws":24,"losses":22,"wins":24},"tencent/hy4-preview":{"draws":24,"losses":58,"wins":46},"thinkingmachines/inkling":{"draws":51,"losses":45,"wins":80},"thinkingmachines/inkling-small":{"draws":38,"losses":24,"wins":70},"unbiased/pareto-26.10":{"draws":3,"losses":40,"wins":1},"unbiased/pareto-26.10-preview":{"draws":1,"losses":43,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":3,"wins":25},"x-ai/grok-4.5":{"draws":28,"losses":60,"wins":44},"x-ai/grok-4.6":{"draws":37,"losses":66,"wins":29},"x-ai/grok-4.7":{"draws":8,"losses":82,"wins":24},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":26},"xiaomi/mimo-v2.5":{"draws":58,"losses":44,"wins":100},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":17,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":36,"wins":38},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":49,"wins":27},"z-ai/glm-5.2":{"draws":78,"losses":82,"wins":104},"z-ai/glm-5.3":{"draws":20,"losses":79,"wins":27},"z-ai/glm-5.3-flash":{"draws":18,"losses":78,"wins":36},"z-ai/glm-5.3-flashx":{"draws":22,"losses":69,"wins":41}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":34,"wins":67},"claude-fable-5":{"draws":33,"losses":74,"wins":37},"claude-fable-5-1":{"draws":13,"losses":136,"wins":13},"claude-haiku-5-5":{"draws":41,"losses":57,"wins":40},"claude-opus-4-5":{"draws":59,"losses":71,"wins":104},"claude-opus-4-8":{"draws":25,"losses":49,"wins":58},"claude-opus-5":{"draws":40,"losses":169,"wins":37},"claude-opus-5-5":{"draws":10,"losses":132,"wins":14},"claude-sonnet-5":{"draws":36,"losses":50,"wins":58},"claude-sonnet-5-5":{"draws":29,"losses":75,"wins":40},"cohere/north-mini-code":{"draws":10,"losses":9,"wins":35},"deepseek/deepseek-v4-flash":{"draws":57,"losses":36,"wins":123},"deepseek/deepseek-v4-pro":{"draws":35,"losses":43,"wins":54},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":33,"wins":66},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":42,"wins":42},"deepseek/deepseek-v4.1-flash-1017":{"draws":33,"losses":70,"wins":41},"elorian/glimpse":{"draws":17,"losses":31,"wins":30},"fireworks/ember-1":{"draws":38,"losses":54,"wins":52},"gemini-3.1-pro-preview":{"draws":28,"losses":50,"wins":66},"gemini-4-argon":{"draws":12,"losses":114,"wins":18},"google/gemini-3.1-flash-lite":{"draws":27,"losses":11,"wins":58},"google/gemini-3.5-flash":{"draws":40,"losses":60,"wins":80},"google/gemini-3.5-flash-lite":{"draws":70,"losses":54,"wins":128},"google/gemini-3.6-flash":{"draws":72,"losses":114,"wins":90},"google/gemini-3.8-flash":{"draws":36,"losses":63,"wins":45},"google/gemma-4-31b-it":{"draws":34,"losses":12,"wins":38},"gpt-4.1":{"draws":9,"losses":14,"wins":25},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":10},"gpt-5":{"draws":33,"losses":31,"wins":62},"gpt-5.4":{"draws":37,"losses":54,"wins":47},"gpt-5.4-mini":{"draws":36,"losses":20,"wins":40},"gpt-5.4-nano":{"draws":35,"losses":37,"wins":72},"gpt-5.5":{"draws":39,"losses":44,"wins":49},"gpt-5.6-luna":{"draws":40,"losses":35,"wins":69},"gpt-5.6-sol":{"draws":23,"losses":77,"wins":44},"gpt-5.6-terra":{"draws":46,"losses":35,"wins":57},"gpt-6-astra":{"draws":13,"losses":124,"wins":7},"gpt-6-luna":{"draws":40,"losses":42,"wins":62},"gpt-6-sol":{"draws":24,"losses":91,"wins":29},"gpt-6.1-sol":{"draws":13,"losses":116,"wins":15},"gpt-6.1-terra":{"draws":24,"losses":104,"wins":16},"gpt-6.1-terra-pro":{"draws":20,"losses":110,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":35,"losses":14,"wins":53},"inception/mercury-3":{"draws":27,"losses":29,"wins":40},"inclusionai/ling-3.0-flash":{"draws":42,"losses":10,"wins":50},"inclusionai/ling-3.1-flash":{"draws":10,"losses":6,"wins":8},"meituan/longcat-2.0":{"draws":26,"losses":33,"wins":97},"meta/muse-glimmer-30b":{"draws":41,"losses":18,"wins":67},"meta/muse-spark-1.2":{"draws":35,"losses":52,"wins":51},"meta/muse-spark-1.3":{"draws":28,"losses":62,"wins":54},"meta/muse-spark-open":{"draws":30,"losses":55,"wins":57},"meta/muse-wonder":{"draws":36,"losses":72,"wins":36},"minimax/minimax-m3":{"draws":15,"losses":18,"wins":45},"minimax/minimax-m3.1-flash":{"draws":34,"losses":25,"wins":67},"mistralai/mistral-large-4-0":{"draws":33,"losses":26,"wins":31},"mistralai/mistral-medium-3-5":{"draws":24,"losses":9,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":35,"losses":45,"wins":58},"moonshotai/kimi-k3.1-pro":{"draws":23,"losses":96,"wins":25},"nex-agi/nex-n2-pro":{"draws":9,"losses":12,"wins":51},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":8,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":17,"wins":52},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":17,"wins":34},"o3":{"draws":38,"losses":66,"wins":94},"openai/gpt-oss-120b":{"draws":29,"losses":26,"wins":71},"poolside/laguna-s-2.1":{"draws":54,"losses":25,"wins":59},"qwen/qwen3.7-max":{"draws":31,"losses":18,"wins":35},"qwen/qwen3.7-plus":{"draws":25,"losses":7,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":49,"wins":60},"qwen/qwen3.8-27b":{"draws":23,"losses":29,"wins":50},"qwen/qwen3.8-flash":{"draws":31,"losses":24,"wins":41},"qwen/qwen3.8-max":{"draws":35,"losses":56,"wins":53},"qwen/qwen3.8-max-0902":{"draws":42,"losses":53,"wins":49},"recursive/flint-v1.0":{"draws":12,"losses":3,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":34,"losses":38,"wins":60},"stealth/ox-alpha":{"draws":100,"losses":188,"wins":186},"stealth/space-bunny-alpha":{"draws":24,"losses":28,"wins":62},"stepfun/step-3.7-flash":{"draws":20,"losses":16,"wins":66},"stepfun/step-5-preview":{"draws":9,"losses":20,"wins":17},"tencent/hy3-preview":{"draws":22,"losses":17,"wins":39},"tencent/hy4-preview":{"draws":39,"losses":58,"wins":41},"thinkingmachines/inkling":{"draws":61,"losses":31,"wins":100},"thinkingmachines/inkling-small":{"draws":37,"losses":25,"wins":82},"unbiased/pareto-26.10":{"draws":3,"losses":44,"wins":1},"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":67,"wins":46},"x-ai/grok-4.6":{"draws":36,"losses":61,"wins":47},"x-ai/grok-4.7":{"draws":12,"losses":82,"wins":32},"x-ai/grok-build-0.1":{"draws":17,"losses":5,"wins":26},"xiaomi/mimo-v2.5":{"draws":62,"losses":34,"wins":126},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":9,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":34,"wins":40},"xiaomi/mimo-v2.6-pro":{"draws":22,"losses":43,"wins":31},"z-ai/glm-5.2":{"draws":96,"losses":67,"wins":125},"z-ai/glm-5.3":{"draws":21,"losses":88,"wins":29},"z-ai/glm-5.3-flash":{"draws":25,"losses":61,"wins":58},"z-ai/glm-5.3-flashx":{"draws":24,"losses":68,"wins":52}},"deepseek/deepseek-v4.1-flash-1017":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":20,"wins":89},"claude-fable-5":{"draws":26,"losses":65,"wins":53},"claude-fable-5-1":{"draws":9,"losses":133,"wins":20},"claude-haiku-5-5":{"draws":25,"losses":52,"wins":61},"claude-opus-4-5":{"draws":44,"losses":52,"wins":138},"claude-opus-4-8":{"draws":24,"losses":42,"wins":66},"claude-opus-5":{"draws":35,"losses":158,"wins":53},"claude-opus-5-5":{"draws":10,"losses":128,"wins":18},"claude-sonnet-5":{"draws":31,"losses":32,"wins":81},"claude-sonnet-5-5":{"draws":24,"losses":60,"wins":60},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":47},"deepseek/deepseek-v4-flash":{"draws":40,"losses":26,"wins":150},"deepseek/deepseek-v4-pro":{"draws":28,"losses":25,"wins":79},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":32,"wins":76},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":41,"wins":70},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":41,"wins":41},"elorian/glimpse":{"draws":17,"losses":26,"wins":35},"fireworks/ember-1":{"draws":34,"losses":32,"wins":78},"gemini-3.1-pro-preview":{"draws":26,"losses":37,"wins":81},"gemini-4-argon":{"draws":18,"losses":107,"wins":19},"google/gemini-3.1-flash-lite":{"draws":14,"losses":4,"wins":78},"google/gemini-3.5-flash":{"draws":29,"losses":50,"wins":101},"google/gemini-3.5-flash-lite":{"draws":38,"losses":31,"wins":183},"google/gemini-3.6-flash":{"draws":42,"losses":101,"wins":133},"google/gemini-3.8-flash":{"draws":26,"losses":47,"wins":71},"google/gemma-4-31b-it":{"draws":16,"losses":7,"wins":61},"gpt-4.1":{"draws":11,"losses":7,"wins":30},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":10},"gpt-5":{"draws":25,"losses":28,"wins":73},"gpt-5.4":{"draws":26,"losses":49,"wins":63},"gpt-5.4-mini":{"draws":23,"losses":9,"wins":64},"gpt-5.4-nano":{"draws":21,"losses":27,"wins":96},"gpt-5.5":{"draws":39,"losses":43,"wins":50},"gpt-5.6-luna":{"draws":29,"losses":25,"wins":90},"gpt-5.6-sol":{"draws":26,"losses":67,"wins":51},"gpt-5.6-terra":{"draws":33,"losses":25,"wins":80},"gpt-6-astra":{"draws":11,"losses":123,"wins":10},"gpt-6-luna":{"draws":34,"losses":34,"wins":76},"gpt-6-sol":{"draws":15,"losses":89,"wins":40},"gpt-6.1-sol":{"draws":10,"losses":107,"wins":27},"gpt-6.1-terra":{"draws":17,"losses":100,"wins":27},"gpt-6.1-terra-pro":{"draws":17,"losses":109,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":6,"wins":66},"inception/mercury-3":{"draws":26,"losses":15,"wins":55},"inclusionai/ling-3.0-flash":{"draws":20,"losses":3,"wins":79},"inclusionai/ling-3.1-flash":{"draws":6,"losses":5,"wins":19},"meituan/longcat-2.0":{"draws":26,"losses":22,"wins":108},"meta/muse-glimmer-30b":{"draws":30,"losses":12,"wins":84},"meta/muse-spark-1.2":{"draws":26,"losses":44,"wins":68},"meta/muse-spark-1.3":{"draws":16,"losses":62,"wins":66},"meta/muse-spark-open":{"draws":31,"losses":38,"wins":75},"meta/muse-wonder":{"draws":32,"losses":57,"wins":55},"minimax/minimax-m3":{"draws":11,"losses":5,"wins":62},"minimax/minimax-m3.1-flash":{"draws":29,"losses":24,"wins":73},"mistralai/mistral-large-4-0":{"draws":16,"losses":23,"wins":51},"mistralai/mistral-medium-3-5":{"draws":16,"losses":5,"wins":63},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":18,"losses":39,"wins":81},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":102,"wins":29},"nex-agi/nex-n2-pro":{"draws":12,"losses":7,"wins":53},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":2,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":9,"wins":79},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":11,"wins":41},"o3":{"draws":18,"losses":56,"wins":124},"openai/gpt-oss-120b":{"draws":25,"losses":17,"wins":84},"poolside/laguna-s-2.1":{"draws":27,"losses":18,"wins":93},"qwen/qwen3.7-max":{"draws":15,"losses":11,"wins":58},"qwen/qwen3.7-plus":{"draws":13,"losses":9,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":43,"wins":73},"qwen/qwen3.8-27b":{"draws":15,"losses":26,"wins":61},"qwen/qwen3.8-flash":{"draws":21,"losses":24,"wins":51},"qwen/qwen3.8-max":{"draws":29,"losses":33,"wins":82},"qwen/qwen3.8-max-0902":{"draws":32,"losses":40,"wins":72},"recursive/flint-v1.0":{"draws":6,"losses":1,"wins":35},"reflection/beam-1.0-501b-a23b":{"draws":29,"losses":27,"wins":76},"stealth/ox-alpha":{"draws":79,"losses":163,"wins":232},"stealth/space-bunny-alpha":{"draws":20,"losses":18,"wins":76},"stepfun/step-3.7-flash":{"draws":13,"losses":15,"wins":74},"stepfun/step-5-preview":{"draws":2,"losses":12,"wins":14},"tencent/hy3-preview":{"draws":20,"losses":10,"wins":48},"tencent/hy4-preview":{"draws":24,"losses":43,"wins":71},"thinkingmachines/inkling":{"draws":46,"losses":25,"wins":121},"thinkingmachines/inkling-small":{"draws":25,"losses":14,"wins":105},"unbiased/pareto-26.10":{"draws":6,"losses":40,"wins":2},"unbiased/pareto-26.10-preview":{"draws":1,"losses":37,"wins":10},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":31},"x-ai/grok-4.5":{"draws":27,"losses":56,"wins":61},"x-ai/grok-4.6":{"draws":40,"losses":47,"wins":57},"x-ai/grok-4.7":{"draws":20,"losses":68,"wins":38},"x-ai/grok-build-0.1":{"draws":6,"losses":7,"wins":35},"xiaomi/mimo-v2.5":{"draws":47,"losses":16,"wins":159},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":5,"wins":39},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":22,"wins":53},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":44,"wins":42},"z-ai/glm-5.2":{"draws":62,"losses":53,"wins":173},"z-ai/glm-5.3":{"draws":24,"losses":73,"wins":41},"z-ai/glm-5.3-flash":{"draws":25,"losses":45,"wins":74},"z-ai/glm-5.3-flashx":{"draws":24,"losses":48,"wins":72}},"elorian/glimpse":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":22,"wins":34},"claude-fable-5":{"draws":11,"losses":39,"wins":28},"claude-fable-5-1":{"draws":7,"losses":74,"wins":9},"claude-haiku-5-5":{"draws":11,"losses":34,"wins":29},"claude-opus-4-5":{"draws":29,"losses":41,"wins":56},"claude-opus-4-8":{"draws":14,"losses":27,"wins":29},"claude-opus-5":{"draws":19,"losses":91,"wins":28},"claude-opus-5-5":{"draws":7,"losses":72,"wins":7},"claude-sonnet-5":{"draws":18,"losses":29,"wins":31},"claude-sonnet-5-5":{"draws":16,"losses":43,"wins":19},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":21},"deepseek/deepseek-v4-flash":{"draws":25,"losses":30,"wins":61},"deepseek/deepseek-v4-pro":{"draws":20,"losses":17,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":28,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":30,"wins":31},"deepseek/deepseek-v4.1-flash-1017":{"draws":17,"losses":35,"wins":26},"elorian/glimpse":{"draws":2,"losses":9,"wins":9},"fireworks/ember-1":{"draws":18,"losses":31,"wins":29},"gemini-3.1-pro-preview":{"draws":15,"losses":31,"wins":32},"gemini-4-argon":{"draws":8,"losses":59,"wins":11},"google/gemini-3.1-flash-lite":{"draws":13,"losses":7,"wins":30},"google/gemini-3.5-flash":{"draws":19,"losses":34,"wins":45},"google/gemini-3.5-flash-lite":{"draws":38,"losses":27,"wins":71},"google/gemini-3.6-flash":{"draws":30,"losses":62,"wins":58},"google/gemini-3.8-flash":{"draws":13,"losses":35,"wins":30},"google/gemma-4-31b-it":{"draws":12,"losses":9,"wins":23},"gpt-4.1":{"draws":6,"losses":8,"wins":12},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":22,"wins":34},"gpt-5.4":{"draws":18,"losses":32,"wins":26},"gpt-5.4-mini":{"draws":15,"losses":13,"wins":24},"gpt-5.4-nano":{"draws":13,"losses":22,"wins":39},"gpt-5.5":{"draws":17,"losses":33,"wins":24},"gpt-5.6-luna":{"draws":22,"losses":20,"wins":36},"gpt-5.6-sol":{"draws":10,"losses":46,"wins":22},"gpt-5.6-terra":{"draws":19,"losses":25,"wins":32},"gpt-6-astra":{"draws":6,"losses":65,"wins":7},"gpt-6-luna":{"draws":14,"losses":27,"wins":37},"gpt-6-sol":{"draws":10,"losses":53,"wins":15},"gpt-6.1-sol":{"draws":4,"losses":64,"wins":10},"gpt-6.1-terra":{"draws":5,"losses":59,"wins":14},"gpt-6.1-terra-pro":{"draws":10,"losses":61,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":5,"wins":32},"inception/mercury-3":{"draws":8,"losses":21,"wins":23},"inclusionai/ling-3.0-flash":{"draws":16,"losses":10,"wins":32},"inclusionai/ling-3.1-flash":{"draws":3,"losses":5,"wins":4},"meituan/longcat-2.0":{"draws":17,"losses":20,"wins":47},"meta/muse-glimmer-30b":{"draws":19,"losses":17,"wins":36},"meta/muse-spark-1.2":{"draws":16,"losses":35,"wins":25},"meta/muse-spark-1.3":{"draws":16,"losses":37,"wins":25},"meta/muse-spark-open":{"draws":13,"losses":28,"wins":35},"meta/muse-wonder":{"draws":15,"losses":42,"wins":21},"minimax/minimax-m3":{"draws":9,"losses":10,"wins":23},"minimax/minimax-m3.1-flash":{"draws":18,"losses":15,"wins":35},"mistralai/mistral-large-4-0":{"draws":12,"losses":21,"wins":17},"mistralai/mistral-medium-3-5":{"draws":9,"losses":7,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":19,"losses":26,"wins":31},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":56,"wins":15},"nex-agi/nex-n2-pro":{"draws":8,"losses":10,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":7,"wins":37},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":10,"wins":17},"o3":{"draws":14,"losses":36,"wins":56},"openai/gpt-oss-120b":{"draws":14,"losses":18,"wins":36},"poolside/laguna-s-2.1":{"draws":18,"losses":16,"wins":40},"qwen/qwen3.7-max":{"draws":8,"losses":14,"wins":22},"qwen/qwen3.7-plus":{"draws":8,"losses":7,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":29,"wins":29},"qwen/qwen3.8-27b":{"draws":11,"losses":21,"wins":22},"qwen/qwen3.8-flash":{"draws":13,"losses":17,"wins":22},"qwen/qwen3.8-max":{"draws":17,"losses":31,"wins":30},"qwen/qwen3.8-max-0902":{"draws":20,"losses":30,"wins":28},"recursive/flint-v1.0":{"draws":5,"losses":4,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":21,"wins":33},"stealth/ox-alpha":{"draws":65,"losses":107,"wins":94},"stealth/space-bunny-alpha":{"draws":13,"losses":18,"wins":31},"stepfun/step-3.7-flash":{"draws":5,"losses":13,"wins":38},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":12,"losses":11,"wins":19},"tencent/hy4-preview":{"draws":13,"losses":30,"wins":33},"thinkingmachines/inkling":{"draws":27,"losses":26,"wins":53},"thinkingmachines/inkling-small":{"draws":18,"losses":12,"wins":48},"unbiased/pareto-26.10":{"draws":1,"losses":25,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":2},"upstage/solar-mini4":{"draws":4,"losses":4,"wins":10},"x-ai/grok-4.5":{"draws":14,"losses":36,"wins":28},"x-ai/grok-4.6":{"draws":20,"losses":33,"wins":25},"x-ai/grok-4.7":{"draws":7,"losses":44,"wins":17},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":14},"xiaomi/mimo-v2.5":{"draws":34,"losses":20,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":9,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":26,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":22,"wins":22},"z-ai/glm-5.2":{"draws":35,"losses":49,"wins":72},"z-ai/glm-5.3":{"draws":13,"losses":46,"wins":15},"z-ai/glm-5.3-flash":{"draws":12,"losses":35,"wins":31},"z-ai/glm-5.3-flashx":{"draws":17,"losses":32,"wins":29}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":27,"wins":70},"claude-fable-5":{"draws":30,"losses":92,"wins":22},"claude-fable-5-1":{"draws":5,"losses":147,"wins":10},"claude-haiku-5-5":{"draws":37,"losses":63,"wins":38},"claude-opus-4-5":{"draws":78,"losses":66,"wins":90},"claude-opus-4-8":{"draws":41,"losses":54,"wins":37},"claude-opus-5":{"draws":27,"losses":179,"wins":40},"claude-opus-5-5":{"draws":8,"losses":136,"wins":12},"claude-sonnet-5":{"draws":37,"losses":45,"wins":62},"claude-sonnet-5-5":{"draws":28,"losses":72,"wins":44},"cohere/north-mini-code":{"draws":8,"losses":9,"wins":37},"deepseek/deepseek-v4-flash":{"draws":60,"losses":49,"wins":107},"deepseek/deepseek-v4-pro":{"draws":35,"losses":40,"wins":57},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":43,"wins":59},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":52,"wins":54},"deepseek/deepseek-v4.1-flash-1017":{"draws":34,"losses":78,"wins":32},"elorian/glimpse":{"draws":18,"losses":29,"wins":31},"fireworks/ember-1":{"draws":24,"losses":36,"wins":36},"gemini-3.1-pro-preview":{"draws":31,"losses":44,"wins":69},"gemini-4-argon":{"draws":10,"losses":118,"wins":16},"google/gemini-3.1-flash-lite":{"draws":19,"losses":6,"wins":71},"google/gemini-3.5-flash":{"draws":43,"losses":67,"wins":70},"google/gemini-3.5-flash-lite":{"draws":82,"losses":50,"wins":120},"google/gemini-3.6-flash":{"draws":76,"losses":97,"wins":103},"google/gemini-3.8-flash":{"draws":29,"losses":67,"wins":48},"google/gemma-4-31b-it":{"draws":31,"losses":12,"wins":41},"gpt-4.1":{"draws":13,"losses":14,"wins":21},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":9},"gpt-5":{"draws":30,"losses":35,"wins":61},"gpt-5.4":{"draws":34,"losses":65,"wins":39},"gpt-5.4-mini":{"draws":36,"losses":14,"wins":46},"gpt-5.4-nano":{"draws":30,"losses":33,"wins":81},"gpt-5.5":{"draws":38,"losses":50,"wins":44},"gpt-5.6-luna":{"draws":44,"losses":44,"wins":56},"gpt-5.6-sol":{"draws":22,"losses":87,"wins":35},"gpt-5.6-terra":{"draws":38,"losses":39,"wins":61},"gpt-6-astra":{"draws":10,"losses":129,"wins":5},"gpt-6-luna":{"draws":37,"losses":44,"wins":63},"gpt-6-sol":{"draws":20,"losses":101,"wins":23},"gpt-6.1-sol":{"draws":10,"losses":116,"wins":18},"gpt-6.1-terra":{"draws":11,"losses":116,"wins":17},"gpt-6.1-terra-pro":{"draws":18,"losses":113,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":38,"losses":8,"wins":56},"inception/mercury-3":{"draws":33,"losses":32,"wins":31},"inclusionai/ling-3.0-flash":{"draws":41,"losses":7,"wins":54},"inclusionai/ling-3.1-flash":{"draws":8,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":35,"losses":33,"wins":88},"meta/muse-glimmer-30b":{"draws":38,"losses":19,"wins":69},"meta/muse-spark-1.2":{"draws":35,"losses":49,"wins":54},"meta/muse-spark-1.3":{"draws":32,"losses":67,"wins":45},"meta/muse-spark-open":{"draws":34,"losses":60,"wins":50},"meta/muse-wonder":{"draws":38,"losses":76,"wins":30},"minimax/minimax-m3":{"draws":16,"losses":7,"wins":55},"minimax/minimax-m3.1-flash":{"draws":31,"losses":38,"wins":57},"mistralai/mistral-large-4-0":{"draws":26,"losses":33,"wins":31},"mistralai/mistral-medium-3-5":{"draws":23,"losses":9,"wins":52},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":5,"wins":0},"moonshotai/kimi-k3":{"draws":39,"losses":42,"wins":57},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":115,"wins":14},"nex-agi/nex-n2-pro":{"draws":19,"losses":9,"wins":44},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":5,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":21,"wins":62},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":19,"wins":29},"o3":{"draws":34,"losses":52,"wins":112},"openai/gpt-oss-120b":{"draws":40,"losses":20,"wins":66},"poolside/laguna-s-2.1":{"draws":44,"losses":28,"wins":66},"qwen/qwen3.7-max":{"draws":19,"losses":22,"wins":43},"qwen/qwen3.7-plus":{"draws":20,"losses":13,"wins":39},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":49,"wins":50},"qwen/qwen3.8-27b":{"draws":28,"losses":39,"wins":35},"qwen/qwen3.8-flash":{"draws":28,"losses":33,"wins":35},"qwen/qwen3.8-max":{"draws":36,"losses":48,"wins":60},"qwen/qwen3.8-max-0902":{"draws":36,"losses":63,"wins":45},"recursive/flint-v1.0":{"draws":10,"losses":5,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":36,"losses":51,"wins":45},"stealth/ox-alpha":{"draws":109,"losses":188,"wins":177},"stealth/space-bunny-alpha":{"draws":30,"losses":29,"wins":55},"stepfun/step-3.7-flash":{"draws":19,"losses":21,"wins":62},"stepfun/step-5-preview":{"draws":3,"losses":13,"wins":18},"tencent/hy3-preview":{"draws":26,"losses":16,"wins":36},"tencent/hy4-preview":{"draws":36,"losses":55,"wins":47},"thinkingmachines/inkling":{"draws":57,"losses":28,"wins":107},"thinkingmachines/inkling-small":{"draws":41,"losses":21,"wins":82},"unbiased/pareto-26.10":{"draws":2,"losses":45,"wins":1},"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":32,"losses":72,"wins":40},"x-ai/grok-4.6":{"draws":36,"losses":65,"wins":43},"x-ai/grok-4.7":{"draws":10,"losses":88,"wins":28},"x-ai/grok-build-0.1":{"draws":16,"losses":8,"wins":24},"xiaomi/mimo-v2.5":{"draws":69,"losses":38,"wins":115},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":13,"wins":31},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":42,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":46,"wins":29},"z-ai/glm-5.2":{"draws":81,"losses":77,"wins":130},"z-ai/glm-5.3":{"draws":23,"losses":89,"wins":26},"z-ai/glm-5.3-flash":{"draws":23,"losses":74,"wins":47},"z-ai/glm-5.3-flashx":{"draws":28,"losses":67,"wins":49}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":38,"wins":62},"claude-fable-5":{"draws":29,"losses":86,"wins":29},"claude-fable-5-1":{"draws":8,"losses":148,"wins":6},"claude-haiku-5-5":{"draws":34,"losses":58,"wins":46},"claude-opus-4-5":{"draws":58,"losses":103,"wins":73},"claude-opus-4-8":{"draws":29,"losses":65,"wins":38},"claude-opus-5":{"draws":26,"losses":189,"wins":31},"claude-opus-5-5":{"draws":9,"losses":138,"wins":9},"claude-sonnet-5":{"draws":36,"losses":58,"wins":50},"claude-sonnet-5-5":{"draws":21,"losses":81,"wins":42},"cohere/north-mini-code":{"draws":10,"losses":18,"wins":26},"deepseek/deepseek-v4-flash":{"draws":56,"losses":63,"wins":97},"deepseek/deepseek-v4-pro":{"draws":30,"losses":48,"wins":54},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":51,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":28,"losses":66,"wins":50},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":81,"wins":37},"elorian/glimpse":{"draws":15,"losses":32,"wins":31},"fireworks/ember-1":{"draws":31,"losses":69,"wins":44},"gemini-3.1-pro-preview":{"draws":20,"losses":38,"wins":38},"gemini-4-argon":{"draws":11,"losses":118,"wins":15},"google/gemini-3.1-flash-lite":{"draws":20,"losses":20,"wins":56},"google/gemini-3.5-flash":{"draws":33,"losses":85,"wins":62},"google/gemini-3.5-flash-lite":{"draws":79,"losses":64,"wins":109},"google/gemini-3.6-flash":{"draws":65,"losses":124,"wins":87},"google/gemini-3.8-flash":{"draws":27,"losses":82,"wins":35},"google/gemma-4-31b-it":{"draws":28,"losses":16,"wins":40},"gpt-4.1":{"draws":11,"losses":19,"wins":18},"gpt-4.1-nano":{"draws":11,"losses":3,"wins":4},"gpt-5":{"draws":36,"losses":36,"wins":54},"gpt-5.4":{"draws":30,"losses":67,"wins":41},"gpt-5.4-mini":{"draws":31,"losses":25,"wins":40},"gpt-5.4-nano":{"draws":31,"losses":40,"wins":73},"gpt-5.5":{"draws":31,"losses":65,"wins":36},"gpt-5.6-luna":{"draws":36,"losses":52,"wins":56},"gpt-5.6-sol":{"draws":16,"losses":94,"wins":34},"gpt-5.6-terra":{"draws":44,"losses":48,"wins":46},"gpt-6-astra":{"draws":7,"losses":133,"wins":4},"gpt-6-luna":{"draws":34,"losses":51,"wins":59},"gpt-6-sol":{"draws":14,"losses":102,"wins":28},"gpt-6.1-sol":{"draws":3,"losses":128,"wins":13},"gpt-6.1-terra":{"draws":16,"losses":114,"wins":14},"gpt-6.1-terra-pro":{"draws":7,"losses":120,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":36,"losses":24,"wins":42},"inception/mercury-3":{"draws":32,"losses":41,"wins":25},"inclusionai/ling-3.0-flash":{"draws":34,"losses":18,"wins":50},"inclusionai/ling-3.1-flash":{"draws":5,"losses":6,"wins":5},"meituan/longcat-2.0":{"draws":33,"losses":51,"wins":72},"meta/muse-glimmer-30b":{"draws":44,"losses":21,"wins":61},"meta/muse-spark-1.2":{"draws":31,"losses":58,"wins":49},"meta/muse-spark-1.3":{"draws":22,"losses":83,"wins":39},"meta/muse-spark-open":{"draws":33,"losses":69,"wins":40},"meta/muse-wonder":{"draws":21,"losses":97,"wins":26},"minimax/minimax-m3":{"draws":15,"losses":23,"wins":40},"minimax/minimax-m3.1-flash":{"draws":34,"losses":43,"wins":49},"mistralai/mistral-large-4-0":{"draws":21,"losses":35,"wins":34},"mistralai/mistral-medium-3-5":{"draws":25,"losses":13,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":1},"moonshotai/kimi-k3":{"draws":34,"losses":65,"wins":39},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":105,"wins":24},"nex-agi/nex-n2-pro":{"draws":19,"losses":11,"wins":42},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":8,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":32,"wins":53},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":25,"wins":26},"o3":{"draws":28,"losses":91,"wins":79},"openai/gpt-oss-120b":{"draws":34,"losses":33,"wins":59},"poolside/laguna-s-2.1":{"draws":42,"losses":35,"wins":61},"qwen/qwen3.7-max":{"draws":21,"losses":29,"wins":34},"qwen/qwen3.7-plus":{"draws":24,"losses":14,"wins":34},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":67,"wins":43},"qwen/qwen3.8-27b":{"draws":22,"losses":48,"wins":32},"qwen/qwen3.8-flash":{"draws":30,"losses":35,"wins":31},"qwen/qwen3.8-max":{"draws":36,"losses":61,"wins":47},"qwen/qwen3.8-max-0902":{"draws":31,"losses":72,"wins":41},"recursive/flint-v1.0":{"draws":11,"losses":4,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":31,"losses":53,"wins":48},"stealth/ox-alpha":{"draws":93,"losses":234,"wins":147},"stealth/space-bunny-alpha":{"draws":25,"losses":41,"wins":48},"stepfun/step-3.7-flash":{"draws":20,"losses":33,"wins":49},"stepfun/step-5-preview":{"draws":5,"losses":11,"wins":14},"tencent/hy3-preview":{"draws":19,"losses":25,"wins":34},"tencent/hy4-preview":{"draws":30,"losses":64,"wins":44},"thinkingmachines/inkling":{"draws":59,"losses":48,"wins":85},"thinkingmachines/inkling-small":{"draws":37,"losses":29,"wins":78},"unbiased/pareto-26.10":{"draws":3,"losses":42,"wins":3},"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":30,"losses":70,"wins":44},"x-ai/grok-4.6":{"draws":34,"losses":80,"wins":30},"x-ai/grok-4.7":{"draws":12,"losses":89,"wins":25},"x-ai/grok-build-0.1":{"draws":12,"losses":14,"wins":22},"xiaomi/mimo-v2.5":{"draws":65,"losses":61,"wins":96},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":18,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":49,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":57,"wins":24},"z-ai/glm-5.2":{"draws":74,"losses":98,"wins":116},"z-ai/glm-5.3":{"draws":24,"losses":87,"wins":27},"z-ai/glm-5.3-flash":{"draws":30,"losses":73,"wins":41},"z-ai/glm-5.3-flashx":{"draws":28,"losses":75,"wins":41}},"gemini-4-argon":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":6,"wins":123},"claude-fable-5":{"draws":13,"losses":30,"wins":101},"claude-fable-5-1":{"draws":14,"losses":95,"wins":53},"claude-haiku-5-5":{"draws":14,"losses":26,"wins":98},"claude-opus-4-5":{"draws":9,"losses":18,"wins":207},"claude-opus-4-8":{"draws":9,"losses":25,"wins":98},"claude-opus-5":{"draws":30,"losses":102,"wins":114},"claude-opus-5-5":{"draws":9,"losses":100,"wins":47},"claude-sonnet-5":{"draws":12,"losses":8,"wins":124},"claude-sonnet-5-5":{"draws":12,"losses":44,"wins":88},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":52},"deepseek/deepseek-v4-flash":{"draws":13,"losses":4,"wins":199},"deepseek/deepseek-v4-pro":{"draws":14,"losses":14,"wins":104},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":8,"wins":111},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":18,"wins":114},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":19,"wins":107},"elorian/glimpse":{"draws":8,"losses":11,"wins":59},"fireworks/ember-1":{"draws":10,"losses":16,"wins":118},"gemini-3.1-pro-preview":{"draws":11,"losses":15,"wins":118},"gemini-4-argon":{"draws":14,"losses":41,"wins":41},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":92},"google/gemini-3.5-flash":{"draws":12,"losses":8,"wins":160},"google/gemini-3.5-flash-lite":{"draws":14,"losses":11,"wins":227},"google/gemini-3.6-flash":{"draws":18,"losses":32,"wins":226},"google/gemini-3.8-flash":{"draws":15,"losses":21,"wins":108},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":80},"gpt-4.1":{"draws":5,"losses":0,"wins":43},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":18},"gpt-5":{"draws":4,"losses":9,"wins":113},"gpt-5.4":{"draws":13,"losses":22,"wins":103},"gpt-5.4-mini":{"draws":13,"losses":0,"wins":83},"gpt-5.4-nano":{"draws":2,"losses":8,"wins":134},"gpt-5.5":{"draws":9,"losses":23,"wins":100},"gpt-5.6-luna":{"draws":13,"losses":8,"wins":123},"gpt-5.6-sol":{"draws":11,"losses":33,"wins":100},"gpt-5.6-terra":{"draws":14,"losses":8,"wins":116},"gpt-6-astra":{"draws":17,"losses":87,"wins":40},"gpt-6-luna":{"draws":10,"losses":8,"wins":126},"gpt-6-sol":{"draws":14,"losses":58,"wins":72},"gpt-6.1-sol":{"draws":19,"losses":79,"wins":46},"gpt-6.1-terra":{"draws":25,"losses":67,"wins":52},"gpt-6.1-terra-pro":{"draws":19,"losses":74,"wins":51},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":94},"inception/mercury-3":{"draws":11,"losses":8,"wins":77},"inclusionai/ling-3.0-flash":{"draws":7,"losses":4,"wins":91},"inclusionai/ling-3.1-flash":{"draws":1,"losses":2,"wins":23},"meituan/longcat-2.0":{"draws":8,"losses":10,"wins":138},"meta/muse-glimmer-30b":{"draws":13,"losses":4,"wins":109},"meta/muse-spark-1.2":{"draws":10,"losses":14,"wins":114},"meta/muse-spark-1.3":{"draws":12,"losses":19,"wins":113},"meta/muse-spark-open":{"draws":14,"losses":22,"wins":106},"meta/muse-wonder":{"draws":17,"losses":32,"wins":95},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":75},"minimax/minimax-m3.1-flash":{"draws":15,"losses":10,"wins":101},"mistralai/mistral-large-4-0":{"draws":8,"losses":9,"wins":73},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":79},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":10},"moonshotai/kimi-k3":{"draws":6,"losses":15,"wins":117},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":57,"wins":72},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":59},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":1,"wins":101},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":55},"o3":{"draws":2,"losses":9,"wins":187},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":121},"poolside/laguna-s-2.1":{"draws":8,"losses":3,"wins":127},"qwen/qwen3.7-max":{"draws":4,"losses":7,"wins":73},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":68},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":23,"wins":112},"qwen/qwen3.8-27b":{"draws":7,"losses":7,"wins":88},"qwen/qwen3.8-flash":{"draws":12,"losses":11,"wins":73},"qwen/qwen3.8-max":{"draws":9,"losses":12,"wins":123},"qwen/qwen3.8-max-0902":{"draws":12,"losses":14,"wins":118},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":39},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":13,"wins":112},"stealth/ox-alpha":{"draws":45,"losses":49,"wins":380},"stealth/space-bunny-alpha":{"draws":7,"losses":4,"wins":103},"stepfun/step-3.7-flash":{"draws":0,"losses":4,"wins":98},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":27},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":71},"tencent/hy4-preview":{"draws":15,"losses":18,"wins":105},"thinkingmachines/inkling":{"draws":17,"losses":11,"wins":164},"thinkingmachines/inkling-small":{"draws":16,"losses":4,"wins":124},"unbiased/pareto-26.10":{"draws":4,"losses":31,"wins":13},"unbiased/pareto-26.10-preview":{"draws":3,"losses":27,"wins":18},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":33},"x-ai/grok-4.5":{"draws":10,"losses":26,"wins":108},"x-ai/grok-4.6":{"draws":19,"losses":20,"wins":105},"x-ai/grok-4.7":{"draws":16,"losses":40,"wins":70},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":44},"xiaomi/mimo-v2.5":{"draws":16,"losses":1,"wins":205},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":1,"wins":59},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":8,"wins":79},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":23,"wins":64},"z-ai/glm-5.2":{"draws":27,"losses":14,"wins":247},"z-ai/glm-5.3":{"draws":15,"losses":40,"wins":83},"z-ai/glm-5.3-flash":{"draws":15,"losses":19,"wins":110},"z-ai/glm-5.3-flashx":{"draws":12,"losses":22,"wins":110}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":47,"wins":19},"claude-fable-5":{"draws":9,"losses":83,"wins":4},"claude-fable-5-1":{"draws":7,"losses":99,"wins":0},"claude-haiku-5-5":{"draws":20,"losses":68,"wins":8},"claude-opus-4-5":{"draws":35,"losses":118,"wins":7},"claude-opus-4-8":{"draws":19,"losses":70,"wins":7},"claude-opus-5":{"draws":18,"losses":127,"wins":5},"claude-opus-5-5":{"draws":8,"losses":96,"wins":0},"claude-sonnet-5":{"draws":26,"losses":65,"wins":5},"claude-sonnet-5-5":{"draws":15,"losses":69,"wins":12},"cohere/north-mini-code":{"draws":6,"losses":22,"wins":14},"deepseek/deepseek-v4-flash":{"draws":32,"losses":84,"wins":30},"deepseek/deepseek-v4-pro":{"draws":23,"losses":60,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":56,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":58,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":78,"wins":4},"elorian/glimpse":{"draws":13,"losses":30,"wins":7},"fireworks/ember-1":{"draws":19,"losses":71,"wins":6},"gemini-3.1-pro-preview":{"draws":20,"losses":56,"wins":20},"gemini-4-argon":{"draws":4,"losses":92,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":22,"wins":22},"google/gemini-3.5-flash":{"draws":26,"losses":86,"wins":14},"google/gemini-3.5-flash-lite":{"draws":39,"losses":91,"wins":44},"google/gemini-3.6-flash":{"draws":35,"losses":133,"wins":18},"google/gemini-3.8-flash":{"draws":18,"losses":75,"wins":3},"google/gemma-4-31b-it":{"draws":19,"losses":26,"wins":15},"gpt-4.1":{"draws":9,"losses":19,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":4},"gpt-5":{"draws":14,"losses":60,"wins":10},"gpt-5.4":{"draws":15,"losses":70,"wins":9},"gpt-5.4-mini":{"draws":15,"losses":40,"wins":9},"gpt-5.4-nano":{"draws":21,"losses":65,"wins":22},"gpt-5.5":{"draws":20,"losses":64,"wins":4},"gpt-5.6-luna":{"draws":18,"losses":57,"wins":21},"gpt-5.6-sol":{"draws":9,"losses":84,"wins":3},"gpt-5.6-terra":{"draws":22,"losses":63,"wins":5},"gpt-6-astra":{"draws":2,"losses":94,"wins":0},"gpt-6-luna":{"draws":23,"losses":60,"wins":13},"gpt-6-sol":{"draws":14,"losses":80,"wins":2},"gpt-6.1-sol":{"draws":4,"losses":92,"wins":0},"gpt-6.1-terra":{"draws":5,"losses":91,"wins":0},"gpt-6.1-terra-pro":{"draws":6,"losses":90,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":22,"losses":29,"wins":21},"inception/mercury-3":{"draws":13,"losses":40,"wins":7},"inclusionai/ling-3.0-flash":{"draws":20,"losses":24,"wins":22},"inclusionai/ling-3.1-flash":{"draws":7,"losses":5,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":67,"wins":32},"meta/muse-glimmer-30b":{"draws":26,"losses":35,"wins":21},"meta/muse-spark-1.2":{"draws":22,"losses":60,"wins":8},"meta/muse-spark-1.3":{"draws":12,"losses":79,"wins":5},"meta/muse-spark-open":{"draws":17,"losses":73,"wins":6},"meta/muse-wonder":{"draws":9,"losses":83,"wins":4},"minimax/minimax-m3":{"draws":13,"losses":24,"wins":17},"minimax/minimax-m3.1-flash":{"draws":17,"losses":59,"wins":10},"mistralai/mistral-large-4-0":{"draws":19,"losses":37,"wins":2},"mistralai/mistral-medium-3-5":{"draws":15,"losses":25,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":25,"losses":56,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":91,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":30,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":14,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":40,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":31,"wins":6},"o3":{"draws":18,"losses":125,"wins":15},"openai/gpt-oss-120b":{"draws":17,"losses":42,"wins":23},"poolside/laguna-s-2.1":{"draws":24,"losses":40,"wins":22},"qwen/qwen3.7-max":{"draws":14,"losses":37,"wins":9},"qwen/qwen3.7-plus":{"draws":11,"losses":32,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":65,"wins":7},"qwen/qwen3.8-27b":{"draws":14,"losses":48,"wins":8},"qwen/qwen3.8-flash":{"draws":17,"losses":37,"wins":10},"qwen/qwen3.8-max":{"draws":23,"losses":72,"wins":1},"qwen/qwen3.8-max-0902":{"draws":24,"losses":69,"wins":3},"recursive/flint-v1.0":{"draws":8,"losses":12,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":65,"wins":7},"stealth/ox-alpha":{"draws":46,"losses":196,"wins":30},"stealth/space-bunny-alpha":{"draws":17,"losses":50,"wins":13},"stepfun/step-3.7-flash":{"draws":13,"losses":48,"wins":13},"stepfun/step-5-preview":{"draws":3,"losses":15,"wins":4},"tencent/hy3-preview":{"draws":16,"losses":22,"wins":14},"tencent/hy4-preview":{"draws":19,"losses":69,"wins":6},"thinkingmachines/inkling":{"draws":33,"losses":58,"wins":35},"thinkingmachines/inkling-small":{"draws":26,"losses":37,"wins":33},"unbiased/pareto-26.10":{"draws":1,"losses":31,"wins":0},"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":17,"losses":77,"wins":2},"x-ai/grok-4.6":{"draws":17,"losses":75,"wins":4},"x-ai/grok-4.7":{"draws":5,"losses":78,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":19,"wins":5},"xiaomi/mimo-v2.5":{"draws":45,"losses":77,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":29,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":49,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":50,"wins":4},"z-ai/glm-5.2":{"draws":39,"losses":127,"wins":26},"z-ai/glm-5.3":{"draws":9,"losses":83,"wins":0},"z-ai/glm-5.3-flash":{"draws":17,"losses":65,"wins":14},"z-ai/glm-5.3-flashx":{"draws":21,"losses":66,"wins":9}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":46,"wins":85},"claude-fable-5":{"draws":28,"losses":119,"wins":33},"claude-fable-5-1":{"draws":11,"losses":184,"wins":7},"claude-haiku-5-5":{"draws":36,"losses":79,"wins":59},"claude-opus-4-5":{"draws":72,"losses":106,"wins":116},"claude-opus-4-8":{"draws":36,"losses":81,"wins":51},"claude-opus-5":{"draws":35,"losses":235,"wins":34},"claude-opus-5-5":{"draws":11,"losses":176,"wins":9},"claude-sonnet-5":{"draws":44,"losses":57,"wins":79},"claude-sonnet-5-5":{"draws":32,"losses":101,"wins":47},"cohere/north-mini-code":{"draws":14,"losses":12,"wins":44},"deepseek/deepseek-v4-flash":{"draws":55,"losses":71,"wins":144},"deepseek/deepseek-v4-pro":{"draws":37,"losses":57,"wins":72},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":53,"wins":76},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":80,"wins":60},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":101,"wins":50},"elorian/glimpse":{"draws":19,"losses":45,"wins":34},"fireworks/ember-1":{"draws":43,"losses":70,"wins":67},"gemini-3.1-pro-preview":{"draws":33,"losses":62,"wins":85},"gemini-4-argon":{"draws":12,"losses":160,"wins":8},"google/gemini-3.1-flash-lite":{"draws":26,"losses":14,"wins":86},"google/gemini-3.5-flash":{"draws":28,"losses":70,"wins":70},"google/gemini-3.5-flash-lite":{"draws":66,"losses":82,"wins":170},"google/gemini-3.6-flash":{"draws":65,"losses":147,"wins":134},"google/gemini-3.8-flash":{"draws":31,"losses":105,"wins":44},"google/gemma-4-31b-it":{"draws":34,"losses":20,"wins":52},"gpt-4.1":{"draws":13,"losses":17,"wins":30},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":10},"gpt-5":{"draws":32,"losses":53,"wins":73},"gpt-5.4":{"draws":21,"losses":98,"wins":55},"gpt-5.4-mini":{"draws":31,"losses":32,"wins":57},"gpt-5.4-nano":{"draws":23,"losses":50,"wins":111},"gpt-5.5":{"draws":42,"losses":76,"wins":48},"gpt-5.6-luna":{"draws":46,"losses":53,"wins":81},"gpt-5.6-sol":{"draws":18,"losses":124,"wins":38},"gpt-5.6-terra":{"draws":41,"losses":73,"wins":58},"gpt-6-astra":{"draws":7,"losses":165,"wins":8},"gpt-6-luna":{"draws":49,"losses":64,"wins":67},"gpt-6-sol":{"draws":22,"losses":127,"wins":31},"gpt-6.1-sol":{"draws":7,"losses":154,"wins":19},"gpt-6.1-terra":{"draws":14,"losses":148,"wins":18},"gpt-6.1-terra-pro":{"draws":9,"losses":156,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":42,"losses":21,"wins":65},"inception/mercury-3":{"draws":27,"losses":48,"wins":43},"inclusionai/ling-3.0-flash":{"draws":35,"losses":16,"wins":77},"inclusionai/ling-3.1-flash":{"draws":8,"losses":8,"wins":16},"meituan/longcat-2.0":{"draws":35,"losses":43,"wins":120},"meta/muse-glimmer-30b":{"draws":39,"losses":29,"wins":90},"meta/muse-spark-1.2":{"draws":32,"losses":82,"wins":58},"meta/muse-spark-1.3":{"draws":30,"losses":102,"wins":48},"meta/muse-spark-open":{"draws":32,"losses":94,"wins":54},"meta/muse-wonder":{"draws":29,"losses":122,"wins":29},"minimax/minimax-m3":{"draws":18,"losses":25,"wins":55},"minimax/minimax-m3.1-flash":{"draws":32,"losses":53,"wins":73},"mistralai/mistral-large-4-0":{"draws":35,"losses":40,"wins":37},"mistralai/mistral-medium-3-5":{"draws":24,"losses":16,"wins":64},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":47,"losses":67,"wins":58},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":148,"wins":20},"nex-agi/nex-n2-pro":{"draws":17,"losses":20,"wins":53},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":14,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":36,"wins":69},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":31,"wins":35},"o3":{"draws":31,"losses":89,"wins":138},"openai/gpt-oss-120b":{"draws":35,"losses":38,"wins":83},"poolside/laguna-s-2.1":{"draws":29,"losses":34,"wins":107},"qwen/qwen3.7-max":{"draws":24,"losses":40,"wins":42},"qwen/qwen3.7-plus":{"draws":17,"losses":19,"wins":56},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":78,"wins":54},"qwen/qwen3.8-27b":{"draws":20,"losses":51,"wins":57},"qwen/qwen3.8-flash":{"draws":25,"losses":42,"wins":53},"qwen/qwen3.8-max":{"draws":46,"losses":68,"wins":66},"qwen/qwen3.8-max-0902":{"draws":42,"losses":92,"wins":46},"recursive/flint-v1.0":{"draws":10,"losses":8,"wins":36},"reflection/beam-1.0-501b-a23b":{"draws":41,"losses":68,"wins":55},"stealth/ox-alpha":{"draws":90,"losses":279,"wins":207},"stealth/space-bunny-alpha":{"draws":38,"losses":39,"wins":67},"stepfun/step-3.7-flash":{"draws":23,"losses":27,"wins":80},"stepfun/step-5-preview":{"draws":4,"losses":15,"wins":25},"tencent/hy3-preview":{"draws":25,"losses":30,"wins":43},"tencent/hy4-preview":{"draws":34,"losses":84,"wins":56},"thinkingmachines/inkling":{"draws":47,"losses":49,"wins":144},"thinkingmachines/inkling-small":{"draws":41,"losses":35,"wins":104},"unbiased/pareto-26.10":{"draws":7,"losses":50,"wins":3},"unbiased/pareto-26.10-preview":{"draws":2,"losses":53,"wins":5},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":29},"x-ai/grok-4.5":{"draws":33,"losses":86,"wins":61},"x-ai/grok-4.6":{"draws":40,"losses":101,"wins":39},"x-ai/grok-4.7":{"draws":17,"losses":118,"wins":23},"x-ai/grok-build-0.1":{"draws":13,"losses":9,"wins":38},"xiaomi/mimo-v2.5":{"draws":70,"losses":59,"wins":155},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":28,"wins":52},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":55,"wins":43},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":64,"wins":37},"z-ai/glm-5.2":{"draws":82,"losses":118,"wins":160},"z-ai/glm-5.3":{"draws":28,"losses":109,"wins":35},"z-ai/glm-5.3-flash":{"draws":21,"losses":102,"wins":57},"z-ai/glm-5.3-flashx":{"draws":33,"losses":95,"wins":52}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":71,"losses":87,"wins":76},"claude-fable-5":{"draws":38,"losses":186,"wins":28},"claude-fable-5-1":{"draws":16,"losses":265,"wins":3},"claude-haiku-5-5":{"draws":51,"losses":151,"wins":40},"claude-opus-4-5":{"draws":121,"losses":199,"wins":90},"claude-opus-4-8":{"draws":53,"losses":151,"wins":28},"claude-opus-5":{"draws":51,"losses":339,"wins":34},"claude-opus-5-5":{"draws":17,"losses":254,"wins":1},"claude-sonnet-5":{"draws":61,"losses":135,"wins":56},"claude-sonnet-5-5":{"draws":47,"losses":166,"wins":39},"cohere/north-mini-code":{"draws":28,"losses":35,"wins":35},"deepseek/deepseek-v4-flash":{"draws":87,"losses":153,"wins":134},"deepseek/deepseek-v4-pro":{"draws":55,"losses":105,"wins":72},"deepseek/deepseek-v4-pro-0813":{"draws":63,"losses":119,"wins":50},"deepseek/deepseek-v4.1-flash":{"draws":70,"losses":128,"wins":54},"deepseek/deepseek-v4.1-flash-1017":{"draws":38,"losses":183,"wins":31},"elorian/glimpse":{"draws":38,"losses":71,"wins":27},"fireworks/ember-1":{"draws":82,"losses":120,"wins":50},"gemini-3.1-pro-preview":{"draws":79,"losses":109,"wins":64},"gemini-4-argon":{"draws":14,"losses":227,"wins":11},"google/gemini-3.1-flash-lite":{"draws":39,"losses":44,"wins":91},"google/gemini-3.5-flash":{"draws":66,"losses":170,"wins":82},"google/gemini-3.5-flash-lite":{"draws":90,"losses":137,"wins":137},"google/gemini-3.6-flash":{"draws":111,"losses":270,"wins":105},"google/gemini-3.8-flash":{"draws":43,"losses":187,"wins":22},"google/gemma-4-31b-it":{"draws":57,"losses":33,"wins":58},"gpt-4.1":{"draws":23,"losses":33,"wins":28},"gpt-4.1-nano":{"draws":17,"losses":3,"wins":10},"gpt-5":{"draws":50,"losses":106,"wins":64},"gpt-5.4":{"draws":53,"losses":145,"wins":46},"gpt-5.4-mini":{"draws":51,"losses":65,"wins":52},"gpt-5.4-nano":{"draws":45,"losses":97,"wins":110},"gpt-5.5":{"draws":78,"losses":118,"wins":36},"gpt-5.6-luna":{"draws":65,"losses":110,"wins":77},"gpt-5.6-sol":{"draws":34,"losses":195,"wins":23},"gpt-5.6-terra":{"draws":60,"losses":129,"wins":51},"gpt-6-astra":{"draws":14,"losses":238,"wins":0},"gpt-6-luna":{"draws":73,"losses":116,"wins":63},"gpt-6-sol":{"draws":36,"losses":193,"wins":23},"gpt-6.1-sol":{"draws":15,"losses":235,"wins":2},"gpt-6.1-terra":{"draws":23,"losses":225,"wins":4},"gpt-6.1-terra-pro":{"draws":14,"losses":228,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":64,"losses":45,"wins":71},"inception/mercury-3":{"draws":47,"losses":84,"wins":31},"inclusionai/ling-3.0-flash":{"draws":56,"losses":42,"wins":78},"inclusionai/ling-3.1-flash":{"draws":16,"losses":25,"wins":9},"meituan/longcat-2.0":{"draws":65,"losses":103,"wins":110},"meta/muse-glimmer-30b":{"draws":67,"losses":67,"wins":86},"meta/muse-spark-1.2":{"draws":62,"losses":130,"wins":48},"meta/muse-spark-1.3":{"draws":46,"losses":167,"wins":39},"meta/muse-spark-open":{"draws":48,"losses":164,"wins":40},"meta/muse-wonder":{"draws":44,"losses":180,"wins":28},"minimax/minimax-m3":{"draws":33,"losses":47,"wins":54},"minimax/minimax-m3.1-flash":{"draws":54,"losses":101,"wins":69},"mistralai/mistral-large-4-0":{"draws":52,"losses":75,"wins":29},"mistralai/mistral-medium-3-5":{"draws":40,"losses":39,"wins":69},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":9,"wins":2},"moonshotai/kimi-k3":{"draws":75,"losses":119,"wins":46},"moonshotai/kimi-k3.1-pro":{"draws":31,"losses":209,"wins":12},"nex-agi/nex-n2-pro":{"draws":24,"losses":47,"wins":57},"nex-agi/nex-n2.5-pro":{"draws":13,"losses":17,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":51,"losses":66,"wins":65},"nvidia/nemotron-3.5-super-vl":{"draws":36,"losses":55,"wins":25},"o3":{"draws":53,"losses":204,"wins":99},"openai/gpt-oss-120b":{"draws":60,"losses":80,"wins":78},"poolside/laguna-s-2.1":{"draws":57,"losses":108,"wins":73},"qwen/qwen3.7-max":{"draws":32,"losses":69,"wins":45},"qwen/qwen3.7-plus":{"draws":31,"losses":40,"wins":55},"qwen/qwen3.8-2.4t-a95b":{"draws":77,"losses":134,"wins":41},"qwen/qwen3.8-27b":{"draws":34,"losses":102,"wins":44},"qwen/qwen3.8-flash":{"draws":47,"losses":85,"wins":36},"qwen/qwen3.8-max":{"draws":64,"losses":137,"wins":51},"qwen/qwen3.8-max-0902":{"draws":67,"losses":148,"wins":37},"recursive/flint-v1.0":{"draws":20,"losses":12,"wins":42},"reflection/beam-1.0-501b-a23b":{"draws":63,"losses":120,"wins":47},"stealth/ox-alpha":{"draws":167,"losses":488,"wins":171},"stealth/space-bunny-alpha":{"draws":52,"losses":89,"wins":61},"stepfun/step-3.7-flash":{"draws":43,"losses":58,"wins":79},"stepfun/step-5-preview":{"draws":10,"losses":33,"wins":19},"tencent/hy3-preview":{"draws":46,"losses":62,"wins":28},"tencent/hy4-preview":{"draws":60,"losses":132,"wins":52},"thinkingmachines/inkling":{"draws":86,"losses":112,"wins":140},"thinkingmachines/inkling-small":{"draws":65,"losses":79,"wins":108},"unbiased/pareto-26.10":{"draws":5,"losses":79,"wins":0},"unbiased/pareto-26.10-preview":{"draws":3,"losses":81,"wins":0},"upstage/solar-mini4":{"draws":19,"losses":25,"wins":24},"x-ai/grok-4.5":{"draws":60,"losses":145,"wins":47},"x-ai/grok-4.6":{"draws":56,"losses":163,"wins":33},"x-ai/grok-4.7":{"draws":21,"losses":170,"wins":27},"x-ai/grok-build-0.1":{"draws":26,"losses":29,"wins":29},"xiaomi/mimo-v2.5":{"draws":109,"losses":144,"wins":139},"xiaomi/mimo-v2.5-pro":{"draws":30,"losses":36,"wins":60},"xiaomi/mimo-v2.6-flash":{"draws":23,"losses":113,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":117,"wins":30},"z-ai/glm-5.2":{"draws":140,"losses":215,"wins":149},"z-ai/glm-5.3":{"draws":36,"losses":193,"wins":13},"z-ai/glm-5.3-flash":{"draws":45,"losses":159,"wins":48},"z-ai/glm-5.3-flashx":{"draws":58,"losses":147,"wins":47}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":53,"losses":59,"wins":142},"claude-fable-5":{"draws":41,"losses":156,"wins":79},"claude-fable-5-1":{"draws":16,"losses":277,"wins":19},"claude-haiku-5-5":{"draws":62,"losses":102,"wins":100},"claude-opus-4-5":{"draws":115,"losses":125,"wins":208},"claude-opus-4-8":{"draws":52,"losses":94,"wins":106},"claude-opus-5":{"draws":59,"losses":316,"wins":93},"claude-opus-5-5":{"draws":20,"losses":251,"wins":25},"claude-sonnet-5":{"draws":64,"losses":91,"wins":121},"claude-sonnet-5-5":{"draws":52,"losses":130,"wins":94},"cohere/north-mini-code":{"draws":17,"losses":8,"wins":79},"deepseek/deepseek-v4-flash":{"draws":88,"losses":68,"wins":256},"deepseek/deepseek-v4-pro":{"draws":61,"losses":83,"wins":110},"deepseek/deepseek-v4-pro-0813":{"draws":48,"losses":82,"wins":124},"deepseek/deepseek-v4.1-flash":{"draws":72,"losses":90,"wins":114},"deepseek/deepseek-v4.1-flash-1017":{"draws":42,"losses":133,"wins":101},"elorian/glimpse":{"draws":30,"losses":58,"wins":62},"fireworks/ember-1":{"draws":76,"losses":103,"wins":97},"gemini-3.1-pro-preview":{"draws":65,"losses":87,"wins":124},"gemini-4-argon":{"draws":18,"losses":226,"wins":32},"google/gemini-3.1-flash-lite":{"draws":35,"losses":18,"wins":133},"google/gemini-3.5-flash":{"draws":65,"losses":134,"wins":147},"google/gemini-3.5-flash-lite":{"draws":111,"losses":105,"wins":270},"google/gemini-3.6-flash":{"draws":96,"losses":172,"wins":172},"google/gemini-3.8-flash":{"draws":53,"losses":138,"wins":85},"google/gemma-4-31b-it":{"draws":49,"losses":19,"wins":92},"gpt-4.1":{"draws":23,"losses":19,"wins":50},"gpt-4.1-nano":{"draws":14,"losses":2,"wins":18},"gpt-5":{"draws":45,"losses":81,"wins":116},"gpt-5.4":{"draws":49,"losses":111,"wins":106},"gpt-5.4-mini":{"draws":50,"losses":33,"wins":101},"gpt-5.4-nano":{"draws":44,"losses":63,"wins":167},"gpt-5.5":{"draws":65,"losses":103,"wins":86},"gpt-5.6-luna":{"draws":69,"losses":61,"wins":146},"gpt-5.6-sol":{"draws":33,"losses":168,"wins":75},"gpt-5.6-terra":{"draws":65,"losses":67,"wins":132},"gpt-6-astra":{"draws":19,"losses":239,"wins":18},"gpt-6-luna":{"draws":74,"losses":78,"wins":124},"gpt-6-sol":{"draws":34,"losses":180,"wins":62},"gpt-6.1-sol":{"draws":18,"losses":237,"wins":21},"gpt-6.1-terra":{"draws":28,"losses":223,"wins":25},"gpt-6.1-terra-pro":{"draws":24,"losses":219,"wins":33},"ibm-granite/granite-4.2-8b":{"draws":11,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":60,"losses":16,"wins":118},"inception/mercury-3":{"draws":45,"losses":48,"wins":87},"inclusionai/ling-3.0-flash":{"draws":62,"losses":21,"wins":111},"inclusionai/ling-3.1-flash":{"draws":9,"losses":10,"wins":21},"meituan/longcat-2.0":{"draws":55,"losses":52,"wins":193},"meta/muse-glimmer-30b":{"draws":64,"losses":40,"wins":138},"meta/muse-spark-1.2":{"draws":56,"losses":107,"wins":101},"meta/muse-spark-1.3":{"draws":44,"losses":136,"wins":96},"meta/muse-spark-open":{"draws":54,"losses":113,"wins":107},"meta/muse-wonder":{"draws":50,"losses":157,"wins":69},"minimax/minimax-m3":{"draws":27,"losses":29,"wins":92},"minimax/minimax-m3.1-flash":{"draws":59,"losses":61,"wins":126},"mistralai/mistral-large-4-0":{"draws":41,"losses":58,"wins":73},"mistralai/mistral-medium-3-5":{"draws":43,"losses":19,"wins":98},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":11,"wins":2},"moonshotai/kimi-k3":{"draws":70,"losses":90,"wins":104},"moonshotai/kimi-k3.1-pro":{"draws":29,"losses":203,"wins":44},"nex-agi/nex-n2-pro":{"draws":23,"losses":23,"wins":92},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":14,"wins":33},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":53,"losses":38,"wins":109},"nvidia/nemotron-3.5-super-vl":{"draws":33,"losses":31,"wins":62},"o3":{"draws":45,"losses":130,"wins":209},"openai/gpt-oss-120b":{"draws":59,"losses":39,"wins":142},"poolside/laguna-s-2.1":{"draws":60,"losses":57,"wins":145},"qwen/qwen3.7-max":{"draws":36,"losses":42,"wins":82},"qwen/qwen3.7-plus":{"draws":33,"losses":23,"wins":82},"qwen/qwen3.8-2.4t-a95b":{"draws":63,"losses":98,"wins":115},"qwen/qwen3.8-27b":{"draws":43,"losses":65,"wins":90},"qwen/qwen3.8-flash":{"draws":47,"losses":53,"wins":84},"qwen/qwen3.8-max":{"draws":58,"losses":97,"wins":121},"qwen/qwen3.8-max-0902":{"draws":69,"losses":107,"wins":100},"recursive/flint-v1.0":{"draws":26,"losses":9,"wins":45},"reflection/beam-1.0-501b-a23b":{"draws":59,"losses":79,"wins":114},"stealth/ox-alpha":{"draws":175,"losses":376,"wins":365},"stealth/space-bunny-alpha":{"draws":54,"losses":49,"wins":117},"stepfun/step-3.7-flash":{"draws":32,"losses":33,"wins":133},"stepfun/step-5-preview":{"draws":8,"losses":28,"wins":36},"tencent/hy3-preview":{"draws":42,"losses":31,"wins":75},"tencent/hy4-preview":{"draws":48,"losses":100,"wins":118},"thinkingmachines/inkling":{"draws":103,"losses":51,"wins":218},"thinkingmachines/inkling-small":{"draws":72,"losses":48,"wins":156},"unbiased/pareto-26.10":{"draws":8,"losses":81,"wins":3},"unbiased/pareto-26.10-preview":{"draws":1,"losses":82,"wins":9},"upstage/solar-mini4":{"draws":14,"losses":9,"wins":49},"x-ai/grok-4.5":{"draws":59,"losses":113,"wins":104},"x-ai/grok-4.6":{"draws":64,"losses":130,"wins":82},"x-ai/grok-4.7":{"draws":14,"losses":166,"wins":60},"x-ai/grok-build-0.1":{"draws":25,"losses":8,"wins":59},"xiaomi/mimo-v2.5":{"draws":113,"losses":63,"wins":248},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":30,"wins":83},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":77,"wins":73},"xiaomi/mimo-v2.6-pro":{"draws":39,"losses":86,"wins":59},"z-ai/glm-5.2":{"draws":133,"losses":159,"wins":260},"z-ai/glm-5.3":{"draws":47,"losses":155,"wins":62},"z-ai/glm-5.3-flash":{"draws":41,"losses":143,"wins":92},"z-ai/glm-5.3-flashx":{"draws":62,"losses":113,"wins":101}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":23,"wins":84},"claude-fable-5":{"draws":19,"losses":69,"wins":56},"claude-fable-5-1":{"draws":11,"losses":138,"wins":13},"claude-haiku-5-5":{"draws":34,"losses":43,"wins":61},"claude-opus-4-5":{"draws":66,"losses":47,"wins":121},"claude-opus-4-8":{"draws":26,"losses":44,"wins":62},"claude-opus-5":{"draws":26,"losses":167,"wins":53},"claude-opus-5-5":{"draws":13,"losses":123,"wins":20},"claude-sonnet-5":{"draws":30,"losses":36,"wins":78},"claude-sonnet-5-5":{"draws":19,"losses":70,"wins":55},"cohere/north-mini-code":{"draws":8,"losses":6,"wins":40},"deepseek/deepseek-v4-flash":{"draws":40,"losses":21,"wins":155},"deepseek/deepseek-v4-pro":{"draws":25,"losses":33,"wins":74},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":34,"wins":70},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":45,"wins":63},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":71,"wins":47},"elorian/glimpse":{"draws":13,"losses":30,"wins":35},"fireworks/ember-1":{"draws":29,"losses":48,"wins":67},"gemini-3.1-pro-preview":{"draws":27,"losses":35,"wins":82},"gemini-4-argon":{"draws":15,"losses":108,"wins":21},"google/gemini-3.1-flash-lite":{"draws":18,"losses":3,"wins":75},"google/gemini-3.5-flash":{"draws":31,"losses":44,"wins":105},"google/gemini-3.5-flash-lite":{"draws":43,"losses":22,"wins":187},"google/gemini-3.6-flash":{"draws":53,"losses":85,"wins":138},"google/gemini-3.8-flash":{"draws":20,"losses":38,"wins":38},"google/gemma-4-31b-it":{"draws":23,"losses":9,"wins":52},"gpt-4.1":{"draws":14,"losses":8,"wins":26},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":21,"losses":31,"wins":74},"gpt-5.4":{"draws":24,"losses":52,"wins":62},"gpt-5.4-mini":{"draws":21,"losses":13,"wins":62},"gpt-5.4-nano":{"draws":24,"losses":23,"wins":97},"gpt-5.5":{"draws":39,"losses":46,"wins":47},"gpt-5.6-luna":{"draws":29,"losses":26,"wins":89},"gpt-5.6-sol":{"draws":19,"losses":76,"wins":49},"gpt-5.6-terra":{"draws":35,"losses":39,"wins":64},"gpt-6-astra":{"draws":13,"losses":121,"wins":10},"gpt-6-luna":{"draws":38,"losses":34,"wins":72},"gpt-6-sol":{"draws":21,"losses":90,"wins":33},"gpt-6.1-sol":{"draws":16,"losses":110,"wins":18},"gpt-6.1-terra":{"draws":21,"losses":99,"wins":24},"gpt-6.1-terra-pro":{"draws":20,"losses":108,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":31,"losses":4,"wins":67},"inception/mercury-3":{"draws":24,"losses":23,"wins":49},"inclusionai/ling-3.0-flash":{"draws":25,"losses":2,"wins":75},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":25,"losses":19,"wins":112},"meta/muse-glimmer-30b":{"draws":27,"losses":16,"wins":83},"meta/muse-spark-1.2":{"draws":22,"losses":58,"wins":58},"meta/muse-spark-1.3":{"draws":33,"losses":52,"wins":59},"meta/muse-spark-open":{"draws":27,"losses":54,"wins":63},"meta/muse-wonder":{"draws":36,"losses":67,"wins":41},"minimax/minimax-m3":{"draws":14,"losses":7,"wins":57},"minimax/minimax-m3.1-flash":{"draws":26,"losses":25,"wins":75},"mistralai/mistral-large-4-0":{"draws":29,"losses":25,"wins":36},"mistralai/mistral-medium-3-5":{"draws":15,"losses":7,"wins":62},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":31,"losses":34,"wins":73},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":103,"wins":28},"nex-agi/nex-n2-pro":{"draws":12,"losses":6,"wins":54},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":6,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":13,"wins":70},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":18,"wins":38},"o3":{"draws":20,"losses":47,"wins":131},"openai/gpt-oss-120b":{"draws":25,"losses":9,"wins":92},"poolside/laguna-s-2.1":{"draws":21,"losses":17,"wins":100},"qwen/qwen3.7-max":{"draws":22,"losses":20,"wins":42},"qwen/qwen3.7-plus":{"draws":15,"losses":7,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":46,"wins":68},"qwen/qwen3.8-27b":{"draws":16,"losses":25,"wins":61},"qwen/qwen3.8-flash":{"draws":17,"losses":29,"wins":50},"qwen/qwen3.8-max":{"draws":29,"losses":52,"wins":63},"qwen/qwen3.8-max-0902":{"draws":37,"losses":48,"wins":59},"recursive/flint-v1.0":{"draws":7,"losses":2,"wins":33},"reflection/beam-1.0-501b-a23b":{"draws":26,"losses":35,"wins":71},"stealth/ox-alpha":{"draws":91,"losses":155,"wins":228},"stealth/space-bunny-alpha":{"draws":23,"losses":19,"wins":72},"stepfun/step-3.7-flash":{"draws":16,"losses":9,"wins":77},"stepfun/step-5-preview":{"draws":3,"losses":11,"wins":22},"tencent/hy3-preview":{"draws":31,"losses":8,"wins":39},"tencent/hy4-preview":{"draws":29,"losses":53,"wins":56},"thinkingmachines/inkling":{"draws":47,"losses":20,"wins":125},"thinkingmachines/inkling-small":{"draws":34,"losses":20,"wins":90},"unbiased/pareto-26.10":{"draws":4,"losses":39,"wins":5},"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":24,"losses":67,"wins":53},"x-ai/grok-4.6":{"draws":38,"losses":52,"wins":54},"x-ai/grok-4.7":{"draws":11,"losses":90,"wins":25},"x-ai/grok-build-0.1":{"draws":12,"losses":4,"wins":32},"xiaomi/mimo-v2.5":{"draws":55,"losses":20,"wins":147},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":13,"wins":55},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":29,"wins":44},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":47,"wins":29},"z-ai/glm-5.2":{"draws":67,"losses":59,"wins":162},"z-ai/glm-5.3":{"draws":28,"losses":72,"wins":38},"z-ai/glm-5.3-flash":{"draws":18,"losses":54,"wins":72},"z-ai/glm-5.3-flashx":{"draws":27,"losses":51,"wins":66}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":25,"wins":24},"claude-fable-5":{"draws":21,"losses":56,"wins":7},"claude-fable-5-1":{"draws":4,"losses":88,"wins":2},"claude-haiku-5-5":{"draws":22,"losses":51,"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":19,"losses":111,"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":32,"losses":38,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":38,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":61,"wins":7},"elorian/glimpse":{"draws":12,"losses":23,"wins":9},"fireworks/ember-1":{"draws":31,"losses":41,"wins":12},"gemini-3.1-pro-preview":{"draws":28,"losses":40,"wins":16},"gemini-4-argon":{"draws":3,"losses":80,"wins":1},"google/gemini-3.1-flash-lite":{"draws":19,"losses":15,"wins":26},"google/gemini-3.5-flash":{"draws":34,"losses":52,"wins":20},"google/gemini-3.5-flash-lite":{"draws":57,"losses":58,"wins":33},"google/gemini-3.6-flash":{"draws":49,"losses":92,"wins":19},"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},"gpt-6.1-terra":{"draws":10,"losses":74,"wins":0},"gpt-6.1-terra-pro":{"draws":4,"losses":79,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":31,"losses":16,"wins":17},"inception/mercury-3":{"draws":19,"losses":29,"wins":8},"inclusionai/ling-3.0-flash":{"draws":32,"losses":13,"wins":13},"inclusionai/ling-3.1-flash":{"draws":6,"losses":7,"wins":1},"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":25,"losses":38,"wins":17},"meta/muse-spark-1.3":{"draws":23,"losses":53,"wins":8},"meta/muse-spark-open":{"draws":24,"losses":54,"wins":6},"meta/muse-wonder":{"draws":17,"losses":60,"wins":7},"minimax/minimax-m3":{"draws":19,"losses":16,"wins":11},"minimax/minimax-m3.1-flash":{"draws":20,"losses":35,"wins":17},"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":3,"losses":9,"wins":0},"moonshotai/kimi-k3":{"draws":29,"losses":38,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":73,"wins":2},"nex-agi/nex-n2-pro":{"draws":17,"losses":11,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":11,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":22,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":22,"wins":6},"o3":{"draws":25,"losses":72,"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},"recursive/flint-v1.0":{"draws":7,"losses":7,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":19,"losses":47,"wins":12},"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":5,"losses":10,"wins":5},"tencent/hy3-preview":{"draws":21,"losses":16,"wins":9},"tencent/hy4-preview":{"draws":26,"losses":43,"wins":11},"thinkingmachines/inkling":{"draws":39,"losses":37,"wins":32},"thinkingmachines/inkling-small":{"draws":35,"losses":25,"wins":24},"unbiased/pareto-26.10":{"draws":2,"losses":26,"wins":0},"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":17,"losses":57,"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":60,"losses":41,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":17,"wins":9},"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":14,"losses":11,"wins":19},"claude-fable-5":{"draws":8,"losses":28,"wins":12},"claude-fable-5-1":{"draws":5,"losses":47,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":24,"wins":8},"claude-opus-4-5":{"draws":26,"losses":35,"wins":17},"claude-opus-4-8":{"draws":10,"losses":27,"wins":7},"claude-opus-5":{"draws":11,"losses":67,"wins":4},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":12,"losses":21,"wins":15},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":5,"losses":3,"wins":10},"deepseek/deepseek-v4-flash":{"draws":18,"losses":17,"wins":37},"deepseek/deepseek-v4-pro":{"draws":12,"losses":23,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":20,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":25,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":30,"wins":7},"elorian/glimpse":{"draws":6,"losses":12,"wins":8},"fireworks/ember-1":{"draws":13,"losses":21,"wins":14},"gemini-3.1-pro-preview":{"draws":11,"losses":18,"wins":19},"gemini-4-argon":{"draws":5,"losses":43,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":19},"google/gemini-3.5-flash":{"draws":13,"losses":30,"wins":17},"google/gemini-3.5-flash-lite":{"draws":23,"losses":28,"wins":33},"google/gemini-3.6-flash":{"draws":23,"losses":50,"wins":19},"google/gemini-3.8-flash":{"draws":14,"losses":26,"wins":8},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":16,"wins":15},"gpt-5.4":{"draws":9,"losses":22,"wins":15},"gpt-5.4-mini":{"draws":12,"losses":14,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":18,"wins":21},"gpt-5.5":{"draws":8,"losses":25,"wins":11},"gpt-5.6-luna":{"draws":13,"losses":14,"wins":21},"gpt-5.6-sol":{"draws":8,"losses":35,"wins":5},"gpt-5.6-terra":{"draws":16,"losses":15,"wins":15},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":9,"losses":20,"wins":19},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"gpt-6.1-terra":{"draws":3,"losses":44,"wins":1},"gpt-6.1-terra-pro":{"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":8,"wins":14},"inception/mercury-3":{"draws":8,"losses":15,"wins":9},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":20},"inclusionai/ling-3.1-flash":{"draws":6,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":12,"wins":30},"meta/muse-glimmer-30b":{"draws":15,"losses":10,"wins":17},"meta/muse-spark-1.2":{"draws":16,"losses":21,"wins":9},"meta/muse-spark-1.3":{"draws":14,"losses":28,"wins":6},"meta/muse-spark-open":{"draws":9,"losses":28,"wins":11},"meta/muse-wonder":{"draws":7,"losses":35,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":15},"minimax/minimax-m3.1-flash":{"draws":8,"losses":17,"wins":17},"mistralai/mistral-large-4-0":{"draws":12,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":10,"losses":5,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":22,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":43,"wins":3},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":9,"wins":7},"o3":{"draws":11,"losses":26,"wins":29},"openai/gpt-oss-120b":{"draws":11,"losses":9,"wins":22},"poolside/laguna-s-2.1":{"draws":14,"losses":13,"wins":19},"qwen/qwen3.7-max":{"draws":11,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":23,"wins":8},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":11},"qwen/qwen3.8-flash":{"draws":9,"losses":15,"wins":8},"qwen/qwen3.8-max":{"draws":16,"losses":18,"wins":14},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":18,"wins":13},"stealth/ox-alpha":{"draws":39,"losses":81,"wins":38},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":12},"tencent/hy4-preview":{"draws":13,"losses":23,"wins":10},"thinkingmachines/inkling":{"draws":16,"losses":20,"wins":28},"thinkingmachines/inkling-small":{"draws":13,"losses":15,"wins":20},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":28,"wins":9},"x-ai/grok-4.6":{"draws":17,"losses":24,"wins":7},"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":24,"losses":16,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":17,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":33,"losses":40,"wins":23},"z-ai/glm-5.3":{"draws":6,"losses":32,"wins":8},"z-ai/glm-5.3-flash":{"draws":5,"losses":28,"wins":15},"z-ai/glm-5.3-flashx":{"draws":8,"losses":30,"wins":10}},"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":6,"losses":20,"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":7,"losses":10,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":10,"wins":0},"elorian/glimpse":{"draws":6,"losses":2,"wins":0},"fireworks/ember-1":{"draws":8,"losses":9,"wins":1},"gemini-3.1-pro-preview":{"draws":11,"losses":4,"wins":3},"gemini-4-argon":{"draws":0,"losses":18,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":2},"google/gemini-3.5-flash":{"draws":9,"losses":10,"wins":1},"google/gemini-3.5-flash-lite":{"draws":17,"losses":10,"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},"gpt-6.1-terra":{"draws":5,"losses":13,"wins":0},"gpt-6.1-terra-pro":{"draws":4,"losses":14,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":3,"wins":5},"inception/mercury-3":{"draws":8,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"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-spark-open":{"draws":9,"losses":6,"wins":1},"meta/muse-wonder":{"draws":9,"losses":9,"wins":0},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":1},"minimax/minimax-m3.1-flash":{"draws":9,"losses":6,"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},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":15,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":2,"wins":0},"o3":{"draws":6,"losses":11,"wins":1},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":13,"losses":3,"wins":2},"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},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":7,"wins":0},"stealth/ox-alpha":{"draws":33,"losses":35,"wins":4},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":0},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":6,"losses":10,"wins":0},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":1},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":2},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"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":6,"losses":4,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":7,"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":32,"losses":41,"wins":43},"claude-fable-5":{"draws":20,"losses":85,"wins":21},"claude-fable-5-1":{"draws":3,"losses":139,"wins":0},"claude-haiku-5-5":{"draws":31,"losses":63,"wins":26},"claude-opus-4-5":{"draws":60,"losses":77,"wins":67},"claude-opus-4-8":{"draws":25,"losses":57,"wins":32},"claude-opus-5":{"draws":26,"losses":177,"wins":17},"claude-opus-5-5":{"draws":8,"losses":128,"wins":2},"claude-sonnet-5":{"draws":33,"losses":55,"wins":38},"claude-sonnet-5-5":{"draws":26,"losses":74,"wins":26},"cohere/north-mini-code":{"draws":10,"losses":6,"wins":34},"deepseek/deepseek-v4-flash":{"draws":44,"losses":48,"wins":98},"deepseek/deepseek-v4-pro":{"draws":26,"losses":52,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":46,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":62,"wins":31},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":73,"wins":28},"elorian/glimpse":{"draws":14,"losses":34,"wins":22},"fireworks/ember-1":{"draws":30,"losses":61,"wins":35},"gemini-3.1-pro-preview":{"draws":36,"losses":54,"wins":36},"gemini-4-argon":{"draws":4,"losses":113,"wins":9},"google/gemini-3.1-flash-lite":{"draws":14,"losses":10,"wins":60},"google/gemini-3.5-flash":{"draws":32,"losses":73,"wins":53},"google/gemini-3.5-flash-lite":{"draws":50,"losses":64,"wins":106},"google/gemini-3.6-flash":{"draws":45,"losses":116,"wins":81},"google/gemini-3.8-flash":{"draws":21,"losses":74,"wins":31},"google/gemma-4-31b-it":{"draws":31,"losses":9,"wins":32},"gpt-4.1":{"draws":11,"losses":15,"wins":16},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":4},"gpt-5":{"draws":16,"losses":28,"wins":28},"gpt-5.4":{"draws":17,"losses":68,"wins":37},"gpt-5.4-mini":{"draws":22,"losses":28,"wins":34},"gpt-5.4-nano":{"draws":16,"losses":44,"wins":68},"gpt-5.5":{"draws":37,"losses":52,"wins":29},"gpt-5.6-luna":{"draws":32,"losses":38,"wins":56},"gpt-5.6-sol":{"draws":17,"losses":92,"wins":17},"gpt-5.6-terra":{"draws":27,"losses":53,"wins":40},"gpt-6-astra":{"draws":9,"losses":116,"wins":1},"gpt-6-luna":{"draws":38,"losses":47,"wins":41},"gpt-6-sol":{"draws":13,"losses":97,"wins":16},"gpt-6.1-sol":{"draws":6,"losses":116,"wins":4},"gpt-6.1-terra":{"draws":12,"losses":110,"wins":4},"gpt-6.1-terra-pro":{"draws":12,"losses":109,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":31,"losses":9,"wins":44},"inception/mercury-3":{"draws":17,"losses":40,"wins":27},"inclusionai/ling-3.0-flash":{"draws":29,"losses":20,"wins":39},"inclusionai/ling-3.1-flash":{"draws":8,"losses":7,"wins":5},"meituan/longcat-2.0":{"draws":26,"losses":38,"wins":74},"meta/muse-glimmer-30b":{"draws":30,"losses":27,"wins":57},"meta/muse-spark-1.2":{"draws":26,"losses":65,"wins":31},"meta/muse-spark-1.3":{"draws":23,"losses":75,"wins":28},"meta/muse-spark-open":{"draws":29,"losses":73,"wins":24},"meta/muse-wonder":{"draws":23,"losses":80,"wins":23},"minimax/minimax-m3":{"draws":13,"losses":16,"wins":41},"minimax/minimax-m3.1-flash":{"draws":25,"losses":34,"wins":51},"mistralai/mistral-large-4-0":{"draws":30,"losses":34,"wins":16},"mistralai/mistral-medium-3-5":{"draws":19,"losses":16,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":28,"losses":50,"wins":44},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":103,"wins":14},"nex-agi/nex-n2-pro":{"draws":10,"losses":22,"wins":32},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":6,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":23,"wins":50},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":22,"wins":23},"o3":{"draws":23,"losses":68,"wins":89},"openai/gpt-oss-120b":{"draws":27,"losses":23,"wins":62},"poolside/laguna-s-2.1":{"draws":29,"losses":41,"wins":56},"qwen/qwen3.7-max":{"draws":23,"losses":20,"wins":31},"qwen/qwen3.7-plus":{"draws":14,"losses":10,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":55,"wins":35},"qwen/qwen3.8-27b":{"draws":17,"losses":41,"wins":30},"qwen/qwen3.8-flash":{"draws":14,"losses":38,"wins":32},"qwen/qwen3.8-max":{"draws":33,"losses":65,"wins":28},"qwen/qwen3.8-max-0902":{"draws":32,"losses":62,"wins":32},"recursive/flint-v1.0":{"draws":5,"losses":10,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":23,"losses":54,"wins":39},"stealth/ox-alpha":{"draws":87,"losses":203,"wins":134},"stealth/space-bunny-alpha":{"draws":20,"losses":39,"wins":41},"stepfun/step-3.7-flash":{"draws":21,"losses":18,"wins":53},"stepfun/step-5-preview":{"draws":4,"losses":9,"wins":11},"tencent/hy3-preview":{"draws":20,"losses":28,"wins":20},"tencent/hy4-preview":{"draws":32,"losses":54,"wins":36},"thinkingmachines/inkling":{"draws":37,"losses":39,"wins":96},"thinkingmachines/inkling-small":{"draws":38,"losses":23,"wins":65},"unbiased/pareto-26.10":{"draws":1,"losses":41,"wins":0},"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":68,"wins":33},"x-ai/grok-4.6":{"draws":33,"losses":73,"wins":20},"x-ai/grok-4.7":{"draws":9,"losses":85,"wins":18},"x-ai/grok-build-0.1":{"draws":11,"losses":9,"wins":22},"xiaomi/mimo-v2.5":{"draws":49,"losses":46,"wins":95},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":21,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":44,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":51,"wins":23},"z-ai/glm-5.2":{"draws":72,"losses":79,"wins":101},"z-ai/glm-5.3":{"draws":15,"losses":86,"wins":19},"z-ai/glm-5.3-flash":{"draws":18,"losses":73,"wins":35},"z-ai/glm-5.3-flashx":{"draws":27,"losses":64,"wins":35}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":29,"wins":70},"claude-fable-5":{"draws":31,"losses":67,"wins":40},"claude-fable-5-1":{"draws":9,"losses":132,"wins":15},"claude-haiku-5-5":{"draws":31,"losses":49,"wins":52},"claude-opus-4-5":{"draws":59,"losses":54,"wins":111},"claude-opus-4-8":{"draws":28,"losses":41,"wins":57},"claude-opus-5":{"draws":29,"losses":170,"wins":35},"claude-opus-5-5":{"draws":9,"losses":129,"wins":12},"claude-sonnet-5":{"draws":33,"losses":32,"wins":73},"claude-sonnet-5-5":{"draws":32,"losses":64,"wins":42},"cohere/north-mini-code":{"draws":9,"losses":10,"wins":35},"deepseek/deepseek-v4-flash":{"draws":51,"losses":32,"wins":123},"deepseek/deepseek-v4-pro":{"draws":28,"losses":37,"wins":63},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":37,"wins":67},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":47,"wins":54},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":63,"wins":49},"elorian/glimpse":{"draws":18,"losses":26,"wins":32},"fireworks/ember-1":{"draws":34,"losses":39,"wins":65},"gemini-3.1-pro-preview":{"draws":30,"losses":41,"wins":67},"gemini-4-argon":{"draws":13,"losses":103,"wins":22},"google/gemini-3.1-flash-lite":{"draws":15,"losses":9,"wins":70},"google/gemini-3.5-flash":{"draws":21,"losses":55,"wins":98},"google/gemini-3.5-flash-lite":{"draws":53,"losses":46,"wins":145},"google/gemini-3.6-flash":{"draws":49,"losses":106,"wins":111},"google/gemini-3.8-flash":{"draws":24,"losses":62,"wins":52},"google/gemma-4-31b-it":{"draws":28,"losses":9,"wins":43},"gpt-4.1":{"draws":9,"losses":15,"wins":22},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":6},"gpt-5":{"draws":17,"losses":37,"wins":68},"gpt-5.4":{"draws":20,"losses":34,"wins":34},"gpt-5.4-mini":{"draws":25,"losses":7,"wins":60},"gpt-5.4-nano":{"draws":16,"losses":32,"wins":90},"gpt-5.5":{"draws":33,"losses":44,"wins":51},"gpt-5.6-luna":{"draws":43,"losses":22,"wins":73},"gpt-5.6-sol":{"draws":22,"losses":69,"wins":47},"gpt-5.6-terra":{"draws":32,"losses":37,"wins":63},"gpt-6-astra":{"draws":6,"losses":114,"wins":18},"gpt-6-luna":{"draws":41,"losses":37,"wins":60},"gpt-6-sol":{"draws":13,"losses":103,"wins":22},"gpt-6.1-sol":{"draws":9,"losses":110,"wins":19},"gpt-6.1-terra":{"draws":9,"losses":109,"wins":20},"gpt-6.1-terra-pro":{"draws":14,"losses":102,"wins":22},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":37,"losses":8,"wins":51},"inception/mercury-3":{"draws":16,"losses":30,"wins":44},"inclusionai/ling-3.0-flash":{"draws":24,"losses":17,"wins":57},"inclusionai/ling-3.1-flash":{"draws":7,"losses":4,"wins":17},"meituan/longcat-2.0":{"draws":30,"losses":25,"wins":97},"meta/muse-glimmer-30b":{"draws":27,"losses":20,"wins":75},"meta/muse-spark-1.2":{"draws":22,"losses":49,"wins":61},"meta/muse-spark-1.3":{"draws":30,"losses":53,"wins":55},"meta/muse-spark-open":{"draws":30,"losses":56,"wins":52},"meta/muse-wonder":{"draws":28,"losses":67,"wins":43},"minimax/minimax-m3":{"draws":14,"losses":15,"wins":45},"minimax/minimax-m3.1-flash":{"draws":24,"losses":25,"wins":73},"mistralai/mistral-large-4-0":{"draws":30,"losses":16,"wins":40},"mistralai/mistral-medium-3-5":{"draws":20,"losses":14,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":25,"losses":38,"wins":69},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":99,"wins":27},"nex-agi/nex-n2-pro":{"draws":16,"losses":16,"wins":38},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":10,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":18,"wins":60},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":14,"wins":34},"o3":{"draws":19,"losses":50,"wins":127},"openai/gpt-oss-120b":{"draws":31,"losses":20,"wins":69},"poolside/laguna-s-2.1":{"draws":29,"losses":22,"wins":81},"qwen/qwen3.7-max":{"draws":14,"losses":20,"wins":46},"qwen/qwen3.7-plus":{"draws":10,"losses":8,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":52,"wins":58},"qwen/qwen3.8-27b":{"draws":20,"losses":20,"wins":58},"qwen/qwen3.8-flash":{"draws":18,"losses":29,"wins":45},"qwen/qwen3.8-max":{"draws":32,"losses":52,"wins":54},"qwen/qwen3.8-max-0902":{"draws":29,"losses":47,"wins":62},"recursive/flint-v1.0":{"draws":6,"losses":4,"wins":30},"reflection/beam-1.0-501b-a23b":{"draws":31,"losses":37,"wins":58},"stealth/ox-alpha":{"draws":109,"losses":165,"wins":184},"stealth/space-bunny-alpha":{"draws":30,"losses":19,"wins":61},"stepfun/step-3.7-flash":{"draws":18,"losses":16,"wins":66},"stepfun/step-5-preview":{"draws":5,"losses":12,"wins":17},"tencent/hy3-preview":{"draws":24,"losses":15,"wins":35},"tencent/hy4-preview":{"draws":25,"losses":48,"wins":61},"thinkingmachines/inkling":{"draws":46,"losses":30,"wins":110},"thinkingmachines/inkling-small":{"draws":37,"losses":17,"wins":84},"unbiased/pareto-26.10":{"draws":4,"losses":38,"wins":4},"unbiased/pareto-26.10-preview":{"draws":0,"losses":39,"wins":7},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":29},"x-ai/grok-4.5":{"draws":32,"losses":47,"wins":59},"x-ai/grok-4.6":{"draws":37,"losses":55,"wins":46},"x-ai/grok-4.7":{"draws":12,"losses":81,"wins":27},"x-ai/grok-build-0.1":{"draws":9,"losses":8,"wins":29},"xiaomi/mimo-v2.5":{"draws":52,"losses":22,"wins":138},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":13,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":25,"wins":39},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":39,"wins":38},"z-ai/glm-5.2":{"draws":74,"losses":61,"wins":141},"z-ai/glm-5.3":{"draws":23,"losses":70,"wins":39},"z-ai/glm-5.3-flash":{"draws":16,"losses":59,"wins":63},"z-ai/glm-5.3-flashx":{"draws":28,"losses":55,"wins":55}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":33,"wins":26},"claude-fable-5":{"draws":19,"losses":66,"wins":11},"claude-fable-5-1":{"draws":6,"losses":102,"wins":0},"claude-haiku-5-5":{"draws":27,"losses":53,"wins":12},"claude-opus-4-5":{"draws":54,"losses":70,"wins":32},"claude-opus-4-8":{"draws":20,"losses":44,"wins":24},"claude-opus-5":{"draws":30,"losses":121,"wins":13},"claude-opus-5-5":{"draws":5,"losses":96,"wins":3},"claude-sonnet-5":{"draws":38,"losses":30,"wins":28},"claude-sonnet-5-5":{"draws":17,"losses":62,"wins":17},"cohere/north-mini-code":{"draws":7,"losses":12,"wins":17},"deepseek/deepseek-v4-flash":{"draws":51,"losses":42,"wins":51},"deepseek/deepseek-v4-pro":{"draws":27,"losses":34,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":40,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":40,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":23,"losses":64,"wins":9},"elorian/glimpse":{"draws":15,"losses":24,"wins":13},"fireworks/ember-1":{"draws":36,"losses":46,"wins":14},"gemini-3.1-pro-preview":{"draws":31,"losses":40,"wins":25},"gemini-4-argon":{"draws":13,"losses":83,"wins":0},"google/gemini-3.1-flash-lite":{"draws":15,"losses":9,"wins":40},"google/gemini-3.5-flash":{"draws":31,"losses":57,"wins":32},"google/gemini-3.5-flash-lite":{"draws":51,"losses":52,"wins":65},"google/gemini-3.6-flash":{"draws":50,"losses":101,"wins":33},"google/gemini-3.8-flash":{"draws":21,"losses":62,"wins":13},"google/gemma-4-31b-it":{"draws":22,"losses":10,"wins":24},"gpt-4.1":{"draws":12,"losses":6,"wins":14},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":3},"gpt-5":{"draws":22,"losses":34,"wins":28},"gpt-5.4":{"draws":25,"losses":60,"wins":7},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":11},"gpt-5.4-nano":{"draws":21,"losses":46,"wins":29},"gpt-5.5":{"draws":36,"losses":35,"wins":17},"gpt-5.6-luna":{"draws":36,"losses":35,"wins":25},"gpt-5.6-sol":{"draws":17,"losses":67,"wins":12},"gpt-5.6-terra":{"draws":37,"losses":36,"wins":19},"gpt-6-astra":{"draws":6,"losses":90,"wins":0},"gpt-6-luna":{"draws":42,"losses":39,"wins":15},"gpt-6-sol":{"draws":13,"losses":73,"wins":10},"gpt-6.1-sol":{"draws":3,"losses":88,"wins":5},"gpt-6.1-terra":{"draws":17,"losses":73,"wins":6},"gpt-6.1-terra-pro":{"draws":11,"losses":80,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":16,"wins":24},"inception/mercury-3":{"draws":21,"losses":34,"wins":9},"inclusionai/ling-3.0-flash":{"draws":26,"losses":16,"wins":26},"inclusionai/ling-3.1-flash":{"draws":6,"losses":5,"wins":3},"meituan/longcat-2.0":{"draws":32,"losses":32,"wins":40},"meta/muse-glimmer-30b":{"draws":37,"losses":15,"wins":32},"meta/muse-spark-1.2":{"draws":27,"losses":47,"wins":18},"meta/muse-spark-1.3":{"draws":20,"losses":65,"wins":11},"meta/muse-spark-open":{"draws":27,"losses":55,"wins":14},"meta/muse-wonder":{"draws":24,"losses":62,"wins":10},"minimax/minimax-m3":{"draws":15,"losses":19,"wins":18},"minimax/minimax-m3.1-flash":{"draws":32,"losses":34,"wins":18},"mistralai/mistral-large-4-0":{"draws":29,"losses":21,"wins":10},"mistralai/mistral-medium-3-5":{"draws":21,"losses":10,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":0},"moonshotai/kimi-k3":{"draws":29,"losses":42,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":81,"wins":6},"nex-agi/nex-n2-pro":{"draws":15,"losses":17,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":7,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":28,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":24,"wins":6},"o3":{"draws":21,"losses":76,"wins":35},"openai/gpt-oss-120b":{"draws":31,"losses":21,"wins":32},"poolside/laguna-s-2.1":{"draws":28,"losses":30,"wins":34},"qwen/qwen3.7-max":{"draws":11,"losses":29,"wins":16},"qwen/qwen3.7-plus":{"draws":12,"losses":21,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":52,"wins":13},"qwen/qwen3.8-27b":{"draws":15,"losses":36,"wins":17},"qwen/qwen3.8-flash":{"draws":18,"losses":30,"wins":16},"qwen/qwen3.8-max":{"draws":35,"losses":41,"wins":20},"qwen/qwen3.8-max-0902":{"draws":38,"losses":43,"wins":15},"recursive/flint-v1.0":{"draws":8,"losses":8,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":28,"losses":42,"wins":18},"stealth/ox-alpha":{"draws":84,"losses":171,"wins":61},"stealth/space-bunny-alpha":{"draws":23,"losses":36,"wins":17},"stepfun/step-3.7-flash":{"draws":19,"losses":24,"wins":25},"stepfun/step-5-preview":{"draws":3,"losses":21,"wins":6},"tencent/hy3-preview":{"draws":20,"losses":17,"wins":15},"tencent/hy4-preview":{"draws":27,"losses":50,"wins":15},"thinkingmachines/inkling":{"draws":45,"losses":36,"wins":47},"thinkingmachines/inkling-small":{"draws":37,"losses":27,"wins":32},"unbiased/pareto-26.10":{"draws":2,"losses":30,"wins":0},"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":28,"losses":52,"wins":16},"x-ai/grok-4.6":{"draws":31,"losses":53,"wins":12},"x-ai/grok-4.7":{"draws":13,"losses":66,"wins":5},"x-ai/grok-build-0.1":{"draws":9,"losses":9,"wins":14},"xiaomi/mimo-v2.5":{"draws":49,"losses":42,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":12,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":36,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":40,"wins":9},"z-ai/glm-5.2":{"draws":70,"losses":83,"wins":39},"z-ai/glm-5.3":{"draws":20,"losses":64,"wins":8},"z-ai/glm-5.3-flash":{"draws":21,"losses":54,"wins":21},"z-ai/glm-5.3-flashx":{"draws":24,"losses":59,"wins":13}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":58,"wins":48},"claude-fable-5":{"draws":16,"losses":114,"wins":14},"claude-fable-5-1":{"draws":2,"losses":151,"wins":1},"claude-haiku-5-5":{"draws":29,"losses":74,"wins":39},"claude-opus-4-5":{"draws":59,"losses":115,"wins":64},"claude-opus-4-8":{"draws":25,"losses":84,"wins":31},"claude-opus-5":{"draws":22,"losses":199,"wins":15},"claude-opus-5-5":{"draws":6,"losses":153,"wins":1},"claude-sonnet-5":{"draws":33,"losses":70,"wins":41},"claude-sonnet-5-5":{"draws":20,"losses":105,"wins":19},"cohere/north-mini-code":{"draws":7,"losses":13,"wins":36},"deepseek/deepseek-v4-flash":{"draws":48,"losses":82,"wins":96},"deepseek/deepseek-v4-pro":{"draws":15,"losses":67,"wins":48},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":64,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":72,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":21,"losses":96,"wins":27},"elorian/glimpse":{"draws":13,"losses":39,"wins":22},"fireworks/ember-1":{"draws":30,"losses":81,"wins":33},"gemini-3.1-pro-preview":{"draws":31,"losses":73,"wins":40},"gemini-4-argon":{"draws":2,"losses":134,"wins":8},"google/gemini-3.1-flash-lite":{"draws":21,"losses":22,"wins":65},"google/gemini-3.5-flash":{"draws":23,"losses":111,"wins":50},"google/gemini-3.5-flash-lite":{"draws":45,"losses":110,"wins":97},"google/gemini-3.6-flash":{"draws":44,"losses":167,"wins":63},"google/gemini-3.8-flash":{"draws":24,"losses":97,"wins":23},"google/gemma-4-31b-it":{"draws":26,"losses":17,"wins":43},"gpt-4.1":{"draws":9,"losses":21,"wins":18},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":7},"gpt-5":{"draws":16,"losses":68,"wins":44},"gpt-5.4":{"draws":16,"losses":90,"wins":32},"gpt-5.4-mini":{"draws":21,"losses":29,"wins":46},"gpt-5.4-nano":{"draws":16,"losses":52,"wins":52},"gpt-5.5":{"draws":27,"losses":71,"wins":32},"gpt-5.6-luna":{"draws":32,"losses":61,"wins":51},"gpt-5.6-sol":{"draws":12,"losses":115,"wins":17},"gpt-5.6-terra":{"draws":23,"losses":75,"wins":38},"gpt-6-astra":{"draws":3,"losses":139,"wins":2},"gpt-6-luna":{"draws":29,"losses":72,"wins":43},"gpt-6-sol":{"draws":20,"losses":112,"wins":12},"gpt-6.1-sol":{"draws":5,"losses":134,"wins":5},"gpt-6.1-terra":{"draws":7,"losses":134,"wins":3},"gpt-6.1-terra-pro":{"draws":10,"losses":127,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":30,"losses":15,"wins":57},"inception/mercury-3":{"draws":26,"losses":46,"wins":28},"inclusionai/ling-3.0-flash":{"draws":24,"losses":30,"wins":50},"inclusionai/ling-3.1-flash":{"draws":5,"losses":8,"wins":9},"meituan/longcat-2.0":{"draws":24,"losses":51,"wins":85},"meta/muse-glimmer-30b":{"draws":25,"losses":44,"wins":53},"meta/muse-spark-1.2":{"draws":23,"losses":69,"wins":44},"meta/muse-spark-1.3":{"draws":21,"losses":95,"wins":28},"meta/muse-spark-open":{"draws":25,"losses":94,"wins":25},"meta/muse-wonder":{"draws":18,"losses":104,"wins":22},"minimax/minimax-m3":{"draws":15,"losses":29,"wins":40},"minimax/minimax-m3.1-flash":{"draws":16,"losses":57,"wins":49},"mistralai/mistral-large-4-0":{"draws":17,"losses":47,"wins":24},"mistralai/mistral-medium-3-5":{"draws":15,"losses":19,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":32,"losses":70,"wins":34},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":128,"wins":5},"nex-agi/nex-n2-pro":{"draws":10,"losses":27,"wins":35},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":14,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":47,"wins":50},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":29,"wins":24},"o3":{"draws":16,"losses":107,"wins":103},"openai/gpt-oss-120b":{"draws":35,"losses":47,"wins":44},"poolside/laguna-s-2.1":{"draws":26,"losses":59,"wins":59},"qwen/qwen3.7-max":{"draws":20,"losses":39,"wins":33},"qwen/qwen3.7-plus":{"draws":15,"losses":34,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":84,"wins":26},"qwen/qwen3.8-27b":{"draws":18,"losses":51,"wins":35},"qwen/qwen3.8-flash":{"draws":17,"losses":50,"wins":29},"qwen/qwen3.8-max":{"draws":31,"losses":74,"wins":39},"qwen/qwen3.8-max-0902":{"draws":35,"losses":74,"wins":35},"recursive/flint-v1.0":{"draws":10,"losses":17,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":25,"losses":69,"wins":34},"stealth/ox-alpha":{"draws":70,"losses":231,"wins":123},"stealth/space-bunny-alpha":{"draws":23,"losses":50,"wins":39},"stepfun/step-3.7-flash":{"draws":16,"losses":35,"wins":59},"stepfun/step-5-preview":{"draws":2,"losses":17,"wins":9},"tencent/hy3-preview":{"draws":20,"losses":37,"wins":23},"tencent/hy4-preview":{"draws":17,"losses":92,"wins":29},"thinkingmachines/inkling":{"draws":38,"losses":71,"wins":79},"thinkingmachines/inkling-small":{"draws":40,"losses":41,"wins":63},"unbiased/pareto-26.10":{"draws":3,"losses":43,"wins":2},"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":31,"losses":84,"wins":29},"x-ai/grok-4.6":{"draws":21,"losses":97,"wins":26},"x-ai/grok-4.7":{"draws":14,"losses":110,"wins":8},"x-ai/grok-build-0.1":{"draws":7,"losses":15,"wins":26},"xiaomi/mimo-v2.5":{"draws":51,"losses":75,"wins":110},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":28,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":53,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":66,"wins":16},"z-ai/glm-5.2":{"draws":59,"losses":131,"wins":98},"z-ai/glm-5.3":{"draws":19,"losses":96,"wins":21},"z-ai/glm-5.3-flash":{"draws":20,"losses":85,"wins":39},"z-ai/glm-5.3-flashx":{"draws":28,"losses":80,"wins":36}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":24,"wins":57},"claude-fable-5":{"draws":30,"losses":63,"wins":39},"claude-fable-5-1":{"draws":6,"losses":128,"wins":16},"claude-haiku-5-5":{"draws":46,"losses":45,"wins":35},"claude-opus-4-5":{"draws":83,"losses":50,"wins":81},"claude-opus-4-8":{"draws":34,"losses":36,"wins":50},"claude-opus-5":{"draws":30,"losses":155,"wins":47},"claude-opus-5-5":{"draws":13,"losses":116,"wins":15},"claude-sonnet-5":{"draws":43,"losses":31,"wins":58},"claude-sonnet-5-5":{"draws":29,"losses":61,"wins":42},"cohere/north-mini-code":{"draws":12,"losses":4,"wins":36},"deepseek/deepseek-v4-flash":{"draws":58,"losses":26,"wins":112},"deepseek/deepseek-v4-pro":{"draws":36,"losses":27,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":38,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":39,"losses":49,"wins":44},"deepseek/deepseek-v4.1-flash-1017":{"draws":39,"losses":50,"wins":43},"elorian/glimpse":{"draws":17,"losses":24,"wins":33},"fireworks/ember-1":{"draws":38,"losses":44,"wins":50},"gemini-3.1-pro-preview":{"draws":31,"losses":36,"wins":65},"gemini-4-argon":{"draws":9,"losses":100,"wins":23},"google/gemini-3.1-flash-lite":{"draws":20,"losses":4,"wins":64},"google/gemini-3.5-flash":{"draws":42,"losses":48,"wins":76},"google/gemini-3.5-flash-lite":{"draws":78,"losses":36,"wins":118},"google/gemini-3.6-flash":{"draws":65,"losses":86,"wins":103},"google/gemini-3.8-flash":{"draws":39,"losses":47,"wins":46},"google/gemma-4-31b-it":{"draws":30,"losses":6,"wins":40},"gpt-4.1":{"draws":8,"losses":11,"wins":25},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":4},"gpt-5":{"draws":37,"losses":29,"wins":52},"gpt-5.4":{"draws":33,"losses":51,"wins":44},"gpt-5.4-mini":{"draws":36,"losses":17,"wins":35},"gpt-5.4-nano":{"draws":27,"losses":32,"wins":71},"gpt-5.5":{"draws":32,"losses":24,"wins":24},"gpt-5.6-luna":{"draws":44,"losses":25,"wins":63},"gpt-5.6-sol":{"draws":24,"losses":63,"wins":45},"gpt-5.6-terra":{"draws":40,"losses":32,"wins":54},"gpt-6-astra":{"draws":5,"losses":119,"wins":8},"gpt-6-luna":{"draws":45,"losses":30,"wins":57},"gpt-6-sol":{"draws":19,"losses":83,"wins":30},"gpt-6.1-sol":{"draws":7,"losses":103,"wins":22},"gpt-6.1-terra":{"draws":13,"losses":97,"wins":22},"gpt-6.1-terra-pro":{"draws":15,"losses":102,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":2,"wins":1},"inception/mercury-2.5-preview":{"draws":35,"losses":11,"wins":44},"inception/mercury-3":{"draws":26,"losses":21,"wins":39},"inclusionai/ling-3.0-flash":{"draws":38,"losses":9,"wins":45},"inclusionai/ling-3.1-flash":{"draws":10,"losses":6,"wins":8},"meituan/longcat-2.0":{"draws":38,"losses":27,"wins":79},"meta/muse-glimmer-30b":{"draws":40,"losses":18,"wins":62},"meta/muse-spark-1.2":{"draws":24,"losses":44,"wins":60},"meta/muse-spark-1.3":{"draws":30,"losses":53,"wins":49},"meta/muse-spark-open":{"draws":28,"losses":55,"wins":49},"meta/muse-wonder":{"draws":35,"losses":60,"wins":37},"minimax/minimax-m3":{"draws":20,"losses":11,"wins":41},"minimax/minimax-m3.1-flash":{"draws":38,"losses":28,"wins":50},"mistralai/mistral-large-4-0":{"draws":29,"losses":22,"wins":33},"mistralai/mistral-medium-3-5":{"draws":23,"losses":9,"wins":44},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":34,"losses":46,"wins":48},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":94,"wins":28},"nex-agi/nex-n2-pro":{"draws":13,"losses":9,"wins":44},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":18,"wins":51},"nvidia/nemotron-3.5-super-vl":{"draws":23,"losses":10,"wins":29},"o3":{"draws":33,"losses":46,"wins":105},"openai/gpt-oss-120b":{"draws":41,"losses":16,"wins":59},"poolside/laguna-s-2.1":{"draws":43,"losses":27,"wins":58},"qwen/qwen3.7-max":{"draws":24,"losses":14,"wins":38},"qwen/qwen3.7-plus":{"draws":22,"losses":6,"wins":36},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":46,"wins":47},"qwen/qwen3.8-27b":{"draws":26,"losses":28,"wins":38},"qwen/qwen3.8-flash":{"draws":29,"losses":20,"wins":39},"qwen/qwen3.8-max":{"draws":40,"losses":43,"wins":49},"qwen/qwen3.8-max-0902":{"draws":43,"losses":44,"wins":45},"recursive/flint-v1.0":{"draws":11,"losses":2,"wins":25},"reflection/beam-1.0-501b-a23b":{"draws":30,"losses":32,"wins":60},"stealth/ox-alpha":{"draws":110,"losses":173,"wins":159},"stealth/space-bunny-alpha":{"draws":38,"losses":21,"wins":47},"stepfun/step-3.7-flash":{"draws":24,"losses":14,"wins":56},"stepfun/step-5-preview":{"draws":2,"losses":10,"wins":16},"tencent/hy3-preview":{"draws":31,"losses":9,"wins":32},"tencent/hy4-preview":{"draws":38,"losses":48,"wins":42},"thinkingmachines/inkling":{"draws":55,"losses":27,"wins":98},"thinkingmachines/inkling-small":{"draws":42,"losses":21,"wins":69},"unbiased/pareto-26.10":{"draws":2,"losses":37,"wins":5},"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":55,"wins":42},"x-ai/grok-4.6":{"draws":35,"losses":58,"wins":39},"x-ai/grok-4.7":{"draws":10,"losses":69,"wins":37},"x-ai/grok-build-0.1":{"draws":19,"losses":8,"wins":17},"xiaomi/mimo-v2.5":{"draws":78,"losses":25,"wins":99},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":14,"wins":32},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":25,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":22,"losses":37,"wins":29},"z-ai/glm-5.2":{"draws":91,"losses":50,"wins":123},"z-ai/glm-5.3":{"draws":27,"losses":76,"wins":23},"z-ai/glm-5.3-flash":{"draws":24,"losses":58,"wins":50},"z-ai/glm-5.3-flashx":{"draws":34,"losses":51,"wins":47}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":39,"losses":47,"wins":46},"claude-fable-5":{"draws":27,"losses":99,"wins":18},"claude-fable-5-1":{"draws":10,"losses":146,"wins":6},"claude-haiku-5-5":{"draws":40,"losses":74,"wins":24},"claude-opus-4-5":{"draws":80,"losses":95,"wins":59},"claude-opus-4-8":{"draws":34,"losses":65,"wins":33},"claude-opus-5":{"draws":28,"losses":194,"wins":24},"claude-opus-5-5":{"draws":16,"losses":136,"wins":4},"claude-sonnet-5":{"draws":36,"losses":65,"wins":43},"claude-sonnet-5-5":{"draws":33,"losses":84,"wins":27},"cohere/north-mini-code":{"draws":12,"losses":12,"wins":30},"deepseek/deepseek-v4-flash":{"draws":70,"losses":62,"wins":84},"deepseek/deepseek-v4-pro":{"draws":40,"losses":54,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":56,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":69,"wins":35},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":90,"wins":25},"elorian/glimpse":{"draws":22,"losses":36,"wins":20},"fireworks/ember-1":{"draws":44,"losses":56,"wins":44},"gemini-3.1-pro-preview":{"draws":36,"losses":56,"wins":52},"gemini-4-argon":{"draws":13,"losses":123,"wins":8},"google/gemini-3.1-flash-lite":{"draws":18,"losses":21,"wins":57},"google/gemini-3.5-flash":{"draws":46,"losses":81,"wins":53},"google/gemini-3.5-flash-lite":{"draws":65,"losses":77,"wins":110},"google/gemini-3.6-flash":{"draws":69,"losses":146,"wins":61},"google/gemini-3.8-flash":{"draws":29,"losses":89,"wins":26},"google/gemma-4-31b-it":{"draws":34,"losses":20,"wins":30},"gpt-4.1":{"draws":13,"losses":21,"wins":14},"gpt-4.1-nano":{"draws":11,"losses":1,"wins":6},"gpt-5":{"draws":32,"losses":56,"wins":38},"gpt-5.4":{"draws":43,"losses":73,"wins":22},"gpt-5.4-mini":{"draws":36,"losses":25,"wins":35},"gpt-5.4-nano":{"draws":32,"losses":51,"wins":61},"gpt-5.5":{"draws":44,"losses":63,"wins":25},"gpt-5.6-luna":{"draws":30,"losses":33,"wins":33},"gpt-5.6-sol":{"draws":21,"losses":98,"wins":25},"gpt-5.6-terra":{"draws":37,"losses":56,"wins":45},"gpt-6-astra":{"draws":12,"losses":128,"wins":4},"gpt-6-luna":{"draws":44,"losses":60,"wins":40},"gpt-6-sol":{"draws":23,"losses":107,"wins":14},"gpt-6.1-sol":{"draws":10,"losses":125,"wins":9},"gpt-6.1-terra":{"draws":20,"losses":114,"wins":10},"gpt-6.1-terra-pro":{"draws":13,"losses":126,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":40,"losses":22,"wins":40},"inception/mercury-3":{"draws":32,"losses":40,"wins":24},"inclusionai/ling-3.0-flash":{"draws":48,"losses":19,"wins":35},"inclusionai/ling-3.1-flash":{"draws":11,"losses":5,"wins":6},"meituan/longcat-2.0":{"draws":33,"losses":53,"wins":70},"meta/muse-glimmer-30b":{"draws":40,"losses":32,"wins":54},"meta/muse-spark-1.2":{"draws":38,"losses":66,"wins":34},"meta/muse-spark-1.3":{"draws":34,"losses":80,"wins":30},"meta/muse-spark-open":{"draws":40,"losses":71,"wins":33},"meta/muse-wonder":{"draws":28,"losses":90,"wins":26},"minimax/minimax-m3":{"draws":24,"losses":20,"wins":34},"minimax/minimax-m3.1-flash":{"draws":30,"losses":50,"wins":46},"mistralai/mistral-large-4-0":{"draws":32,"losses":43,"wins":15},"mistralai/mistral-medium-3-5":{"draws":30,"losses":12,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":46,"losses":62,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":122,"wins":13},"nex-agi/nex-n2-pro":{"draws":15,"losses":17,"wins":40},"nex-agi/nex-n2.5-pro":{"draws":11,"losses":13,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":30,"wins":44},"nvidia/nemotron-3.5-super-vl":{"draws":21,"losses":28,"wins":17},"o3":{"draws":36,"losses":92,"wins":70},"openai/gpt-oss-120b":{"draws":43,"losses":32,"wins":51},"poolside/laguna-s-2.1":{"draws":47,"losses":41,"wins":50},"qwen/qwen3.7-max":{"draws":23,"losses":34,"wins":27},"qwen/qwen3.7-plus":{"draws":27,"losses":18,"wins":27},"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":43,"losses":72,"wins":29},"qwen/qwen3.8-max-0902":{"draws":43,"losses":65,"wins":36},"recursive/flint-v1.0":{"draws":9,"losses":10,"wins":23},"reflection/beam-1.0-501b-a23b":{"draws":43,"losses":55,"wins":34},"stealth/ox-alpha":{"draws":139,"losses":231,"wins":104},"stealth/space-bunny-alpha":{"draws":33,"losses":45,"wins":36},"stepfun/step-3.7-flash":{"draws":25,"losses":31,"wins":46},"stepfun/step-5-preview":{"draws":2,"losses":19,"wins":7},"tencent/hy3-preview":{"draws":21,"losses":31,"wins":26},"tencent/hy4-preview":{"draws":40,"losses":69,"wins":29},"thinkingmachines/inkling":{"draws":58,"losses":46,"wins":88},"thinkingmachines/inkling-small":{"draws":51,"losses":38,"wins":55},"unbiased/pareto-26.10":{"draws":3,"losses":44,"wins":1},"unbiased/pareto-26.10-preview":{"draws":2,"losses":43,"wins":3},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":17},"x-ai/grok-4.5":{"draws":36,"losses":72,"wins":36},"x-ai/grok-4.6":{"draws":32,"losses":90,"wins":22},"x-ai/grok-4.7":{"draws":13,"losses":96,"wins":17},"x-ai/grok-build-0.1":{"draws":15,"losses":11,"wins":22},"xiaomi/mimo-v2.5":{"draws":71,"losses":58,"wins":93},"xiaomi/mimo-v2.5-pro":{"draws":27,"losses":25,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":47,"wins":32},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":62,"wins":17},"z-ai/glm-5.2":{"draws":95,"losses":115,"wins":78},"z-ai/glm-5.3":{"draws":23,"losses":97,"wins":18},"z-ai/glm-5.3-flash":{"draws":33,"losses":81,"wins":30},"z-ai/glm-5.3-flashx":{"draws":31,"losses":77,"wins":36}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":13,"wins":97},"claude-fable-5":{"draws":16,"losses":63,"wins":65},"claude-fable-5-1":{"draws":13,"losses":130,"wins":19},"claude-haiku-5-5":{"draws":20,"losses":41,"wins":77},"claude-opus-4-5":{"draws":44,"losses":38,"wins":152},"claude-opus-4-8":{"draws":21,"losses":38,"wins":73},"claude-opus-5":{"draws":30,"losses":150,"wins":66},"claude-opus-5-5":{"draws":11,"losses":125,"wins":20},"claude-sonnet-5":{"draws":20,"losses":19,"wins":105},"claude-sonnet-5-5":{"draws":14,"losses":56,"wins":74},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":47},"deepseek/deepseek-v4-flash":{"draws":29,"losses":19,"wins":168},"deepseek/deepseek-v4-pro":{"draws":16,"losses":29,"wins":87},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":27,"wins":90},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":44,"wins":77},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":51,"wins":67},"elorian/glimpse":{"draws":10,"losses":22,"wins":46},"fireworks/ember-1":{"draws":22,"losses":35,"wins":87},"gemini-3.1-pro-preview":{"draws":16,"losses":34,"wins":94},"gemini-4-argon":{"draws":11,"losses":100,"wins":33},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":84},"google/gemini-3.5-flash":{"draws":18,"losses":38,"wins":124},"google/gemini-3.5-flash-lite":{"draws":34,"losses":23,"wins":195},"google/gemini-3.6-flash":{"draws":33,"losses":75,"wins":168},"google/gemini-3.8-flash":{"draws":19,"losses":49,"wins":76},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":67},"gpt-4.1":{"draws":8,"losses":5,"wins":35},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":14},"gpt-5":{"draws":17,"losses":17,"wins":92},"gpt-5.4":{"draws":22,"losses":47,"wins":69},"gpt-5.4-mini":{"draws":17,"losses":12,"wins":67},"gpt-5.4-nano":{"draws":12,"losses":17,"wins":115},"gpt-5.5":{"draws":24,"losses":45,"wins":63},"gpt-5.6-luna":{"draws":21,"losses":25,"wins":98},"gpt-5.6-sol":{"draws":8,"losses":44,"wins":44},"gpt-5.6-terra":{"draws":25,"losses":24,"wins":89},"gpt-6-astra":{"draws":14,"losses":114,"wins":16},"gpt-6-luna":{"draws":27,"losses":24,"wins":93},"gpt-6-sol":{"draws":13,"losses":84,"wins":47},"gpt-6.1-sol":{"draws":12,"losses":106,"wins":26},"gpt-6.1-terra":{"draws":21,"losses":99,"wins":24},"gpt-6.1-terra-pro":{"draws":19,"losses":98,"wins":27},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":18,"losses":0,"wins":84},"inception/mercury-3":{"draws":14,"losses":17,"wins":65},"inclusionai/ling-3.0-flash":{"draws":12,"losses":5,"wins":85},"inclusionai/ling-3.1-flash":{"draws":0,"losses":4,"wins":14},"meituan/longcat-2.0":{"draws":19,"losses":14,"wins":123},"meta/muse-glimmer-30b":{"draws":19,"losses":8,"wins":99},"meta/muse-spark-1.2":{"draws":18,"losses":32,"wins":88},"meta/muse-spark-1.3":{"draws":22,"losses":48,"wins":74},"meta/muse-spark-open":{"draws":26,"losses":43,"wins":75},"meta/muse-wonder":{"draws":22,"losses":65,"wins":57},"minimax/minimax-m3":{"draws":13,"losses":4,"wins":61},"minimax/minimax-m3.1-flash":{"draws":15,"losses":25,"wins":86},"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":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":23,"losses":30,"wins":85},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":97,"wins":35},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":59},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":7,"wins":82},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":13,"wins":44},"o3":{"draws":11,"losses":32,"wins":155},"openai/gpt-oss-120b":{"draws":15,"losses":8,"wins":103},"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":13,"losses":7,"wins":52},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":37,"wins":87},"qwen/qwen3.8-27b":{"draws":15,"losses":16,"wins":71},"qwen/qwen3.8-flash":{"draws":17,"losses":18,"wins":61},"qwen/qwen3.8-max":{"draws":24,"losses":31,"wins":89},"qwen/qwen3.8-max-0902":{"draws":21,"losses":33,"wins":90},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":38},"reflection/beam-1.0-501b-a23b":{"draws":21,"losses":24,"wins":87},"stealth/ox-alpha":{"draws":69,"losses":114,"wins":291},"stealth/space-bunny-alpha":{"draws":19,"losses":14,"wins":81},"stepfun/step-3.7-flash":{"draws":11,"losses":6,"wins":85},"stepfun/step-5-preview":{"draws":6,"losses":8,"wins":16},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":56},"tencent/hy4-preview":{"draws":19,"losses":48,"wins":71},"thinkingmachines/inkling":{"draws":27,"losses":17,"wins":148},"thinkingmachines/inkling-small":{"draws":22,"losses":13,"wins":109},"unbiased/pareto-26.10":{"draws":4,"losses":41,"wins":3},"unbiased/pareto-26.10-preview":{"draws":2,"losses":44,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":32},"x-ai/grok-4.5":{"draws":18,"losses":44,"wins":82},"x-ai/grok-4.6":{"draws":28,"losses":59,"wins":57},"x-ai/grok-4.7":{"draws":16,"losses":68,"wins":42},"x-ai/grok-build-0.1":{"draws":10,"losses":4,"wins":34},"xiaomi/mimo-v2.5":{"draws":36,"losses":12,"wins":174},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":10,"wins":58},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":20,"wins":61},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":35,"wins":44},"z-ai/glm-5.2":{"draws":37,"losses":44,"wins":207},"z-ai/glm-5.3":{"draws":22,"losses":55,"wins":61},"z-ai/glm-5.3-flash":{"draws":24,"losses":47,"wins":73},"z-ai/glm-5.3-flashx":{"draws":24,"losses":41,"wins":79}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":26,"wins":69},"claude-fable-5":{"draws":31,"losses":87,"wins":20},"claude-fable-5-1":{"draws":7,"losses":143,"wins":6},"claude-haiku-5-5":{"draws":39,"losses":56,"wins":37},"claude-opus-4-5":{"draws":72,"losses":83,"wins":69},"claude-opus-4-8":{"draws":28,"losses":58,"wins":40},"claude-opus-5":{"draws":25,"losses":186,"wins":23},"claude-opus-5-5":{"draws":8,"losses":139,"wins":3},"claude-sonnet-5":{"draws":46,"losses":46,"wins":46},"claude-sonnet-5-5":{"draws":31,"losses":76,"wins":31},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":33},"deepseek/deepseek-v4-flash":{"draws":55,"losses":38,"wins":115},"deepseek/deepseek-v4-pro":{"draws":38,"losses":42,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":42,"wins":54},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":57,"wins":35},"deepseek/deepseek-v4.1-flash-1017":{"draws":33,"losses":80,"wins":25},"elorian/glimpse":{"draws":19,"losses":32,"wins":25},"fireworks/ember-1":{"draws":38,"losses":61,"wins":39},"gemini-3.1-pro-preview":{"draws":44,"losses":46,"wins":48},"gemini-4-argon":{"draws":14,"losses":116,"wins":8},"google/gemini-3.1-flash-lite":{"draws":22,"losses":5,"wins":63},"google/gemini-3.5-flash":{"draws":41,"losses":58,"wins":73},"google/gemini-3.5-flash-lite":{"draws":60,"losses":51,"wins":129},"google/gemini-3.6-flash":{"draws":65,"losses":132,"wins":67},"google/gemini-3.8-flash":{"draws":35,"losses":64,"wins":39},"google/gemma-4-31b-it":{"draws":32,"losses":9,"wins":39},"gpt-4.1":{"draws":16,"losses":15,"wins":15},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":8},"gpt-5":{"draws":27,"losses":40,"wins":53},"gpt-5.4":{"draws":32,"losses":63,"wins":37},"gpt-5.4-mini":{"draws":37,"losses":19,"wins":36},"gpt-5.4-nano":{"draws":23,"losses":38,"wins":75},"gpt-5.5":{"draws":40,"losses":54,"wins":32},"gpt-5.6-luna":{"draws":37,"losses":45,"wins":56},"gpt-5.6-sol":{"draws":25,"losses":89,"wins":24},"gpt-5.6-terra":{"draws":32,"losses":28,"wins":28},"gpt-6-astra":{"draws":12,"losses":123,"wins":3},"gpt-6-luna":{"draws":38,"losses":59,"wins":41},"gpt-6-sol":{"draws":23,"losses":98,"wins":17},"gpt-6.1-sol":{"draws":9,"losses":120,"wins":9},"gpt-6.1-terra":{"draws":20,"losses":109,"wins":9},"gpt-6.1-terra-pro":{"draws":12,"losses":114,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":35,"losses":9,"wins":54},"inception/mercury-3":{"draws":29,"losses":35,"wins":32},"inclusionai/ling-3.0-flash":{"draws":32,"losses":7,"wins":63},"inclusionai/ling-3.1-flash":{"draws":8,"losses":5,"wins":3},"meituan/longcat-2.0":{"draws":38,"losses":36,"wins":74},"meta/muse-glimmer-30b":{"draws":38,"losses":18,"wins":64},"meta/muse-spark-1.2":{"draws":38,"losses":57,"wins":37},"meta/muse-spark-1.3":{"draws":30,"losses":69,"wins":39},"meta/muse-spark-open":{"draws":42,"losses":63,"wins":33},"meta/muse-wonder":{"draws":30,"losses":79,"wins":29},"minimax/minimax-m3":{"draws":16,"losses":13,"wins":45},"minimax/minimax-m3.1-flash":{"draws":32,"losses":37,"wins":51},"mistralai/mistral-large-4-0":{"draws":41,"losses":26,"wins":19},"mistralai/mistral-medium-3-5":{"draws":20,"losses":11,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":37,"losses":50,"wins":45},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":112,"wins":17},"nex-agi/nex-n2-pro":{"draws":13,"losses":14,"wins":41},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":11,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":22,"wins":49},"nvidia/nemotron-3.5-super-vl":{"draws":24,"losses":18,"wins":22},"o3":{"draws":31,"losses":66,"wins":89},"openai/gpt-oss-120b":{"draws":37,"losses":13,"wins":70},"poolside/laguna-s-2.1":{"draws":40,"losses":16,"wins":74},"qwen/qwen3.7-max":{"draws":20,"losses":17,"wins":43},"qwen/qwen3.7-plus":{"draws":26,"losses":10,"wins":32},"qwen/qwen3.8-2.4t-a95b":{"draws":44,"losses":61,"wins":33},"qwen/qwen3.8-27b":{"draws":33,"losses":31,"wins":34},"qwen/qwen3.8-flash":{"draws":25,"losses":31,"wins":36},"qwen/qwen3.8-max":{"draws":46,"losses":51,"wins":41},"qwen/qwen3.8-max-0902":{"draws":43,"losses":58,"wins":37},"recursive/flint-v1.0":{"draws":10,"losses":2,"wins":28},"reflection/beam-1.0-501b-a23b":{"draws":35,"losses":48,"wins":43},"stealth/ox-alpha":{"draws":117,"losses":209,"wins":130},"stealth/space-bunny-alpha":{"draws":35,"losses":32,"wins":41},"stepfun/step-3.7-flash":{"draws":22,"losses":21,"wins":55},"stepfun/step-5-preview":{"draws":6,"losses":10,"wins":16},"tencent/hy3-preview":{"draws":27,"losses":17,"wins":30},"tencent/hy4-preview":{"draws":33,"losses":56,"wins":43},"thinkingmachines/inkling":{"draws":53,"losses":38,"wins":91},"thinkingmachines/inkling-small":{"draws":37,"losses":24,"wins":77},"unbiased/pareto-26.10":{"draws":3,"losses":42,"wins":1},"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":66,"wins":33},"x-ai/grok-4.6":{"draws":42,"losses":76,"wins":20},"x-ai/grok-4.7":{"draws":11,"losses":87,"wins":22},"x-ai/grok-build-0.1":{"draws":14,"losses":6,"wins":26},"xiaomi/mimo-v2.5":{"draws":68,"losses":19,"wins":125},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":9,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":36,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":45,"wins":23},"z-ai/glm-5.2":{"draws":99,"losses":73,"wins":104},"z-ai/glm-5.3":{"draws":29,"losses":82,"wins":21},"z-ai/glm-5.3-flash":{"draws":30,"losses":66,"wins":42},"z-ai/glm-5.3-flashx":{"draws":32,"losses":64,"wins":42}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":120},"claude-fable-5":{"draws":11,"losses":21,"wins":112},"claude-fable-5-1":{"draws":15,"losses":65,"wins":82},"claude-haiku-5-5":{"draws":7,"losses":8,"wins":123},"claude-opus-4-5":{"draws":15,"losses":8,"wins":211},"claude-opus-4-8":{"draws":8,"losses":10,"wins":114},"claude-opus-5":{"draws":22,"losses":56,"wins":168},"claude-opus-5-5":{"draws":15,"losses":69,"wins":72},"claude-sonnet-5":{"draws":6,"losses":6,"wins":132},"claude-sonnet-5-5":{"draws":11,"losses":33,"wins":100},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":52},"deepseek/deepseek-v4-flash":{"draws":10,"losses":5,"wins":201},"deepseek/deepseek-v4-pro":{"draws":11,"losses":7,"wins":114},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":1,"wins":123},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":7,"wins":124},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":10,"wins":123},"elorian/glimpse":{"draws":6,"losses":7,"wins":65},"fireworks/ember-1":{"draws":10,"losses":5,"wins":129},"gemini-3.1-pro-preview":{"draws":7,"losses":4,"wins":133},"gemini-4-argon":{"draws":17,"losses":40,"wins":87},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":94},"google/gemini-3.5-flash":{"draws":7,"losses":8,"wins":165},"google/gemini-3.5-flash-lite":{"draws":14,"losses":0,"wins":238},"google/gemini-3.6-flash":{"draws":19,"losses":18,"wins":239},"google/gemini-3.8-flash":{"draws":13,"losses":10,"wins":121},"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":1,"wins":116},"gpt-5.4":{"draws":6,"losses":18,"wins":114},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":90},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":139},"gpt-5.5":{"draws":5,"losses":8,"wins":119},"gpt-5.6-luna":{"draws":12,"losses":4,"wins":128},"gpt-5.6-sol":{"draws":14,"losses":16,"wins":114},"gpt-5.6-terra":{"draws":12,"losses":3,"wins":123},"gpt-6-astra":{"draws":10,"losses":43,"wins":43},"gpt-6-luna":{"draws":13,"losses":10,"wins":121},"gpt-6-sol":{"draws":18,"losses":26,"wins":100},"gpt-6.1-sol":{"draws":19,"losses":53,"wins":72},"gpt-6.1-terra":{"draws":19,"losses":38,"wins":87},"gpt-6.1-terra-pro":{"draws":19,"losses":42,"wins":83},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":95},"inception/mercury-3":{"draws":11,"losses":2,"wins":83},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":96},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":23},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":146},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":120},"meta/muse-spark-1.2":{"draws":8,"losses":4,"wins":126},"meta/muse-spark-1.3":{"draws":14,"losses":13,"wins":117},"meta/muse-spark-open":{"draws":8,"losses":3,"wins":131},"meta/muse-wonder":{"draws":16,"losses":13,"wins":115},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":76},"minimax/minimax-m3.1-flash":{"draws":9,"losses":0,"wins":117},"mistralai/mistral-large-4-0":{"draws":8,"losses":6,"wins":76},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":78},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":11,"losses":9,"wins":118},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":38,"wins":95},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":68},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":100},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":64},"o3":{"draws":7,"losses":1,"wins":190},"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":5,"losses":0,"wins":79},"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":12,"losses":3,"wins":81},"qwen/qwen3.8-max":{"draws":13,"losses":4,"wins":127},"qwen/qwen3.8-max-0902":{"draws":9,"losses":6,"wins":129},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":39},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":4,"wins":117},"stealth/ox-alpha":{"draws":35,"losses":24,"wins":415},"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":2,"losses":0,"wins":30},"tencent/hy3-preview":{"draws":10,"losses":0,"wins":68},"tencent/hy4-preview":{"draws":11,"losses":5,"wins":122},"thinkingmachines/inkling":{"draws":12,"losses":1,"wins":179},"thinkingmachines/inkling-small":{"draws":9,"losses":0,"wins":135},"unbiased/pareto-26.10":{"draws":8,"losses":18,"wins":22},"unbiased/pareto-26.10-preview":{"draws":3,"losses":21,"wins":24},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":34},"x-ai/grok-4.5":{"draws":9,"losses":15,"wins":120},"x-ai/grok-4.6":{"draws":12,"losses":11,"wins":121},"x-ai/grok-4.7":{"draws":12,"losses":23,"wins":91},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":44},"xiaomi/mimo-v2.5":{"draws":14,"losses":2,"wins":206},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":0,"wins":69},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":5,"wins":82},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":7,"wins":80},"z-ai/glm-5.2":{"draws":21,"losses":8,"wins":259},"z-ai/glm-5.3":{"draws":15,"losses":11,"wins":112},"z-ai/glm-5.3-flash":{"draws":12,"losses":8,"wins":124},"z-ai/glm-5.3-flashx":{"draws":15,"losses":8,"wins":121}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":39,"wins":53},"claude-fable-5":{"draws":28,"losses":88,"wins":28},"claude-fable-5-1":{"draws":12,"losses":144,"wins":6},"claude-haiku-5-5":{"draws":35,"losses":64,"wins":39},"claude-opus-4-5":{"draws":72,"losses":85,"wins":77},"claude-opus-4-8":{"draws":29,"losses":64,"wins":39},"claude-opus-5":{"draws":40,"losses":180,"wins":26},"claude-opus-5-5":{"draws":12,"losses":141,"wins":3},"claude-sonnet-5":{"draws":36,"losses":54,"wins":54},"claude-sonnet-5-5":{"draws":32,"losses":68,"wins":44},"cohere/north-mini-code":{"draws":12,"losses":9,"wins":33},"deepseek/deepseek-v4-flash":{"draws":59,"losses":51,"wins":106},"deepseek/deepseek-v4-pro":{"draws":34,"losses":42,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":48,"wins":51},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":62,"wins":42},"deepseek/deepseek-v4.1-flash-1017":{"draws":34,"losses":76,"wins":34},"elorian/glimpse":{"draws":14,"losses":37,"wins":27},"fireworks/ember-1":{"draws":37,"losses":63,"wins":44},"gemini-3.1-pro-preview":{"draws":34,"losses":59,"wins":51},"gemini-4-argon":{"draws":10,"losses":126,"wins":8},"google/gemini-3.1-flash-lite":{"draws":23,"losses":13,"wins":60},"google/gemini-3.5-flash":{"draws":49,"losses":67,"wins":64},"google/gemini-3.5-flash-lite":{"draws":73,"losses":63,"wins":116},"google/gemini-3.6-flash":{"draws":74,"losses":124,"wins":78},"google/gemini-3.8-flash":{"draws":38,"losses":72,"wins":34},"google/gemma-4-31b-it":{"draws":28,"losses":18,"wins":38},"gpt-4.1":{"draws":9,"losses":19,"wins":20},"gpt-4.1-nano":{"draws":9,"losses":2,"wins":7},"gpt-5":{"draws":38,"losses":41,"wins":47},"gpt-5.4":{"draws":41,"losses":60,"wins":37},"gpt-5.4-mini":{"draws":42,"losses":15,"wins":39},"gpt-5.4-nano":{"draws":29,"losses":43,"wins":72},"gpt-5.5":{"draws":45,"losses":57,"wins":30},"gpt-5.6-luna":{"draws":44,"losses":40,"wins":60},"gpt-5.6-sol":{"draws":27,"losses":93,"wins":24},"gpt-5.6-terra":{"draws":38,"losses":41,"wins":59},"gpt-6-astra":{"draws":13,"losses":121,"wins":10},"gpt-6-luna":{"draws":24,"losses":36,"wins":36},"gpt-6-sol":{"draws":21,"losses":105,"wins":18},"gpt-6.1-sol":{"draws":13,"losses":125,"wins":6},"gpt-6.1-terra":{"draws":22,"losses":113,"wins":9},"gpt-6.1-terra-pro":{"draws":16,"losses":119,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":38,"losses":10,"wins":54},"inception/mercury-3":{"draws":26,"losses":31,"wins":39},"inclusionai/ling-3.0-flash":{"draws":32,"losses":15,"wins":55},"inclusionai/ling-3.1-flash":{"draws":14,"losses":9,"wins":13},"meituan/longcat-2.0":{"draws":35,"losses":35,"wins":86},"meta/muse-glimmer-30b":{"draws":39,"losses":23,"wins":64},"meta/muse-spark-1.2":{"draws":37,"losses":62,"wins":39},"meta/muse-spark-1.3":{"draws":25,"losses":83,"wins":36},"meta/muse-spark-open":{"draws":33,"losses":64,"wins":43},"meta/muse-wonder":{"draws":34,"losses":77,"wins":33},"minimax/minimax-m3":{"draws":22,"losses":15,"wins":41},"minimax/minimax-m3.1-flash":{"draws":26,"losses":44,"wins":56},"mistralai/mistral-large-4-0":{"draws":27,"losses":31,"wins":32},"mistralai/mistral-medium-3-5":{"draws":27,"losses":7,"wins":50},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":7,"wins":8},"moonshotai/kimi-k3":{"draws":43,"losses":52,"wins":43},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":119,"wins":11},"nex-agi/nex-n2-pro":{"draws":13,"losses":14,"wins":45},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":8,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":22,"wins":53},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":15,"wins":33},"o3":{"draws":33,"losses":66,"wins":99},"openai/gpt-oss-120b":{"draws":38,"losses":29,"wins":59},"poolside/laguna-s-2.1":{"draws":43,"losses":38,"wins":57},"qwen/qwen3.7-max":{"draws":21,"losses":27,"wins":36},"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":24,"losses":37,"wins":41},"qwen/qwen3.8-flash":{"draws":26,"losses":34,"wins":36},"qwen/qwen3.8-max":{"draws":35,"losses":61,"wins":48},"qwen/qwen3.8-max-0902":{"draws":38,"losses":58,"wins":48},"recursive/flint-v1.0":{"draws":11,"losses":5,"wins":26},"reflection/beam-1.0-501b-a23b":{"draws":28,"losses":47,"wins":57},"stealth/ox-alpha":{"draws":104,"losses":211,"wins":159},"stealth/space-bunny-alpha":{"draws":37,"losses":25,"wins":52},"stepfun/step-3.7-flash":{"draws":21,"losses":24,"wins":57},"stepfun/step-5-preview":{"draws":5,"losses":18,"wins":11},"tencent/hy3-preview":{"draws":25,"losses":21,"wins":32},"tencent/hy4-preview":{"draws":40,"losses":61,"wins":37},"thinkingmachines/inkling":{"draws":56,"losses":41,"wins":95},"thinkingmachines/inkling-small":{"draws":39,"losses":33,"wins":72},"unbiased/pareto-26.10":{"draws":3,"losses":44,"wins":1},"unbiased/pareto-26.10-preview":{"draws":3,"losses":44,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":10,"wins":25},"x-ai/grok-4.5":{"draws":33,"losses":66,"wins":45},"x-ai/grok-4.6":{"draws":36,"losses":83,"wins":25},"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":74,"losses":32,"wins":116},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":14,"wins":39},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":40,"wins":32},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":50,"wins":26},"z-ai/glm-5.2":{"draws":100,"losses":73,"wins":115},"z-ai/glm-5.3":{"draws":23,"losses":86,"wins":29},"z-ai/glm-5.3-flash":{"draws":39,"losses":71,"wins":34},"z-ai/glm-5.3-flashx":{"draws":27,"losses":71,"wins":46}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":15,"wins":102},"claude-fable-5":{"draws":18,"losses":43,"wins":83},"claude-fable-5-1":{"draws":12,"losses":108,"wins":42},"claude-haiku-5-5":{"draws":25,"losses":28,"wins":85},"claude-opus-4-5":{"draws":35,"losses":25,"wins":174},"claude-opus-4-8":{"draws":17,"losses":35,"wins":80},"claude-opus-5":{"draws":38,"losses":119,"wins":89},"claude-opus-5-5":{"draws":14,"losses":103,"wins":39},"claude-sonnet-5":{"draws":23,"losses":19,"wins":102},"claude-sonnet-5-5":{"draws":11,"losses":51,"wins":82},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":49},"deepseek/deepseek-v4-flash":{"draws":32,"losses":15,"wins":169},"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":24,"losses":29,"wins":91},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":40,"wins":89},"elorian/glimpse":{"draws":10,"losses":15,"wins":53},"fireworks/ember-1":{"draws":20,"losses":23,"wins":101},"gemini-3.1-pro-preview":{"draws":14,"losses":28,"wins":102},"gemini-4-argon":{"draws":14,"losses":72,"wins":58},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":80},"google/gemini-3.5-flash":{"draws":22,"losses":31,"wins":127},"google/gemini-3.5-flash-lite":{"draws":36,"losses":23,"wins":193},"google/gemini-3.6-flash":{"draws":34,"losses":62,"wins":180},"google/gemini-3.8-flash":{"draws":21,"losses":33,"wins":90},"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":13,"losses":16,"wins":97},"gpt-5.4":{"draws":13,"losses":22,"wins":103},"gpt-5.4-mini":{"draws":13,"losses":10,"wins":73},"gpt-5.4-nano":{"draws":20,"losses":12,"wins":112},"gpt-5.5":{"draws":19,"losses":30,"wins":83},"gpt-5.6-luna":{"draws":23,"losses":14,"wins":107},"gpt-5.6-sol":{"draws":13,"losses":47,"wins":84},"gpt-5.6-terra":{"draws":23,"losses":17,"wins":98},"gpt-6-astra":{"draws":18,"losses":100,"wins":26},"gpt-6-luna":{"draws":21,"losses":18,"wins":105},"gpt-6-sol":{"draws":12,"losses":42,"wins":42},"gpt-6.1-sol":{"draws":14,"losses":90,"wins":40},"gpt-6.1-terra":{"draws":15,"losses":76,"wins":53},"gpt-6.1-terra-pro":{"draws":20,"losses":97,"wins":27},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":83},"inception/mercury-3":{"draws":16,"losses":14,"wins":66},"inclusionai/ling-3.0-flash":{"draws":15,"losses":8,"wins":79},"inclusionai/ling-3.1-flash":{"draws":6,"losses":2,"wins":22},"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":16,"losses":25,"wins":97},"meta/muse-spark-1.3":{"draws":22,"losses":24,"wins":98},"meta/muse-spark-open":{"draws":13,"losses":22,"wins":107},"meta/muse-wonder":{"draws":17,"losses":46,"wins":81},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":62},"minimax/minimax-m3.1-flash":{"draws":15,"losses":9,"wins":102},"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":0,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":14,"losses":26,"wins":98},"moonshotai/kimi-k3.1-pro":{"draws":17,"losses":82,"wins":45},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":62},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":9,"wins":83},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":52},"o3":{"draws":9,"losses":17,"wins":172},"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":16,"losses":14,"wins":72},"qwen/qwen3.8-flash":{"draws":9,"losses":19,"wins":68},"qwen/qwen3.8-max":{"draws":16,"losses":26,"wins":102},"qwen/qwen3.8-max-0902":{"draws":18,"losses":28,"wins":98},"recursive/flint-v1.0":{"draws":5,"losses":2,"wins":35},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":16,"wins":98},"stealth/ox-alpha":{"draws":61,"losses":71,"wins":342},"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":7,"losses":7,"wins":26},"tencent/hy3-preview":{"draws":15,"losses":5,"wins":58},"tencent/hy4-preview":{"draws":18,"losses":25,"wins":95},"thinkingmachines/inkling":{"draws":25,"losses":13,"wins":154},"thinkingmachines/inkling-small":{"draws":18,"losses":8,"wins":118},"unbiased/pareto-26.10":{"draws":3,"losses":38,"wins":7},"unbiased/pareto-26.10-preview":{"draws":2,"losses":35,"wins":11},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":32},"x-ai/grok-4.5":{"draws":19,"losses":31,"wins":94},"x-ai/grok-4.6":{"draws":21,"losses":29,"wins":94},"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":36,"losses":17,"wins":169},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":8,"wins":55},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":19,"wins":62},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":26,"wins":52},"z-ai/glm-5.2":{"draws":42,"losses":35,"wins":211},"z-ai/glm-5.3":{"draws":20,"losses":45,"wins":73},"z-ai/glm-5.3-flash":{"draws":19,"losses":35,"wins":90},"z-ai/glm-5.3-flashx":{"draws":16,"losses":42,"wins":86}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":9,"wins":113},"claude-fable-5":{"draws":9,"losses":34,"wins":101},"claude-fable-5-1":{"draws":10,"losses":72,"wins":80},"claude-haiku-5-5":{"draws":13,"losses":11,"wins":114},"claude-opus-4-5":{"draws":20,"losses":15,"wins":199},"claude-opus-4-8":{"draws":6,"losses":16,"wins":110},"claude-opus-5":{"draws":32,"losses":74,"wins":140},"claude-opus-5-5":{"draws":16,"losses":74,"wins":66},"claude-sonnet-5":{"draws":6,"losses":8,"wins":130},"claude-sonnet-5-5":{"draws":3,"losses":35,"wins":106},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":52},"deepseek/deepseek-v4-flash":{"draws":14,"losses":6,"wins":196},"deepseek/deepseek-v4-pro":{"draws":7,"losses":8,"wins":117},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":2,"wins":123},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":15,"wins":116},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":27,"wins":107},"elorian/glimpse":{"draws":4,"losses":10,"wins":64},"fireworks/ember-1":{"draws":10,"losses":18,"wins":116},"gemini-3.1-pro-preview":{"draws":3,"losses":13,"wins":128},"gemini-4-argon":{"draws":19,"losses":46,"wins":79},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":92},"google/gemini-3.5-flash":{"draws":7,"losses":19,"wins":154},"google/gemini-3.5-flash-lite":{"draws":15,"losses":2,"wins":235},"google/gemini-3.6-flash":{"draws":18,"losses":21,"wins":237},"google/gemini-3.8-flash":{"draws":16,"losses":18,"wins":110},"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":4,"wins":116},"gpt-5.4":{"draws":9,"losses":19,"wins":110},"gpt-5.4-mini":{"draws":3,"losses":5,"wins":88},"gpt-5.4-nano":{"draws":5,"losses":5,"wins":134},"gpt-5.5":{"draws":7,"losses":22,"wins":103},"gpt-5.6-luna":{"draws":10,"losses":9,"wins":125},"gpt-5.6-sol":{"draws":12,"losses":26,"wins":106},"gpt-5.6-terra":{"draws":9,"losses":9,"wins":120},"gpt-6-astra":{"draws":19,"losses":72,"wins":53},"gpt-6-luna":{"draws":13,"losses":6,"wins":125},"gpt-6-sol":{"draws":14,"losses":40,"wins":90},"gpt-6.1-sol":{"draws":2,"losses":47,"wins":47},"gpt-6.1-terra":{"draws":21,"losses":44,"wins":79},"gpt-6.1-terra-pro":{"draws":15,"losses":60,"wins":69},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":93},"inception/mercury-3":{"draws":7,"losses":7,"wins":82},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":98},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":24},"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":11,"losses":17,"wins":110},"meta/muse-spark-1.3":{"draws":11,"losses":14,"wins":119},"meta/muse-spark-open":{"draws":9,"losses":13,"wins":122},"meta/muse-wonder":{"draws":16,"losses":31,"wins":97},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":70},"minimax/minimax-m3.1-flash":{"draws":12,"losses":2,"wins":112},"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":1,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":116},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":47,"wins":83},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":68},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":4,"wins":92},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":2,"wins":58},"o3":{"draws":3,"losses":8,"wins":187},"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":6,"losses":2,"wins":76},"qwen/qwen3.7-plus":{"draws":3,"losses":4,"wins":65},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":20,"wins":116},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":91},"qwen/qwen3.8-flash":{"draws":8,"losses":7,"wins":81},"qwen/qwen3.8-max":{"draws":10,"losses":6,"wins":128},"qwen/qwen3.8-max-0902":{"draws":11,"losses":12,"wins":121},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":41},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":6,"wins":120},"stealth/ox-alpha":{"draws":39,"losses":32,"wins":403},"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":1,"losses":0,"wins":25},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":68},"tencent/hy4-preview":{"draws":7,"losses":12,"wins":119},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":175},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":138},"unbiased/pareto-26.10":{"draws":6,"losses":25,"wins":17},"unbiased/pareto-26.10-preview":{"draws":1,"losses":28,"wins":19},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":35},"x-ai/grok-4.5":{"draws":10,"losses":18,"wins":116},"x-ai/grok-4.6":{"draws":17,"losses":12,"wins":115},"x-ai/grok-4.7":{"draws":6,"losses":38,"wins":82},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":48},"xiaomi/mimo-v2.5":{"draws":18,"losses":8,"wins":196},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":0,"wins":59},"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":29,"losses":11,"wins":248},"z-ai/glm-5.3":{"draws":20,"losses":24,"wins":94},"z-ai/glm-5.3-flash":{"draws":12,"losses":16,"wins":116},"z-ai/glm-5.3-flashx":{"draws":15,"losses":18,"wins":111}},"gpt-6.1-terra":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":10,"wins":104},"claude-fable-5":{"draws":18,"losses":37,"wins":89},"claude-fable-5-1":{"draws":17,"losses":87,"wins":58},"claude-haiku-5-5":{"draws":18,"losses":19,"wins":101},"claude-opus-4-5":{"draws":35,"losses":8,"wins":191},"claude-opus-4-8":{"draws":9,"losses":18,"wins":105},"claude-opus-5":{"draws":28,"losses":94,"wins":124},"claude-opus-5-5":{"draws":12,"losses":91,"wins":53},"claude-sonnet-5":{"draws":16,"losses":9,"wins":119},"claude-sonnet-5-5":{"draws":18,"losses":38,"wins":88},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":53},"deepseek/deepseek-v4-flash":{"draws":20,"losses":2,"wins":194},"deepseek/deepseek-v4-pro":{"draws":17,"losses":7,"wins":108},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":5,"wins":110},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":16,"wins":104},"deepseek/deepseek-v4.1-flash-1017":{"draws":17,"losses":27,"wins":100},"elorian/glimpse":{"draws":5,"losses":14,"wins":59},"fireworks/ember-1":{"draws":11,"losses":17,"wins":116},"gemini-3.1-pro-preview":{"draws":16,"losses":14,"wins":114},"gemini-4-argon":{"draws":25,"losses":52,"wins":67},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":91},"google/gemini-3.5-flash":{"draws":14,"losses":18,"wins":148},"google/gemini-3.5-flash-lite":{"draws":23,"losses":4,"wins":225},"google/gemini-3.6-flash":{"draws":28,"losses":25,"wins":223},"google/gemini-3.8-flash":{"draws":21,"losses":24,"wins":99},"google/gemma-4-31b-it":{"draws":10,"losses":0,"wins":74},"gpt-4.1":{"draws":3,"losses":1,"wins":44},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":13},"gpt-5":{"draws":12,"losses":4,"wins":110},"gpt-5.4":{"draws":9,"losses":20,"wins":109},"gpt-5.4-mini":{"draws":17,"losses":6,"wins":73},"gpt-5.4-nano":{"draws":7,"losses":3,"wins":134},"gpt-5.5":{"draws":13,"losses":22,"wins":97},"gpt-5.6-luna":{"draws":20,"losses":10,"wins":114},"gpt-5.6-sol":{"draws":21,"losses":24,"wins":99},"gpt-5.6-terra":{"draws":20,"losses":9,"wins":109},"gpt-6-astra":{"draws":19,"losses":87,"wins":38},"gpt-6-luna":{"draws":22,"losses":9,"wins":113},"gpt-6-sol":{"draws":15,"losses":53,"wins":76},"gpt-6.1-sol":{"draws":21,"losses":79,"wins":44},"gpt-6.1-terra":{"draws":18,"losses":39,"wins":39},"gpt-6.1-terra-pro":{"draws":19,"losses":70,"wins":55},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":10,"losses":1,"wins":91},"inception/mercury-3":{"draws":18,"losses":6,"wins":72},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":94},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":20},"meituan/longcat-2.0":{"draws":13,"losses":8,"wins":135},"meta/muse-glimmer-30b":{"draws":15,"losses":2,"wins":109},"meta/muse-spark-1.2":{"draws":11,"losses":10,"wins":117},"meta/muse-spark-1.3":{"draws":15,"losses":13,"wins":116},"meta/muse-spark-open":{"draws":16,"losses":15,"wins":109},"meta/muse-wonder":{"draws":31,"losses":29,"wins":84},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":69},"minimax/minimax-m3.1-flash":{"draws":19,"losses":3,"wins":104},"mistralai/mistral-large-4-0":{"draws":16,"losses":9,"wins":65},"mistralai/mistral-medium-3-5":{"draws":6,"losses":4,"wins":74},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":11},"moonshotai/kimi-k3":{"draws":14,"losses":20,"wins":104},"moonshotai/kimi-k3.1-pro":{"draws":26,"losses":52,"wins":66},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":66},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":2,"wins":99},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":3,"wins":55},"o3":{"draws":9,"losses":5,"wins":184},"openai/gpt-oss-120b":{"draws":18,"losses":0,"wins":108},"poolside/laguna-s-2.1":{"draws":19,"losses":1,"wins":118},"qwen/qwen3.7-max":{"draws":10,"losses":2,"wins":72},"qwen/qwen3.7-plus":{"draws":11,"losses":0,"wins":61},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":17,"wins":113},"qwen/qwen3.8-27b":{"draws":15,"losses":4,"wins":83},"qwen/qwen3.8-flash":{"draws":10,"losses":12,"wins":74},"qwen/qwen3.8-max":{"draws":15,"losses":14,"wins":115},"qwen/qwen3.8-max-0902":{"draws":15,"losses":12,"wins":117},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":41},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":6,"wins":116},"stealth/ox-alpha":{"draws":66,"losses":46,"wins":362},"stealth/space-bunny-alpha":{"draws":13,"losses":6,"wins":95},"stepfun/step-3.7-flash":{"draws":9,"losses":1,"wins":92},"stepfun/step-5-preview":{"draws":4,"losses":2,"wins":22},"tencent/hy3-preview":{"draws":13,"losses":3,"wins":62},"tencent/hy4-preview":{"draws":12,"losses":11,"wins":115},"thinkingmachines/inkling":{"draws":24,"losses":7,"wins":161},"thinkingmachines/inkling-small":{"draws":10,"losses":0,"wins":134},"unbiased/pareto-26.10":{"draws":7,"losses":33,"wins":8},"unbiased/pareto-26.10-preview":{"draws":6,"losses":29,"wins":13},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":36},"x-ai/grok-4.5":{"draws":18,"losses":24,"wins":102},"x-ai/grok-4.6":{"draws":22,"losses":9,"wins":113},"x-ai/grok-4.7":{"draws":12,"losses":48,"wins":66},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":41},"xiaomi/mimo-v2.5":{"draws":26,"losses":3,"wins":193},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":2,"wins":49},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":6,"wins":72},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":25,"wins":59},"z-ai/glm-5.2":{"draws":29,"losses":19,"wins":240},"z-ai/glm-5.3":{"draws":23,"losses":26,"wins":89},"z-ai/glm-5.3-flash":{"draws":24,"losses":15,"wins":105},"z-ai/glm-5.3-flashx":{"draws":18,"losses":17,"wins":109}},"gpt-6.1-terra-pro":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":9,"wins":108},"claude-fable-5":{"draws":11,"losses":31,"wins":102},"claude-fable-5-1":{"draws":22,"losses":76,"wins":64},"claude-haiku-5-5":{"draws":15,"losses":12,"wins":111},"claude-opus-4-5":{"draws":27,"losses":17,"wins":190},"claude-opus-4-8":{"draws":13,"losses":15,"wins":104},"claude-opus-5":{"draws":29,"losses":92,"wins":125},"claude-opus-5-5":{"draws":13,"losses":88,"wins":55},"claude-sonnet-5":{"draws":13,"losses":9,"wins":122},"claude-sonnet-5-5":{"draws":12,"losses":41,"wins":91},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":54},"deepseek/deepseek-v4-flash":{"draws":13,"losses":8,"wins":195},"deepseek/deepseek-v4-pro":{"draws":10,"losses":10,"wins":112},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":8,"wins":113},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":14,"wins":110},"deepseek/deepseek-v4.1-flash-1017":{"draws":17,"losses":18,"wins":109},"elorian/glimpse":{"draws":10,"losses":7,"wins":61},"fireworks/ember-1":{"draws":18,"losses":13,"wins":113},"gemini-3.1-pro-preview":{"draws":7,"losses":17,"wins":120},"gemini-4-argon":{"draws":19,"losses":51,"wins":74},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":90},"google/gemini-3.5-flash":{"draws":9,"losses":15,"wins":156},"google/gemini-3.5-flash-lite":{"draws":14,"losses":10,"wins":228},"google/gemini-3.6-flash":{"draws":24,"losses":33,"wins":219},"google/gemini-3.8-flash":{"draws":20,"losses":16,"wins":108},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":79},"gpt-4.1":{"draws":3,"losses":4,"wins":41},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":14},"gpt-5":{"draws":12,"losses":5,"wins":109},"gpt-5.4":{"draws":14,"losses":22,"wins":102},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":80},"gpt-5.4-nano":{"draws":10,"losses":7,"wins":127},"gpt-5.5":{"draws":15,"losses":15,"wins":102},"gpt-5.6-luna":{"draws":13,"losses":5,"wins":126},"gpt-5.6-sol":{"draws":19,"losses":27,"wins":98},"gpt-5.6-terra":{"draws":12,"losses":12,"wins":114},"gpt-6-astra":{"draws":19,"losses":83,"wins":42},"gpt-6-luna":{"draws":16,"losses":9,"wins":119},"gpt-6-sol":{"draws":20,"losses":27,"wins":97},"gpt-6.1-sol":{"draws":15,"losses":69,"wins":60},"gpt-6.1-terra":{"draws":19,"losses":55,"wins":70},"gpt-6.1-terra-pro":{"draws":10,"losses":43,"wins":43},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":13,"losses":0,"wins":89},"inception/mercury-3":{"draws":15,"losses":5,"wins":78},"inclusionai/ling-3.0-flash":{"draws":5,"losses":4,"wins":93},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":18},"meituan/longcat-2.0":{"draws":13,"losses":7,"wins":136},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":115},"meta/muse-spark-1.2":{"draws":11,"losses":11,"wins":116},"meta/muse-spark-1.3":{"draws":13,"losses":14,"wins":117},"meta/muse-spark-open":{"draws":13,"losses":17,"wins":110},"meta/muse-wonder":{"draws":17,"losses":31,"wins":96},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":70},"minimax/minimax-m3.1-flash":{"draws":15,"losses":3,"wins":108},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":69},"mistralai/mistral-medium-3-5":{"draws":8,"losses":0,"wins":76},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":15,"losses":14,"wins":109},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":50,"wins":80},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":67},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":28},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":6,"wins":95},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":63},"o3":{"draws":6,"losses":17,"wins":175},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":114},"poolside/laguna-s-2.1":{"draws":11,"losses":12,"wins":115},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":68},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":61},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":115},"qwen/qwen3.8-27b":{"draws":13,"losses":9,"wins":80},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":77},"qwen/qwen3.8-max":{"draws":11,"losses":16,"wins":117},"qwen/qwen3.8-max-0902":{"draws":16,"losses":14,"wins":114},"recursive/flint-v1.0":{"draws":2,"losses":3,"wins":37},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":7,"wins":118},"stealth/ox-alpha":{"draws":57,"losses":39,"wins":378},"stealth/space-bunny-alpha":{"draws":9,"losses":8,"wins":97},"stepfun/step-3.7-flash":{"draws":7,"losses":0,"wins":95},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":22},"tencent/hy3-preview":{"draws":6,"losses":8,"wins":64},"tencent/hy4-preview":{"draws":10,"losses":13,"wins":115},"thinkingmachines/inkling":{"draws":24,"losses":4,"wins":164},"thinkingmachines/inkling-small":{"draws":10,"losses":3,"wins":131},"unbiased/pareto-26.10":{"draws":5,"losses":31,"wins":12},"unbiased/pareto-26.10-preview":{"draws":4,"losses":26,"wins":18},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":35},"x-ai/grok-4.5":{"draws":13,"losses":22,"wins":109},"x-ai/grok-4.6":{"draws":24,"losses":15,"wins":105},"x-ai/grok-4.7":{"draws":13,"losses":38,"wins":75},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":43},"xiaomi/mimo-v2.5":{"draws":27,"losses":9,"wins":186},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":49},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":7,"wins":74},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":15,"wins":65},"z-ai/glm-5.2":{"draws":32,"losses":17,"wins":239},"z-ai/glm-5.3":{"draws":18,"losses":28,"wins":92},"z-ai/glm-5.3-flash":{"draws":18,"losses":18,"wins":108},"z-ai/glm-5.3-flashx":{"draws":14,"losses":14,"wins":116}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":3,"losses":3,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":1,"wins":0},"elorian/glimpse":{"draws":3,"losses":1,"wins":0},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"gemini-4-argon":{"draws":1,"losses":5,"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},"gpt-6.1-terra":{"draws":1,"losses":4,"wins":1},"gpt-6.1-terra-pro":{"draws":1,"losses":5,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":1,"wins":0},"inception/mercury-3":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"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-spark-open":{"draws":4,"losses":2,"wins":0},"meta/muse-wonder":{"draws":4,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3.1-flash":{"draws":5,"losses":0,"wins":1},"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":1,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":0},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":5,"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},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"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},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":0},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":3,"wins":0},"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},"stepfun/step-5-preview":{"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":7,"losses":1,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10":{"draws":1,"losses":1,"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":33,"losses":35,"wins":24},"claude-fable-5":{"draws":26,"losses":71,"wins":5},"claude-fable-5-1":{"draws":8,"losses":106,"wins":0},"claude-haiku-5-5":{"draws":30,"losses":66,"wins":4},"claude-opus-4-5":{"draws":70,"losses":90,"wins":8},"claude-opus-4-8":{"draws":29,"losses":58,"wins":11},"claude-opus-5":{"draws":31,"losses":128,"wins":7},"claude-opus-5-5":{"draws":8,"losses":102,"wins":0},"claude-sonnet-5":{"draws":34,"losses":57,"wins":11},"claude-sonnet-5-5":{"draws":25,"losses":65,"wins":12},"cohere/north-mini-code":{"draws":10,"losses":13,"wins":15},"deepseek/deepseek-v4-flash":{"draws":53,"losses":70,"wins":29},"deepseek/deepseek-v4-pro":{"draws":35,"losses":46,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":46,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":53,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":30,"losses":66,"wins":6},"elorian/glimpse":{"draws":15,"losses":32,"wins":5},"fireworks/ember-1":{"draws":38,"losses":56,"wins":8},"gemini-3.1-pro-preview":{"draws":36,"losses":42,"wins":24},"gemini-4-argon":{"draws":8,"losses":94,"wins":0},"google/gemini-3.1-flash-lite":{"draws":22,"losses":21,"wins":29},"google/gemini-3.5-flash":{"draws":42,"losses":65,"wins":21},"google/gemini-3.5-flash-lite":{"draws":64,"losses":71,"wins":45},"google/gemini-3.6-flash":{"draws":60,"losses":118,"wins":16},"google/gemini-3.8-flash":{"draws":31,"losses":67,"wins":4},"google/gemma-4-31b-it":{"draws":31,"losses":17,"wins":16},"gpt-4.1":{"draws":12,"losses":14,"wins":8},"gpt-4.1-nano":{"draws":6,"losses":5,"wins":3},"gpt-5":{"draws":31,"losses":44,"wins":9},"gpt-5.4":{"draws":37,"losses":51,"wins":8},"gpt-5.4-mini":{"draws":28,"losses":24,"wins":16},"gpt-5.4-nano":{"draws":30,"losses":57,"wins":15},"gpt-5.5":{"draws":35,"losses":44,"wins":11},"gpt-5.6-luna":{"draws":40,"losses":40,"wins":22},"gpt-5.6-sol":{"draws":18,"losses":84,"wins":0},"gpt-5.6-terra":{"draws":35,"losses":54,"wins":9},"gpt-6-astra":{"draws":7,"losses":95,"wins":0},"gpt-6-luna":{"draws":38,"losses":54,"wins":10},"gpt-6-sol":{"draws":15,"losses":83,"wins":4},"gpt-6.1-sol":{"draws":9,"losses":93,"wins":0},"gpt-6.1-terra":{"draws":10,"losses":91,"wins":1},"gpt-6.1-terra-pro":{"draws":13,"losses":89,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":24,"losses":12,"wins":12},"inception/mercury-3":{"draws":30,"losses":30,"wins":8},"inclusionai/ling-3.0-flash":{"draws":35,"losses":20,"wins":17},"inclusionai/ling-3.1-flash":{"draws":11,"losses":5,"wins":2},"meituan/longcat-2.0":{"draws":33,"losses":44,"wins":35},"meta/muse-glimmer-30b":{"draws":34,"losses":26,"wins":24},"meta/muse-spark-1.2":{"draws":33,"losses":51,"wins":12},"meta/muse-spark-1.3":{"draws":25,"losses":67,"wins":10},"meta/muse-spark-open":{"draws":32,"losses":64,"wins":6},"meta/muse-wonder":{"draws":28,"losses":70,"wins":4},"minimax/minimax-m3":{"draws":24,"losses":19,"wins":11},"minimax/minimax-m3.1-flash":{"draws":30,"losses":47,"wins":11},"mistralai/mistral-large-4-0":{"draws":26,"losses":27,"wins":9},"mistralai/mistral-medium-3-5":{"draws":26,"losses":18,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":44,"losses":44,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":18,"losses":81,"wins":3},"nex-agi/nex-n2-pro":{"draws":16,"losses":19,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":8,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":24,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":25,"wins":6},"o3":{"draws":28,"losses":91,"wins":17},"openai/gpt-oss-120b":{"draws":30,"losses":31,"wins":27},"poolside/laguna-s-2.1":{"draws":36,"losses":30,"wins":24},"qwen/qwen3.7-max":{"draws":21,"losses":23,"wins":16},"qwen/qwen3.7-plus":{"draws":22,"losses":23,"wins":9},"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":29,"losses":33,"wins":6},"qwen/qwen3.8-max":{"draws":37,"losses":57,"wins":8},"qwen/qwen3.8-max-0902":{"draws":39,"losses":53,"wins":10},"recursive/flint-v1.0":{"draws":12,"losses":12,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":36,"losses":52,"wins":6},"stealth/ox-alpha":{"draws":92,"losses":185,"wins":33},"stealth/space-bunny-alpha":{"draws":31,"losses":37,"wins":14},"stepfun/step-3.7-flash":{"draws":18,"losses":38,"wins":12},"stepfun/step-5-preview":{"draws":3,"losses":9,"wins":4},"tencent/hy3-preview":{"draws":25,"losses":16,"wins":15},"tencent/hy4-preview":{"draws":35,"losses":50,"wins":11},"thinkingmachines/inkling":{"draws":48,"losses":46,"wins":34},"thinkingmachines/inkling-small":{"draws":40,"losses":33,"wins":29},"unbiased/pareto-26.10":{"draws":1,"losses":33,"wins":0},"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":27,"losses":68,"wins":7},"x-ai/grok-4.7":{"draws":13,"losses":72,"wins":3},"x-ai/grok-build-0.1":{"draws":16,"losses":10,"wins":8},"xiaomi/mimo-v2.5":{"draws":66,"losses":71,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":18,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":45,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":49,"wins":1},"z-ai/glm-5.2":{"draws":79,"losses":103,"wins":22},"z-ai/glm-5.3":{"draws":24,"losses":69,"wins":7},"z-ai/glm-5.3-flash":{"draws":23,"losses":67,"wins":12},"z-ai/glm-5.3-flashx":{"draws":21,"losses":72,"wins":9}},"inception/mercury-3":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":27,"wins":36},"claude-fable-5":{"draws":24,"losses":61,"wins":13},"claude-fable-5-1":{"draws":4,"losses":101,"wins":1},"claude-haiku-5-5":{"draws":23,"losses":40,"wins":29},"claude-opus-4-5":{"draws":49,"losses":55,"wins":52},"claude-opus-4-8":{"draws":24,"losses":44,"wins":20},"claude-opus-5":{"draws":18,"losses":128,"wins":18},"claude-opus-5-5":{"draws":5,"losses":102,"wins":1},"claude-sonnet-5":{"draws":31,"losses":32,"wins":33},"claude-sonnet-5-5":{"draws":21,"losses":53,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":26},"deepseek/deepseek-v4-flash":{"draws":43,"losses":39,"wins":72},"deepseek/deepseek-v4-pro":{"draws":24,"losses":31,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":28,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":40,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":55,"wins":15},"elorian/glimpse":{"draws":8,"losses":23,"wins":21},"fireworks/ember-1":{"draws":33,"losses":31,"wins":32},"gemini-3.1-pro-preview":{"draws":32,"losses":25,"wins":41},"gemini-4-argon":{"draws":11,"losses":77,"wins":8},"google/gemini-3.1-flash-lite":{"draws":13,"losses":7,"wins":40},"google/gemini-3.5-flash":{"draws":27,"losses":43,"wins":48},"google/gemini-3.5-flash-lite":{"draws":47,"losses":31,"wins":84},"google/gemini-3.6-flash":{"draws":45,"losses":87,"wins":48},"google/gemini-3.8-flash":{"draws":24,"losses":49,"wins":23},"google/gemma-4-31b-it":{"draws":19,"losses":8,"wins":29},"gpt-4.1":{"draws":8,"losses":9,"wins":15},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":6},"gpt-5":{"draws":17,"losses":27,"wins":40},"gpt-5.4":{"draws":16,"losses":44,"wins":30},"gpt-5.4-mini":{"draws":21,"losses":9,"wins":34},"gpt-5.4-nano":{"draws":26,"losses":28,"wins":46},"gpt-5.5":{"draws":26,"losses":39,"wins":21},"gpt-5.6-luna":{"draws":32,"losses":24,"wins":40},"gpt-5.6-sol":{"draws":14,"losses":65,"wins":17},"gpt-5.6-terra":{"draws":29,"losses":32,"wins":35},"gpt-6-astra":{"draws":11,"losses":83,"wins":2},"gpt-6-luna":{"draws":26,"losses":39,"wins":31},"gpt-6-sol":{"draws":16,"losses":66,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":82,"wins":7},"gpt-6.1-terra":{"draws":18,"losses":72,"wins":6},"gpt-6.1-terra-pro":{"draws":15,"losses":78,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":30,"losses":8,"wins":30},"inception/mercury-3":{"draws":14,"losses":13,"wins":13},"inclusionai/ling-3.0-flash":{"draws":20,"losses":16,"wins":38},"inclusionai/ling-3.1-flash":{"draws":2,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":25,"losses":28,"wins":51},"meta/muse-glimmer-30b":{"draws":24,"losses":17,"wins":41},"meta/muse-spark-1.2":{"draws":27,"losses":42,"wins":25},"meta/muse-spark-1.3":{"draws":19,"losses":55,"wins":22},"meta/muse-spark-open":{"draws":20,"losses":50,"wins":22},"meta/muse-wonder":{"draws":24,"losses":50,"wins":22},"minimax/minimax-m3":{"draws":16,"losses":9,"wins":29},"minimax/minimax-m3.1-flash":{"draws":18,"losses":21,"wins":39},"mistralai/mistral-large-4-0":{"draws":17,"losses":18,"wins":25},"mistralai/mistral-medium-3-5":{"draws":16,"losses":6,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":26,"losses":30,"wins":36},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":71,"wins":12},"nex-agi/nex-n2-pro":{"draws":10,"losses":8,"wins":30},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":7,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":15,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":11,"wins":22},"o3":{"draws":17,"losses":38,"wins":77},"openai/gpt-oss-120b":{"draws":26,"losses":21,"wins":39},"poolside/laguna-s-2.1":{"draws":30,"losses":17,"wins":49},"qwen/qwen3.7-max":{"draws":15,"losses":18,"wins":25},"qwen/qwen3.7-plus":{"draws":15,"losses":8,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":34,"wins":30},"qwen/qwen3.8-27b":{"draws":20,"losses":25,"wins":21},"qwen/qwen3.8-flash":{"draws":19,"losses":24,"wins":21},"qwen/qwen3.8-max":{"draws":30,"losses":41,"wins":27},"qwen/qwen3.8-max-0902":{"draws":28,"losses":39,"wins":31},"recursive/flint-v1.0":{"draws":8,"losses":6,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":29,"losses":31,"wins":29},"stealth/ox-alpha":{"draws":79,"losses":130,"wins":105},"stealth/space-bunny-alpha":{"draws":19,"losses":20,"wins":33},"stepfun/step-3.7-flash":{"draws":15,"losses":14,"wins":39},"stepfun/step-5-preview":{"draws":2,"losses":12,"wins":8},"tencent/hy3-preview":{"draws":17,"losses":13,"wins":22},"tencent/hy4-preview":{"draws":22,"losses":40,"wins":28},"thinkingmachines/inkling":{"draws":44,"losses":26,"wins":56},"thinkingmachines/inkling-small":{"draws":29,"losses":15,"wins":52},"unbiased/pareto-26.10":{"draws":2,"losses":29,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":32,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":15},"x-ai/grok-4.5":{"draws":31,"losses":42,"wins":23},"x-ai/grok-4.6":{"draws":29,"losses":48,"wins":19},"x-ai/grok-4.7":{"draws":10,"losses":66,"wins":10},"x-ai/grok-build-0.1":{"draws":11,"losses":4,"wins":17},"xiaomi/mimo-v2.5":{"draws":52,"losses":24,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":11,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":23,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":32,"wins":18},"z-ai/glm-5.2":{"draws":64,"losses":48,"wins":80},"z-ai/glm-5.3":{"draws":22,"losses":49,"wins":21},"z-ai/glm-5.3-flash":{"draws":23,"losses":39,"wins":36},"z-ai/glm-5.3-flashx":{"draws":21,"losses":42,"wins":33}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":42,"wins":16},"claude-fable-5":{"draws":18,"losses":80,"wins":4},"claude-fable-5-1":{"draws":8,"losses":106,"wins":0},"claude-haiku-5-5":{"draws":29,"losses":64,"wins":5},"claude-opus-4-5":{"draws":59,"losses":89,"wins":18},"claude-opus-4-8":{"draws":30,"losses":64,"wins":0},"claude-opus-5":{"draws":26,"losses":133,"wins":7},"claude-opus-5-5":{"draws":8,"losses":106,"wins":0},"claude-sonnet-5":{"draws":34,"losses":60,"wins":8},"claude-sonnet-5-5":{"draws":26,"losses":69,"wins":7},"cohere/north-mini-code":{"draws":12,"losses":9,"wins":13},"deepseek/deepseek-v4-flash":{"draws":59,"losses":56,"wins":43},"deepseek/deepseek-v4-pro":{"draws":32,"losses":42,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":44,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":50,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":20,"losses":79,"wins":3},"elorian/glimpse":{"draws":16,"losses":32,"wins":10},"fireworks/ember-1":{"draws":41,"losses":54,"wins":7},"gemini-3.1-pro-preview":{"draws":34,"losses":50,"wins":18},"gemini-4-argon":{"draws":7,"losses":91,"wins":4},"google/gemini-3.1-flash-lite":{"draws":20,"losses":22,"wins":24},"google/gemini-3.5-flash":{"draws":35,"losses":77,"wins":16},"google/gemini-3.5-flash-lite":{"draws":56,"losses":78,"wins":42},"google/gemini-3.6-flash":{"draws":62,"losses":111,"wins":21},"google/gemini-3.8-flash":{"draws":25,"losses":75,"wins":2},"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":29,"losses":39,"wins":20},"gpt-5.4":{"draws":24,"losses":57,"wins":17},"gpt-5.4-mini":{"draws":26,"losses":26,"wins":16},"gpt-5.4-nano":{"draws":24,"losses":50,"wins":30},"gpt-5.5":{"draws":38,"losses":45,"wins":9},"gpt-5.6-luna":{"draws":48,"losses":35,"wins":19},"gpt-5.6-sol":{"draws":12,"losses":85,"wins":5},"gpt-5.6-terra":{"draws":32,"losses":63,"wins":7},"gpt-6-astra":{"draws":5,"losses":96,"wins":1},"gpt-6-luna":{"draws":32,"losses":55,"wins":15},"gpt-6-sol":{"draws":15,"losses":79,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":98,"wins":1},"gpt-6.1-terra":{"draws":7,"losses":94,"wins":1},"gpt-6.1-terra-pro":{"draws":5,"losses":93,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":35,"losses":17,"wins":20},"inception/mercury-3":{"draws":20,"losses":38,"wins":16},"inclusionai/ling-3.0-flash":{"draws":18,"losses":17,"wins":17},"inclusionai/ling-3.1-flash":{"draws":9,"losses":6,"wins":3},"meituan/longcat-2.0":{"draws":45,"losses":39,"wins":24},"meta/muse-glimmer-30b":{"draws":46,"losses":22,"wins":18},"meta/muse-spark-1.2":{"draws":28,"losses":57,"wins":11},"meta/muse-spark-1.3":{"draws":16,"losses":77,"wins":9},"meta/muse-spark-open":{"draws":19,"losses":75,"wins":8},"meta/muse-wonder":{"draws":16,"losses":81,"wins":5},"minimax/minimax-m3":{"draws":17,"losses":22,"wins":15},"minimax/minimax-m3.1-flash":{"draws":23,"losses":45,"wins":18},"mistralai/mistral-large-4-0":{"draws":28,"losses":25,"wins":9},"mistralai/mistral-medium-3-5":{"draws":21,"losses":18,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":27,"losses":56,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":84,"wins":5},"nex-agi/nex-n2-pro":{"draws":13,"losses":18,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":4,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":25,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":22,"wins":10},"o3":{"draws":26,"losses":91,"wins":23},"openai/gpt-oss-120b":{"draws":37,"losses":41,"wins":8},"poolside/laguna-s-2.1":{"draws":30,"losses":35,"wins":29},"qwen/qwen3.7-max":{"draws":19,"losses":30,"wins":11},"qwen/qwen3.7-plus":{"draws":16,"losses":18,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":60,"wins":4},"qwen/qwen3.8-27b":{"draws":14,"losses":46,"wins":14},"qwen/qwen3.8-flash":{"draws":21,"losses":38,"wins":9},"qwen/qwen3.8-max":{"draws":37,"losses":51,"wins":14},"qwen/qwen3.8-max-0902":{"draws":37,"losses":56,"wins":9},"recursive/flint-v1.0":{"draws":8,"losses":14,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":29,"losses":45,"wins":16},"stealth/ox-alpha":{"draws":84,"losses":211,"wins":33},"stealth/space-bunny-alpha":{"draws":30,"losses":33,"wins":13},"stepfun/step-3.7-flash":{"draws":26,"losses":30,"wins":20},"stepfun/step-5-preview":{"draws":4,"losses":22,"wins":4},"tencent/hy3-preview":{"draws":22,"losses":24,"wins":8},"tencent/hy4-preview":{"draws":32,"losses":54,"wins":12},"thinkingmachines/inkling":{"draws":47,"losses":52,"wins":31},"thinkingmachines/inkling-small":{"draws":42,"losses":32,"wins":28},"unbiased/pareto-26.10":{"draws":2,"losses":32,"wins":0},"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":33,"losses":64,"wins":5},"x-ai/grok-4.7":{"draws":10,"losses":73,"wins":5},"x-ai/grok-build-0.1":{"draws":10,"losses":19,"wins":5},"xiaomi/mimo-v2.5":{"draws":68,"losses":54,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":18,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":42,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":49,"wins":5},"z-ai/glm-5.2":{"draws":85,"losses":78,"wins":41},"z-ai/glm-5.3":{"draws":21,"losses":72,"wins":3},"z-ai/glm-5.3-flash":{"draws":29,"losses":58,"wins":15},"z-ai/glm-5.3-flashx":{"draws":33,"losses":61,"wins":8}},"inclusionai/ling-3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":4,"wins":7},"claude-fable-5":{"draws":2,"losses":12,"wins":2},"claude-fable-5-1":{"draws":0,"losses":22,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":4,"wins":5},"claude-opus-4-5":{"draws":16,"losses":15,"wins":7},"claude-opus-4-8":{"draws":2,"losses":8,"wins":4},"claude-opus-5":{"draws":8,"losses":28,"wins":2},"claude-opus-5-5":{"draws":2,"losses":24,"wins":0},"claude-sonnet-5":{"draws":5,"losses":5,"wins":8},"claude-sonnet-5-5":{"draws":5,"losses":12,"wins":3},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":16,"losses":4,"wins":6},"deepseek/deepseek-v4-pro":{"draws":12,"losses":9,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":8,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":8,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":19,"wins":5},"elorian/glimpse":{"draws":3,"losses":4,"wins":5},"fireworks/ember-1":{"draws":8,"losses":4,"wins":2},"gemini-3.1-pro-preview":{"draws":5,"losses":5,"wins":6},"gemini-4-argon":{"draws":1,"losses":23,"wins":2},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":5},"google/gemini-3.5-flash":{"draws":8,"losses":16,"wins":8},"google/gemini-3.5-flash-lite":{"draws":16,"losses":9,"wins":25},"google/gemini-3.6-flash":{"draws":9,"losses":21,"wins":10},"google/gemini-3.8-flash":{"draws":10,"losses":10,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":7},"gpt-4.1":{"draws":6,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":8,"losses":5,"wins":7},"gpt-5.4":{"draws":7,"losses":17,"wins":4},"gpt-5.4-mini":{"draws":6,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":8},"gpt-5.5":{"draws":10,"losses":8,"wins":6},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":14,"wins":4},"gpt-5.6-terra":{"draws":8,"losses":3,"wins":5},"gpt-6-astra":{"draws":1,"losses":23,"wins":0},"gpt-6-luna":{"draws":14,"losses":13,"wins":9},"gpt-6-sol":{"draws":6,"losses":22,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":24,"wins":2},"gpt-6.1-terra":{"draws":3,"losses":20,"wins":1},"gpt-6.1-terra-pro":{"draws":2,"losses":18,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":5},"inception/mercury-3":{"draws":2,"losses":7,"wins":3},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":6},"meituan/longcat-2.0":{"draws":6,"losses":6,"wins":10},"meta/muse-glimmer-30b":{"draws":6,"losses":8,"wins":8},"meta/muse-spark-1.2":{"draws":11,"losses":7,"wins":6},"meta/muse-spark-1.3":{"draws":7,"losses":15,"wins":4},"meta/muse-spark-open":{"draws":8,"losses":7,"wins":3},"meta/muse-wonder":{"draws":10,"losses":20,"wins":2},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":8},"minimax/minimax-m3.1-flash":{"draws":5,"losses":8,"wins":7},"mistralai/mistral-large-4-0":{"draws":6,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":5,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":19,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":10,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":5,"wins":4},"o3":{"draws":2,"losses":14,"wins":16},"openai/gpt-oss-120b":{"draws":3,"losses":6,"wins":9},"poolside/laguna-s-2.1":{"draws":13,"losses":4,"wins":5},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":8,"wins":3},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":2},"qwen/qwen3.8-flash":{"draws":7,"losses":5,"wins":2},"qwen/qwen3.8-max":{"draws":8,"losses":10,"wins":8},"qwen/qwen3.8-max-0902":{"draws":8,"losses":6,"wins":4},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":6,"wins":7},"stealth/ox-alpha":{"draws":25,"losses":30,"wins":13},"stealth/space-bunny-alpha":{"draws":6,"losses":10,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":8,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":6},"tencent/hy4-preview":{"draws":7,"losses":14,"wins":3},"thinkingmachines/inkling":{"draws":18,"losses":5,"wins":15},"thinkingmachines/inkling-small":{"draws":7,"losses":6,"wins":9},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":4,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":8,"losses":10,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":12,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":12,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":3},"xiaomi/mimo-v2.5":{"draws":9,"losses":8,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":7,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":4,"wins":4},"z-ai/glm-5.2":{"draws":13,"losses":12,"wins":17},"z-ai/glm-5.3":{"draws":7,"losses":13,"wins":4},"z-ai/glm-5.3-flash":{"draws":8,"losses":14,"wins":4},"z-ai/glm-5.3-flashx":{"draws":6,"losses":9,"wins":1}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":65,"wins":45},"claude-fable-5":{"draws":14,"losses":122,"wins":20},"claude-fable-5-1":{"draws":4,"losses":165,"wins":7},"claude-haiku-5-5":{"draws":32,"losses":97,"wins":21},"claude-opus-4-5":{"draws":57,"losses":155,"wins":42},"claude-opus-4-8":{"draws":28,"losses":92,"wins":24},"claude-opus-5":{"draws":22,"losses":213,"wins":21},"claude-opus-5-5":{"draws":11,"losses":155,"wins":6},"claude-sonnet-5":{"draws":34,"losses":89,"wins":33},"claude-sonnet-5-5":{"draws":19,"losses":106,"wins":31},"cohere/north-mini-code":{"draws":12,"losses":16,"wins":40},"deepseek/deepseek-v4-flash":{"draws":50,"losses":103,"wins":81},"deepseek/deepseek-v4-pro":{"draws":27,"losses":86,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":72,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":97,"wins":33},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":108,"wins":22},"elorian/glimpse":{"draws":17,"losses":47,"wins":20},"fireworks/ember-1":{"draws":35,"losses":88,"wins":33},"gemini-3.1-pro-preview":{"draws":33,"losses":72,"wins":51},"gemini-4-argon":{"draws":8,"losses":138,"wins":10},"google/gemini-3.1-flash-lite":{"draws":13,"losses":32,"wins":67},"google/gemini-3.5-flash":{"draws":35,"losses":120,"wins":43},"google/gemini-3.5-flash-lite":{"draws":65,"losses":110,"wins":103},"google/gemini-3.6-flash":{"draws":55,"losses":193,"wins":52},"google/gemini-3.8-flash":{"draws":25,"losses":112,"wins":19},"google/gemma-4-31b-it":{"draws":33,"losses":26,"wins":35},"gpt-4.1":{"draws":10,"losses":30,"wins":12},"gpt-4.1-nano":{"draws":10,"losses":2,"wins":6},"gpt-5":{"draws":26,"losses":74,"wins":38},"gpt-5.4":{"draws":30,"losses":97,"wins":25},"gpt-5.4-mini":{"draws":32,"losses":40,"wins":32},"gpt-5.4-nano":{"draws":24,"losses":85,"wins":51},"gpt-5.5":{"draws":38,"losses":79,"wins":27},"gpt-5.6-luna":{"draws":33,"losses":70,"wins":53},"gpt-5.6-sol":{"draws":19,"losses":123,"wins":14},"gpt-5.6-terra":{"draws":38,"losses":74,"wins":36},"gpt-6-astra":{"draws":7,"losses":146,"wins":3},"gpt-6-luna":{"draws":35,"losses":86,"wins":35},"gpt-6-sol":{"draws":11,"losses":132,"wins":13},"gpt-6.1-sol":{"draws":6,"losses":140,"wins":10},"gpt-6.1-terra":{"draws":13,"losses":135,"wins":8},"gpt-6.1-terra-pro":{"draws":13,"losses":136,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":33,"losses":35,"wins":44},"inception/mercury-3":{"draws":25,"losses":51,"wins":28},"inclusionai/ling-3.0-flash":{"draws":45,"losses":24,"wins":39},"inclusionai/ling-3.1-flash":{"draws":6,"losses":10,"wins":6},"meituan/longcat-2.0":{"draws":26,"losses":51,"wins":51},"meta/muse-glimmer-30b":{"draws":41,"losses":45,"wins":50},"meta/muse-spark-1.2":{"draws":27,"losses":94,"wins":27},"meta/muse-spark-1.3":{"draws":23,"losses":107,"wins":26},"meta/muse-spark-open":{"draws":32,"losses":106,"wins":18},"meta/muse-wonder":{"draws":31,"losses":104,"wins":21},"minimax/minimax-m3":{"draws":14,"losses":29,"wins":41},"minimax/minimax-m3.1-flash":{"draws":30,"losses":66,"wins":40},"mistralai/mistral-large-4-0":{"draws":34,"losses":46,"wins":16},"mistralai/mistral-medium-3-5":{"draws":28,"losses":24,"wins":40},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":39,"losses":83,"wins":26},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":133,"wins":12},"nex-agi/nex-n2-pro":{"draws":10,"losses":31,"wins":45},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":17,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":37,"wins":49},"nvidia/nemotron-3.5-super-vl":{"draws":22,"losses":36,"wins":16},"o3":{"draws":30,"losses":137,"wins":65},"openai/gpt-oss-120b":{"draws":29,"losses":43,"wins":66},"poolside/laguna-s-2.1":{"draws":43,"losses":56,"wins":51},"qwen/qwen3.7-max":{"draws":19,"losses":52,"wins":21},"qwen/qwen3.7-plus":{"draws":15,"losses":32,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":93,"wins":23},"qwen/qwen3.8-27b":{"draws":21,"losses":69,"wins":18},"qwen/qwen3.8-flash":{"draws":27,"losses":52,"wins":25},"qwen/qwen3.8-max":{"draws":37,"losses":91,"wins":28},"qwen/qwen3.8-max-0902":{"draws":23,"losses":106,"wins":27},"recursive/flint-v1.0":{"draws":11,"losses":13,"wins":22},"reflection/beam-1.0-501b-a23b":{"draws":30,"losses":85,"wins":29},"stealth/ox-alpha":{"draws":98,"losses":328,"wins":84},"stealth/space-bunny-alpha":{"draws":30,"losses":65,"wins":31},"stepfun/step-3.7-flash":{"draws":20,"losses":49,"wins":45},"stepfun/step-5-preview":{"draws":3,"losses":24,"wins":9},"tencent/hy3-preview":{"draws":22,"losses":34,"wins":26},"tencent/hy4-preview":{"draws":39,"losses":90,"wins":23},"thinkingmachines/inkling":{"draws":50,"losses":79,"wins":77},"thinkingmachines/inkling-small":{"draws":40,"losses":49,"wins":67},"unbiased/pareto-26.10":{"draws":1,"losses":51,"wins":0},"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":30,"losses":101,"wins":25},"x-ai/grok-4.6":{"draws":32,"losses":99,"wins":25},"x-ai/grok-4.7":{"draws":8,"losses":121,"wins":7},"x-ai/grok-build-0.1":{"draws":14,"losses":19,"wins":19},"xiaomi/mimo-v2.5":{"draws":59,"losses":90,"wins":89},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":39,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":62,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":75,"wins":11},"z-ai/glm-5.2":{"draws":80,"losses":155,"wins":77},"z-ai/glm-5.3":{"draws":21,"losses":118,"wins":13},"z-ai/glm-5.3-flash":{"draws":24,"losses":98,"wins":34},"z-ai/glm-5.3-flashx":{"draws":23,"losses":114,"wins":19}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":44,"wins":37},"claude-fable-5":{"draws":22,"losses":97,"wins":7},"claude-fable-5-1":{"draws":8,"losses":136,"wins":0},"claude-haiku-5-5":{"draws":36,"losses":69,"wins":15},"claude-opus-4-5":{"draws":67,"losses":109,"wins":28},"claude-opus-4-8":{"draws":24,"losses":71,"wins":19},"claude-opus-5":{"draws":15,"losses":193,"wins":22},"claude-opus-5-5":{"draws":7,"losses":131,"wins":0},"claude-sonnet-5":{"draws":37,"losses":70,"wins":19},"claude-sonnet-5-5":{"draws":21,"losses":84,"wins":21},"cohere/north-mini-code":{"draws":16,"losses":17,"wins":17},"deepseek/deepseek-v4-flash":{"draws":65,"losses":74,"wins":47},"deepseek/deepseek-v4-pro":{"draws":33,"losses":56,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":65,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":67,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":30,"losses":84,"wins":12},"elorian/glimpse":{"draws":19,"losses":36,"wins":17},"fireworks/ember-1":{"draws":38,"losses":69,"wins":19},"gemini-3.1-pro-preview":{"draws":44,"losses":61,"wins":21},"gemini-4-argon":{"draws":13,"losses":109,"wins":4},"google/gemini-3.1-flash-lite":{"draws":26,"losses":21,"wins":35},"google/gemini-3.5-flash":{"draws":39,"losses":90,"wins":29},"google/gemini-3.5-flash-lite":{"draws":67,"losses":86,"wins":67},"google/gemini-3.6-flash":{"draws":64,"losses":138,"wins":40},"google/gemini-3.8-flash":{"draws":27,"losses":83,"wins":16},"google/gemma-4-31b-it":{"draws":38,"losses":17,"wins":17},"gpt-4.1":{"draws":15,"losses":17,"wins":10},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":2},"gpt-5":{"draws":30,"losses":57,"wins":27},"gpt-5.4":{"draws":27,"losses":75,"wins":20},"gpt-5.4-mini":{"draws":37,"losses":32,"wins":15},"gpt-5.4-nano":{"draws":25,"losses":53,"wins":44},"gpt-5.5":{"draws":40,"losses":62,"wins":18},"gpt-5.6-luna":{"draws":40,"losses":54,"wins":32},"gpt-5.6-sol":{"draws":19,"losses":99,"wins":8},"gpt-5.6-terra":{"draws":38,"losses":64,"wins":18},"gpt-6-astra":{"draws":6,"losses":120,"wins":0},"gpt-6-luna":{"draws":39,"losses":64,"wins":23},"gpt-6-sol":{"draws":19,"losses":97,"wins":10},"gpt-6.1-sol":{"draws":8,"losses":117,"wins":1},"gpt-6.1-terra":{"draws":15,"losses":109,"wins":2},"gpt-6.1-terra-pro":{"draws":7,"losses":115,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":34,"losses":24,"wins":26},"inception/mercury-3":{"draws":24,"losses":41,"wins":17},"inclusionai/ling-3.0-flash":{"draws":46,"losses":18,"wins":22},"inclusionai/ling-3.1-flash":{"draws":6,"losses":8,"wins":8},"meituan/longcat-2.0":{"draws":41,"losses":50,"wins":45},"meta/muse-glimmer-30b":{"draws":40,"losses":18,"wins":18},"meta/muse-spark-1.2":{"draws":34,"losses":72,"wins":18},"meta/muse-spark-1.3":{"draws":32,"losses":78,"wins":16},"meta/muse-spark-open":{"draws":32,"losses":78,"wins":16},"meta/muse-wonder":{"draws":26,"losses":85,"wins":15},"minimax/minimax-m3":{"draws":19,"losses":27,"wins":24},"minimax/minimax-m3.1-flash":{"draws":28,"losses":55,"wins":27},"mistralai/mistral-large-4-0":{"draws":27,"losses":36,"wins":19},"mistralai/mistral-medium-3-5":{"draws":27,"losses":14,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":32,"losses":73,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":20,"losses":101,"wins":5},"nex-agi/nex-n2-pro":{"draws":18,"losses":22,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":10,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":33,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":31,"wins":11},"o3":{"draws":29,"losses":106,"wins":37},"openai/gpt-oss-120b":{"draws":35,"losses":44,"wins":33},"poolside/laguna-s-2.1":{"draws":39,"losses":48,"wins":37},"qwen/qwen3.7-max":{"draws":23,"losses":31,"wins":18},"qwen/qwen3.7-plus":{"draws":21,"losses":15,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":43,"losses":68,"wins":15},"qwen/qwen3.8-27b":{"draws":23,"losses":49,"wins":14},"qwen/qwen3.8-flash":{"draws":27,"losses":32,"wins":25},"qwen/qwen3.8-max":{"draws":33,"losses":69,"wins":24},"qwen/qwen3.8-max-0902":{"draws":38,"losses":75,"wins":13},"recursive/flint-v1.0":{"draws":11,"losses":8,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":36,"losses":62,"wins":20},"stealth/ox-alpha":{"draws":88,"losses":277,"wins":61},"stealth/space-bunny-alpha":{"draws":35,"losses":40,"wins":27},"stepfun/step-3.7-flash":{"draws":20,"losses":27,"wins":41},"stepfun/step-5-preview":{"draws":2,"losses":25,"wins":13},"tencent/hy3-preview":{"draws":22,"losses":32,"wins":16},"tencent/hy4-preview":{"draws":33,"losses":75,"wins":14},"thinkingmachines/inkling":{"draws":56,"losses":57,"wins":61},"thinkingmachines/inkling-small":{"draws":44,"losses":28,"wins":54},"unbiased/pareto-26.10":{"draws":2,"losses":40,"wins":0},"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":34,"losses":82,"wins":10},"x-ai/grok-4.7":{"draws":6,"losses":92,"wins":14},"x-ai/grok-build-0.1":{"draws":14,"losses":16,"wins":12},"xiaomi/mimo-v2.5":{"draws":66,"losses":65,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":25,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":51,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":56,"wins":13},"z-ai/glm-5.2":{"draws":94,"losses":107,"wins":51},"z-ai/glm-5.3":{"draws":22,"losses":89,"wins":9},"z-ai/glm-5.3-flash":{"draws":25,"losses":83,"wins":18},"z-ai/glm-5.3-flashx":{"draws":28,"losses":78,"wins":20}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":31,"wins":63},"claude-fable-5":{"draws":17,"losses":90,"wins":31},"claude-fable-5-1":{"draws":8,"losses":139,"wins":9},"claude-haiku-5-5":{"draws":28,"losses":64,"wins":40},"claude-opus-4-5":{"draws":60,"losses":59,"wins":105},"claude-opus-4-8":{"draws":27,"losses":52,"wins":47},"claude-opus-5":{"draws":33,"losses":175,"wins":36},"claude-opus-5-5":{"draws":13,"losses":127,"wins":10},"claude-sonnet-5":{"draws":37,"losses":37,"wins":64},"claude-sonnet-5-5":{"draws":28,"losses":68,"wins":42},"cohere/north-mini-code":{"draws":4,"losses":9,"wins":39},"deepseek/deepseek-v4-flash":{"draws":52,"losses":33,"wins":121},"deepseek/deepseek-v4-pro":{"draws":23,"losses":46,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":37,"wins":67},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":51,"wins":52},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":68,"wins":44},"elorian/glimpse":{"draws":16,"losses":25,"wins":35},"fireworks/ember-1":{"draws":35,"losses":54,"wins":49},"gemini-3.1-pro-preview":{"draws":31,"losses":49,"wins":58},"gemini-4-argon":{"draws":10,"losses":114,"wins":14},"google/gemini-3.1-flash-lite":{"draws":22,"losses":8,"wins":60},"google/gemini-3.5-flash":{"draws":32,"losses":58,"wins":82},"google/gemini-3.5-flash-lite":{"draws":62,"losses":48,"wins":130},"google/gemini-3.6-flash":{"draws":56,"losses":101,"wins":107},"google/gemini-3.8-flash":{"draws":22,"losses":58,"wins":58},"google/gemma-4-31b-it":{"draws":25,"losses":17,"wins":38},"gpt-4.1":{"draws":16,"losses":9,"wins":21},"gpt-4.1-nano":{"draws":9,"losses":2,"wins":5},"gpt-5":{"draws":26,"losses":31,"wins":65},"gpt-5.4":{"draws":22,"losses":61,"wins":49},"gpt-5.4-mini":{"draws":27,"losses":18,"wins":47},"gpt-5.4-nano":{"draws":23,"losses":44,"wins":69},"gpt-5.5":{"draws":24,"losses":60,"wins":44},"gpt-5.6-luna":{"draws":38,"losses":34,"wins":66},"gpt-5.6-sol":{"draws":18,"losses":88,"wins":32},"gpt-5.6-terra":{"draws":38,"losses":37,"wins":57},"gpt-6-astra":{"draws":8,"losses":126,"wins":4},"gpt-6-luna":{"draws":37,"losses":39,"wins":62},"gpt-6-sol":{"draws":16,"losses":97,"wins":25},"gpt-6.1-sol":{"draws":11,"losses":110,"wins":17},"gpt-6.1-terra":{"draws":11,"losses":117,"wins":10},"gpt-6.1-terra-pro":{"draws":11,"losses":116,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":33,"losses":12,"wins":51},"inception/mercury-3":{"draws":27,"losses":25,"wins":42},"inclusionai/ling-3.0-flash":{"draws":28,"losses":11,"wins":57},"inclusionai/ling-3.1-flash":{"draws":11,"losses":6,"wins":7},"meituan/longcat-2.0":{"draws":27,"losses":27,"wins":94},"meta/muse-glimmer-30b":{"draws":34,"losses":18,"wins":72},"meta/muse-spark-1.2":{"draws":24,"losses":32,"wins":32},"meta/muse-spark-1.3":{"draws":31,"losses":56,"wins":51},"meta/muse-spark-open":{"draws":30,"losses":63,"wins":43},"meta/muse-wonder":{"draws":26,"losses":70,"wins":42},"minimax/minimax-m3":{"draws":13,"losses":11,"wins":52},"minimax/minimax-m3.1-flash":{"draws":25,"losses":39,"wins":56},"mistralai/mistral-large-4-0":{"draws":19,"losses":25,"wins":44},"mistralai/mistral-medium-3-5":{"draws":21,"losses":12,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":26,"losses":50,"wins":58},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":108,"wins":17},"nex-agi/nex-n2-pro":{"draws":11,"losses":10,"wins":47},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":4,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":18,"wins":61},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":13,"wins":32},"o3":{"draws":22,"losses":70,"wins":94},"openai/gpt-oss-120b":{"draws":32,"losses":13,"wins":77},"poolside/laguna-s-2.1":{"draws":28,"losses":21,"wins":85},"qwen/qwen3.7-max":{"draws":15,"losses":18,"wins":47},"qwen/qwen3.7-plus":{"draws":16,"losses":12,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":53,"wins":46},"qwen/qwen3.8-27b":{"draws":22,"losses":40,"wins":34},"qwen/qwen3.8-flash":{"draws":21,"losses":28,"wins":43},"qwen/qwen3.8-max":{"draws":37,"losses":51,"wins":50},"qwen/qwen3.8-max-0902":{"draws":35,"losses":54,"wins":49},"recursive/flint-v1.0":{"draws":7,"losses":3,"wins":30},"reflection/beam-1.0-501b-a23b":{"draws":29,"losses":44,"wins":55},"stealth/ox-alpha":{"draws":99,"losses":204,"wins":155},"stealth/space-bunny-alpha":{"draws":29,"losses":26,"wins":55},"stepfun/step-3.7-flash":{"draws":15,"losses":24,"wins":57},"stepfun/step-5-preview":{"draws":5,"losses":17,"wins":12},"tencent/hy3-preview":{"draws":21,"losses":12,"wins":43},"tencent/hy4-preview":{"draws":25,"losses":58,"wins":49},"thinkingmachines/inkling":{"draws":49,"losses":33,"wins":104},"thinkingmachines/inkling-small":{"draws":37,"losses":26,"wins":75},"unbiased/pareto-26.10":{"draws":2,"losses":44,"wins":0},"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":32,"losses":69,"wins":37},"x-ai/grok-4.6":{"draws":27,"losses":81,"wins":30},"x-ai/grok-4.7":{"draws":6,"losses":86,"wins":30},"x-ai/grok-build-0.1":{"draws":9,"losses":8,"wins":29},"xiaomi/mimo-v2.5":{"draws":59,"losses":27,"wins":126},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":12,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":32,"wins":45},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":55,"wins":27},"z-ai/glm-5.2":{"draws":66,"losses":73,"wins":137},"z-ai/glm-5.3":{"draws":23,"losses":67,"wins":42},"z-ai/glm-5.3-flash":{"draws":21,"losses":60,"wins":57},"z-ai/glm-5.3-flashx":{"draws":28,"losses":58,"wins":52}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":23,"wins":82},"claude-fable-5":{"draws":22,"losses":80,"wins":42},"claude-fable-5-1":{"draws":9,"losses":137,"wins":16},"claude-haiku-5-5":{"draws":27,"losses":60,"wins":51},"claude-opus-4-5":{"draws":52,"losses":53,"wins":129},"claude-opus-4-8":{"draws":23,"losses":54,"wins":55},"claude-opus-5":{"draws":30,"losses":165,"wins":51},"claude-opus-5-5":{"draws":10,"losses":132,"wins":14},"claude-sonnet-5":{"draws":32,"losses":35,"wins":77},"claude-sonnet-5-5":{"draws":21,"losses":69,"wins":54},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":47},"deepseek/deepseek-v4-flash":{"draws":37,"losses":28,"wins":151},"deepseek/deepseek-v4-pro":{"draws":18,"losses":35,"wins":79},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":38,"wins":68},"deepseek/deepseek-v4.1-flash":{"draws":28,"losses":54,"wins":62},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":66,"wins":62},"elorian/glimpse":{"draws":16,"losses":25,"wins":37},"fireworks/ember-1":{"draws":32,"losses":45,"wins":67},"gemini-3.1-pro-preview":{"draws":22,"losses":39,"wins":83},"gemini-4-argon":{"draws":12,"losses":113,"wins":19},"google/gemini-3.1-flash-lite":{"draws":12,"losses":5,"wins":79},"google/gemini-3.5-flash":{"draws":30,"losses":48,"wins":102},"google/gemini-3.5-flash-lite":{"draws":46,"losses":39,"wins":167},"google/gemini-3.6-flash":{"draws":44,"losses":96,"wins":136},"google/gemini-3.8-flash":{"draws":33,"losses":59,"wins":52},"google/gemma-4-31b-it":{"draws":23,"losses":8,"wins":53},"gpt-4.1":{"draws":14,"losses":6,"wins":28},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":23,"losses":28,"wins":75},"gpt-5.4":{"draws":30,"losses":55,"wins":53},"gpt-5.4-mini":{"draws":20,"losses":11,"wins":65},"gpt-5.4-nano":{"draws":21,"losses":28,"wins":95},"gpt-5.5":{"draws":30,"losses":49,"wins":53},"gpt-5.6-luna":{"draws":34,"losses":30,"wins":80},"gpt-5.6-sol":{"draws":22,"losses":74,"wins":48},"gpt-5.6-terra":{"draws":30,"losses":39,"wins":69},"gpt-6-astra":{"draws":14,"losses":117,"wins":13},"gpt-6-luna":{"draws":25,"losses":36,"wins":83},"gpt-6-sol":{"draws":22,"losses":98,"wins":24},"gpt-6.1-sol":{"draws":11,"losses":119,"wins":14},"gpt-6.1-terra":{"draws":15,"losses":116,"wins":13},"gpt-6.1-terra-pro":{"draws":13,"losses":117,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":2,"wins":1},"inception/mercury-2.5-preview":{"draws":25,"losses":10,"wins":67},"inception/mercury-3":{"draws":19,"losses":22,"wins":55},"inclusionai/ling-3.0-flash":{"draws":16,"losses":9,"wins":77},"inclusionai/ling-3.1-flash":{"draws":7,"losses":4,"wins":15},"meituan/longcat-2.0":{"draws":23,"losses":26,"wins":107},"meta/muse-glimmer-30b":{"draws":32,"losses":16,"wins":78},"meta/muse-spark-1.2":{"draws":31,"losses":51,"wins":56},"meta/muse-spark-1.3":{"draws":18,"losses":39,"wins":39},"meta/muse-spark-open":{"draws":25,"losses":52,"wins":65},"meta/muse-wonder":{"draws":28,"losses":75,"wins":41},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":63},"minimax/minimax-m3.1-flash":{"draws":19,"losses":29,"wins":78},"mistralai/mistral-large-4-0":{"draws":23,"losses":22,"wins":45},"mistralai/mistral-medium-3-5":{"draws":16,"losses":4,"wins":64},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":7},"moonshotai/kimi-k3":{"draws":29,"losses":43,"wins":66},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":113,"wins":20},"nex-agi/nex-n2-pro":{"draws":9,"losses":8,"wins":55},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":11,"wins":77},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":19,"wins":37},"o3":{"draws":18,"losses":53,"wins":127},"openai/gpt-oss-120b":{"draws":26,"losses":14,"wins":86},"poolside/laguna-s-2.1":{"draws":28,"losses":26,"wins":84},"qwen/qwen3.7-max":{"draws":16,"losses":21,"wins":47},"qwen/qwen3.7-plus":{"draws":13,"losses":13,"wins":46},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":50,"wins":59},"qwen/qwen3.8-27b":{"draws":20,"losses":29,"wins":53},"qwen/qwen3.8-flash":{"draws":21,"losses":28,"wins":47},"qwen/qwen3.8-max":{"draws":33,"losses":40,"wins":71},"qwen/qwen3.8-max-0902":{"draws":36,"losses":54,"wins":54},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":34},"reflection/beam-1.0-501b-a23b":{"draws":23,"losses":36,"wins":73},"stealth/ox-alpha":{"draws":89,"losses":165,"wins":220},"stealth/space-bunny-alpha":{"draws":18,"losses":22,"wins":74},"stepfun/step-3.7-flash":{"draws":10,"losses":13,"wins":79},"stepfun/step-5-preview":{"draws":6,"losses":9,"wins":15},"tencent/hy3-preview":{"draws":12,"losses":15,"wins":51},"tencent/hy4-preview":{"draws":25,"losses":51,"wins":62},"thinkingmachines/inkling":{"draws":34,"losses":19,"wins":139},"thinkingmachines/inkling-small":{"draws":32,"losses":13,"wins":99},"unbiased/pareto-26.10":{"draws":3,"losses":45,"wins":0},"unbiased/pareto-26.10-preview":{"draws":3,"losses":40,"wins":5},"upstage/solar-mini4":{"draws":3,"losses":8,"wins":25},"x-ai/grok-4.5":{"draws":23,"losses":61,"wins":60},"x-ai/grok-4.6":{"draws":33,"losses":56,"wins":55},"x-ai/grok-4.7":{"draws":12,"losses":81,"wins":33},"x-ai/grok-build-0.1":{"draws":12,"losses":8,"wins":28},"xiaomi/mimo-v2.5":{"draws":45,"losses":26,"wins":151},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":6,"wins":49},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":30,"wins":51},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":49,"wins":32},"z-ai/glm-5.2":{"draws":57,"losses":68,"wins":163},"z-ai/glm-5.3":{"draws":22,"losses":76,"wins":40},"z-ai/glm-5.3-flash":{"draws":27,"losses":67,"wins":50},"z-ai/glm-5.3-flashx":{"draws":22,"losses":60,"wins":62}},"meta/muse-spark-open":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":27,"wins":76},"claude-fable-5":{"draws":23,"losses":89,"wins":32},"claude-fable-5-1":{"draws":6,"losses":141,"wins":15},"claude-haiku-5-5":{"draws":23,"losses":60,"wins":55},"claude-opus-4-5":{"draws":70,"losses":61,"wins":103},"claude-opus-4-8":{"draws":32,"losses":53,"wins":47},"claude-opus-5":{"draws":27,"losses":177,"wins":42},"claude-opus-5-5":{"draws":10,"losses":131,"wins":15},"claude-sonnet-5":{"draws":38,"losses":32,"wins":74},"claude-sonnet-5-5":{"draws":26,"losses":64,"wins":52},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":41},"deepseek/deepseek-v4-flash":{"draws":47,"losses":31,"wins":138},"deepseek/deepseek-v4-pro":{"draws":31,"losses":30,"wins":71},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":35,"wins":74},"deepseek/deepseek-v4.1-flash":{"draws":30,"losses":57,"wins":55},"deepseek/deepseek-v4.1-flash-1017":{"draws":31,"losses":75,"wins":38},"elorian/glimpse":{"draws":13,"losses":35,"wins":28},"fireworks/ember-1":{"draws":34,"losses":50,"wins":60},"gemini-3.1-pro-preview":{"draws":33,"losses":40,"wins":69},"gemini-4-argon":{"draws":14,"losses":106,"wins":22},"google/gemini-3.1-flash-lite":{"draws":17,"losses":6,"wins":73},"google/gemini-3.5-flash":{"draws":32,"losses":54,"wins":94},"google/gemini-3.5-flash-lite":{"draws":48,"losses":40,"wins":164},"google/gemini-3.6-flash":{"draws":54,"losses":107,"wins":113},"google/gemini-3.8-flash":{"draws":27,"losses":63,"wins":54},"google/gemma-4-31b-it":{"draws":24,"losses":6,"wins":54},"gpt-4.1":{"draws":9,"losses":11,"wins":28},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":6},"gpt-5":{"draws":29,"losses":24,"wins":73},"gpt-5.4":{"draws":30,"losses":52,"wins":56},"gpt-5.4-mini":{"draws":27,"losses":14,"wins":55},"gpt-5.4-nano":{"draws":25,"losses":25,"wins":94},"gpt-5.5":{"draws":28,"losses":49,"wins":55},"gpt-5.6-luna":{"draws":40,"losses":33,"wins":71},"gpt-5.6-sol":{"draws":26,"losses":75,"wins":43},"gpt-5.6-terra":{"draws":42,"losses":33,"wins":63},"gpt-6-astra":{"draws":8,"losses":131,"wins":3},"gpt-6-luna":{"draws":33,"losses":43,"wins":64},"gpt-6-sol":{"draws":13,"losses":107,"wins":22},"gpt-6.1-sol":{"draws":9,"losses":122,"wins":13},"gpt-6.1-terra":{"draws":16,"losses":109,"wins":15},"gpt-6.1-terra-pro":{"draws":13,"losses":110,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":32,"losses":6,"wins":64},"inception/mercury-3":{"draws":20,"losses":22,"wins":50},"inclusionai/ling-3.0-flash":{"draws":19,"losses":8,"wins":75},"inclusionai/ling-3.1-flash":{"draws":8,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":32,"losses":18,"wins":106},"meta/muse-glimmer-30b":{"draws":32,"losses":16,"wins":78},"meta/muse-spark-1.2":{"draws":30,"losses":43,"wins":63},"meta/muse-spark-1.3":{"draws":25,"losses":65,"wins":52},"meta/muse-spark-open":{"draws":16,"losses":36,"wins":36},"meta/muse-wonder":{"draws":25,"losses":70,"wins":47},"minimax/minimax-m3":{"draws":18,"losses":6,"wins":54},"minimax/minimax-m3.1-flash":{"draws":24,"losses":34,"wins":66},"mistralai/mistral-large-4-0":{"draws":18,"losses":24,"wins":46},"mistralai/mistral-medium-3-5":{"draws":21,"losses":8,"wins":55},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":33,"losses":45,"wins":58},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":113,"wins":16},"nex-agi/nex-n2-pro":{"draws":14,"losses":9,"wins":49},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":4,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":20,"wins":63},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":11,"wins":40},"o3":{"draws":21,"losses":41,"wins":134},"openai/gpt-oss-120b":{"draws":33,"losses":10,"wins":83},"poolside/laguna-s-2.1":{"draws":31,"losses":21,"wins":86},"qwen/qwen3.7-max":{"draws":19,"losses":18,"wins":47},"qwen/qwen3.7-plus":{"draws":19,"losses":10,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":51,"wins":57},"qwen/qwen3.8-27b":{"draws":23,"losses":29,"wins":48},"qwen/qwen3.8-flash":{"draws":23,"losses":31,"wins":42},"qwen/qwen3.8-max":{"draws":34,"losses":44,"wins":66},"qwen/qwen3.8-max-0902":{"draws":35,"losses":57,"wins":52},"recursive/flint-v1.0":{"draws":6,"losses":3,"wins":33},"reflection/beam-1.0-501b-a23b":{"draws":28,"losses":35,"wins":65},"stealth/ox-alpha":{"draws":98,"losses":163,"wins":213},"stealth/space-bunny-alpha":{"draws":28,"losses":24,"wins":62},"stepfun/step-3.7-flash":{"draws":13,"losses":16,"wins":71},"stepfun/step-5-preview":{"draws":4,"losses":13,"wins":15},"tencent/hy3-preview":{"draws":19,"losses":17,"wins":42},"tencent/hy4-preview":{"draws":24,"losses":50,"wins":64},"thinkingmachines/inkling":{"draws":45,"losses":23,"wins":124},"thinkingmachines/inkling-small":{"draws":35,"losses":16,"wins":93},"unbiased/pareto-26.10":{"draws":3,"losses":43,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":45,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":29},"x-ai/grok-4.5":{"draws":30,"losses":65,"wins":49},"x-ai/grok-4.6":{"draws":34,"losses":67,"wins":43},"x-ai/grok-4.7":{"draws":9,"losses":89,"wins":26},"x-ai/grok-build-0.1":{"draws":12,"losses":7,"wins":29},"xiaomi/mimo-v2.5":{"draws":63,"losses":19,"wins":140},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":5,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":29,"wins":48},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":44,"wins":37},"z-ai/glm-5.2":{"draws":80,"losses":61,"wins":147},"z-ai/glm-5.3":{"draws":24,"losses":79,"wins":35},"z-ai/glm-5.3-flash":{"draws":25,"losses":59,"wins":60},"z-ai/glm-5.3-flashx":{"draws":30,"losses":57,"wins":55}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":16,"wins":86},"claude-fable-5":{"draws":27,"losses":60,"wins":57},"claude-fable-5-1":{"draws":12,"losses":118,"wins":32},"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":140,"wins":77},"claude-opus-5-5":{"draws":9,"losses":117,"wins":30},"claude-sonnet-5":{"draws":31,"losses":28,"wins":85},"claude-sonnet-5-5":{"draws":22,"losses":68,"wins":54},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":47},"deepseek/deepseek-v4-flash":{"draws":38,"losses":32,"wins":146},"deepseek/deepseek-v4-pro":{"draws":21,"losses":31,"wins":80},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":29,"wins":79},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":36,"wins":72},"deepseek/deepseek-v4.1-flash-1017":{"draws":32,"losses":55,"wins":57},"elorian/glimpse":{"draws":15,"losses":21,"wins":42},"fireworks/ember-1":{"draws":38,"losses":30,"wins":76},"gemini-3.1-pro-preview":{"draws":21,"losses":26,"wins":97},"gemini-4-argon":{"draws":17,"losses":95,"wins":32},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":83},"google/gemini-3.5-flash":{"draws":29,"losses":29,"wins":122},"google/gemini-3.5-flash-lite":{"draws":44,"losses":28,"wins":180},"google/gemini-3.6-flash":{"draws":50,"losses":69,"wins":157},"google/gemini-3.8-flash":{"draws":36,"losses":41,"wins":67},"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":28,"losses":43,"wins":67},"gpt-5.4-mini":{"draws":24,"losses":10,"wins":62},"gpt-5.4-nano":{"draws":18,"losses":22,"wins":104},"gpt-5.5":{"draws":35,"losses":37,"wins":60},"gpt-5.6-luna":{"draws":28,"losses":26,"wins":90},"gpt-5.6-sol":{"draws":22,"losses":57,"wins":65},"gpt-5.6-terra":{"draws":30,"losses":29,"wins":79},"gpt-6-astra":{"draws":16,"losses":115,"wins":13},"gpt-6-luna":{"draws":34,"losses":33,"wins":77},"gpt-6-sol":{"draws":17,"losses":81,"wins":46},"gpt-6.1-sol":{"draws":16,"losses":97,"wins":31},"gpt-6.1-terra":{"draws":31,"losses":84,"wins":29},"gpt-6.1-terra-pro":{"draws":17,"losses":96,"wins":31},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":4,"wins":70},"inception/mercury-3":{"draws":24,"losses":22,"wins":50},"inclusionai/ling-3.0-flash":{"draws":16,"losses":5,"wins":81},"inclusionai/ling-3.1-flash":{"draws":10,"losses":2,"wins":20},"meituan/longcat-2.0":{"draws":31,"losses":21,"wins":104},"meta/muse-glimmer-30b":{"draws":26,"losses":15,"wins":85},"meta/muse-spark-1.2":{"draws":26,"losses":42,"wins":70},"meta/muse-spark-1.3":{"draws":28,"losses":41,"wins":75},"meta/muse-spark-open":{"draws":25,"losses":47,"wins":70},"meta/muse-wonder":{"draws":18,"losses":39,"wins":39},"minimax/minimax-m3":{"draws":13,"losses":12,"wins":53},"minimax/minimax-m3.1-flash":{"draws":22,"losses":22,"wins":82},"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":4,"losses":4,"wins":10},"moonshotai/kimi-k3":{"draws":25,"losses":27,"wins":86},"moonshotai/kimi-k3.1-pro":{"draws":18,"losses":82,"wins":44},"nex-agi/nex-n2-pro":{"draws":13,"losses":6,"wins":53},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":5,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":11,"wins":76},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":10,"wins":44},"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":12,"wins":104},"qwen/qwen3.7-max":{"draws":11,"losses":12,"wins":61},"qwen/qwen3.7-plus":{"draws":14,"losses":3,"wins":55},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":45,"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},"recursive/flint-v1.0":{"draws":6,"losses":0,"wins":36},"reflection/beam-1.0-501b-a23b":{"draws":21,"losses":26,"wins":85},"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":11,"losses":10,"wins":81},"stepfun/step-5-preview":{"draws":5,"losses":9,"wins":20},"tencent/hy3-preview":{"draws":15,"losses":12,"wins":51},"tencent/hy4-preview":{"draws":27,"losses":39,"wins":72},"thinkingmachines/inkling":{"draws":44,"losses":22,"wins":126},"thinkingmachines/inkling-small":{"draws":33,"losses":15,"wins":96},"unbiased/pareto-26.10":{"draws":6,"losses":34,"wins":8},"unbiased/pareto-26.10-preview":{"draws":2,"losses":37,"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":40,"losses":41,"wins":63},"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":11,"losses":10,"wins":45},"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":64,"losses":45,"wins":179},"z-ai/glm-5.3":{"draws":17,"losses":58,"wins":63},"z-ai/glm-5.3-flash":{"draws":31,"losses":42,"wins":71},"z-ai/glm-5.3-flashx":{"draws":32,"losses":38,"wins":74}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":40,"wins":14},"claude-fable-5":{"draws":18,"losses":54,"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":38,"losses":78,"wins":12},"claude-opus-4-8":{"draws":15,"losses":48,"wins":11},"claude-opus-5":{"draws":17,"losses":115,"wins":6},"claude-opus-5-5":{"draws":2,"losses":83,"wins":1},"claude-sonnet-5":{"draws":18,"losses":45,"wins":15},"claude-sonnet-5-5":{"draws":13,"losses":52,"wins":13},"cohere/north-mini-code":{"draws":3,"losses":10,"wins":17},"deepseek/deepseek-v4-flash":{"draws":27,"losses":47,"wins":46},"deepseek/deepseek-v4-pro":{"draws":11,"losses":47,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":40,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":45,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":62,"wins":5},"elorian/glimpse":{"draws":9,"losses":23,"wins":10},"fireworks/ember-1":{"draws":16,"losses":55,"wins":7},"gemini-3.1-pro-preview":{"draws":15,"losses":40,"wins":23},"gemini-4-argon":{"draws":2,"losses":75,"wins":1},"google/gemini-3.1-flash-lite":{"draws":13,"losses":17,"wins":24},"google/gemini-3.5-flash":{"draws":18,"losses":55,"wins":25},"google/gemini-3.5-flash-lite":{"draws":33,"losses":54,"wins":47},"google/gemini-3.6-flash":{"draws":27,"losses":92,"wins":29},"google/gemini-3.8-flash":{"draws":14,"losses":57,"wins":7},"google/gemma-4-31b-it":{"draws":19,"losses":11,"wins":16},"gpt-4.1":{"draws":6,"losses":15,"wins":5},"gpt-4.1-nano":{"draws":5,"losses":1,"wins":2},"gpt-5":{"draws":13,"losses":41,"wins":16},"gpt-5.4":{"draws":14,"losses":45,"wins":15},"gpt-5.4-mini":{"draws":15,"losses":18,"wins":19},"gpt-5.4-nano":{"draws":15,"losses":40,"wins":29},"gpt-5.5":{"draws":20,"losses":41,"wins":11},"gpt-5.6-luna":{"draws":24,"losses":34,"wins":20},"gpt-5.6-sol":{"draws":13,"losses":61,"wins":4},"gpt-5.6-terra":{"draws":16,"losses":45,"wins":13},"gpt-6-astra":{"draws":1,"losses":76,"wins":1},"gpt-6-luna":{"draws":22,"losses":41,"wins":15},"gpt-6-sol":{"draws":9,"losses":62,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":70,"wins":3},"gpt-6.1-terra":{"draws":6,"losses":69,"wins":3},"gpt-6.1-terra-pro":{"draws":5,"losses":70,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":24,"losses":11,"wins":19},"inception/mercury-3":{"draws":16,"losses":29,"wins":9},"inclusionai/ling-3.0-flash":{"draws":17,"losses":15,"wins":22},"inclusionai/ling-3.1-flash":{"draws":5,"losses":8,"wins":5},"meituan/longcat-2.0":{"draws":14,"losses":41,"wins":29},"meta/muse-glimmer-30b":{"draws":19,"losses":24,"wins":27},"meta/muse-spark-1.2":{"draws":13,"losses":52,"wins":11},"meta/muse-spark-1.3":{"draws":8,"losses":63,"wins":7},"meta/muse-spark-open":{"draws":18,"losses":54,"wins":6},"meta/muse-wonder":{"draws":13,"losses":53,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":8},"minimax/minimax-m3.1-flash":{"draws":14,"losses":36,"wins":16},"mistralai/mistral-large-4-0":{"draws":12,"losses":25,"wins":13},"mistralai/mistral-medium-3-5":{"draws":12,"losses":14,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":50,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":71,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":15,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":5,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":30,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":15,"wins":12},"o3":{"draws":13,"losses":71,"wins":28},"openai/gpt-oss-120b":{"draws":18,"losses":28,"wins":24},"poolside/laguna-s-2.1":{"draws":19,"losses":33,"wins":26},"qwen/qwen3.7-max":{"draws":13,"losses":24,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":18,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":52,"wins":8},"qwen/qwen3.8-27b":{"draws":13,"losses":33,"wins":8},"qwen/qwen3.8-flash":{"draws":9,"losses":26,"wins":17},"qwen/qwen3.8-max":{"draws":17,"losses":48,"wins":13},"qwen/qwen3.8-max-0902":{"draws":17,"losses":51,"wins":10},"recursive/flint-v1.0":{"draws":7,"losses":8,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":47,"wins":12},"stealth/ox-alpha":{"draws":47,"losses":155,"wins":40},"stealth/space-bunny-alpha":{"draws":13,"losses":34,"wins":15},"stepfun/step-3.7-flash":{"draws":11,"losses":17,"wins":28},"stepfun/step-5-preview":{"draws":4,"losses":15,"wins":3},"tencent/hy3-preview":{"draws":14,"losses":18,"wins":12},"tencent/hy4-preview":{"draws":15,"losses":50,"wins":9},"thinkingmachines/inkling":{"draws":24,"losses":45,"wins":35},"thinkingmachines/inkling-small":{"draws":21,"losses":21,"wins":36},"unbiased/pareto-26.10":{"draws":0,"losses":25,"wins":1},"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":16,"losses":60,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":61,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":11,"wins":9},"xiaomi/mimo-v2.5":{"draws":38,"losses":46,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":19,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":32,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":37,"wins":8},"z-ai/glm-5.2":{"draws":39,"losses":76,"wins":41},"z-ai/glm-5.3":{"draws":14,"losses":53,"wins":7},"z-ai/glm-5.3-flash":{"draws":15,"losses":48,"wins":15},"z-ai/glm-5.3-flashx":{"draws":15,"losses":51,"wins":12}},"minimax/minimax-m3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":43,"wins":47},"claude-fable-5":{"draws":23,"losses":83,"wins":20},"claude-fable-5-1":{"draws":8,"losses":131,"wins":5},"claude-haiku-5-5":{"draws":24,"losses":68,"wins":28},"claude-opus-4-5":{"draws":53,"losses":85,"wins":66},"claude-opus-4-8":{"draws":26,"losses":60,"wins":28},"claude-opus-5":{"draws":29,"losses":160,"wins":21},"claude-opus-5-5":{"draws":7,"losses":121,"wins":2},"claude-sonnet-5":{"draws":32,"losses":57,"wins":37},"claude-sonnet-5-5":{"draws":25,"losses":79,"wins":22},"cohere/north-mini-code":{"draws":8,"losses":11,"wins":27},"deepseek/deepseek-v4-flash":{"draws":39,"losses":61,"wins":86},"deepseek/deepseek-v4-pro":{"draws":32,"losses":55,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":55,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":67,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":73,"wins":24},"elorian/glimpse":{"draws":18,"losses":35,"wins":15},"fireworks/ember-1":{"draws":31,"losses":57,"wins":38},"gemini-3.1-pro-preview":{"draws":34,"losses":49,"wins":43},"gemini-4-argon":{"draws":15,"losses":101,"wins":10},"google/gemini-3.1-flash-lite":{"draws":17,"losses":10,"wins":59},"google/gemini-3.5-flash":{"draws":32,"losses":73,"wins":53},"google/gemini-3.5-flash-lite":{"draws":54,"losses":69,"wins":101},"google/gemini-3.6-flash":{"draws":59,"losses":126,"wins":61},"google/gemini-3.8-flash":{"draws":26,"losses":75,"wins":25},"google/gemma-4-31b-it":{"draws":20,"losses":17,"wins":35},"gpt-4.1":{"draws":8,"losses":17,"wins":17},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":6},"gpt-5":{"draws":25,"losses":51,"wins":34},"gpt-5.4":{"draws":24,"losses":73,"wins":25},"gpt-5.4-mini":{"draws":32,"losses":18,"wins":34},"gpt-5.4-nano":{"draws":16,"losses":49,"wins":57},"gpt-5.5":{"draws":38,"losses":50,"wins":28},"gpt-5.6-luna":{"draws":30,"losses":46,"wins":50},"gpt-5.6-sol":{"draws":15,"losses":86,"wins":25},"gpt-5.6-terra":{"draws":32,"losses":51,"wins":37},"gpt-6-astra":{"draws":9,"losses":117,"wins":0},"gpt-6-luna":{"draws":26,"losses":56,"wins":44},"gpt-6-sol":{"draws":15,"losses":102,"wins":9},"gpt-6.1-sol":{"draws":12,"losses":112,"wins":2},"gpt-6.1-terra":{"draws":19,"losses":104,"wins":3},"gpt-6.1-terra-pro":{"draws":15,"losses":108,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":30,"losses":11,"wins":47},"inception/mercury-3":{"draws":18,"losses":39,"wins":21},"inclusionai/ling-3.0-flash":{"draws":23,"losses":18,"wins":45},"inclusionai/ling-3.1-flash":{"draws":5,"losses":7,"wins":8},"meituan/longcat-2.0":{"draws":30,"losses":40,"wins":66},"meta/muse-glimmer-30b":{"draws":28,"losses":27,"wins":55},"meta/muse-spark-1.2":{"draws":25,"losses":56,"wins":39},"meta/muse-spark-1.3":{"draws":19,"losses":78,"wins":29},"meta/muse-spark-open":{"draws":24,"losses":66,"wins":34},"meta/muse-wonder":{"draws":22,"losses":82,"wins":22},"minimax/minimax-m3":{"draws":14,"losses":16,"wins":36},"minimax/minimax-m3.1-flash":{"draws":12,"losses":32,"wins":32},"mistralai/mistral-large-4-0":{"draws":16,"losses":38,"wins":24},"mistralai/mistral-medium-3-5":{"draws":19,"losses":13,"wins":40},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":29,"losses":51,"wins":40},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":99,"wins":15},"nex-agi/nex-n2-pro":{"draws":17,"losses":14,"wins":31},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":7,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":29,"wins":37},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":20,"wins":20},"o3":{"draws":20,"losses":81,"wins":75},"openai/gpt-oss-120b":{"draws":26,"losses":29,"wins":53},"poolside/laguna-s-2.1":{"draws":25,"losses":40,"wins":51},"qwen/qwen3.7-max":{"draws":11,"losses":31,"wins":30},"qwen/qwen3.7-plus":{"draws":11,"losses":16,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":62,"wins":29},"qwen/qwen3.8-27b":{"draws":20,"losses":39,"wins":35},"qwen/qwen3.8-flash":{"draws":23,"losses":34,"wins":27},"qwen/qwen3.8-max":{"draws":30,"losses":59,"wins":37},"qwen/qwen3.8-max-0902":{"draws":31,"losses":65,"wins":30},"recursive/flint-v1.0":{"draws":10,"losses":7,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":28,"losses":46,"wins":40},"stealth/ox-alpha":{"draws":87,"losses":224,"wins":115},"stealth/space-bunny-alpha":{"draws":24,"losses":41,"wins":37},"stepfun/step-3.7-flash":{"draws":12,"losses":26,"wins":54},"stepfun/step-5-preview":{"draws":2,"losses":18,"wins":6},"tencent/hy3-preview":{"draws":16,"losses":28,"wins":22},"tencent/hy4-preview":{"draws":26,"losses":55,"wins":41},"thinkingmachines/inkling":{"draws":41,"losses":52,"wins":81},"thinkingmachines/inkling-small":{"draws":35,"losses":32,"wins":59},"unbiased/pareto-26.10":{"draws":1,"losses":40,"wins":1},"unbiased/pareto-26.10-preview":{"draws":1,"losses":40,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":32,"losses":63,"wins":31},"x-ai/grok-4.6":{"draws":35,"losses":64,"wins":27},"x-ai/grok-4.7":{"draws":10,"losses":77,"wins":21},"x-ai/grok-build-0.1":{"draws":13,"losses":11,"wins":18},"xiaomi/mimo-v2.5":{"draws":46,"losses":55,"wins":91},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":19,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":44,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":50,"wins":19},"z-ai/glm-5.2":{"draws":62,"losses":97,"wins":93},"z-ai/glm-5.3":{"draws":17,"losses":78,"wins":25},"z-ai/glm-5.3-flash":{"draws":16,"losses":67,"wins":43},"z-ai/glm-5.3-flashx":{"draws":22,"losses":75,"wins":29}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":24,"wins":33},"claude-fable-5":{"draws":20,"losses":50,"wins":20},"claude-fable-5-1":{"draws":6,"losses":88,"wins":8},"claude-haiku-5-5":{"draws":29,"losses":29,"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":26,"losses":117,"wins":19},"claude-opus-5-5":{"draws":15,"losses":79,"wins":4},"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":43,"losses":20,"wins":71},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":51,"wins":23},"elorian/glimpse":{"draws":12,"losses":17,"wins":21},"fireworks/ember-1":{"draws":26,"losses":31,"wins":33},"gemini-3.1-pro-preview":{"draws":21,"losses":34,"wins":35},"gemini-4-argon":{"draws":8,"losses":73,"wins":9},"google/gemini-3.1-flash-lite":{"draws":19,"losses":2,"wins":37},"google/gemini-3.5-flash":{"draws":35,"losses":37,"wins":40},"google/gemini-3.5-flash-lite":{"draws":52,"losses":29,"wins":75},"google/gemini-3.6-flash":{"draws":41,"losses":73,"wins":58},"google/gemini-3.8-flash":{"draws":29,"losses":36,"wins":25},"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":29,"losses":10,"wins":21},"gpt-5.4-nano":{"draws":17,"losses":24,"wins":47},"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":8,"losses":76,"wins":6},"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},"gpt-6.1-terra":{"draws":16,"losses":65,"wins":9},"gpt-6.1-terra-pro":{"draws":11,"losses":69,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":9,"wins":27},"inception/mercury-3":{"draws":17,"losses":25,"wins":18},"inclusionai/ling-3.0-flash":{"draws":28,"losses":9,"wins":25},"inclusionai/ling-3.1-flash":{"draws":6,"losses":5,"wins":5},"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":19,"losses":44,"wins":25},"meta/muse-spark-1.3":{"draws":23,"losses":45,"wins":22},"meta/muse-spark-open":{"draws":18,"losses":46,"wins":24},"meta/muse-wonder":{"draws":19,"losses":48,"wins":23},"minimax/minimax-m3":{"draws":12,"losses":13,"wins":25},"minimax/minimax-m3.1-flash":{"draws":16,"losses":24,"wins":38},"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":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":29,"losses":31,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":72,"wins":10},"nex-agi/nex-n2-pro":{"draws":13,"losses":5,"wins":26},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":4,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":21,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":11,"wins":17},"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},"recursive/flint-v1.0":{"draws":6,"losses":3,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":25,"losses":33,"wins":26},"stealth/ox-alpha":{"draws":97,"losses":120,"wins":83},"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":6,"losses":9,"wins":13},"tencent/hy3-preview":{"draws":20,"losses":16,"wins":14},"tencent/hy4-preview":{"draws":22,"losses":37,"wins":27},"thinkingmachines/inkling":{"draws":42,"losses":22,"wins":58},"thinkingmachines/inkling-small":{"draws":31,"losses":14,"wins":45},"unbiased/pareto-26.10":{"draws":3,"losses":26,"wins":1},"unbiased/pareto-26.10-preview":{"draws":2,"losses":25,"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":56,"losses":19,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":8,"wins":21},"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":14,"losses":52,"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":30,"losses":29,"wins":19},"claude-fable-5":{"draws":17,"losses":61,"wins":6},"claude-fable-5-1":{"draws":6,"losses":87,"wins":1},"claude-haiku-5-5":{"draws":21,"losses":55,"wins":4},"claude-opus-4-5":{"draws":40,"losses":85,"wins":11},"claude-opus-4-8":{"draws":21,"losses":49,"wins":6},"claude-opus-5":{"draws":23,"losses":109,"wins":12},"claude-opus-5-5":{"draws":7,"losses":85,"wins":0},"claude-sonnet-5":{"draws":26,"losses":47,"wins":11},"claude-sonnet-5-5":{"draws":18,"losses":58,"wins":8},"cohere/north-mini-code":{"draws":9,"losses":12,"wins":11},"deepseek/deepseek-v4-flash":{"draws":46,"losses":48,"wins":30},"deepseek/deepseek-v4-pro":{"draws":19,"losses":46,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":45,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":51,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":63,"wins":5},"elorian/glimpse":{"draws":9,"losses":28,"wins":7},"fireworks/ember-1":{"draws":23,"losses":52,"wins":9},"gemini-3.1-pro-preview":{"draws":25,"losses":46,"wins":13},"gemini-4-argon":{"draws":3,"losses":79,"wins":2},"google/gemini-3.1-flash-lite":{"draws":15,"losses":14,"wins":25},"google/gemini-3.5-flash":{"draws":24,"losses":64,"wins":16},"google/gemini-3.5-flash-lite":{"draws":40,"losses":69,"wins":39},"google/gemini-3.6-flash":{"draws":43,"losses":98,"wins":19},"google/gemini-3.8-flash":{"draws":15,"losses":62,"wins":7},"google/gemma-4-31b-it":{"draws":22,"losses":21,"wins":7},"gpt-4.1":{"draws":10,"losses":13,"wins":5},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":4},"gpt-5":{"draws":19,"losses":37,"wins":16},"gpt-5.4":{"draws":20,"losses":46,"wins":14},"gpt-5.4-mini":{"draws":21,"losses":25,"wins":10},"gpt-5.4-nano":{"draws":15,"losses":48,"wins":19},"gpt-5.5":{"draws":23,"losses":44,"wins":9},"gpt-5.6-luna":{"draws":30,"losses":42,"wins":12},"gpt-5.6-sol":{"draws":13,"losses":66,"wins":5},"gpt-5.6-terra":{"draws":20,"losses":49,"wins":11},"gpt-6-astra":{"draws":6,"losses":78,"wins":0},"gpt-6-luna":{"draws":27,"losses":50,"wins":7},"gpt-6-sol":{"draws":7,"losses":73,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":81,"wins":0},"gpt-6.1-terra":{"draws":6,"losses":74,"wins":4},"gpt-6.1-terra-pro":{"draws":8,"losses":76,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":26,"losses":18,"wins":18},"inception/mercury-3":{"draws":16,"losses":34,"wins":6},"inclusionai/ling-3.0-flash":{"draws":21,"losses":19,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":3,"wins":1},"meituan/longcat-2.0":{"draws":28,"losses":40,"wins":24},"meta/muse-glimmer-30b":{"draws":27,"losses":31,"wins":14},"meta/muse-spark-1.2":{"draws":21,"losses":47,"wins":12},"meta/muse-spark-1.3":{"draws":16,"losses":64,"wins":4},"meta/muse-spark-open":{"draws":21,"losses":55,"wins":8},"meta/muse-wonder":{"draws":16,"losses":62,"wins":6},"minimax/minimax-m3":{"draws":12,"losses":18,"wins":14},"minimax/minimax-m3.1-flash":{"draws":19,"losses":40,"wins":13},"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":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":23,"losses":48,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":78,"wins":3},"nex-agi/nex-n2-pro":{"draws":8,"losses":11,"wins":25},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":8,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":29,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":20,"wins":5},"o3":{"draws":21,"losses":75,"wins":14},"openai/gpt-oss-120b":{"draws":30,"losses":28,"wins":16},"poolside/laguna-s-2.1":{"draws":25,"losses":38,"wins":19},"qwen/qwen3.7-max":{"draws":18,"losses":25,"wins":5},"qwen/qwen3.7-plus":{"draws":15,"losses":14,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":59,"wins":3},"qwen/qwen3.8-27b":{"draws":19,"losses":35,"wins":4},"qwen/qwen3.8-flash":{"draws":18,"losses":31,"wins":7},"qwen/qwen3.8-max":{"draws":23,"losses":51,"wins":10},"qwen/qwen3.8-max-0902":{"draws":24,"losses":52,"wins":8},"recursive/flint-v1.0":{"draws":8,"losses":8,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":19,"losses":51,"wins":8},"stealth/ox-alpha":{"draws":66,"losses":173,"wins":43},"stealth/space-bunny-alpha":{"draws":18,"losses":36,"wins":12},"stepfun/step-3.7-flash":{"draws":19,"losses":24,"wins":13},"stepfun/step-5-preview":{"draws":3,"losses":9,"wins":4},"tencent/hy3-preview":{"draws":15,"losses":17,"wins":14},"tencent/hy4-preview":{"draws":19,"losses":49,"wins":12},"thinkingmachines/inkling":{"draws":35,"losses":49,"wins":26},"thinkingmachines/inkling-small":{"draws":33,"losses":32,"wins":19},"unbiased/pareto-26.10":{"draws":3,"losses":25,"wins":0},"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":19,"losses":58,"wins":7},"x-ai/grok-4.6":{"draws":21,"losses":56,"wins":7},"x-ai/grok-4.7":{"draws":8,"losses":61,"wins":3},"x-ai/grok-build-0.1":{"draws":12,"losses":13,"wins":3},"xiaomi/mimo-v2.5":{"draws":50,"losses":49,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":21,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":37,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":42,"wins":7},"z-ai/glm-5.2":{"draws":61,"losses":83,"wins":24},"z-ai/glm-5.3":{"draws":13,"losses":66,"wins":3},"z-ai/glm-5.3-flash":{"draws":21,"losses":53,"wins":10},"z-ai/glm-5.3-flashx":{"draws":15,"losses":60,"wins":9}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":3,"wins":8},"claude-fable-5":{"draws":5,"losses":6,"wins":3},"claude-fable-5-1":{"draws":0,"losses":6,"wins":2},"claude-haiku-5-5":{"draws":3,"losses":9,"wins":4},"claude-opus-4-5":{"draws":4,"losses":3,"wins":5},"claude-opus-4-8":{"draws":4,"losses":2,"wins":2},"claude-opus-5":{"draws":2,"losses":5,"wins":3},"claude-opus-5-5":{"draws":0,"losses":8,"wins":2},"claude-sonnet-5":{"draws":1,"losses":1,"wins":2},"claude-sonnet-5-5":{"draws":2,"losses":4,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":4},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":3,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":4,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":4,"wins":4},"elorian/glimpse":{"draws":4,"losses":7,"wins":3},"fireworks/ember-1":{"draws":7,"losses":0,"wins":5},"gemini-3.1-pro-preview":{"draws":3,"losses":1,"wins":6},"gemini-4-argon":{"draws":0,"losses":10,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":2},"google/gemini-3.5-flash-lite":{"draws":7,"losses":2,"wins":9},"google/gemini-3.6-flash":{"draws":7,"losses":2,"wins":11},"google/gemini-3.8-flash":{"draws":1,"losses":4,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":9},"gpt-4.1":{"draws":5,"losses":0,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":7,"losses":3,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":5},"gpt-5.4-nano":{"draws":1,"losses":3,"wins":4},"gpt-5.5":{"draws":2,"losses":3,"wins":3},"gpt-5.6-luna":{"draws":6,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":7,"losses":2,"wins":5},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":7,"losses":8,"wins":7},"gpt-6-sol":{"draws":0,"losses":6,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":3,"wins":4},"gpt-6.1-terra":{"draws":1,"losses":11,"wins":4},"gpt-6.1-terra-pro":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":8},"inception/mercury-3":{"draws":0,"losses":2,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":2},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":0,"wins":2},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":4},"meta/muse-spark-1.2":{"draws":7,"losses":2,"wins":1},"meta/muse-spark-1.3":{"draws":2,"losses":7,"wins":5},"meta/muse-spark-open":{"draws":5,"losses":4,"wins":5},"meta/muse-wonder":{"draws":4,"losses":10,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":4},"minimax/minimax-m3.1-flash":{"draws":1,"losses":2,"wins":5},"mistralai/mistral-large-4-0":{"draws":2,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":1,"wins":2},"o3":{"draws":3,"losses":3,"wins":4},"poolside/laguna-s-2.1":{"draws":5,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":0,"wins":3},"qwen/qwen3.8-27b":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":3,"losses":2,"wins":5},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":6},"qwen/qwen3.8-max-0902":{"draws":6,"losses":0,"wins":4},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":1,"wins":6},"stealth/ox-alpha":{"draws":7,"losses":8,"wins":9},"stealth/space-bunny-alpha":{"draws":2,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":6},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":6,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":5,"losses":1,"wins":6},"thinkingmachines/inkling-small":{"draws":3,"losses":2,"wins":9},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":8,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":8,"losses":2,"wins":0},"x-ai/grok-4.6":{"draws":4,"losses":3,"wins":7},"x-ai/grok-4.7":{"draws":1,"losses":1,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":10,"losses":0,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":2,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":0,"wins":4},"z-ai/glm-5.3":{"draws":3,"losses":5,"wins":4},"z-ai/glm-5.3-flash":{"draws":1,"losses":0,"wins":7},"z-ai/glm-5.3-flashx":{"draws":2,"losses":4,"wins":6}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":32,"wins":60},"claude-fable-5":{"draws":24,"losses":86,"wins":28},"claude-fable-5-1":{"draws":7,"losses":138,"wins":11},"claude-haiku-5-5":{"draws":34,"losses":59,"wins":39},"claude-opus-4-5":{"draws":74,"losses":68,"wins":82},"claude-opus-4-8":{"draws":34,"losses":49,"wins":43},"claude-opus-5":{"draws":37,"losses":167,"wins":40},"claude-opus-5-5":{"draws":5,"losses":135,"wins":10},"claude-sonnet-5":{"draws":38,"losses":42,"wins":58},"claude-sonnet-5-5":{"draws":28,"losses":64,"wins":46},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":35},"deepseek/deepseek-v4-flash":{"draws":59,"losses":41,"wins":106},"deepseek/deepseek-v4-pro":{"draws":28,"losses":40,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":51,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":58,"wins":45},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":81,"wins":39},"elorian/glimpse":{"draws":19,"losses":31,"wins":26},"fireworks/ember-1":{"draws":39,"losses":57,"wins":42},"gemini-3.1-pro-preview":{"draws":34,"losses":39,"wins":65},"gemini-4-argon":{"draws":6,"losses":117,"wins":15},"google/gemini-3.1-flash-lite":{"draws":25,"losses":9,"wins":56},"google/gemini-3.5-flash":{"draws":47,"losses":58,"wins":67},"google/gemini-3.5-flash-lite":{"draws":75,"losses":46,"wins":119},"google/gemini-3.6-flash":{"draws":70,"losses":104,"wins":90},"google/gemini-3.8-flash":{"draws":31,"losses":73,"wins":34},"google/gemma-4-31b-it":{"draws":29,"losses":13,"wins":38},"gpt-4.1":{"draws":13,"losses":11,"wins":22},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":8},"gpt-5":{"draws":28,"losses":44,"wins":50},"gpt-5.4":{"draws":25,"losses":69,"wins":38},"gpt-5.4-mini":{"draws":29,"losses":21,"wins":42},"gpt-5.4-nano":{"draws":32,"losses":34,"wins":70},"gpt-5.5":{"draws":34,"losses":48,"wins":46},"gpt-5.6-luna":{"draws":46,"losses":30,"wins":62},"gpt-5.6-sol":{"draws":23,"losses":85,"wins":30},"gpt-5.6-terra":{"draws":37,"losses":45,"wins":50},"gpt-6-astra":{"draws":11,"losses":118,"wins":9},"gpt-6-luna":{"draws":43,"losses":43,"wins":52},"gpt-6-sol":{"draws":14,"losses":98,"wins":26},"gpt-6.1-sol":{"draws":8,"losses":116,"wins":14},"gpt-6.1-terra":{"draws":14,"losses":104,"wins":20},"gpt-6.1-terra-pro":{"draws":15,"losses":109,"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},"inception/mercury-3":{"draws":26,"losses":36,"wins":30},"inclusionai/ling-3.0-flash":{"draws":27,"losses":13,"wins":56},"inclusionai/ling-3.1-flash":{"draws":9,"losses":4,"wins":5},"meituan/longcat-2.0":{"draws":39,"losses":26,"wins":83},"meta/muse-glimmer-30b":{"draws":32,"losses":19,"wins":73},"meta/muse-spark-1.2":{"draws":26,"losses":58,"wins":50},"meta/muse-spark-1.3":{"draws":29,"losses":66,"wins":43},"meta/muse-spark-open":{"draws":33,"losses":58,"wins":45},"meta/muse-wonder":{"draws":25,"losses":86,"wins":27},"minimax/minimax-m3":{"draws":12,"losses":14,"wins":50},"minimax/minimax-m3.1-flash":{"draws":29,"losses":40,"wins":51},"mistralai/mistral-large-4-0":{"draws":29,"losses":28,"wins":31},"mistralai/mistral-medium-3-5":{"draws":23,"losses":9,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":28,"losses":30,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":108,"wins":18},"nex-agi/nex-n2-pro":{"draws":15,"losses":10,"wins":43},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":6,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":19,"wins":52},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":16,"wins":29},"o3":{"draws":27,"losses":73,"wins":86},"openai/gpt-oss-120b":{"draws":34,"losses":19,"wins":69},"poolside/laguna-s-2.1":{"draws":40,"losses":24,"wins":70},"qwen/qwen3.7-max":{"draws":18,"losses":19,"wins":43},"qwen/qwen3.7-plus":{"draws":24,"losses":14,"wins":30},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":52,"wins":51},"qwen/qwen3.8-27b":{"draws":27,"losses":28,"wins":41},"qwen/qwen3.8-flash":{"draws":25,"losses":32,"wins":35},"qwen/qwen3.8-max":{"draws":36,"losses":55,"wins":47},"qwen/qwen3.8-max-0902":{"draws":32,"losses":72,"wins":34},"recursive/flint-v1.0":{"draws":10,"losses":3,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":35,"losses":41,"wins":52},"stealth/ox-alpha":{"draws":103,"losses":185,"wins":170},"stealth/space-bunny-alpha":{"draws":35,"losses":22,"wins":53},"stepfun/step-3.7-flash":{"draws":21,"losses":16,"wins":59},"stepfun/step-5-preview":{"draws":5,"losses":19,"wins":16},"tencent/hy3-preview":{"draws":28,"losses":20,"wins":28},"tencent/hy4-preview":{"draws":31,"losses":56,"wins":45},"thinkingmachines/inkling":{"draws":53,"losses":40,"wins":93},"thinkingmachines/inkling-small":{"draws":44,"losses":21,"wins":73},"unbiased/pareto-26.10":{"draws":3,"losses":42,"wins":1},"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":28,"losses":66,"wins":44},"x-ai/grok-4.6":{"draws":31,"losses":73,"wins":34},"x-ai/grok-4.7":{"draws":10,"losses":83,"wins":29},"x-ai/grok-build-0.1":{"draws":17,"losses":4,"wins":25},"xiaomi/mimo-v2.5":{"draws":74,"losses":31,"wins":107},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":14,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":37,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":50,"wins":24},"z-ai/glm-5.2":{"draws":88,"losses":75,"wins":113},"z-ai/glm-5.3":{"draws":30,"losses":63,"wins":39},"z-ai/glm-5.3-flash":{"draws":27,"losses":68,"wins":43},"z-ai/glm-5.3-flashx":{"draws":33,"losses":66,"wins":39}},"moonshotai/kimi-k3.1-pro":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":8,"wins":105},"claude-fable-5":{"draws":11,"losses":35,"wins":98},"claude-fable-5-1":{"draws":15,"losses":104,"wins":43},"claude-haiku-5-5":{"draws":16,"losses":23,"wins":99},"claude-opus-4-5":{"draws":25,"losses":20,"wins":189},"claude-opus-4-8":{"draws":13,"losses":13,"wins":106},"claude-opus-5":{"draws":26,"losses":109,"wins":111},"claude-opus-5-5":{"draws":12,"losses":94,"wins":50},"claude-sonnet-5":{"draws":15,"losses":11,"wins":118},"claude-sonnet-5-5":{"draws":14,"losses":40,"wins":90},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":53},"deepseek/deepseek-v4-flash":{"draws":19,"losses":9,"wins":188},"deepseek/deepseek-v4-pro":{"draws":13,"losses":16,"wins":103},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":15,"wins":105},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":25,"wins":96},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":29,"wins":102},"elorian/glimpse":{"draws":7,"losses":15,"wins":56},"fireworks/ember-1":{"draws":15,"losses":14,"wins":115},"gemini-3.1-pro-preview":{"draws":15,"losses":24,"wins":105},"gemini-4-argon":{"draws":15,"losses":72,"wins":57},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":91},"google/gemini-3.5-flash":{"draws":12,"losses":20,"wins":148},"google/gemini-3.5-flash-lite":{"draws":31,"losses":12,"wins":209},"google/gemini-3.6-flash":{"draws":29,"losses":44,"wins":203},"google/gemini-3.8-flash":{"draws":13,"losses":28,"wins":103},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":73},"gpt-4.1":{"draws":2,"losses":3,"wins":43},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":15},"gpt-5":{"draws":9,"losses":14,"wins":103},"gpt-5.4":{"draws":12,"losses":27,"wins":99},"gpt-5.4-mini":{"draws":9,"losses":6,"wins":81},"gpt-5.4-nano":{"draws":11,"losses":5,"wins":128},"gpt-5.5":{"draws":10,"losses":28,"wins":94},"gpt-5.6-luna":{"draws":9,"losses":13,"wins":122},"gpt-5.6-sol":{"draws":12,"losses":35,"wins":97},"gpt-5.6-terra":{"draws":9,"losses":17,"wins":112},"gpt-6-astra":{"draws":11,"losses":95,"wins":38},"gpt-6-luna":{"draws":14,"losses":11,"wins":119},"gpt-6-sol":{"draws":17,"losses":45,"wins":82},"gpt-6.1-sol":{"draws":14,"losses":83,"wins":47},"gpt-6.1-terra":{"draws":26,"losses":66,"wins":52},"gpt-6.1-terra-pro":{"draws":14,"losses":80,"wins":50},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":18,"losses":3,"wins":81},"inception/mercury-3":{"draws":13,"losses":12,"wins":71},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":84},"inclusionai/ling-3.1-flash":{"draws":11,"losses":2,"wins":19},"meituan/longcat-2.0":{"draws":11,"losses":12,"wins":133},"meta/muse-glimmer-30b":{"draws":20,"losses":5,"wins":101},"meta/muse-spark-1.2":{"draws":13,"losses":17,"wins":108},"meta/muse-spark-1.3":{"draws":11,"losses":20,"wins":113},"meta/muse-spark-open":{"draws":13,"losses":16,"wins":113},"meta/muse-wonder":{"draws":18,"losses":44,"wins":82},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":71},"minimax/minimax-m3.1-flash":{"draws":12,"losses":15,"wins":99},"mistralai/mistral-large-4-0":{"draws":8,"losses":10,"wins":72},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":78},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":108},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":43,"wins":43},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":61},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":7,"wins":86},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":6,"wins":56},"o3":{"draws":6,"losses":18,"wins":174},"openai/gpt-oss-120b":{"draws":15,"losses":5,"wins":106},"poolside/laguna-s-2.1":{"draws":18,"losses":11,"wins":109},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":69},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":60},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":19,"wins":108},"qwen/qwen3.8-27b":{"draws":12,"losses":8,"wins":82},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":75},"qwen/qwen3.8-max":{"draws":6,"losses":24,"wins":114},"qwen/qwen3.8-max-0902":{"draws":12,"losses":20,"wins":112},"recursive/flint-v1.0":{"draws":7,"losses":0,"wins":35},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":12,"wins":111},"stealth/ox-alpha":{"draws":54,"losses":68,"wins":352},"stealth/space-bunny-alpha":{"draws":7,"losses":10,"wins":97},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":96},"stepfun/step-5-preview":{"draws":1,"losses":4,"wins":28},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":63},"tencent/hy4-preview":{"draws":13,"losses":22,"wins":103},"thinkingmachines/inkling":{"draws":19,"losses":10,"wins":163},"thinkingmachines/inkling-small":{"draws":11,"losses":9,"wins":124},"unbiased/pareto-26.10":{"draws":5,"losses":28,"wins":15},"unbiased/pareto-26.10-preview":{"draws":5,"losses":27,"wins":16},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":36},"x-ai/grok-4.5":{"draws":19,"losses":27,"wins":98},"x-ai/grok-4.6":{"draws":11,"losses":28,"wins":105},"x-ai/grok-4.7":{"draws":11,"losses":46,"wins":69},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":37},"xiaomi/mimo-v2.5":{"draws":26,"losses":6,"wins":190},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":5,"wins":59},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":10,"wins":70},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":27,"wins":53},"z-ai/glm-5.2":{"draws":32,"losses":26,"wins":230},"z-ai/glm-5.3":{"draws":19,"losses":38,"wins":81},"z-ai/glm-5.3-flash":{"draws":16,"losses":24,"wins":104},"z-ai/glm-5.3-flashx":{"draws":12,"losses":22,"wins":110}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":36,"wins":16},"claude-fable-5":{"draws":12,"losses":58,"wins":2},"claude-fable-5-1":{"draws":4,"losses":77,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":44,"wins":10},"claude-opus-4-5":{"draws":27,"losses":74,"wins":15},"claude-opus-4-8":{"draws":13,"losses":46,"wins":5},"claude-opus-5":{"draws":4,"losses":109,"wins":3},"claude-opus-5-5":{"draws":6,"losses":74,"wins":0},"claude-sonnet-5":{"draws":20,"losses":42,"wins":10},"claude-sonnet-5-5":{"draws":14,"losses":48,"wins":10},"cohere/north-mini-code":{"draws":5,"losses":12,"wins":17},"deepseek/deepseek-v4-flash":{"draws":21,"losses":54,"wins":33},"deepseek/deepseek-v4-pro":{"draws":15,"losses":37,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":39,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":51,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":53,"wins":7},"elorian/glimpse":{"draws":8,"losses":20,"wins":10},"fireworks/ember-1":{"draws":19,"losses":44,"wins":9},"gemini-3.1-pro-preview":{"draws":19,"losses":42,"wins":11},"gemini-4-argon":{"draws":8,"losses":59,"wins":5},"google/gemini-3.1-flash-lite":{"draws":6,"losses":14,"wins":30},"google/gemini-3.5-flash":{"draws":17,"losses":53,"wins":20},"google/gemini-3.5-flash-lite":{"draws":24,"losses":57,"wins":47},"google/gemini-3.6-flash":{"draws":23,"losses":92,"wins":23},"google/gemini-3.8-flash":{"draws":12,"losses":54,"wins":6},"google/gemma-4-31b-it":{"draws":17,"losses":16,"wins":11},"gpt-4.1":{"draws":3,"losses":16,"wins":5},"gpt-4.1-nano":{"draws":5,"losses":2,"wins":3},"gpt-5":{"draws":10,"losses":32,"wins":22},"gpt-5.4":{"draws":16,"losses":38,"wins":16},"gpt-5.4-mini":{"draws":15,"losses":16,"wins":17},"gpt-5.4-nano":{"draws":10,"losses":35,"wins":27},"gpt-5.5":{"draws":13,"losses":44,"wins":9},"gpt-5.6-luna":{"draws":15,"losses":40,"wins":17},"gpt-5.6-sol":{"draws":7,"losses":59,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":41,"wins":14},"gpt-6-astra":{"draws":4,"losses":68,"wins":0},"gpt-6-luna":{"draws":13,"losses":45,"wins":14},"gpt-6-sol":{"draws":7,"losses":62,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":68,"wins":1},"gpt-6.1-terra":{"draws":6,"losses":66,"wins":0},"gpt-6.1-terra-pro":{"draws":5,"losses":67,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":17,"wins":19},"inception/mercury-3":{"draws":10,"losses":30,"wins":8},"inclusionai/ling-3.0-flash":{"draws":13,"losses":17,"wins":18},"inclusionai/ling-3.1-flash":{"draws":5,"losses":9,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":45,"wins":31},"meta/muse-glimmer-30b":{"draws":18,"losses":22,"wins":22},"meta/muse-spark-1.2":{"draws":11,"losses":47,"wins":10},"meta/muse-spark-1.3":{"draws":9,"losses":55,"wins":8},"meta/muse-spark-open":{"draws":14,"losses":49,"wins":9},"meta/muse-wonder":{"draws":13,"losses":53,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":16,"wins":15},"minimax/minimax-m3.1-flash":{"draws":17,"losses":31,"wins":14},"mistralai/mistral-large-4-0":{"draws":13,"losses":26,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":25,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":43,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":61,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":9,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":10,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":31,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":14,"wins":10},"o3":{"draws":8,"losses":76,"wins":22},"openai/gpt-oss-120b":{"draws":15,"losses":23,"wins":28},"poolside/laguna-s-2.1":{"draws":17,"losses":30,"wins":25},"qwen/qwen3.7-max":{"draws":9,"losses":25,"wins":8},"qwen/qwen3.7-plus":{"draws":5,"losses":18,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":48,"wins":9},"qwen/qwen3.8-27b":{"draws":10,"losses":27,"wins":11},"qwen/qwen3.8-flash":{"draws":12,"losses":28,"wins":8},"qwen/qwen3.8-max":{"draws":18,"losses":46,"wins":8},"qwen/qwen3.8-max-0902":{"draws":18,"losses":44,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":8,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":42,"wins":12},"stealth/ox-alpha":{"draws":52,"losses":165,"wins":33},"stealth/space-bunny-alpha":{"draws":15,"losses":30,"wins":13},"stepfun/step-3.7-flash":{"draws":8,"losses":27,"wins":17},"stepfun/step-5-preview":{"draws":4,"losses":16,"wins":4},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":15},"tencent/hy4-preview":{"draws":12,"losses":50,"wins":8},"thinkingmachines/inkling":{"draws":23,"losses":43,"wins":28},"thinkingmachines/inkling-small":{"draws":17,"losses":32,"wins":23},"unbiased/pareto-26.10":{"draws":0,"losses":24,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":10,"wins":6},"x-ai/grok-4.5":{"draws":12,"losses":51,"wins":9},"x-ai/grok-4.6":{"draws":15,"losses":52,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":54,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":11,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":47,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":15,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":31,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":37,"wins":4},"z-ai/glm-5.2":{"draws":43,"losses":73,"wins":28},"z-ai/glm-5.3":{"draws":11,"losses":57,"wins":4},"z-ai/glm-5.3-flash":{"draws":12,"losses":50,"wins":10},"z-ai/glm-5.3-flashx":{"draws":10,"losses":52,"wins":10}},"nex-agi/nex-n2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":10,"wins":9},"claude-fable-5":{"draws":2,"losses":22,"wins":6},"claude-fable-5-1":{"draws":0,"losses":35,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":16,"wins":6},"claude-opus-4-5":{"draws":11,"losses":29,"wins":8},"claude-opus-4-8":{"draws":3,"losses":19,"wins":4},"claude-opus-5":{"draws":4,"losses":46,"wins":2},"claude-opus-5-5":{"draws":3,"losses":31,"wins":0},"claude-sonnet-5":{"draws":8,"losses":15,"wins":7},"claude-sonnet-5-5":{"draws":6,"losses":19,"wins":5},"cohere/north-mini-code":{"draws":1,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":10,"losses":15,"wins":23},"deepseek/deepseek-v4-pro":{"draws":7,"losses":16,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":16,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":17,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":23,"wins":2},"elorian/glimpse":{"draws":3,"losses":12,"wins":3},"fireworks/ember-1":{"draws":5,"losses":20,"wins":5},"gemini-3.1-pro-preview":{"draws":6,"losses":16,"wins":8},"gemini-4-argon":{"draws":0,"losses":29,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":14},"google/gemini-3.5-flash":{"draws":5,"losses":17,"wins":14},"google/gemini-3.5-flash-lite":{"draws":13,"losses":18,"wins":17},"google/gemini-3.6-flash":{"draws":9,"losses":33,"wins":14},"google/gemini-3.8-flash":{"draws":6,"losses":18,"wins":6},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":11},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":7,"losses":15,"wins":6},"gpt-5.4":{"draws":8,"losses":10,"wins":10},"gpt-5.4-mini":{"draws":6,"losses":7,"wins":7},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":14},"gpt-5.5":{"draws":5,"losses":16,"wins":7},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":13},"gpt-5.6-sol":{"draws":2,"losses":26,"wins":2},"gpt-5.6-terra":{"draws":8,"losses":11,"wins":11},"gpt-6-astra":{"draws":1,"losses":29,"wins":0},"gpt-6-luna":{"draws":7,"losses":15,"wins":8},"gpt-6-sol":{"draws":1,"losses":25,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":29,"wins":0},"gpt-6.1-terra":{"draws":1,"losses":27,"wins":2},"gpt-6.1-terra-pro":{"draws":2,"losses":28,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":4,"wins":8},"inception/mercury-3":{"draws":6,"losses":11,"wins":7},"inclusionai/ling-3.0-flash":{"draws":5,"losses":13,"wins":4},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":5,"losses":12,"wins":17},"meta/muse-glimmer-30b":{"draws":8,"losses":10,"wins":10},"meta/muse-spark-1.2":{"draws":7,"losses":19,"wins":4},"meta/muse-spark-1.3":{"draws":3,"losses":21,"wins":6},"meta/muse-spark-open":{"draws":6,"losses":20,"wins":4},"meta/muse-wonder":{"draws":6,"losses":19,"wins":5},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":5},"minimax/minimax-m3.1-flash":{"draws":6,"losses":11,"wins":7},"mistralai/mistral-large-4-0":{"draws":7,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":17,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":27,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":4,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":7,"wins":6},"o3":{"draws":3,"losses":22,"wins":15},"openai/gpt-oss-120b":{"draws":8,"losses":6,"wins":16},"poolside/laguna-s-2.1":{"draws":10,"losses":11,"wins":9},"qwen/qwen3.7-max":{"draws":3,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":16,"wins":7},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"wins":5},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":8},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":16,"wins":7},"recursive/flint-v1.0":{"draws":2,"losses":3,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":13,"wins":11},"stealth/ox-alpha":{"draws":26,"losses":62,"wins":20},"stealth/space-bunny-alpha":{"draws":4,"losses":14,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":11},"stepfun/step-5-preview":{"draws":3,"losses":3,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":4},"tencent/hy4-preview":{"draws":4,"losses":18,"wins":6},"thinkingmachines/inkling":{"draws":9,"losses":12,"wins":17},"thinkingmachines/inkling-small":{"draws":9,"losses":11,"wins":10},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":6,"losses":21,"wins":3},"x-ai/grok-4.6":{"draws":5,"losses":22,"wins":3},"x-ai/grok-4.7":{"draws":1,"losses":26,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":4},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":14,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":15,"wins":1},"z-ai/glm-5.2":{"draws":16,"losses":23,"wins":21},"z-ai/glm-5.3":{"draws":3,"losses":24,"wins":3},"z-ai/glm-5.3-flash":{"draws":4,"losses":21,"wins":5},"z-ai/glm-5.3-flashx":{"draws":5,"losses":17,"wins":8}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":37,"wins":37},"claude-fable-5":{"draws":20,"losses":75,"wins":11},"claude-fable-5-1":{"draws":9,"losses":103,"wins":2},"claude-haiku-5-5":{"draws":27,"losses":53,"wins":20},"claude-opus-4-5":{"draws":59,"losses":100,"wins":33},"claude-opus-4-8":{"draws":21,"losses":61,"wins":22},"claude-opus-5":{"draws":26,"losses":157,"wins":9},"claude-opus-5-5":{"draws":6,"losses":114,"wins":4},"claude-sonnet-5":{"draws":35,"losses":52,"wins":21},"claude-sonnet-5-5":{"draws":22,"losses":72,"wins":18},"cohere/north-mini-code":{"draws":12,"losses":10,"wins":26},"deepseek/deepseek-v4-flash":{"draws":43,"losses":71,"wins":48},"deepseek/deepseek-v4-pro":{"draws":30,"losses":43,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":50,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":52,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":79,"wins":9},"elorian/glimpse":{"draws":14,"losses":37,"wins":7},"fireworks/ember-1":{"draws":33,"losses":62,"wins":21},"gemini-3.1-pro-preview":{"draws":33,"losses":53,"wins":32},"gemini-4-argon":{"draws":8,"losses":101,"wins":1},"google/gemini-3.1-flash-lite":{"draws":16,"losses":24,"wins":40},"google/gemini-3.5-flash":{"draws":31,"losses":69,"wins":36},"google/gemini-3.5-flash-lite":{"draws":51,"losses":65,"wins":66},"google/gemini-3.6-flash":{"draws":53,"losses":109,"wins":38},"google/gemini-3.8-flash":{"draws":29,"losses":70,"wins":13},"google/gemma-4-31b-it":{"draws":33,"losses":15,"wins":22},"gpt-4.1":{"draws":12,"losses":14,"wins":8},"gpt-4.1-nano":{"draws":8,"losses":2,"wins":2},"gpt-5":{"draws":27,"losses":50,"wins":23},"gpt-5.4":{"draws":26,"losses":60,"wins":18},"gpt-5.4-mini":{"draws":23,"losses":25,"wins":28},"gpt-5.4-nano":{"draws":19,"losses":50,"wins":47},"gpt-5.5":{"draws":45,"losses":51,"wins":18},"gpt-5.6-luna":{"draws":32,"losses":44,"wins":30},"gpt-5.6-sol":{"draws":13,"losses":82,"wins":7},"gpt-5.6-terra":{"draws":33,"losses":49,"wins":22},"gpt-6-astra":{"draws":8,"losses":100,"wins":0},"gpt-6-luna":{"draws":31,"losses":53,"wins":22},"gpt-6-sol":{"draws":14,"losses":83,"wins":9},"gpt-6.1-sol":{"draws":6,"losses":92,"wins":4},"gpt-6.1-terra":{"draws":9,"losses":99,"wins":2},"gpt-6.1-terra-pro":{"draws":11,"losses":95,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":28,"wins":24},"inception/mercury-3":{"draws":22,"losses":33,"wins":15},"inclusionai/ling-3.0-flash":{"draws":33,"losses":18,"wins":25},"inclusionai/ling-3.1-flash":{"draws":13,"losses":11,"wins":10},"meituan/longcat-2.0":{"draws":30,"losses":49,"wins":37},"meta/muse-glimmer-30b":{"draws":33,"losses":30,"wins":33},"meta/muse-spark-1.2":{"draws":25,"losses":61,"wins":18},"meta/muse-spark-1.3":{"draws":22,"losses":77,"wins":11},"meta/muse-spark-open":{"draws":29,"losses":63,"wins":20},"meta/muse-wonder":{"draws":29,"losses":76,"wins":11},"minimax/minimax-m3":{"draws":16,"losses":18,"wins":30},"minimax/minimax-m3.1-flash":{"draws":22,"losses":37,"wins":29},"mistralai/mistral-large-4-0":{"draws":24,"losses":29,"wins":21},"mistralai/mistral-medium-3-5":{"draws":24,"losses":17,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":27,"losses":52,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":86,"wins":7},"nex-agi/nex-n2-pro":{"draws":12,"losses":15,"wins":31},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":7,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":16,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":23,"wins":14},"o3":{"draws":25,"losses":83,"wins":46},"openai/gpt-oss-120b":{"draws":30,"losses":33,"wins":37},"poolside/laguna-s-2.1":{"draws":35,"losses":37,"wins":34},"qwen/qwen3.7-max":{"draws":22,"losses":24,"wins":20},"qwen/qwen3.7-plus":{"draws":17,"losses":25,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":55,"wins":14},"qwen/qwen3.8-27b":{"draws":22,"losses":34,"wins":14},"qwen/qwen3.8-flash":{"draws":23,"losses":33,"wins":20},"qwen/qwen3.8-max":{"draws":31,"losses":60,"wins":17},"qwen/qwen3.8-max-0902":{"draws":36,"losses":61,"wins":17},"recursive/flint-v1.0":{"draws":7,"losses":11,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":24,"losses":54,"wins":18},"stealth/ox-alpha":{"draws":73,"losses":203,"wins":52},"stealth/space-bunny-alpha":{"draws":28,"losses":38,"wins":24},"stepfun/step-3.7-flash":{"draws":19,"losses":27,"wins":28},"stepfun/step-5-preview":{"draws":5,"losses":16,"wins":11},"tencent/hy3-preview":{"draws":25,"losses":20,"wins":19},"tencent/hy4-preview":{"draws":29,"losses":60,"wins":19},"thinkingmachines/inkling":{"draws":47,"losses":42,"wins":59},"thinkingmachines/inkling-small":{"draws":34,"losses":33,"wins":41},"unbiased/pareto-26.10":{"draws":2,"losses":34,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":37,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":13,"wins":10},"x-ai/grok-4.5":{"draws":26,"losses":70,"wins":10},"x-ai/grok-4.6":{"draws":35,"losses":61,"wins":12},"x-ai/grok-4.7":{"draws":6,"losses":85,"wins":7},"x-ai/grok-build-0.1":{"draws":16,"losses":13,"wins":11},"xiaomi/mimo-v2.5":{"draws":57,"losses":60,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":19,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":45,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":48,"wins":8},"z-ai/glm-5.2":{"draws":67,"losses":89,"wins":62},"z-ai/glm-5.3":{"draws":18,"losses":78,"wins":6},"z-ai/glm-5.3-flash":{"draws":19,"losses":60,"wins":29},"z-ai/glm-5.3-flashx":{"draws":20,"losses":73,"wins":15}},"nvidia/nemotron-3.5-super-vl":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":16,"wins":22},"claude-fable-5":{"draws":13,"losses":49,"wins":4},"claude-fable-5-1":{"draws":4,"losses":71,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":33,"wins":20},"claude-opus-4-5":{"draws":36,"losses":39,"wins":33},"claude-opus-4-8":{"draws":15,"losses":35,"wins":12},"claude-opus-5":{"draws":18,"losses":81,"wins":15},"claude-opus-5-5":{"draws":4,"losses":66,"wins":4},"claude-sonnet-5":{"draws":18,"losses":31,"wins":17},"claude-sonnet-5-5":{"draws":16,"losses":39,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":22},"deepseek/deepseek-v4-flash":{"draws":22,"losses":32,"wins":44},"deepseek/deepseek-v4-pro":{"draws":17,"losses":25,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":23,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":34,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":41,"wins":11},"elorian/glimpse":{"draws":11,"losses":17,"wins":10},"fireworks/ember-1":{"draws":18,"losses":29,"wins":19},"gemini-3.1-pro-preview":{"draws":15,"losses":26,"wins":25},"gemini-4-argon":{"draws":4,"losses":55,"wins":7},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":31},"google/gemini-3.5-flash":{"draws":18,"losses":35,"wins":31},"google/gemini-3.5-flash-lite":{"draws":36,"losses":25,"wins":55},"google/gemini-3.6-flash":{"draws":33,"losses":62,"wins":31},"google/gemini-3.8-flash":{"draws":10,"losses":38,"wins":18},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":22},"gpt-4.1":{"draws":6,"losses":7,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":23,"wins":22},"gpt-5.4":{"draws":16,"losses":34,"wins":14},"gpt-5.4-mini":{"draws":14,"losses":6,"wins":24},"gpt-5.4-nano":{"draws":11,"losses":24,"wins":29},"gpt-5.5":{"draws":23,"losses":29,"wins":10},"gpt-5.6-luna":{"draws":21,"losses":17,"wins":28},"gpt-5.6-sol":{"draws":9,"losses":44,"wins":13},"gpt-5.6-terra":{"draws":24,"losses":22,"wins":18},"gpt-6-astra":{"draws":2,"losses":64,"wins":0},"gpt-6-luna":{"draws":18,"losses":33,"wins":15},"gpt-6-sol":{"draws":7,"losses":52,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":58,"wins":2},"gpt-6.1-terra":{"draws":8,"losses":55,"wins":3},"gpt-6.1-terra-pro":{"draws":3,"losses":63,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":6,"wins":25},"inception/mercury-3":{"draws":13,"losses":22,"wins":11},"inclusionai/ling-3.0-flash":{"draws":16,"losses":10,"wins":22},"inclusionai/ling-3.1-flash":{"draws":5,"losses":4,"wins":5},"meituan/longcat-2.0":{"draws":22,"losses":16,"wins":36},"meta/muse-glimmer-30b":{"draws":18,"losses":11,"wins":31},"meta/muse-spark-1.2":{"draws":19,"losses":32,"wins":13},"meta/muse-spark-1.3":{"draws":10,"losses":37,"wins":19},"meta/muse-spark-open":{"draws":13,"losses":40,"wins":11},"meta/muse-wonder":{"draws":12,"losses":44,"wins":10},"minimax/minimax-m3":{"draws":9,"losses":12,"wins":15},"minimax/minimax-m3.1-flash":{"draws":16,"losses":20,"wins":20},"mistralai/mistral-large-4-0":{"draws":14,"losses":17,"wins":11},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":19,"losses":29,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":56,"wins":6},"nex-agi/nex-n2-pro":{"draws":10,"losses":10,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":14,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":5,"wins":5},"o3":{"draws":10,"losses":33,"wins":49},"openai/gpt-oss-120b":{"draws":13,"losses":10,"wins":35},"poolside/laguna-s-2.1":{"draws":14,"losses":15,"wins":31},"qwen/qwen3.7-max":{"draws":8,"losses":16,"wins":14},"qwen/qwen3.7-plus":{"draws":7,"losses":9,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":33,"wins":15},"qwen/qwen3.8-27b":{"draws":10,"losses":21,"wins":13},"qwen/qwen3.8-flash":{"draws":14,"losses":18,"wins":12},"qwen/qwen3.8-max":{"draws":17,"losses":31,"wins":18},"qwen/qwen3.8-max-0902":{"draws":18,"losses":32,"wins":16},"recursive/flint-v1.0":{"draws":6,"losses":1,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":16,"losses":28,"wins":18},"stealth/ox-alpha":{"draws":55,"losses":101,"wins":54},"stealth/space-bunny-alpha":{"draws":17,"losses":16,"wins":21},"stepfun/step-3.7-flash":{"draws":9,"losses":7,"wins":30},"stepfun/step-5-preview":{"draws":5,"losses":8,"wins":7},"tencent/hy3-preview":{"draws":13,"losses":7,"wins":16},"tencent/hy4-preview":{"draws":15,"losses":33,"wins":16},"thinkingmachines/inkling":{"draws":25,"losses":19,"wins":42},"thinkingmachines/inkling-small":{"draws":19,"losses":9,"wins":38},"unbiased/pareto-26.10":{"draws":2,"losses":20,"wins":0},"unbiased/pareto-26.10-preview":{"draws":3,"losses":19,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":19,"losses":37,"wins":10},"x-ai/grok-4.6":{"draws":14,"losses":42,"wins":10},"x-ai/grok-4.7":{"draws":4,"losses":43,"wins":11},"x-ai/grok-build-0.1":{"draws":3,"losses":5,"wins":14},"xiaomi/mimo-v2.5":{"draws":33,"losses":24,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":4,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":18,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":27,"wins":13},"z-ai/glm-5.2":{"draws":42,"losses":44,"wins":46},"z-ai/glm-5.3":{"draws":9,"losses":51,"wins":4},"z-ai/glm-5.3-flash":{"draws":10,"losses":35,"wins":21},"z-ai/glm-5.3-flashx":{"draws":13,"losses":39,"wins":14}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":38,"losses":56,"wins":90},"claude-fable-5":{"draws":17,"losses":151,"wins":30},"claude-fable-5-1":{"draws":3,"losses":205,"wins":10},"claude-haiku-5-5":{"draws":32,"losses":101,"wins":61},"claude-opus-4-5":{"draws":38,"losses":191,"wins":97},"claude-opus-4-8":{"draws":25,"losses":110,"wins":55},"claude-opus-5":{"draws":24,"losses":265,"wins":23},"claude-opus-5-5":{"draws":11,"losses":204,"wins":3},"claude-sonnet-5":{"draws":26,"losses":89,"wins":83},"claude-sonnet-5-5":{"draws":17,"losses":135,"wins":46},"cohere/north-mini-code":{"draws":13,"losses":14,"wins":61},"deepseek/deepseek-v4-flash":{"draws":38,"losses":85,"wins":183},"deepseek/deepseek-v4-pro":{"draws":20,"losses":92,"wins":72},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":101,"wins":56},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":94,"wins":66},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":124,"wins":56},"elorian/glimpse":{"draws":14,"losses":56,"wins":36},"fireworks/ember-1":{"draws":34,"losses":112,"wins":52},"gemini-3.1-pro-preview":{"draws":28,"losses":79,"wins":91},"gemini-4-argon":{"draws":2,"losses":187,"wins":9},"google/gemini-3.1-flash-lite":{"draws":18,"losses":15,"wins":125},"google/gemini-3.5-flash":{"draws":31,"losses":138,"wins":89},"google/gemini-3.5-flash-lite":{"draws":53,"losses":99,"wins":204},"google/gemini-3.6-flash":{"draws":45,"losses":209,"wins":130},"google/gemini-3.8-flash":{"draws":20,"losses":131,"wins":47},"google/gemma-4-31b-it":{"draws":25,"losses":21,"wins":72},"gpt-4.1":{"draws":11,"losses":29,"wins":26},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":11},"gpt-5":{"draws":23,"losses":89,"wins":68},"gpt-5.4":{"draws":19,"losses":127,"wins":50},"gpt-5.4-mini":{"draws":21,"losses":35,"wins":76},"gpt-5.4-nano":{"draws":16,"losses":103,"wins":107},"gpt-5.5":{"draws":33,"losses":105,"wins":46},"gpt-5.6-luna":{"draws":36,"losses":70,"wins":92},"gpt-5.6-sol":{"draws":11,"losses":155,"wins":32},"gpt-5.6-terra":{"draws":31,"losses":89,"wins":66},"gpt-6-astra":{"draws":7,"losses":190,"wins":1},"gpt-6-luna":{"draws":33,"losses":99,"wins":66},"gpt-6-sol":{"draws":9,"losses":172,"wins":17},"gpt-6.1-sol":{"draws":3,"losses":187,"wins":8},"gpt-6.1-terra":{"draws":9,"losses":184,"wins":5},"gpt-6.1-terra-pro":{"draws":6,"losses":175,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":28,"losses":17,"wins":91},"inception/mercury-3":{"draws":17,"losses":77,"wins":38},"inclusionai/ling-3.0-flash":{"draws":26,"losses":23,"wins":91},"inclusionai/ling-3.1-flash":{"draws":2,"losses":16,"wins":14},"meituan/longcat-2.0":{"draws":30,"losses":65,"wins":137},"meta/muse-glimmer-30b":{"draws":29,"losses":37,"wins":106},"meta/muse-spark-1.2":{"draws":22,"losses":94,"wins":70},"meta/muse-spark-1.3":{"draws":18,"losses":127,"wins":53},"meta/muse-spark-open":{"draws":21,"losses":134,"wins":41},"meta/muse-wonder":{"draws":13,"losses":151,"wins":34},"minimax/minimax-m3":{"draws":13,"losses":28,"wins":71},"minimax/minimax-m3.1-flash":{"draws":20,"losses":75,"wins":81},"mistralai/mistral-large-4-0":{"draws":28,"losses":53,"wins":39},"mistralai/mistral-medium-3-5":{"draws":21,"losses":14,"wins":75},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":27,"losses":86,"wins":73},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":174,"wins":18},"nex-agi/nex-n2-pro":{"draws":8,"losses":22,"wins":76},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":15,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":46,"wins":83},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":49,"wins":33},"o3":{"draws":22,"losses":123,"wins":123},"openai/gpt-oss-120b":{"draws":22,"losses":30,"wins":120},"poolside/laguna-s-2.1":{"draws":28,"losses":64,"wins":100},"qwen/qwen3.7-max":{"draws":17,"losses":46,"wins":61},"qwen/qwen3.7-plus":{"draws":10,"losses":29,"wins":71},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":112,"wins":59},"qwen/qwen3.8-27b":{"draws":12,"losses":74,"wins":58},"qwen/qwen3.8-flash":{"draws":17,"losses":63,"wins":52},"qwen/qwen3.8-max":{"draws":31,"losses":103,"wins":64},"qwen/qwen3.8-max-0902":{"draws":33,"losses":101,"wins":64},"recursive/flint-v1.0":{"draws":4,"losses":6,"wins":52},"reflection/beam-1.0-501b-a23b":{"draws":24,"losses":88,"wins":64},"stealth/ox-alpha":{"draws":72,"losses":321,"wins":211},"stealth/space-bunny-alpha":{"draws":24,"losses":57,"wins":79},"stepfun/step-3.7-flash":{"draws":22,"losses":44,"wins":94},"stepfun/step-5-preview":{"draws":4,"losses":18,"wins":14},"tencent/hy3-preview":{"draws":22,"losses":39,"wins":43},"tencent/hy4-preview":{"draws":25,"losses":104,"wins":67},"thinkingmachines/inkling":{"draws":38,"losses":58,"wins":170},"thinkingmachines/inkling-small":{"draws":34,"losses":44,"wins":120},"unbiased/pareto-26.10":{"draws":0,"losses":66,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":63,"wins":3},"upstage/solar-mini4":{"draws":9,"losses":13,"wins":40},"x-ai/grok-4.5":{"draws":21,"losses":120,"wins":57},"x-ai/grok-4.6":{"draws":33,"losses":120,"wins":45},"x-ai/grok-4.7":{"draws":12,"losses":130,"wins":36},"x-ai/grok-build-0.1":{"draws":11,"losses":17,"wins":38},"xiaomi/mimo-v2.5":{"draws":49,"losses":69,"wins":198},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":23,"wins":70},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":80,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":96,"wins":25},"z-ai/glm-5.2":{"draws":62,"losses":153,"wins":181},"z-ai/glm-5.3":{"draws":14,"losses":140,"wins":34},"z-ai/glm-5.3-flash":{"draws":20,"losses":101,"wins":77},"z-ai/glm-5.3-flashx":{"draws":16,"losses":123,"wins":59}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":47,"wins":35},"claude-fable-5":{"draws":26,"losses":89,"wins":11},"claude-fable-5-1":{"draws":5,"losses":137,"wins":0},"claude-haiku-5-5":{"draws":29,"losses":79,"wins":12},"claude-opus-4-5":{"draws":61,"losses":111,"wins":32},"claude-opus-4-8":{"draws":31,"losses":68,"wins":15},"claude-opus-5":{"draws":26,"losses":183,"wins":11},"claude-opus-5-5":{"draws":9,"losses":129,"wins":0},"claude-sonnet-5":{"draws":34,"losses":75,"wins":17},"claude-sonnet-5-5":{"draws":25,"losses":83,"wins":18},"cohere/north-mini-code":{"draws":13,"losses":17,"wins":20},"deepseek/deepseek-v4-flash":{"draws":57,"losses":68,"wins":65},"deepseek/deepseek-v4-pro":{"draws":30,"losses":58,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":53,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":71,"wins":26},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":84,"wins":17},"elorian/glimpse":{"draws":14,"losses":36,"wins":18},"fireworks/ember-1":{"draws":40,"losses":66,"wins":20},"gemini-3.1-pro-preview":{"draws":34,"losses":59,"wins":33},"gemini-4-argon":{"draws":3,"losses":121,"wins":2},"google/gemini-3.1-flash-lite":{"draws":17,"losses":23,"wins":42},"google/gemini-3.5-flash":{"draws":35,"losses":83,"wins":38},"google/gemini-3.5-flash-lite":{"draws":60,"losses":78,"wins":80},"google/gemini-3.6-flash":{"draws":59,"losses":142,"wins":39},"google/gemini-3.8-flash":{"draws":25,"losses":92,"wins":9},"google/gemma-4-31b-it":{"draws":31,"losses":10,"wins":33},"gpt-4.1":{"draws":11,"losses":22,"wins":9},"gpt-4.1-nano":{"draws":12,"losses":0,"wins":4},"gpt-5":{"draws":27,"losses":62,"wins":23},"gpt-5.4":{"draws":31,"losses":69,"wins":20},"gpt-5.4-mini":{"draws":31,"losses":32,"wins":21},"gpt-5.4-nano":{"draws":35,"losses":44,"wins":47},"gpt-5.5":{"draws":41,"losses":59,"wins":16},"gpt-5.6-luna":{"draws":43,"losses":51,"wins":32},"gpt-5.6-sol":{"draws":15,"losses":103,"wins":8},"gpt-5.6-terra":{"draws":37,"losses":70,"wins":13},"gpt-6-astra":{"draws":12,"losses":114,"wins":0},"gpt-6-luna":{"draws":38,"losses":59,"wins":29},"gpt-6-sol":{"draws":19,"losses":101,"wins":6},"gpt-6.1-sol":{"draws":7,"losses":118,"wins":1},"gpt-6.1-terra":{"draws":18,"losses":108,"wins":0},"gpt-6.1-terra-pro":{"draws":8,"losses":114,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":30,"losses":27,"wins":31},"inception/mercury-3":{"draws":26,"losses":39,"wins":21},"inclusionai/ling-3.0-flash":{"draws":37,"losses":8,"wins":41},"inclusionai/ling-3.1-flash":{"draws":3,"losses":9,"wins":6},"meituan/longcat-2.0":{"draws":29,"losses":66,"wins":43},"meta/muse-glimmer-30b":{"draws":35,"losses":33,"wins":44},"meta/muse-spark-1.2":{"draws":32,"losses":77,"wins":13},"meta/muse-spark-1.3":{"draws":26,"losses":86,"wins":14},"meta/muse-spark-open":{"draws":33,"losses":83,"wins":10},"meta/muse-wonder":{"draws":23,"losses":93,"wins":10},"minimax/minimax-m3":{"draws":18,"losses":24,"wins":28},"minimax/minimax-m3.1-flash":{"draws":26,"losses":53,"wins":29},"mistralai/mistral-large-4-0":{"draws":31,"losses":35,"wins":14},"mistralai/mistral-medium-3-5":{"draws":30,"losses":16,"wins":28},"moonshotai/kimi-k3":{"draws":34,"losses":69,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":106,"wins":5},"nex-agi/nex-n2-pro":{"draws":15,"losses":28,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":16,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":37,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":35,"wins":10},"o3":{"draws":22,"losses":120,"wins":30},"openai/gpt-oss-120b":{"draws":18,"losses":27,"wins":27},"poolside/laguna-s-2.1":{"draws":44,"losses":43,"wins":39},"qwen/qwen3.7-max":{"draws":23,"losses":33,"wins":18},"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":23,"losses":38,"wins":23},"qwen/qwen3.8-max":{"draws":38,"losses":78,"wins":10},"qwen/qwen3.8-max-0902":{"draws":33,"losses":77,"wins":16},"recursive/flint-v1.0":{"draws":8,"losses":9,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":36,"losses":65,"wins":17},"stealth/ox-alpha":{"draws":99,"losses":262,"wins":63},"stealth/space-bunny-alpha":{"draws":28,"losses":48,"wins":24},"stepfun/step-3.7-flash":{"draws":27,"losses":36,"wins":25},"stepfun/step-5-preview":{"draws":1,"losses":18,"wins":3},"tencent/hy3-preview":{"draws":22,"losses":27,"wins":19},"tencent/hy4-preview":{"draws":38,"losses":61,"wins":21},"thinkingmachines/inkling":{"draws":42,"losses":65,"wins":61},"thinkingmachines/inkling-small":{"draws":38,"losses":34,"wins":54},"unbiased/pareto-26.10":{"draws":0,"losses":42,"wins":0},"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":35,"losses":78,"wins":13},"x-ai/grok-4.6":{"draws":33,"losses":81,"wins":12},"x-ai/grok-4.7":{"draws":9,"losses":98,"wins":5},"x-ai/grok-build-0.1":{"draws":13,"losses":17,"wins":12},"xiaomi/mimo-v2.5":{"draws":55,"losses":61,"wins":72},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":23,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":57,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":62,"wins":6},"z-ai/glm-5.2":{"draws":87,"losses":113,"wins":52},"z-ai/glm-5.3":{"draws":26,"losses":91,"wins":5},"z-ai/glm-5.3-flash":{"draws":23,"losses":81,"wins":22},"z-ai/glm-5.3-flashx":{"draws":25,"losses":85,"wins":16}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":47,"wins":40},"claude-fable-5":{"draws":20,"losses":98,"wins":20},"claude-fable-5-1":{"draws":5,"losses":144,"wins":3},"claude-haiku-5-5":{"draws":33,"losses":61,"wins":36},"claude-opus-4-5":{"draws":70,"losses":116,"wins":36},"claude-opus-4-8":{"draws":33,"losses":71,"wins":18},"claude-opus-5":{"draws":24,"losses":211,"wins":13},"claude-opus-5-5":{"draws":10,"losses":144,"wins":0},"claude-sonnet-5":{"draws":40,"losses":71,"wins":27},"claude-sonnet-5-5":{"draws":26,"losses":86,"wins":26},"cohere/north-mini-code":{"draws":13,"losses":22,"wins":19},"deepseek/deepseek-v4-flash":{"draws":62,"losses":74,"wins":74},"deepseek/deepseek-v4-pro":{"draws":28,"losses":50,"wins":50},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":64,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":54,"losses":59,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":27,"losses":93,"wins":18},"elorian/glimpse":{"draws":18,"losses":40,"wins":16},"fireworks/ember-1":{"draws":44,"losses":66,"wins":28},"gemini-3.1-pro-preview":{"draws":42,"losses":61,"wins":35},"gemini-4-argon":{"draws":8,"losses":127,"wins":3},"google/gemini-3.1-flash-lite":{"draws":24,"losses":22,"wins":40},"google/gemini-3.5-flash":{"draws":29,"losses":107,"wins":34},"google/gemini-3.5-flash-lite":{"draws":57,"losses":73,"wins":108},"google/gemini-3.6-flash":{"draws":60,"losses":145,"wins":57},"google/gemini-3.8-flash":{"draws":21,"losses":100,"wins":17},"google/gemma-4-31b-it":{"draws":33,"losses":20,"wins":25},"gpt-4.1":{"draws":14,"losses":19,"wins":13},"gpt-4.1-nano":{"draws":13,"losses":2,"wins":3},"gpt-5":{"draws":29,"losses":56,"wins":41},"gpt-5.4":{"draws":29,"losses":81,"wins":22},"gpt-5.4-mini":{"draws":28,"losses":34,"wins":30},"gpt-5.4-nano":{"draws":26,"losses":59,"wins":59},"gpt-5.5":{"draws":43,"losses":58,"wins":27},"gpt-5.6-luna":{"draws":47,"losses":50,"wins":41},"gpt-5.6-sol":{"draws":19,"losses":111,"wins":8},"gpt-5.6-terra":{"draws":40,"losses":74,"wins":16},"gpt-6-astra":{"draws":7,"losses":131,"wins":0},"gpt-6-luna":{"draws":43,"losses":57,"wins":38},"gpt-6-sol":{"draws":22,"losses":105,"wins":11},"gpt-6.1-sol":{"draws":9,"losses":128,"wins":1},"gpt-6.1-terra":{"draws":19,"losses":118,"wins":1},"gpt-6.1-terra-pro":{"draws":11,"losses":115,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":36,"losses":24,"wins":30},"inception/mercury-3":{"draws":30,"losses":49,"wins":17},"inclusionai/ling-3.0-flash":{"draws":30,"losses":29,"wins":35},"inclusionai/ling-3.1-flash":{"draws":13,"losses":5,"wins":4},"meituan/longcat-2.0":{"draws":43,"losses":51,"wins":56},"meta/muse-glimmer-30b":{"draws":39,"losses":37,"wins":48},"meta/muse-spark-1.2":{"draws":28,"losses":85,"wins":21},"meta/muse-spark-1.3":{"draws":28,"losses":84,"wins":26},"meta/muse-spark-open":{"draws":31,"losses":86,"wins":21},"meta/muse-wonder":{"draws":22,"losses":104,"wins":12},"minimax/minimax-m3":{"draws":19,"losses":26,"wins":33},"minimax/minimax-m3.1-flash":{"draws":25,"losses":51,"wins":40},"mistralai/mistral-large-4-0":{"draws":32,"losses":36,"wins":20},"mistralai/mistral-medium-3-5":{"draws":25,"losses":19,"wins":38},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":40,"losses":70,"wins":24},"moonshotai/kimi-k3.1-pro":{"draws":18,"losses":109,"wins":11},"nex-agi/nex-n2-pro":{"draws":17,"losses":25,"wins":30},"nex-agi/nex-n2.5-pro":{"draws":10,"losses":9,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":34,"wins":37},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":31,"wins":15},"o3":{"draws":28,"losses":100,"wins":64},"openai/gpt-oss-120b":{"draws":44,"losses":39,"wins":43},"poolside/laguna-s-2.1":{"draws":28,"losses":38,"wins":38},"qwen/qwen3.7-max":{"draws":24,"losses":35,"wins":23},"qwen/qwen3.7-plus":{"draws":16,"losses":13,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":86,"wins":15},"qwen/qwen3.8-27b":{"draws":25,"losses":47,"wins":22},"qwen/qwen3.8-flash":{"draws":23,"losses":42,"wins":27},"qwen/qwen3.8-max":{"draws":35,"losses":71,"wins":32},"qwen/qwen3.8-max-0902":{"draws":41,"losses":73,"wins":24},"recursive/flint-v1.0":{"draws":7,"losses":7,"wins":24},"reflection/beam-1.0-501b-a23b":{"draws":30,"losses":69,"wins":29},"stealth/ox-alpha":{"draws":109,"losses":278,"wins":91},"stealth/space-bunny-alpha":{"draws":31,"losses":46,"wins":29},"stepfun/step-3.7-flash":{"draws":29,"losses":29,"wins":40},"stepfun/step-5-preview":{"draws":2,"losses":12,"wins":10},"tencent/hy3-preview":{"draws":25,"losses":27,"wins":24},"tencent/hy4-preview":{"draws":27,"losses":70,"wins":35},"thinkingmachines/inkling":{"draws":52,"losses":54,"wins":82},"thinkingmachines/inkling-small":{"draws":41,"losses":24,"wins":73},"unbiased/pareto-26.10":{"draws":1,"losses":45,"wins":0},"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":35,"losses":84,"wins":19},"x-ai/grok-4.6":{"draws":33,"losses":86,"wins":19},"x-ai/grok-4.7":{"draws":12,"losses":99,"wins":13},"x-ai/grok-build-0.1":{"draws":14,"losses":18,"wins":14},"xiaomi/mimo-v2.5":{"draws":55,"losses":62,"wins":85},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":19,"wins":46},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":54,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":64,"wins":18},"z-ai/glm-5.2":{"draws":87,"losses":105,"wins":84},"z-ai/glm-5.3":{"draws":25,"losses":94,"wins":13},"z-ai/glm-5.3-flash":{"draws":27,"losses":77,"wins":34},"z-ai/glm-5.3-flashx":{"draws":36,"losses":76,"wins":26}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":26,"wins":29},"claude-fable-5":{"draws":11,"losses":60,"wins":13},"claude-fable-5-1":{"draws":2,"losses":89,"wins":1},"claude-haiku-5-5":{"draws":28,"losses":34,"wins":20},"claude-opus-4-5":{"draws":35,"losses":68,"wins":35},"claude-opus-4-8":{"draws":21,"losses":37,"wins":22},"claude-opus-5":{"draws":17,"losses":111,"wins":12},"claude-opus-5-5":{"draws":6,"losses":86,"wins":0},"claude-sonnet-5":{"draws":23,"losses":40,"wins":21},"claude-sonnet-5-5":{"draws":18,"losses":44,"wins":22},"cohere/north-mini-code":{"draws":9,"losses":6,"wins":17},"deepseek/deepseek-v4-flash":{"draws":39,"losses":39,"wins":52},"deepseek/deepseek-v4-pro":{"draws":18,"losses":39,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":37,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":35,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":58,"wins":11},"elorian/glimpse":{"draws":8,"losses":22,"wins":14},"fireworks/ember-1":{"draws":19,"losses":43,"wins":22},"gemini-3.1-pro-preview":{"draws":21,"losses":34,"wins":29},"gemini-4-argon":{"draws":4,"losses":73,"wins":7},"google/gemini-3.1-flash-lite":{"draws":14,"losses":9,"wins":37},"google/gemini-3.5-flash":{"draws":24,"losses":42,"wins":40},"google/gemini-3.5-flash-lite":{"draws":32,"losses":45,"wins":69},"google/gemini-3.6-flash":{"draws":36,"losses":82,"wins":42},"google/gemini-3.8-flash":{"draws":22,"losses":42,"wins":20},"google/gemma-4-31b-it":{"draws":17,"losses":13,"wins":20},"gpt-4.1":{"draws":11,"losses":5,"wins":12},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":2},"gpt-5":{"draws":23,"losses":31,"wins":20},"gpt-5.4":{"draws":14,"losses":46,"wins":20},"gpt-5.4-mini":{"draws":11,"losses":16,"wins":29},"gpt-5.4-nano":{"draws":20,"losses":33,"wins":39},"gpt-5.5":{"draws":24,"losses":38,"wins":14},"gpt-5.6-luna":{"draws":23,"losses":27,"wins":34},"gpt-5.6-sol":{"draws":11,"losses":59,"wins":14},"gpt-5.6-terra":{"draws":20,"losses":43,"wins":17},"gpt-6-astra":{"draws":5,"losses":79,"wins":0},"gpt-6-luna":{"draws":21,"losses":36,"wins":27},"gpt-6-sol":{"draws":16,"losses":58,"wins":10},"gpt-6.1-sol":{"draws":6,"losses":76,"wins":2},"gpt-6.1-terra":{"draws":10,"losses":72,"wins":2},"gpt-6.1-terra-pro":{"draws":9,"losses":68,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":21,"losses":16,"wins":23},"inception/mercury-3":{"draws":15,"losses":25,"wins":18},"inclusionai/ling-3.0-flash":{"draws":19,"losses":11,"wins":30},"inclusionai/ling-3.1-flash":{"draws":4,"losses":4,"wins":4},"meituan/longcat-2.0":{"draws":19,"losses":21,"wins":52},"meta/muse-glimmer-30b":{"draws":23,"losses":18,"wins":31},"meta/muse-spark-1.2":{"draws":15,"losses":47,"wins":18},"meta/muse-spark-1.3":{"draws":16,"losses":47,"wins":21},"meta/muse-spark-open":{"draws":19,"losses":47,"wins":18},"meta/muse-wonder":{"draws":11,"losses":61,"wins":12},"minimax/minimax-m3":{"draws":13,"losses":11,"wins":24},"minimax/minimax-m3.1-flash":{"draws":11,"losses":30,"wins":31},"mistralai/mistral-large-4-0":{"draws":21,"losses":26,"wins":5},"mistralai/mistral-medium-3-5":{"draws":18,"losses":5,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":18,"losses":43,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":69,"wins":7},"nex-agi/nex-n2-pro":{"draws":9,"losses":8,"wins":25},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":5,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":20,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":14,"wins":16},"o3":{"draws":17,"losses":61,"wins":46},"openai/gpt-oss-120b":{"draws":23,"losses":18,"wins":33},"poolside/laguna-s-2.1":{"draws":24,"losses":23,"wins":35},"qwen/qwen3.7-max":{"draws":2,"losses":11,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":14,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":37,"wins":19},"qwen/qwen3.8-27b":{"draws":16,"losses":25,"wins":19},"qwen/qwen3.8-flash":{"draws":12,"losses":27,"wins":17},"qwen/qwen3.8-max":{"draws":22,"losses":38,"wins":24},"qwen/qwen3.8-max-0902":{"draws":26,"losses":41,"wins":17},"recursive/flint-v1.0":{"draws":5,"losses":8,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":19,"losses":36,"wins":21},"stealth/ox-alpha":{"draws":56,"losses":140,"wins":62},"stealth/space-bunny-alpha":{"draws":15,"losses":22,"wins":29},"stepfun/step-3.7-flash":{"draws":14,"losses":13,"wins":35},"stepfun/step-5-preview":{"draws":3,"losses":11,"wins":2},"tencent/hy3-preview":{"draws":15,"losses":13,"wins":18},"tencent/hy4-preview":{"draws":11,"losses":47,"wins":22},"thinkingmachines/inkling":{"draws":29,"losses":19,"wins":62},"thinkingmachines/inkling-small":{"draws":22,"losses":20,"wins":42},"unbiased/pareto-26.10":{"draws":1,"losses":27,"wins":0},"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":20,"losses":48,"wins":16},"x-ai/grok-4.7":{"draws":10,"losses":50,"wins":16},"x-ai/grok-build-0.1":{"draws":7,"losses":10,"wins":11},"xiaomi/mimo-v2.5":{"draws":39,"losses":33,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":14,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":29,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":35,"wins":13},"z-ai/glm-5.2":{"draws":41,"losses":68,"wins":59},"z-ai/glm-5.3":{"draws":15,"losses":50,"wins":15},"z-ai/glm-5.3-flash":{"draws":21,"losses":43,"wins":20},"z-ai/glm-5.3-flashx":{"draws":18,"losses":47,"wins":19}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":25,"wins":21},"claude-fable-5":{"draws":10,"losses":54,"wins":8},"claude-fable-5-1":{"draws":3,"losses":74,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":50,"wins":8},"claude-opus-4-5":{"draws":38,"losses":55,"wins":27},"claude-opus-4-8":{"draws":18,"losses":43,"wins":11},"claude-opus-5":{"draws":15,"losses":93,"wins":8},"claude-opus-5-5":{"draws":4,"losses":72,"wins":0},"claude-sonnet-5":{"draws":20,"losses":36,"wins":16},"claude-sonnet-5-5":{"draws":15,"losses":44,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":8,"wins":14},"deepseek/deepseek-v4-flash":{"draws":31,"losses":43,"wins":38},"deepseek/deepseek-v4-pro":{"draws":14,"losses":35,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":29,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":40,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":50,"wins":9},"elorian/glimpse":{"draws":8,"losses":21,"wins":7},"fireworks/ember-1":{"draws":20,"losses":39,"wins":13},"gemini-3.1-pro-preview":{"draws":24,"losses":34,"wins":14},"gemini-4-argon":{"draws":3,"losses":68,"wins":1},"google/gemini-3.1-flash-lite":{"draws":11,"losses":13,"wins":32},"google/gemini-3.5-flash":{"draws":17,"losses":56,"wins":19},"google/gemini-3.5-flash-lite":{"draws":31,"losses":55,"wins":40},"google/gemini-3.6-flash":{"draws":33,"losses":82,"wins":23},"google/gemini-3.8-flash":{"draws":15,"losses":50,"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":14,"losses":38,"wins":10},"gpt-5.4":{"draws":10,"losses":50,"wins":8},"gpt-5.4-mini":{"draws":12,"losses":15,"wins":21},"gpt-5.4-nano":{"draws":15,"losses":33,"wins":34},"gpt-5.5":{"draws":22,"losses":36,"wins":6},"gpt-5.6-luna":{"draws":27,"losses":27,"wins":18},"gpt-5.6-sol":{"draws":13,"losses":52,"wins":7},"gpt-5.6-terra":{"draws":26,"losses":32,"wins":10},"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":3,"losses":65,"wins":4},"gpt-6.1-terra":{"draws":11,"losses":61,"wins":0},"gpt-6.1-terra-pro":{"draws":8,"losses":61,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":9,"wins":23},"inception/mercury-3":{"draws":15,"losses":25,"wins":8},"inclusionai/ling-3.0-flash":{"draws":16,"losses":16,"wins":18},"inclusionai/ling-3.1-flash":{"draws":5,"losses":6,"wins":3},"meituan/longcat-2.0":{"draws":15,"losses":31,"wins":32},"meta/muse-glimmer-30b":{"draws":21,"losses":24,"wins":15},"meta/muse-spark-1.2":{"draws":16,"losses":40,"wins":12},"meta/muse-spark-1.3":{"draws":13,"losses":46,"wins":13},"meta/muse-spark-open":{"draws":19,"losses":43,"wins":10},"meta/muse-wonder":{"draws":14,"losses":55,"wins":3},"minimax/minimax-m3":{"draws":9,"losses":15,"wins":18},"minimax/minimax-m3.1-flash":{"draws":11,"losses":37,"wins":16},"mistralai/mistral-large-4-0":{"draws":13,"losses":29,"wins":2},"mistralai/mistral-medium-3-5":{"draws":15,"losses":11,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":24,"losses":30,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":60,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":11,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":8,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":20,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":16,"wins":9},"o3":{"draws":10,"losses":71,"wins":29},"openai/gpt-oss-120b":{"draws":21,"losses":20,"wins":21},"poolside/laguna-s-2.1":{"draws":16,"losses":37,"wins":13},"qwen/qwen3.7-max":{"draws":9,"losses":23,"wins":14},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":37,"wins":9},"qwen/qwen3.8-27b":{"draws":10,"losses":28,"wins":16},"qwen/qwen3.8-flash":{"draws":11,"losses":19,"wins":18},"qwen/qwen3.8-max":{"draws":25,"losses":30,"wins":17},"qwen/qwen3.8-max-0902":{"draws":26,"losses":37,"wins":9},"recursive/flint-v1.0":{"draws":7,"losses":8,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":17,"losses":30,"wins":17},"stealth/ox-alpha":{"draws":38,"losses":137,"wins":27},"stealth/space-bunny-alpha":{"draws":16,"losses":31,"wins":11},"stepfun/step-3.7-flash":{"draws":10,"losses":21,"wins":23},"stepfun/step-5-preview":{"draws":3,"losses":8,"wins":3},"tencent/hy3-preview":{"draws":16,"losses":13,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":41,"wins":16},"thinkingmachines/inkling":{"draws":25,"losses":29,"wins":40},"thinkingmachines/inkling-small":{"draws":24,"losses":26,"wins":22},"unbiased/pareto-26.10":{"draws":1,"losses":23,"wins":0},"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":19,"losses":46,"wins":7},"x-ai/grok-4.7":{"draws":7,"losses":52,"wins":7},"x-ai/grok-build-0.1":{"draws":5,"losses":10,"wins":9},"xiaomi/mimo-v2.5":{"draws":39,"losses":38,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":17,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":32,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":35,"wins":6},"z-ai/glm-5.2":{"draws":36,"losses":74,"wins":34},"z-ai/glm-5.3":{"draws":14,"losses":47,"wins":7},"z-ai/glm-5.3-flash":{"draws":15,"losses":42,"wins":15},"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":39,"losses":30,"wins":63},"claude-fable-5":{"draws":32,"losses":76,"wins":36},"claude-fable-5-1":{"draws":8,"losses":147,"wins":7},"claude-haiku-5-5":{"draws":36,"losses":55,"wins":47},"claude-opus-4-5":{"draws":79,"losses":62,"wins":93},"claude-opus-4-8":{"draws":40,"losses":42,"wins":50},"claude-opus-5":{"draws":31,"losses":173,"wins":42},"claude-opus-5-5":{"draws":10,"losses":129,"wins":17},"claude-sonnet-5":{"draws":45,"losses":37,"wins":62},"claude-sonnet-5-5":{"draws":31,"losses":63,"wins":50},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":45},"deepseek/deepseek-v4-flash":{"draws":65,"losses":31,"wins":120},"deepseek/deepseek-v4-pro":{"draws":33,"losses":37,"wins":62},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":45,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":60,"wins":49},"deepseek/deepseek-v4.1-flash-1017":{"draws":28,"losses":73,"wins":43},"elorian/glimpse":{"draws":20,"losses":29,"wins":29},"fireworks/ember-1":{"draws":45,"losses":50,"wins":49},"gemini-3.1-pro-preview":{"draws":34,"losses":43,"wins":67},"gemini-4-argon":{"draws":9,"losses":112,"wins":23},"google/gemini-3.1-flash-lite":{"draws":24,"losses":7,"wins":65},"google/gemini-3.5-flash":{"draws":48,"losses":54,"wins":78},"google/gemini-3.5-flash-lite":{"draws":77,"losses":41,"wins":134},"google/gemini-3.6-flash":{"draws":63,"losses":115,"wins":98},"google/gemini-3.8-flash":{"draws":30,"losses":68,"wins":46},"google/gemma-4-31b-it":{"draws":29,"losses":10,"wins":45},"gpt-4.1":{"draws":17,"losses":8,"wins":23},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":11},"gpt-5":{"draws":36,"losses":35,"wins":55},"gpt-5.4":{"draws":28,"losses":58,"wins":52},"gpt-5.4-mini":{"draws":31,"losses":13,"wins":52},"gpt-5.4-nano":{"draws":34,"losses":26,"wins":84},"gpt-5.5":{"draws":39,"losses":47,"wins":46},"gpt-5.6-luna":{"draws":51,"losses":27,"wins":66},"gpt-5.6-sol":{"draws":20,"losses":87,"wins":37},"gpt-5.6-terra":{"draws":44,"losses":33,"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":8,"losses":116,"wins":20},"gpt-6.1-terra":{"draws":14,"losses":113,"wins":17},"gpt-6.1-terra-pro":{"draws":13,"losses":115,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":40,"losses":6,"wins":56},"inception/mercury-3":{"draws":32,"losses":30,"wins":34},"inclusionai/ling-3.0-flash":{"draws":38,"losses":4,"wins":60},"inclusionai/ling-3.1-flash":{"draws":11,"losses":3,"wins":8},"meituan/longcat-2.0":{"draws":40,"losses":23,"wins":93},"meta/muse-glimmer-30b":{"draws":43,"losses":15,"wins":68},"meta/muse-spark-1.2":{"draws":39,"losses":46,"wins":53},"meta/muse-spark-1.3":{"draws":35,"losses":59,"wins":50},"meta/muse-spark-open":{"draws":34,"losses":57,"wins":51},"meta/muse-wonder":{"draws":26,"losses":73,"wins":45},"minimax/minimax-m3":{"draws":18,"losses":8,"wins":52},"minimax/minimax-m3.1-flash":{"draws":35,"losses":29,"wins":62},"mistralai/mistral-large-4-0":{"draws":22,"losses":26,"wins":42},"mistralai/mistral-medium-3-5":{"draws":22,"losses":3,"wins":59},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":0},"moonshotai/kimi-k3":{"draws":35,"losses":51,"wins":52},"moonshotai/kimi-k3.1-pro":{"draws":17,"losses":108,"wins":19},"nex-agi/nex-n2-pro":{"draws":15,"losses":9,"wins":48},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":14,"wins":55},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":15,"wins":33},"o3":{"draws":27,"losses":59,"wins":112},"openai/gpt-oss-120b":{"draws":42,"losses":12,"wins":72},"poolside/laguna-s-2.1":{"draws":37,"losses":15,"wins":86},"qwen/qwen3.7-max":{"draws":28,"losses":19,"wins":37},"qwen/qwen3.7-plus":{"draws":26,"losses":9,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":35,"wins":35},"qwen/qwen3.8-27b":{"draws":38,"losses":28,"wins":36},"qwen/qwen3.8-flash":{"draws":23,"losses":31,"wins":42},"qwen/qwen3.8-max":{"draws":42,"losses":54,"wins":48},"qwen/qwen3.8-max-0902":{"draws":44,"losses":55,"wins":45},"recursive/flint-v1.0":{"draws":12,"losses":2,"wins":28},"reflection/beam-1.0-501b-a23b":{"draws":31,"losses":36,"wins":65},"stealth/ox-alpha":{"draws":118,"losses":175,"wins":181},"stealth/space-bunny-alpha":{"draws":41,"losses":28,"wins":45},"stepfun/step-3.7-flash":{"draws":16,"losses":15,"wins":71},"stepfun/step-5-preview":{"draws":3,"losses":14,"wins":17},"tencent/hy3-preview":{"draws":28,"losses":15,"wins":35},"tencent/hy4-preview":{"draws":35,"losses":53,"wins":50},"thinkingmachines/inkling":{"draws":58,"losses":25,"wins":109},"thinkingmachines/inkling-small":{"draws":44,"losses":17,"wins":83},"unbiased/pareto-26.10":{"draws":5,"losses":42,"wins":1},"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":63,"wins":47},"x-ai/grok-4.6":{"draws":33,"losses":61,"wins":50},"x-ai/grok-4.7":{"draws":9,"losses":86,"wins":31},"x-ai/grok-build-0.1":{"draws":18,"losses":6,"wins":24},"xiaomi/mimo-v2.5":{"draws":86,"losses":24,"wins":112},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":15,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":37,"wins":34},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":42,"wins":30},"z-ai/glm-5.2":{"draws":94,"losses":71,"wins":123},"z-ai/glm-5.3":{"draws":25,"losses":83,"wins":30},"z-ai/glm-5.3-flash":{"draws":28,"losses":68,"wins":48},"z-ai/glm-5.3-flashx":{"draws":38,"losses":61,"wins":45}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":24,"wins":48},"claude-fable-5":{"draws":21,"losses":65,"wins":16},"claude-fable-5-1":{"draws":8,"losses":105,"wins":1},"claude-haiku-5-5":{"draws":22,"losses":46,"wins":30},"claude-opus-4-5":{"draws":48,"losses":49,"wins":69},"claude-opus-4-8":{"draws":20,"losses":43,"wins":31},"claude-opus-5":{"draws":29,"losses":124,"wins":13},"claude-opus-5-5":{"draws":5,"losses":98,"wins":3},"claude-sonnet-5":{"draws":24,"losses":38,"wins":40},"claude-sonnet-5-5":{"draws":17,"losses":59,"wins":26},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":25},"deepseek/deepseek-v4-flash":{"draws":38,"losses":35,"wins":81},"deepseek/deepseek-v4-pro":{"draws":26,"losses":32,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":30,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":50,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":61,"wins":26},"elorian/glimpse":{"draws":11,"losses":22,"wins":21},"fireworks/ember-1":{"draws":28,"losses":35,"wins":39},"gemini-3.1-pro-preview":{"draws":22,"losses":32,"wins":48},"gemini-4-argon":{"draws":7,"losses":88,"wins":7},"google/gemini-3.1-flash-lite":{"draws":14,"losses":8,"wins":48},"google/gemini-3.5-flash":{"draws":20,"losses":57,"wins":51},"google/gemini-3.5-flash-lite":{"draws":34,"losses":44,"wins":102},"google/gemini-3.6-flash":{"draws":43,"losses":90,"wins":65},"google/gemini-3.8-flash":{"draws":16,"losses":61,"wins":25},"google/gemma-4-31b-it":{"draws":19,"losses":10,"wins":29},"gpt-4.1":{"draws":8,"losses":11,"wins":15},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":6},"gpt-5":{"draws":17,"losses":30,"wins":41},"gpt-5.4":{"draws":20,"losses":58,"wins":20},"gpt-5.4-mini":{"draws":15,"losses":17,"wins":36},"gpt-5.4-nano":{"draws":18,"losses":35,"wins":51},"gpt-5.5":{"draws":26,"losses":38,"wins":28},"gpt-5.6-luna":{"draws":32,"losses":25,"wins":45},"gpt-5.6-sol":{"draws":15,"losses":71,"wins":16},"gpt-5.6-terra":{"draws":33,"losses":34,"wins":31},"gpt-6-astra":{"draws":4,"losses":97,"wins":1},"gpt-6-luna":{"draws":24,"losses":41,"wins":37},"gpt-6-sol":{"draws":16,"losses":72,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":91,"wins":4},"gpt-6.1-terra":{"draws":15,"losses":83,"wins":4},"gpt-6.1-terra-pro":{"draws":13,"losses":80,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":22,"losses":7,"wins":43},"inception/mercury-3":{"draws":20,"losses":21,"wins":25},"inclusionai/ling-3.0-flash":{"draws":14,"losses":14,"wins":46},"inclusionai/ling-3.1-flash":{"draws":7,"losses":2,"wins":11},"meituan/longcat-2.0":{"draws":21,"losses":18,"wins":69},"meta/muse-glimmer-30b":{"draws":23,"losses":14,"wins":49},"meta/muse-spark-1.2":{"draws":22,"losses":34,"wins":40},"meta/muse-spark-1.3":{"draws":20,"losses":53,"wins":29},"meta/muse-spark-open":{"draws":23,"losses":48,"wins":29},"meta/muse-wonder":{"draws":19,"losses":69,"wins":14},"minimax/minimax-m3":{"draws":13,"losses":8,"wins":33},"minimax/minimax-m3.1-flash":{"draws":20,"losses":35,"wins":39},"mistralai/mistral-large-4-0":{"draws":19,"losses":22,"wins":21},"mistralai/mistral-medium-3-5":{"draws":19,"losses":4,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":27,"losses":41,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":82,"wins":8},"nex-agi/nex-n2-pro":{"draws":10,"losses":11,"wins":27},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":5,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":14,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":13,"wins":21},"o3":{"draws":12,"losses":58,"wins":74},"openai/gpt-oss-120b":{"draws":22,"losses":18,"wins":46},"poolside/laguna-s-2.1":{"draws":25,"losses":22,"wins":47},"qwen/qwen3.7-max":{"draws":16,"losses":19,"wins":25},"qwen/qwen3.7-plus":{"draws":10,"losses":16,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":36,"wins":28},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":18},"qwen/qwen3.8-flash":{"draws":15,"losses":30,"wins":23},"qwen/qwen3.8-max":{"draws":30,"losses":33,"wins":39},"qwen/qwen3.8-max-0902":{"draws":24,"losses":51,"wins":27},"recursive/flint-v1.0":{"draws":5,"losses":7,"wins":18},"reflection/beam-1.0-501b-a23b":{"draws":22,"losses":34,"wins":34},"stealth/ox-alpha":{"draws":72,"losses":152,"wins":108},"stealth/space-bunny-alpha":{"draws":21,"losses":20,"wins":39},"stepfun/step-3.7-flash":{"draws":12,"losses":26,"wins":38},"stepfun/step-5-preview":{"draws":4,"losses":8,"wins":10},"tencent/hy3-preview":{"draws":15,"losses":13,"wins":26},"tencent/hy4-preview":{"draws":25,"losses":45,"wins":28},"thinkingmachines/inkling":{"draws":37,"losses":30,"wins":71},"thinkingmachines/inkling-small":{"draws":28,"losses":16,"wins":58},"unbiased/pareto-26.10":{"draws":2,"losses":32,"wins":0},"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":26,"losses":53,"wins":23},"x-ai/grok-4.7":{"draws":11,"losses":58,"wins":19},"x-ai/grok-build-0.1":{"draws":12,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":38,"losses":31,"wins":91},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":10,"wins":28},"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":63,"losses":71,"wins":70},"z-ai/glm-5.3":{"draws":24,"losses":60,"wins":12},"z-ai/glm-5.3-flash":{"draws":19,"losses":51,"wins":32},"z-ai/glm-5.3-flashx":{"draws":22,"losses":54,"wins":26}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":22,"wins":40},"claude-fable-5":{"draws":18,"losses":56,"wins":22},"claude-fable-5-1":{"draws":7,"losses":96,"wins":5},"claude-haiku-5-5":{"draws":27,"losses":47,"wins":18},"claude-opus-4-5":{"draws":51,"losses":54,"wins":51},"claude-opus-4-8":{"draws":26,"losses":42,"wins":20},"claude-opus-5":{"draws":24,"losses":126,"wins":14},"claude-opus-5-5":{"draws":10,"losses":91,"wins":3},"claude-sonnet-5":{"draws":29,"losses":34,"wins":33},"claude-sonnet-5-5":{"draws":17,"losses":49,"wins":30},"cohere/north-mini-code":{"draws":7,"losses":11,"wins":18},"deepseek/deepseek-v4-flash":{"draws":38,"losses":32,"wins":74},"deepseek/deepseek-v4-pro":{"draws":17,"losses":30,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":30,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":41,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":21,"losses":51,"wins":24},"elorian/glimpse":{"draws":13,"losses":22,"wins":17},"fireworks/ember-1":{"draws":28,"losses":35,"wins":33},"gemini-3.1-pro-preview":{"draws":30,"losses":31,"wins":35},"gemini-4-argon":{"draws":12,"losses":73,"wins":11},"google/gemini-3.1-flash-lite":{"draws":17,"losses":10,"wins":37},"google/gemini-3.5-flash":{"draws":25,"losses":53,"wins":42},"google/gemini-3.5-flash-lite":{"draws":47,"losses":36,"wins":85},"google/gemini-3.6-flash":{"draws":47,"losses":84,"wins":53},"google/gemini-3.8-flash":{"draws":17,"losses":50,"wins":29},"google/gemma-4-31b-it":{"draws":27,"losses":6,"wins":23},"gpt-4.1":{"draws":9,"losses":8,"wins":15},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":7},"gpt-5":{"draws":14,"losses":32,"wins":38},"gpt-5.4":{"draws":18,"losses":45,"wins":29},"gpt-5.4-mini":{"draws":18,"losses":16,"wins":30},"gpt-5.4-nano":{"draws":17,"losses":29,"wins":50},"gpt-5.5":{"draws":29,"losses":39,"wins":20},"gpt-5.6-luna":{"draws":31,"losses":28,"wins":37},"gpt-5.6-sol":{"draws":17,"losses":61,"wins":18},"gpt-5.6-terra":{"draws":25,"losses":36,"wins":31},"gpt-6-astra":{"draws":12,"losses":81,"wins":3},"gpt-6-luna":{"draws":26,"losses":36,"wins":34},"gpt-6-sol":{"draws":9,"losses":68,"wins":19},"gpt-6.1-sol":{"draws":8,"losses":81,"wins":7},"gpt-6.1-terra":{"draws":10,"losses":74,"wins":12},"gpt-6.1-terra-pro":{"draws":10,"losses":77,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":29,"losses":6,"wins":33},"inception/mercury-3":{"draws":19,"losses":21,"wins":24},"inclusionai/ling-3.0-flash":{"draws":21,"losses":9,"wins":38},"inclusionai/ling-3.1-flash":{"draws":7,"losses":2,"wins":5},"meituan/longcat-2.0":{"draws":27,"losses":25,"wins":52},"meta/muse-glimmer-30b":{"draws":27,"losses":25,"wins":32},"meta/muse-spark-1.2":{"draws":21,"losses":43,"wins":28},"meta/muse-spark-1.3":{"draws":21,"losses":47,"wins":28},"meta/muse-spark-open":{"draws":23,"losses":42,"wins":31},"meta/muse-wonder":{"draws":24,"losses":60,"wins":12},"minimax/minimax-m3":{"draws":9,"losses":17,"wins":26},"minimax/minimax-m3.1-flash":{"draws":23,"losses":27,"wins":34},"mistralai/mistral-large-4-0":{"draws":22,"losses":21,"wins":17},"mistralai/mistral-medium-3-5":{"draws":18,"losses":7,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":25,"losses":35,"wins":32},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":75,"wins":14},"nex-agi/nex-n2-pro":{"draws":12,"losses":8,"wins":28},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":8,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":20,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":12,"wins":18},"o3":{"draws":17,"losses":52,"wins":63},"openai/gpt-oss-120b":{"draws":23,"losses":23,"wins":38},"poolside/laguna-s-2.1":{"draws":23,"losses":27,"wins":42},"qwen/qwen3.7-max":{"draws":12,"losses":17,"wins":27},"qwen/qwen3.7-plus":{"draws":11,"losses":18,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":42,"wins":31},"qwen/qwen3.8-27b":{"draws":15,"losses":23,"wins":30},"qwen/qwen3.8-flash":{"draws":14,"losses":9,"wins":9},"qwen/qwen3.8-max":{"draws":26,"losses":40,"wins":30},"qwen/qwen3.8-max-0902":{"draws":30,"losses":34,"wins":32},"recursive/flint-v1.0":{"draws":8,"losses":3,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":21,"losses":34,"wins":33},"stealth/ox-alpha":{"draws":79,"losses":134,"wins":103},"stealth/space-bunny-alpha":{"draws":26,"losses":20,"wins":30},"stepfun/step-3.7-flash":{"draws":14,"losses":14,"wins":40},"stepfun/step-5-preview":{"draws":5,"losses":11,"wins":6},"tencent/hy3-preview":{"draws":18,"losses":12,"wins":22},"tencent/hy4-preview":{"draws":22,"losses":43,"wins":27},"thinkingmachines/inkling":{"draws":40,"losses":25,"wins":63},"thinkingmachines/inkling-small":{"draws":32,"losses":20,"wins":44},"unbiased/pareto-26.10":{"draws":4,"losses":28,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":26,"wins":5},"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":32,"losses":47,"wins":17},"x-ai/grok-4.7":{"draws":8,"losses":63,"wins":13},"x-ai/grok-build-0.1":{"draws":13,"losses":6,"wins":13},"xiaomi/mimo-v2.5":{"draws":49,"losses":35,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":8,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":21,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":36,"wins":14},"z-ai/glm-5.2":{"draws":59,"losses":62,"wins":71},"z-ai/glm-5.3":{"draws":21,"losses":55,"wins":16},"z-ai/glm-5.3-flash":{"draws":18,"losses":43,"wins":35},"z-ai/glm-5.3-flashx":{"draws":26,"losses":45,"wins":25}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":38,"wins":53},"claude-fable-5":{"draws":24,"losses":84,"wins":36},"claude-fable-5-1":{"draws":8,"losses":149,"wins":5},"claude-haiku-5-5":{"draws":34,"losses":67,"wins":37},"claude-opus-4-5":{"draws":68,"losses":71,"wins":95},"claude-opus-4-8":{"draws":25,"losses":60,"wins":47},"claude-opus-5":{"draws":36,"losses":179,"wins":31},"claude-opus-5-5":{"draws":13,"losses":130,"wins":13},"claude-sonnet-5":{"draws":44,"losses":41,"wins":59},"claude-sonnet-5-5":{"draws":20,"losses":82,"wins":42},"cohere/north-mini-code":{"draws":9,"losses":3,"wins":42},"deepseek/deepseek-v4-flash":{"draws":58,"losses":38,"wins":120},"deepseek/deepseek-v4-pro":{"draws":37,"losses":36,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":39,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":53,"wins":56},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":82,"wins":33},"elorian/glimpse":{"draws":17,"losses":30,"wins":31},"fireworks/ember-1":{"draws":36,"losses":60,"wins":48},"gemini-3.1-pro-preview":{"draws":36,"losses":47,"wins":61},"gemini-4-argon":{"draws":9,"losses":123,"wins":12},"google/gemini-3.1-flash-lite":{"draws":23,"losses":1,"wins":72},"google/gemini-3.5-flash":{"draws":46,"losses":66,"wins":68},"google/gemini-3.5-flash-lite":{"draws":64,"losses":51,"wins":137},"google/gemini-3.6-flash":{"draws":58,"losses":121,"wins":97},"google/gemini-3.8-flash":{"draws":29,"losses":63,"wins":52},"google/gemma-4-31b-it":{"draws":33,"losses":8,"wins":43},"gpt-4.1":{"draws":16,"losses":14,"wins":18},"gpt-4.1-nano":{"draws":10,"losses":1,"wins":7},"gpt-5":{"draws":33,"losses":28,"wins":65},"gpt-5.4":{"draws":32,"losses":54,"wins":52},"gpt-5.4-mini":{"draws":35,"losses":20,"wins":41},"gpt-5.4-nano":{"draws":31,"losses":39,"wins":74},"gpt-5.5":{"draws":40,"losses":49,"wins":43},"gpt-5.6-luna":{"draws":43,"losses":29,"wins":72},"gpt-5.6-sol":{"draws":24,"losses":89,"wins":31},"gpt-5.6-terra":{"draws":46,"losses":41,"wins":51},"gpt-6-astra":{"draws":13,"losses":127,"wins":4},"gpt-6-luna":{"draws":35,"losses":48,"wins":61},"gpt-6-sol":{"draws":16,"losses":102,"wins":26},"gpt-6.1-sol":{"draws":10,"losses":128,"wins":6},"gpt-6.1-terra":{"draws":15,"losses":115,"wins":14},"gpt-6.1-terra-pro":{"draws":11,"losses":117,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":3},"inception/mercury-2.5-preview":{"draws":37,"losses":8,"wins":57},"inception/mercury-3":{"draws":30,"losses":27,"wins":41},"inclusionai/ling-3.0-flash":{"draws":37,"losses":14,"wins":51},"inclusionai/ling-3.1-flash":{"draws":8,"losses":8,"wins":10},"meituan/longcat-2.0":{"draws":37,"losses":28,"wins":91},"meta/muse-glimmer-30b":{"draws":33,"losses":24,"wins":69},"meta/muse-spark-1.2":{"draws":37,"losses":50,"wins":51},"meta/muse-spark-1.3":{"draws":33,"losses":71,"wins":40},"meta/muse-spark-open":{"draws":34,"losses":66,"wins":44},"meta/muse-wonder":{"draws":31,"losses":81,"wins":32},"minimax/minimax-m3":{"draws":17,"losses":13,"wins":48},"minimax/minimax-m3.1-flash":{"draws":30,"losses":37,"wins":59},"mistralai/mistral-large-4-0":{"draws":31,"losses":30,"wins":29},"mistralai/mistral-medium-3-5":{"draws":23,"losses":10,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":36,"losses":47,"wins":55},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":114,"wins":24},"nex-agi/nex-n2-pro":{"draws":18,"losses":8,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":7,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":17,"wins":60},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":18,"wins":31},"o3":{"draws":31,"losses":64,"wins":103},"openai/gpt-oss-120b":{"draws":38,"losses":10,"wins":78},"poolside/laguna-s-2.1":{"draws":35,"losses":32,"wins":71},"qwen/qwen3.7-max":{"draws":22,"losses":24,"wins":38},"qwen/qwen3.7-plus":{"draws":25,"losses":17,"wins":30},"qwen/qwen3.8-2.4t-a95b":{"draws":42,"losses":48,"wins":54},"qwen/qwen3.8-27b":{"draws":30,"losses":39,"wins":33},"qwen/qwen3.8-flash":{"draws":26,"losses":30,"wins":40},"qwen/qwen3.8-max":{"draws":24,"losses":36,"wins":36},"qwen/qwen3.8-max-0902":{"draws":35,"losses":62,"wins":47},"recursive/flint-v1.0":{"draws":10,"losses":6,"wins":26},"reflection/beam-1.0-501b-a23b":{"draws":28,"losses":39,"wins":65},"stealth/ox-alpha":{"draws":115,"losses":195,"wins":164},"stealth/space-bunny-alpha":{"draws":33,"losses":30,"wins":51},"stepfun/step-3.7-flash":{"draws":22,"losses":17,"wins":63},"stepfun/step-5-preview":{"draws":4,"losses":10,"wins":14},"tencent/hy3-preview":{"draws":27,"losses":13,"wins":38},"tencent/hy4-preview":{"draws":31,"losses":60,"wins":47},"thinkingmachines/inkling":{"draws":55,"losses":30,"wins":107},"thinkingmachines/inkling-small":{"draws":37,"losses":39,"wins":68},"unbiased/pareto-26.10":{"draws":1,"losses":47,"wins":0},"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":68,"wins":44},"x-ai/grok-4.6":{"draws":37,"losses":63,"wins":44},"x-ai/grok-4.7":{"draws":11,"losses":90,"wins":25},"x-ai/grok-build-0.1":{"draws":15,"losses":7,"wins":26},"xiaomi/mimo-v2.5":{"draws":69,"losses":39,"wins":114},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":17,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":36,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":52,"wins":19},"z-ai/glm-5.2":{"draws":82,"losses":80,"wins":126},"z-ai/glm-5.3":{"draws":27,"losses":80,"wins":31},"z-ai/glm-5.3-flash":{"draws":27,"losses":58,"wins":59},"z-ai/glm-5.3-flashx":{"draws":35,"losses":57,"wins":52}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":24,"wins":77},"claude-fable-5":{"draws":28,"losses":82,"wins":34},"claude-fable-5-1":{"draws":10,"losses":135,"wins":17},"claude-haiku-5-5":{"draws":40,"losses":51,"wins":47},"claude-opus-4-5":{"draws":64,"losses":79,"wins":91},"claude-opus-4-8":{"draws":29,"losses":51,"wins":52},"claude-opus-5":{"draws":36,"losses":169,"wins":41},"claude-opus-5-5":{"draws":13,"losses":132,"wins":11},"claude-sonnet-5":{"draws":35,"losses":39,"wins":70},"claude-sonnet-5-5":{"draws":26,"losses":65,"wins":53},"cohere/north-mini-code":{"draws":8,"losses":5,"wins":41},"deepseek/deepseek-v4-flash":{"draws":53,"losses":37,"wins":126},"deepseek/deepseek-v4-pro":{"draws":34,"losses":36,"wins":62},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":39,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":49,"wins":53},"deepseek/deepseek-v4.1-flash-1017":{"draws":32,"losses":72,"wins":40},"elorian/glimpse":{"draws":20,"losses":28,"wins":30},"fireworks/ember-1":{"draws":36,"losses":45,"wins":63},"gemini-3.1-pro-preview":{"draws":31,"losses":41,"wins":72},"gemini-4-argon":{"draws":12,"losses":118,"wins":14},"google/gemini-3.1-flash-lite":{"draws":24,"losses":3,"wins":69},"google/gemini-3.5-flash":{"draws":42,"losses":46,"wins":92},"google/gemini-3.5-flash-lite":{"draws":67,"losses":37,"wins":148},"google/gemini-3.6-flash":{"draws":69,"losses":100,"wins":107},"google/gemini-3.8-flash":{"draws":37,"losses":59,"wins":48},"google/gemma-4-31b-it":{"draws":29,"losses":9,"wins":46},"gpt-4.1":{"draws":14,"losses":10,"wins":24},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":10},"gpt-5":{"draws":32,"losses":32,"wins":62},"gpt-5.4":{"draws":29,"losses":62,"wins":47},"gpt-5.4-mini":{"draws":38,"losses":15,"wins":43},"gpt-5.4-nano":{"draws":35,"losses":35,"wins":74},"gpt-5.5":{"draws":43,"losses":45,"wins":44},"gpt-5.6-luna":{"draws":43,"losses":36,"wins":65},"gpt-5.6-sol":{"draws":21,"losses":90,"wins":33},"gpt-5.6-terra":{"draws":43,"losses":37,"wins":58},"gpt-6-astra":{"draws":9,"losses":129,"wins":6},"gpt-6-luna":{"draws":38,"losses":48,"wins":58},"gpt-6-sol":{"draws":18,"losses":98,"wins":28},"gpt-6.1-sol":{"draws":11,"losses":121,"wins":12},"gpt-6.1-terra":{"draws":15,"losses":117,"wins":12},"gpt-6.1-terra-pro":{"draws":16,"losses":114,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":39,"losses":10,"wins":53},"inception/mercury-3":{"draws":28,"losses":31,"wins":39},"inclusionai/ling-3.0-flash":{"draws":37,"losses":9,"wins":56},"inclusionai/ling-3.1-flash":{"draws":8,"losses":4,"wins":6},"meituan/longcat-2.0":{"draws":23,"losses":27,"wins":106},"meta/muse-glimmer-30b":{"draws":38,"losses":13,"wins":75},"meta/muse-spark-1.2":{"draws":35,"losses":49,"wins":54},"meta/muse-spark-1.3":{"draws":36,"losses":54,"wins":54},"meta/muse-spark-open":{"draws":35,"losses":52,"wins":57},"meta/muse-wonder":{"draws":33,"losses":78,"wins":33},"minimax/minimax-m3":{"draws":17,"losses":10,"wins":51},"minimax/minimax-m3.1-flash":{"draws":31,"losses":30,"wins":65},"mistralai/mistral-large-4-0":{"draws":32,"losses":18,"wins":40},"mistralai/mistral-medium-3-5":{"draws":24,"losses":8,"wins":52},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":32,"losses":34,"wins":72},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":112,"wins":20},"nex-agi/nex-n2-pro":{"draws":18,"losses":10,"wins":44},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":17,"wins":61},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":16,"wins":32},"o3":{"draws":33,"losses":64,"wins":101},"openai/gpt-oss-120b":{"draws":33,"losses":16,"wins":77},"poolside/laguna-s-2.1":{"draws":41,"losses":24,"wins":73},"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":44,"losses":45,"wins":55},"qwen/qwen3.8-27b":{"draws":24,"losses":27,"wins":51},"qwen/qwen3.8-flash":{"draws":30,"losses":32,"wins":34},"qwen/qwen3.8-max":{"draws":35,"losses":47,"wins":62},"qwen/qwen3.8-max-0902":{"draws":24,"losses":36,"wins":36},"recursive/flint-v1.0":{"draws":9,"losses":6,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":31,"losses":38,"wins":63},"stealth/ox-alpha":{"draws":100,"losses":186,"wins":188},"stealth/space-bunny-alpha":{"draws":30,"losses":22,"wins":62},"stepfun/step-3.7-flash":{"draws":24,"losses":20,"wins":58},"stepfun/step-5-preview":{"draws":5,"losses":18,"wins":15},"tencent/hy3-preview":{"draws":25,"losses":13,"wins":40},"tencent/hy4-preview":{"draws":33,"losses":55,"wins":50},"thinkingmachines/inkling":{"draws":54,"losses":30,"wins":108},"thinkingmachines/inkling-small":{"draws":41,"losses":17,"wins":86},"unbiased/pareto-26.10":{"draws":2,"losses":44,"wins":2},"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":39,"losses":68,"wins":37},"x-ai/grok-4.7":{"draws":18,"losses":79,"wins":29},"x-ai/grok-build-0.1":{"draws":16,"losses":7,"wins":25},"xiaomi/mimo-v2.5":{"draws":72,"losses":31,"wins":119},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":9,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":41,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":52,"wins":29},"z-ai/glm-5.2":{"draws":91,"losses":59,"wins":138},"z-ai/glm-5.3":{"draws":31,"losses":76,"wins":31},"z-ai/glm-5.3-flash":{"draws":38,"losses":53,"wins":53},"z-ai/glm-5.3-flashx":{"draws":30,"losses":61,"wins":53}},"recursive/flint-v1.0":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":21,"wins":9},"claude-fable-5":{"draws":3,"losses":39,"wins":0},"claude-fable-5-1":{"draws":2,"losses":44,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":25,"wins":8},"claude-opus-4-5":{"draws":18,"losses":47,"wins":5},"claude-opus-4-8":{"draws":11,"losses":29,"wins":2},"claude-opus-5":{"draws":7,"losses":62,"wins":1},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":12,"losses":27,"wins":3},"claude-sonnet-5-5":{"draws":7,"losses":31,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":7},"deepseek/deepseek-v4-flash":{"draws":12,"losses":36,"wins":16},"deepseek/deepseek-v4-pro":{"draws":8,"losses":21,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":22,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":27,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":35,"wins":1},"elorian/glimpse":{"draws":5,"losses":13,"wins":4},"fireworks/ember-1":{"draws":10,"losses":27,"wins":5},"gemini-3.1-pro-preview":{"draws":11,"losses":27,"wins":4},"gemini-4-argon":{"draws":3,"losses":39,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":12,"wins":12},"google/gemini-3.5-flash":{"draws":10,"losses":36,"wins":8},"google/gemini-3.5-flash-lite":{"draws":20,"losses":42,"wins":12},"google/gemini-3.6-flash":{"draws":26,"losses":45,"wins":9},"google/gemini-3.8-flash":{"draws":7,"losses":33,"wins":2},"google/gemma-4-31b-it":{"draws":7,"losses":12,"wins":7},"gpt-4.1":{"draws":4,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":5,"losses":21,"wins":10},"gpt-5.4":{"draws":6,"losses":30,"wins":4},"gpt-5.4-mini":{"draws":8,"losses":12,"wins":8},"gpt-5.4-nano":{"draws":10,"losses":19,"wins":17},"gpt-5.5":{"draws":11,"losses":25,"wins":2},"gpt-5.6-luna":{"draws":9,"losses":23,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":38,"wins":1},"gpt-5.6-terra":{"draws":10,"losses":28,"wins":2},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":11,"losses":26,"wins":5},"gpt-6-sol":{"draws":5,"losses":35,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"gpt-6.1-terra":{"draws":1,"losses":41,"wins":0},"gpt-6.1-terra-pro":{"draws":2,"losses":37,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":8,"wins":12},"inception/mercury-3":{"draws":8,"losses":14,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":8,"wins":14},"inclusionai/ling-3.1-flash":{"draws":4,"losses":8,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":22,"wins":13},"meta/muse-glimmer-30b":{"draws":11,"losses":17,"wins":8},"meta/muse-spark-1.2":{"draws":7,"losses":30,"wins":3},"meta/muse-spark-1.3":{"draws":4,"losses":34,"wins":4},"meta/muse-spark-open":{"draws":6,"losses":33,"wins":3},"meta/muse-wonder":{"draws":6,"losses":36,"wins":0},"minimax/minimax-m3":{"draws":7,"losses":9,"wins":8},"minimax/minimax-m3.1-flash":{"draws":10,"losses":19,"wins":7},"mistralai/mistral-large-4-0":{"draws":6,"losses":17,"wins":3},"mistralai/mistral-medium-3-5":{"draws":8,"losses":8,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":27,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":35,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":8,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":14,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":13,"wins":1},"o3":{"draws":4,"losses":52,"wins":6},"openai/gpt-oss-120b":{"draws":8,"losses":19,"wins":9},"poolside/laguna-s-2.1":{"draws":7,"losses":24,"wins":7},"qwen/qwen3.7-max":{"draws":5,"losses":13,"wins":8},"qwen/qwen3.7-plus":{"draws":7,"losses":9,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":28,"wins":2},"qwen/qwen3.8-27b":{"draws":5,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":17,"wins":3},"qwen/qwen3.8-max":{"draws":10,"losses":26,"wins":6},"qwen/qwen3.8-max-0902":{"draws":9,"losses":27,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":29,"wins":1},"stealth/ox-alpha":{"draws":23,"losses":85,"wins":10},"stealth/space-bunny-alpha":{"draws":9,"losses":15,"wins":10},"stepfun/step-3.7-flash":{"draws":3,"losses":16,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":11,"wins":5},"tencent/hy4-preview":{"draws":9,"losses":27,"wins":4},"thinkingmachines/inkling":{"draws":16,"losses":24,"wins":14},"thinkingmachines/inkling-small":{"draws":12,"losses":14,"wins":16},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":12,"losses":30,"wins":0},"x-ai/grok-4.6":{"draws":7,"losses":30,"wins":5},"x-ai/grok-4.7":{"draws":2,"losses":35,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":11,"wins":0},"xiaomi/mimo-v2.5":{"draws":20,"losses":31,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":20,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":20,"wins":2},"z-ai/glm-5.2":{"draws":17,"losses":49,"wins":18},"z-ai/glm-5.3":{"draws":7,"losses":31,"wins":2},"z-ai/glm-5.3-flash":{"draws":9,"losses":24,"wins":9},"z-ai/glm-5.3-flashx":{"draws":10,"losses":29,"wins":3}},"reflection/beam-1.0-501b-a23b":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":31,"wins":57},"claude-fable-5":{"draws":25,"losses":81,"wins":26},"claude-fable-5-1":{"draws":7,"losses":141,"wins":2},"claude-haiku-5-5":{"draws":25,"losses":66,"wins":35},"claude-opus-4-5":{"draws":74,"losses":68,"wins":72},"claude-opus-4-8":{"draws":26,"losses":62,"wins":32},"claude-opus-5":{"draws":29,"losses":180,"wins":23},"claude-opus-5-5":{"draws":14,"losses":126,"wins":4},"claude-sonnet-5":{"draws":39,"losses":47,"wins":46},"claude-sonnet-5-5":{"draws":31,"losses":67,"wins":34},"cohere/north-mini-code":{"draws":4,"losses":9,"wins":39},"deepseek/deepseek-v4-flash":{"draws":42,"losses":42,"wins":112},"deepseek/deepseek-v4-pro":{"draws":30,"losses":45,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":39,"wins":51},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":60,"wins":38},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":76,"wins":27},"elorian/glimpse":{"draws":18,"losses":33,"wins":21},"fireworks/ember-1":{"draws":36,"losses":45,"wins":51},"gemini-3.1-pro-preview":{"draws":31,"losses":48,"wins":53},"gemini-4-argon":{"draws":7,"losses":112,"wins":13},"google/gemini-3.1-flash-lite":{"draws":14,"losses":7,"wins":65},"google/gemini-3.5-flash":{"draws":41,"losses":55,"wins":68},"google/gemini-3.5-flash-lite":{"draws":63,"losses":47,"wins":120},"google/gemini-3.6-flash":{"draws":59,"losses":114,"wins":79},"google/gemini-3.8-flash":{"draws":26,"losses":71,"wins":35},"google/gemma-4-31b-it":{"draws":19,"losses":12,"wins":47},"gpt-4.1":{"draws":13,"losses":13,"wins":18},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":7},"gpt-5":{"draws":23,"losses":39,"wins":54},"gpt-5.4":{"draws":31,"losses":58,"wins":37},"gpt-5.4-mini":{"draws":28,"losses":18,"wins":42},"gpt-5.4-nano":{"draws":25,"losses":34,"wins":69},"gpt-5.5":{"draws":30,"losses":60,"wins":32},"gpt-5.6-luna":{"draws":43,"losses":34,"wins":55},"gpt-5.6-sol":{"draws":21,"losses":87,"wins":24},"gpt-5.6-terra":{"draws":35,"losses":43,"wins":48},"gpt-6-astra":{"draws":11,"losses":117,"wins":4},"gpt-6-luna":{"draws":28,"losses":57,"wins":47},"gpt-6-sol":{"draws":18,"losses":98,"wins":16},"gpt-6.1-sol":{"draws":6,"losses":120,"wins":6},"gpt-6.1-terra":{"draws":10,"losses":116,"wins":6},"gpt-6.1-terra-pro":{"draws":7,"losses":118,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":36,"losses":6,"wins":52},"inception/mercury-3":{"draws":29,"losses":29,"wins":31},"inclusionai/ling-3.0-flash":{"draws":29,"losses":16,"wins":45},"inclusionai/ling-3.1-flash":{"draws":9,"losses":7,"wins":6},"meituan/longcat-2.0":{"draws":30,"losses":29,"wins":85},"meta/muse-glimmer-30b":{"draws":36,"losses":20,"wins":62},"meta/muse-spark-1.2":{"draws":29,"losses":55,"wins":44},"meta/muse-spark-1.3":{"draws":23,"losses":73,"wins":36},"meta/muse-spark-open":{"draws":28,"losses":65,"wins":35},"meta/muse-wonder":{"draws":21,"losses":85,"wins":26},"minimax/minimax-m3":{"draws":13,"losses":12,"wins":47},"minimax/minimax-m3.1-flash":{"draws":28,"losses":40,"wins":46},"mistralai/mistral-large-4-0":{"draws":25,"losses":26,"wins":33},"mistralai/mistral-medium-3-5":{"draws":19,"losses":8,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":6,"wins":1},"moonshotai/kimi-k3":{"draws":35,"losses":52,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":111,"wins":12},"nex-agi/nex-n2-pro":{"draws":14,"losses":12,"wins":42},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":11,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":18,"wins":54},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":18,"wins":28},"o3":{"draws":24,"losses":64,"wins":88},"openai/gpt-oss-120b":{"draws":36,"losses":17,"wins":65},"poolside/laguna-s-2.1":{"draws":30,"losses":29,"wins":69},"qwen/qwen3.7-max":{"draws":19,"losses":21,"wins":36},"qwen/qwen3.7-plus":{"draws":17,"losses":17,"wins":30},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":65,"wins":36},"qwen/qwen3.8-27b":{"draws":22,"losses":34,"wins":34},"qwen/qwen3.8-flash":{"draws":21,"losses":33,"wins":34},"qwen/qwen3.8-max":{"draws":28,"losses":65,"wins":39},"qwen/qwen3.8-max-0902":{"draws":31,"losses":63,"wins":38},"recursive/flint-v1.0":{"draws":8,"losses":1,"wins":29},"reflection/beam-1.0-501b-a23b":{"draws":24,"losses":28,"wins":28},"stealth/ox-alpha":{"draws":93,"losses":200,"wins":149},"stealth/space-bunny-alpha":{"draws":32,"losses":22,"wins":52},"stepfun/step-3.7-flash":{"draws":16,"losses":31,"wins":43},"stepfun/step-5-preview":{"draws":8,"losses":19,"wins":11},"tencent/hy3-preview":{"draws":18,"losses":19,"wins":35},"tencent/hy4-preview":{"draws":35,"losses":60,"wins":31},"thinkingmachines/inkling":{"draws":52,"losses":33,"wins":91},"thinkingmachines/inkling-small":{"draws":42,"losses":27,"wins":63},"unbiased/pareto-26.10":{"draws":2,"losses":42,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":43,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":7,"wins":19},"x-ai/grok-4.5":{"draws":38,"losses":63,"wins":31},"x-ai/grok-4.6":{"draws":35,"losses":69,"wins":28},"x-ai/grok-4.7":{"draws":13,"losses":93,"wins":10},"x-ai/grok-build-0.1":{"draws":12,"losses":11,"wins":21},"xiaomi/mimo-v2.5":{"draws":65,"losses":32,"wins":103},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":13,"wins":32},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":35,"wins":35},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":47,"wins":26},"z-ai/glm-5.2":{"draws":75,"losses":84,"wins":105},"z-ai/glm-5.3":{"draws":18,"losses":88,"wins":22},"z-ai/glm-5.3-flash":{"draws":23,"losses":70,"wins":39},"z-ai/glm-5.3-flashx":{"draws":23,"losses":68,"wins":41}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":92,"losses":89,"wins":259},"claude-fable-5":{"draws":75,"losses":277,"wins":122},"claude-fable-5-1":{"draws":26,"losses":498,"wins":26},"claude-haiku-5-5":{"draws":94,"losses":175,"wins":165},"claude-opus-4-5":{"draws":187,"losses":224,"wins":339},"claude-opus-4-8":{"draws":72,"losses":159,"wins":163},"claude-opus-5":{"draws":133,"losses":578,"wins":121},"claude-opus-5-5":{"draws":45,"losses":434,"wins":27},"claude-sonnet-5":{"draws":99,"losses":134,"wins":241},"claude-sonnet-5-5":{"draws":77,"losses":235,"wins":162},"cohere/north-mini-code":{"draws":24,"losses":22,"wins":132},"deepseek/deepseek-v4-flash":{"draws":156,"losses":137,"wins":403},"deepseek/deepseek-v4-pro":{"draws":102,"losses":131,"wins":209},"deepseek/deepseek-v4-pro-0813":{"draws":99,"losses":151,"wins":190},"deepseek/deepseek-v4.1-flash":{"draws":100,"losses":186,"wins":188},"deepseek/deepseek-v4.1-flash-1017":{"draws":79,"losses":232,"wins":163},"elorian/glimpse":{"draws":65,"losses":94,"wins":107},"fireworks/ember-1":{"draws":109,"losses":177,"wins":188},"gemini-3.1-pro-preview":{"draws":93,"losses":147,"wins":234},"gemini-4-argon":{"draws":45,"losses":380,"wins":49},"google/gemini-3.1-flash-lite":{"draws":46,"losses":30,"wins":196},"google/gemini-3.5-flash":{"draws":90,"losses":207,"wins":279},"google/gemini-3.5-flash-lite":{"draws":167,"losses":171,"wins":488},"google/gemini-3.6-flash":{"draws":175,"losses":365,"wins":376},"google/gemini-3.8-flash":{"draws":91,"losses":228,"wins":155},"google/gemma-4-31b-it":{"draws":60,"losses":40,"wins":160},"gpt-4.1":{"draws":39,"losses":38,"wins":81},"gpt-4.1-nano":{"draws":33,"losses":4,"wins":35},"gpt-5":{"draws":87,"losses":134,"wins":203},"gpt-5.4":{"draws":109,"losses":184,"wins":165},"gpt-5.4-mini":{"draws":84,"losses":61,"wins":171},"gpt-5.4-nano":{"draws":70,"losses":123,"wins":231},"gpt-5.5":{"draws":110,"losses":159,"wins":173},"gpt-5.6-luna":{"draws":139,"losses":104,"wins":231},"gpt-5.6-sol":{"draws":69,"losses":291,"wins":114},"gpt-5.6-terra":{"draws":117,"losses":130,"wins":209},"gpt-6-astra":{"draws":35,"losses":415,"wins":24},"gpt-6-luna":{"draws":104,"losses":159,"wins":211},"gpt-6-sol":{"draws":61,"losses":342,"wins":71},"gpt-6.1-sol":{"draws":39,"losses":403,"wins":32},"gpt-6.1-terra":{"draws":66,"losses":362,"wins":46},"gpt-6.1-terra-pro":{"draws":57,"losses":378,"wins":39},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":1,"wins":8},"inception/mercury-2.5-preview":{"draws":92,"losses":33,"wins":185},"inception/mercury-3":{"draws":79,"losses":105,"wins":130},"inclusionai/ling-3.0-flash":{"draws":84,"losses":33,"wins":211},"inclusionai/ling-3.1-flash":{"draws":25,"losses":13,"wins":30},"meituan/longcat-2.0":{"draws":98,"losses":84,"wins":328},"meta/muse-glimmer-30b":{"draws":88,"losses":61,"wins":277},"meta/muse-spark-1.2":{"draws":99,"losses":155,"wins":204},"meta/muse-spark-1.3":{"draws":89,"losses":220,"wins":165},"meta/muse-spark-open":{"draws":98,"losses":213,"wins":163},"meta/muse-wonder":{"draws":93,"losses":253,"wins":128},"minimax/minimax-m3":{"draws":47,"losses":40,"wins":155},"minimax/minimax-m3.1-flash":{"draws":87,"losses":115,"wins":224},"mistralai/mistral-large-4-0":{"draws":97,"losses":83,"wins":120},"mistralai/mistral-medium-3-5":{"draws":66,"losses":43,"wins":173},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":9,"wins":8},"moonshotai/kimi-k3":{"draws":103,"losses":170,"wins":185},"moonshotai/kimi-k3.1-pro":{"draws":54,"losses":352,"wins":68},"nex-agi/nex-n2-pro":{"draws":52,"losses":33,"wins":165},"nex-agi/nex-n2.5-pro":{"draws":26,"losses":20,"wins":62},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":73,"losses":52,"wins":203},"nvidia/nemotron-3.5-super-vl":{"draws":55,"losses":54,"wins":101},"o3":{"draws":72,"losses":211,"wins":321},"openai/gpt-oss-120b":{"draws":99,"losses":63,"wins":262},"poolside/laguna-s-2.1":{"draws":109,"losses":91,"wins":278},"qwen/qwen3.7-max":{"draws":56,"losses":62,"wins":140},"qwen/qwen3.7-plus":{"draws":38,"losses":27,"wins":137},"qwen/qwen3.8-2.4t-a95b":{"draws":118,"losses":181,"wins":175},"qwen/qwen3.8-27b":{"draws":72,"losses":108,"wins":152},"qwen/qwen3.8-flash":{"draws":79,"losses":103,"wins":134},"qwen/qwen3.8-max":{"draws":115,"losses":164,"wins":195},"qwen/qwen3.8-max-0902":{"draws":100,"losses":188,"wins":186},"recursive/flint-v1.0":{"draws":23,"losses":10,"wins":85},"reflection/beam-1.0-501b-a23b":{"draws":93,"losses":149,"wins":200},"stealth/ox-alpha":{"draws":274,"losses":683,"wins":683},"stealth/space-bunny-alpha":{"draws":90,"losses":87,"wins":193},"stepfun/step-3.7-flash":{"draws":51,"losses":58,"wins":223},"stepfun/step-5-preview":{"draws":16,"losses":45,"wins":41},"tencent/hy3-preview":{"draws":67,"losses":45,"wins":130},"tencent/hy4-preview":{"draws":92,"losses":196,"wins":170},"thinkingmachines/inkling":{"draws":156,"losses":125,"wins":377},"thinkingmachines/inkling-small":{"draws":116,"losses":74,"wins":284},"unbiased/pareto-26.10":{"draws":11,"losses":143,"wins":4},"unbiased/pareto-26.10-preview":{"draws":8,"losses":142,"wins":8},"upstage/solar-mini4":{"draws":13,"losses":15,"wins":74},"x-ai/grok-4.5":{"draws":98,"losses":211,"wins":165},"x-ai/grok-4.6":{"draws":126,"losses":198,"wins":150},"x-ai/grok-4.7":{"draws":42,"losses":282,"wins":76},"x-ai/grok-build-0.1":{"draws":33,"losses":20,"wins":105},"xiaomi/mimo-v2.5":{"draws":153,"losses":101,"wins":392},"xiaomi/mimo-v2.5-pro":{"draws":45,"losses":50,"wins":151},"xiaomi/mimo-v2.6-flash":{"draws":51,"losses":112,"wins":135},"xiaomi/mimo-v2.6-pro":{"draws":56,"losses":154,"wins":106},"z-ai/glm-5.2":{"draws":233,"losses":233,"wins":482},"z-ai/glm-5.3":{"draws":81,"losses":259,"wins":118},"z-ai/glm-5.3-flash":{"draws":71,"losses":216,"wins":187},"z-ai/glm-5.3-flashx":{"draws":79,"losses":227,"wins":168}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":30,"wins":40},"claude-fable-5":{"draws":28,"losses":71,"wins":15},"claude-fable-5-1":{"draws":3,"losses":125,"wins":2},"claude-haiku-5-5":{"draws":30,"losses":57,"wins":23},"claude-opus-4-5":{"draws":54,"losses":84,"wins":48},"claude-opus-4-8":{"draws":25,"losses":54,"wins":27},"claude-opus-5":{"draws":30,"losses":151,"wins":15},"claude-opus-5-5":{"draws":6,"losses":114,"wins":2},"claude-sonnet-5":{"draws":24,"losses":50,"wins":40},"claude-sonnet-5-5":{"draws":21,"losses":69,"wins":24},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":29},"deepseek/deepseek-v4-flash":{"draws":48,"losses":51,"wins":69},"deepseek/deepseek-v4-pro":{"draws":28,"losses":47,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":47,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":62,"wins":28},"deepseek/deepseek-v4.1-flash-1017":{"draws":20,"losses":76,"wins":18},"elorian/glimpse":{"draws":13,"losses":31,"wins":18},"fireworks/ember-1":{"draws":30,"losses":55,"wins":29},"gemini-3.1-pro-preview":{"draws":25,"losses":48,"wins":41},"gemini-4-argon":{"draws":7,"losses":103,"wins":4},"google/gemini-3.1-flash-lite":{"draws":17,"losses":13,"wins":50},"google/gemini-3.5-flash":{"draws":38,"losses":67,"wins":39},"google/gemini-3.5-flash-lite":{"draws":52,"losses":61,"wins":89},"google/gemini-3.6-flash":{"draws":54,"losses":117,"wins":49},"google/gemini-3.8-flash":{"draws":23,"losses":72,"wins":19},"google/gemma-4-31b-it":{"draws":26,"losses":16,"wins":26},"gpt-4.1":{"draws":11,"losses":14,"wins":13},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":5},"gpt-5":{"draws":20,"losses":41,"wins":39},"gpt-5.4":{"draws":30,"losses":61,"wins":19},"gpt-5.4-mini":{"draws":23,"losses":17,"wins":36},"gpt-5.4-nano":{"draws":23,"losses":39,"wins":50},"gpt-5.5":{"draws":38,"losses":47,"wins":21},"gpt-5.6-luna":{"draws":33,"losses":36,"wins":45},"gpt-5.6-sol":{"draws":19,"losses":81,"wins":14},"gpt-5.6-terra":{"draws":35,"losses":41,"wins":32},"gpt-6-astra":{"draws":6,"losses":108,"wins":0},"gpt-6-luna":{"draws":37,"losses":52,"wins":25},"gpt-6-sol":{"draws":16,"losses":87,"wins":11},"gpt-6.1-sol":{"draws":9,"losses":100,"wins":5},"gpt-6.1-terra":{"draws":13,"losses":95,"wins":6},"gpt-6.1-terra-pro":{"draws":9,"losses":97,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":31,"losses":14,"wins":37},"inception/mercury-3":{"draws":19,"losses":33,"wins":20},"inclusionai/ling-3.0-flash":{"draws":30,"losses":13,"wins":33},"inclusionai/ling-3.1-flash":{"draws":6,"losses":4,"wins":10},"meituan/longcat-2.0":{"draws":30,"losses":31,"wins":65},"meta/muse-glimmer-30b":{"draws":35,"losses":27,"wins":40},"meta/muse-spark-1.2":{"draws":29,"losses":55,"wins":26},"meta/muse-spark-1.3":{"draws":18,"losses":74,"wins":22},"meta/muse-spark-open":{"draws":28,"losses":62,"wins":24},"meta/muse-wonder":{"draws":28,"losses":68,"wins":18},"minimax/minimax-m3":{"draws":13,"losses":15,"wins":34},"minimax/minimax-m3.1-flash":{"draws":24,"losses":37,"wins":41},"mistralai/mistral-large-4-0":{"draws":26,"losses":32,"wins":14},"mistralai/mistral-medium-3-5":{"draws":18,"losses":12,"wins":36},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":35,"losses":53,"wins":22},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":97,"wins":10},"nex-agi/nex-n2-pro":{"draws":15,"losses":13,"wins":30},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":6,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":24,"wins":38},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":21,"wins":16},"o3":{"draws":24,"losses":79,"wins":57},"openai/gpt-oss-120b":{"draws":28,"losses":24,"wins":48},"poolside/laguna-s-2.1":{"draws":31,"losses":29,"wins":46},"qwen/qwen3.7-max":{"draws":15,"losses":29,"wins":22},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":45,"wins":28},"qwen/qwen3.8-27b":{"draws":21,"losses":39,"wins":20},"qwen/qwen3.8-flash":{"draws":26,"losses":30,"wins":20},"qwen/qwen3.8-max":{"draws":33,"losses":51,"wins":30},"qwen/qwen3.8-max-0902":{"draws":30,"losses":62,"wins":22},"recursive/flint-v1.0":{"draws":9,"losses":10,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":32,"losses":52,"wins":22},"stealth/ox-alpha":{"draws":90,"losses":193,"wins":87},"stealth/space-bunny-alpha":{"draws":16,"losses":20,"wins":20},"stepfun/step-3.7-flash":{"draws":19,"losses":23,"wins":38},"stepfun/step-5-preview":{"draws":4,"losses":8,"wins":6},"tencent/hy3-preview":{"draws":21,"losses":17,"wins":24},"tencent/hy4-preview":{"draws":30,"losses":53,"wins":27},"thinkingmachines/inkling":{"draws":48,"losses":46,"wins":60},"thinkingmachines/inkling-small":{"draws":31,"losses":26,"wins":57},"unbiased/pareto-26.10":{"draws":3,"losses":35,"wins":0},"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":30,"losses":63,"wins":21},"x-ai/grok-4.6":{"draws":30,"losses":63,"wins":21},"x-ai/grok-4.7":{"draws":10,"losses":73,"wins":17},"x-ai/grok-build-0.1":{"draws":9,"losses":10,"wins":19},"xiaomi/mimo-v2.5":{"draws":60,"losses":43,"wins":75},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":13,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":42,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":38,"wins":19},"z-ai/glm-5.2":{"draws":75,"losses":77,"wins":76},"z-ai/glm-5.3":{"draws":21,"losses":80,"wins":9},"z-ai/glm-5.3-flash":{"draws":26,"losses":68,"wins":20},"z-ai/glm-5.3-flashx":{"draws":24,"losses":66,"wins":24}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":38,"wins":33},"claude-fable-5":{"draws":11,"losses":84,"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":30,"losses":96,"wins":40},"claude-opus-4-8":{"draws":13,"losses":62,"wins":19},"claude-opus-5":{"draws":14,"losses":141,"wins":7},"claude-opus-5-5":{"draws":4,"losses":106,"wins":0},"claude-sonnet-5":{"draws":21,"losses":54,"wins":27},"claude-sonnet-5-5":{"draws":11,"losses":65,"wins":26},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":25},"deepseek/deepseek-v4-flash":{"draws":30,"losses":70,"wins":58},"deepseek/deepseek-v4-pro":{"draws":17,"losses":55,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":58,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":66,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":74,"wins":15},"elorian/glimpse":{"draws":5,"losses":38,"wins":13},"fireworks/ember-1":{"draws":19,"losses":62,"wins":21},"gemini-3.1-pro-preview":{"draws":20,"losses":49,"wins":33},"gemini-4-argon":{"draws":0,"losses":98,"wins":4},"google/gemini-3.1-flash-lite":{"draws":13,"losses":13,"wins":48},"google/gemini-3.5-flash":{"draws":23,"losses":80,"wins":27},"google/gemini-3.5-flash-lite":{"draws":43,"losses":79,"wins":58},"google/gemini-3.6-flash":{"draws":32,"losses":133,"wins":33},"google/gemini-3.8-flash":{"draws":16,"losses":77,"wins":9},"google/gemma-4-31b-it":{"draws":18,"losses":13,"wins":27},"gpt-4.1":{"draws":7,"losses":21,"wins":6},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":6},"gpt-5":{"draws":21,"losses":53,"wins":18},"gpt-5.4":{"draws":18,"losses":66,"wins":16},"gpt-5.4-mini":{"draws":19,"losses":25,"wins":24},"gpt-5.4-nano":{"draws":16,"losses":59,"wins":35},"gpt-5.5":{"draws":24,"losses":56,"wins":14},"gpt-5.6-luna":{"draws":25,"losses":46,"wins":31},"gpt-5.6-sol":{"draws":11,"losses":85,"wins":6},"gpt-5.6-terra":{"draws":22,"losses":55,"wins":21},"gpt-6-astra":{"draws":6,"losses":96,"wins":0},"gpt-6-luna":{"draws":21,"losses":57,"wins":24},"gpt-6-sol":{"draws":13,"losses":85,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":99,"wins":0},"gpt-6.1-terra":{"draws":9,"losses":92,"wins":1},"gpt-6.1-terra-pro":{"draws":7,"losses":95,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":18,"losses":12,"wins":38},"inception/mercury-3":{"draws":15,"losses":39,"wins":14},"inclusionai/ling-3.0-flash":{"draws":26,"losses":20,"wins":30},"inclusionai/ling-3.1-flash":{"draws":4,"losses":11,"wins":5},"meituan/longcat-2.0":{"draws":20,"losses":45,"wins":49},"meta/muse-glimmer-30b":{"draws":20,"losses":41,"wins":27},"meta/muse-spark-1.2":{"draws":15,"losses":57,"wins":24},"meta/muse-spark-1.3":{"draws":10,"losses":79,"wins":13},"meta/muse-spark-open":{"draws":13,"losses":71,"wins":16},"meta/muse-wonder":{"draws":11,"losses":81,"wins":10},"minimax/minimax-m3":{"draws":11,"losses":28,"wins":17},"minimax/minimax-m3.1-flash":{"draws":12,"losses":54,"wins":26},"mistralai/mistral-large-4-0":{"draws":20,"losses":33,"wins":9},"mistralai/mistral-medium-3-5":{"draws":19,"losses":13,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":21,"losses":59,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":96,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":17,"wins":27},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":11,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":28,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":30,"wins":7},"o3":{"draws":22,"losses":94,"wins":44},"openai/gpt-oss-120b":{"draws":27,"losses":25,"wins":36},"poolside/laguna-s-2.1":{"draws":29,"losses":40,"wins":29},"qwen/qwen3.7-max":{"draws":14,"losses":35,"wins":13},"qwen/qwen3.7-plus":{"draws":10,"losses":23,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":71,"wins":15},"qwen/qwen3.8-27b":{"draws":12,"losses":38,"wins":26},"qwen/qwen3.8-flash":{"draws":14,"losses":40,"wins":14},"qwen/qwen3.8-max":{"draws":22,"losses":63,"wins":17},"qwen/qwen3.8-max-0902":{"draws":24,"losses":58,"wins":20},"recursive/flint-v1.0":{"draws":3,"losses":11,"wins":16},"reflection/beam-1.0-501b-a23b":{"draws":16,"losses":43,"wins":31},"stealth/ox-alpha":{"draws":51,"losses":223,"wins":58},"stealth/space-bunny-alpha":{"draws":19,"losses":38,"wins":23},"stepfun/step-3.7-flash":{"draws":8,"losses":20,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":18,"wins":2},"tencent/hy3-preview":{"draws":16,"losses":24,"wins":12},"tencent/hy4-preview":{"draws":20,"losses":63,"wins":17},"thinkingmachines/inkling":{"draws":34,"losses":40,"wins":64},"thinkingmachines/inkling-small":{"draws":26,"losses":39,"wins":37},"unbiased/pareto-26.10":{"draws":3,"losses":31,"wins":0},"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":21,"losses":67,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":75,"wins":10},"x-ai/grok-build-0.1":{"draws":8,"losses":11,"wins":15},"xiaomi/mimo-v2.5":{"draws":38,"losses":59,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":21,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":46,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":52,"wins":8},"z-ai/glm-5.2":{"draws":47,"losses":108,"wins":49},"z-ai/glm-5.3":{"draws":13,"losses":80,"wins":3},"z-ai/glm-5.3-flash":{"draws":15,"losses":67,"wins":20},"z-ai/glm-5.3-flashx":{"draws":13,"losses":75,"wins":14}},"stepfun/step-5-preview":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":9,"wins":17},"claude-fable-5":{"draws":4,"losses":20,"wins":4},"claude-fable-5-1":{"draws":1,"losses":38,"wins":1},"claude-haiku-5-5":{"draws":7,"losses":12,"wins":15},"claude-opus-4-5":{"draws":11,"losses":15,"wins":16},"claude-opus-4-8":{"draws":4,"losses":15,"wins":15},"claude-opus-5":{"draws":6,"losses":47,"wins":5},"claude-opus-5-5":{"draws":4,"losses":33,"wins":3},"claude-sonnet-5":{"draws":6,"losses":15,"wins":15},"claude-sonnet-5-5":{"draws":2,"losses":21,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":11},"deepseek/deepseek-v4-flash":{"draws":6,"losses":15,"wins":39},"deepseek/deepseek-v4-pro":{"draws":3,"losses":9,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":7,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":17,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":14,"wins":12},"elorian/glimpse":{"draws":2,"losses":8,"wins":4},"fireworks/ember-1":{"draws":3,"losses":18,"wins":13},"gemini-3.1-pro-preview":{"draws":5,"losses":14,"wins":11},"gemini-4-argon":{"draws":3,"losses":27,"wins":4},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":15},"google/gemini-3.5-flash":{"draws":4,"losses":25,"wins":15},"google/gemini-3.5-flash-lite":{"draws":10,"losses":19,"wins":33},"google/gemini-3.6-flash":{"draws":8,"losses":36,"wins":28},"google/gemini-3.8-flash":{"draws":3,"losses":22,"wins":11},"google/gemma-4-31b-it":{"draws":5,"losses":5,"wins":10},"gpt-4.1":{"draws":2,"losses":6,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":5},"gpt-5":{"draws":4,"losses":11,"wins":9},"gpt-5.4":{"draws":5,"losses":17,"wins":12},"gpt-5.4-mini":{"draws":3,"losses":6,"wins":21},"gpt-5.4-nano":{"draws":2,"losses":9,"wins":17},"gpt-5.5":{"draws":2,"losses":16,"wins":10},"gpt-5.6-luna":{"draws":2,"losses":7,"wins":19},"gpt-5.6-sol":{"draws":6,"losses":16,"wins":8},"gpt-5.6-terra":{"draws":6,"losses":16,"wins":10},"gpt-6-astra":{"draws":2,"losses":30,"wins":0},"gpt-6-luna":{"draws":5,"losses":11,"wins":18},"gpt-6-sol":{"draws":7,"losses":26,"wins":7},"gpt-6.1-sol":{"draws":1,"losses":25,"wins":0},"gpt-6.1-terra":{"draws":4,"losses":22,"wins":2},"gpt-6.1-terra-pro":{"draws":4,"losses":22,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":4,"wins":9},"inception/mercury-3":{"draws":2,"losses":8,"wins":12},"inclusionai/ling-3.0-flash":{"draws":4,"losses":4,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":3,"losses":9,"wins":24},"meta/muse-glimmer-30b":{"draws":2,"losses":13,"wins":25},"meta/muse-spark-1.2":{"draws":5,"losses":12,"wins":17},"meta/muse-spark-1.3":{"draws":6,"losses":15,"wins":9},"meta/muse-spark-open":{"draws":4,"losses":15,"wins":13},"meta/muse-wonder":{"draws":5,"losses":20,"wins":9},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":15},"minimax/minimax-m3.1-flash":{"draws":2,"losses":6,"wins":18},"mistralai/mistral-large-4-0":{"draws":6,"losses":13,"wins":9},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":16,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":28,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":11,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":7,"wins":8},"o3":{"draws":4,"losses":14,"wins":18},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":18},"poolside/laguna-s-2.1":{"draws":2,"losses":10,"wins":12},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":11},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":17,"wins":14},"qwen/qwen3.8-27b":{"draws":4,"losses":10,"wins":8},"qwen/qwen3.8-flash":{"draws":5,"losses":6,"wins":11},"qwen/qwen3.8-max":{"draws":4,"losses":14,"wins":10},"qwen/qwen3.8-max-0902":{"draws":5,"losses":15,"wins":18},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":11,"wins":19},"stealth/ox-alpha":{"draws":16,"losses":41,"wins":45},"stealth/space-bunny-alpha":{"draws":4,"losses":6,"wins":8},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":18},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":10},"tencent/hy4-preview":{"draws":3,"losses":18,"wins":15},"thinkingmachines/inkling":{"draws":5,"losses":4,"wins":31},"thinkingmachines/inkling-small":{"draws":9,"losses":4,"wins":15},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":5,"losses":9,"wins":14},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":10},"x-ai/grok-4.7":{"draws":2,"losses":23,"wins":7},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":4,"losses":10,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":5,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":15,"wins":9},"z-ai/glm-5.2":{"draws":8,"losses":24,"wins":26},"z-ai/glm-5.3":{"draws":5,"losses":21,"wins":10},"z-ai/glm-5.3-flash":{"draws":5,"losses":15,"wins":16},"z-ai/glm-5.3-flashx":{"draws":3,"losses":16,"wins":15}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":27,"wins":25},"claude-fable-5":{"draws":21,"losses":45,"wins":12},"claude-fable-5-1":{"draws":6,"losses":76,"wins":4},"claude-haiku-5-5":{"draws":25,"losses":31,"wins":20},"claude-opus-4-5":{"draws":44,"losses":56,"wins":28},"claude-opus-4-8":{"draws":17,"losses":40,"wins":17},"claude-opus-5":{"draws":24,"losses":106,"wins":12},"claude-opus-5-5":{"draws":8,"losses":78,"wins":0},"claude-sonnet-5":{"draws":22,"losses":35,"wins":21},"claude-sonnet-5-5":{"draws":19,"losses":49,"wins":10},"cohere/north-mini-code":{"draws":7,"losses":8,"wins":13},"deepseek/deepseek-v4-flash":{"draws":33,"losses":41,"wins":42},"deepseek/deepseek-v4-pro":{"draws":24,"losses":29,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":24,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":39,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":20,"losses":48,"wins":10},"elorian/glimpse":{"draws":12,"losses":19,"wins":11},"fireworks/ember-1":{"draws":26,"losses":36,"wins":16},"gemini-3.1-pro-preview":{"draws":19,"losses":34,"wins":25},"gemini-4-argon":{"draws":4,"losses":71,"wins":3},"google/gemini-3.1-flash-lite":{"draws":16,"losses":14,"wins":22},"google/gemini-3.5-flash":{"draws":25,"losses":43,"wins":30},"google/gemini-3.5-flash-lite":{"draws":46,"losses":28,"wins":62},"google/gemini-3.6-flash":{"draws":42,"losses":75,"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":8,"losses":12,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":2},"gpt-5":{"draws":20,"losses":20,"wins":28},"gpt-5.4":{"draws":24,"losses":35,"wins":15},"gpt-5.4-mini":{"draws":20,"losses":15,"wins":17},"gpt-5.4-nano":{"draws":20,"losses":23,"wins":37},"gpt-5.5":{"draws":31,"losses":32,"wins":9},"gpt-5.6-luna":{"draws":21,"losses":26,"wins":31},"gpt-5.6-sol":{"draws":14,"losses":56,"wins":8},"gpt-5.6-terra":{"draws":27,"losses":30,"wins":17},"gpt-6-astra":{"draws":10,"losses":68,"wins":0},"gpt-6-luna":{"draws":25,"losses":32,"wins":21},"gpt-6-sol":{"draws":15,"losses":58,"wins":5},"gpt-6.1-sol":{"draws":7,"losses":68,"wins":3},"gpt-6.1-terra":{"draws":13,"losses":62,"wins":3},"gpt-6.1-terra-pro":{"draws":6,"losses":64,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":25,"losses":15,"wins":16},"inception/mercury-3":{"draws":17,"losses":22,"wins":13},"inclusionai/ling-3.0-flash":{"draws":22,"losses":8,"wins":24},"inclusionai/ling-3.1-flash":{"draws":6,"losses":6,"wins":2},"meituan/longcat-2.0":{"draws":22,"losses":26,"wins":34},"meta/muse-glimmer-30b":{"draws":22,"losses":16,"wins":32},"meta/muse-spark-1.2":{"draws":21,"losses":43,"wins":12},"meta/muse-spark-1.3":{"draws":12,"losses":51,"wins":15},"meta/muse-spark-open":{"draws":19,"losses":42,"wins":17},"meta/muse-wonder":{"draws":15,"losses":51,"wins":12},"minimax/minimax-m3":{"draws":14,"losses":12,"wins":18},"minimax/minimax-m3.1-flash":{"draws":16,"losses":22,"wins":28},"mistralai/mistral-large-4-0":{"draws":20,"losses":14,"wins":16},"mistralai/mistral-medium-3-5":{"draws":15,"losses":14,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":1},"moonshotai/kimi-k3":{"draws":28,"losses":28,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":63,"wins":5},"nex-agi/nex-n2-pro":{"draws":11,"losses":15,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":19,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":16,"wins":7},"o3":{"draws":22,"losses":43,"wins":39},"openai/gpt-oss-120b":{"draws":22,"losses":19,"wins":27},"poolside/laguna-s-2.1":{"draws":25,"losses":24,"wins":27},"qwen/qwen3.7-max":{"draws":15,"losses":18,"wins":13},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":35,"wins":15},"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":27,"losses":38,"wins":13},"qwen/qwen3.8-max-0902":{"draws":25,"losses":40,"wins":13},"recursive/flint-v1.0":{"draws":8,"losses":5,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":35,"wins":19},"stealth/ox-alpha":{"draws":67,"losses":130,"wins":45},"stealth/space-bunny-alpha":{"draws":21,"losses":24,"wins":17},"stepfun/step-3.7-flash":{"draws":16,"losses":12,"wins":24},"stepfun/step-5-preview":{"draws":5,"losses":10,"wins":5},"tencent/hy3-preview":{"draws":6,"losses":7,"wins":7},"tencent/hy4-preview":{"draws":24,"losses":31,"wins":19},"thinkingmachines/inkling":{"draws":30,"losses":26,"wins":48},"thinkingmachines/inkling-small":{"draws":29,"losses":19,"wins":30},"unbiased/pareto-26.10":{"draws":1,"losses":25,"wins":0},"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":21,"losses":45,"wins":12},"x-ai/grok-4.7":{"draws":12,"losses":54,"wins":4},"x-ai/grok-build-0.1":{"draws":7,"losses":6,"wins":13},"xiaomi/mimo-v2.5":{"draws":47,"losses":36,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":15,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":26,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":33,"wins":10},"z-ai/glm-5.2":{"draws":49,"losses":59,"wins":48},"z-ai/glm-5.3":{"draws":13,"losses":52,"wins":9},"z-ai/glm-5.3-flash":{"draws":22,"losses":42,"wins":14},"z-ai/glm-5.3-flashx":{"draws":16,"losses":49,"wins":13}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":18,"wins":75},"claude-fable-5":{"draws":18,"losses":90,"wins":30},"claude-fable-5-1":{"draws":10,"losses":133,"wins":13},"claude-haiku-5-5":{"draws":30,"losses":48,"wins":54},"claude-opus-4-5":{"draws":57,"losses":62,"wins":105},"claude-opus-4-8":{"draws":28,"losses":48,"wins":50},"claude-opus-5":{"draws":21,"losses":177,"wins":36},"claude-opus-5-5":{"draws":10,"losses":125,"wins":15},"claude-sonnet-5":{"draws":35,"losses":39,"wins":64},"claude-sonnet-5-5":{"draws":22,"losses":68,"wins":48},"cohere/north-mini-code":{"draws":12,"losses":6,"wins":36},"deepseek/deepseek-v4-flash":{"draws":46,"losses":41,"wins":119},"deepseek/deepseek-v4-pro":{"draws":26,"losses":39,"wins":63},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":46,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":39,"losses":41,"wins":58},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":71,"wins":43},"elorian/glimpse":{"draws":13,"losses":33,"wins":30},"fireworks/ember-1":{"draws":36,"losses":47,"wins":55},"gemini-3.1-pro-preview":{"draws":30,"losses":44,"wins":64},"gemini-4-argon":{"draws":15,"losses":105,"wins":18},"google/gemini-3.1-flash-lite":{"draws":19,"losses":6,"wins":69},"google/gemini-3.5-flash":{"draws":34,"losses":56,"wins":84},"google/gemini-3.5-flash-lite":{"draws":60,"losses":52,"wins":132},"google/gemini-3.6-flash":{"draws":48,"losses":118,"wins":100},"google/gemini-3.8-flash":{"draws":29,"losses":56,"wins":53},"google/gemma-4-31b-it":{"draws":26,"losses":11,"wins":43},"gpt-4.1":{"draws":13,"losses":10,"wins":23},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":10},"gpt-5":{"draws":32,"losses":36,"wins":54},"gpt-5.4":{"draws":25,"losses":61,"wins":48},"gpt-5.4-mini":{"draws":27,"losses":15,"wins":50},"gpt-5.4-nano":{"draws":17,"losses":29,"wins":92},"gpt-5.5":{"draws":38,"losses":42,"wins":48},"gpt-5.6-luna":{"draws":40,"losses":29,"wins":69},"gpt-5.6-sol":{"draws":19,"losses":71,"wins":48},"gpt-5.6-terra":{"draws":33,"losses":43,"wins":56},"gpt-6-astra":{"draws":11,"losses":122,"wins":5},"gpt-6-luna":{"draws":40,"losses":37,"wins":61},"gpt-6-sol":{"draws":18,"losses":95,"wins":25},"gpt-6.1-sol":{"draws":7,"losses":119,"wins":12},"gpt-6.1-terra":{"draws":12,"losses":115,"wins":11},"gpt-6.1-terra-pro":{"draws":10,"losses":115,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":35,"losses":11,"wins":50},"inception/mercury-3":{"draws":22,"losses":28,"wins":40},"inclusionai/ling-3.0-flash":{"draws":32,"losses":12,"wins":54},"inclusionai/ling-3.1-flash":{"draws":7,"losses":3,"wins":14},"meituan/longcat-2.0":{"draws":39,"losses":23,"wins":90},"meta/muse-glimmer-30b":{"draws":33,"losses":14,"wins":75},"meta/muse-spark-1.2":{"draws":25,"losses":49,"wins":58},"meta/muse-spark-1.3":{"draws":25,"losses":62,"wins":51},"meta/muse-spark-open":{"draws":24,"losses":64,"wins":50},"meta/muse-wonder":{"draws":27,"losses":72,"wins":39},"minimax/minimax-m3":{"draws":15,"losses":9,"wins":50},"minimax/minimax-m3.1-flash":{"draws":26,"losses":41,"wins":55},"mistralai/mistral-large-4-0":{"draws":22,"losses":27,"wins":37},"mistralai/mistral-medium-3-5":{"draws":19,"losses":12,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":31,"losses":45,"wins":56},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":103,"wins":22},"nex-agi/nex-n2-pro":{"draws":12,"losses":8,"wins":50},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":6,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":19,"wins":60},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":16,"wins":33},"o3":{"draws":25,"losses":67,"wins":104},"openai/gpt-oss-120b":{"draws":38,"losses":21,"wins":61},"poolside/laguna-s-2.1":{"draws":27,"losses":35,"wins":70},"qwen/qwen3.7-max":{"draws":11,"losses":22,"wins":47},"qwen/qwen3.7-plus":{"draws":11,"losses":16,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":50,"wins":53},"qwen/qwen3.8-27b":{"draws":25,"losses":28,"wins":45},"qwen/qwen3.8-flash":{"draws":22,"losses":27,"wins":43},"qwen/qwen3.8-max":{"draws":31,"losses":47,"wins":60},"qwen/qwen3.8-max-0902":{"draws":33,"losses":50,"wins":55},"recursive/flint-v1.0":{"draws":9,"losses":4,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":35,"losses":31,"wins":60},"stealth/ox-alpha":{"draws":92,"losses":170,"wins":196},"stealth/space-bunny-alpha":{"draws":30,"losses":27,"wins":53},"stepfun/step-3.7-flash":{"draws":20,"losses":17,"wins":63},"stepfun/step-5-preview":{"draws":3,"losses":15,"wins":18},"tencent/hy3-preview":{"draws":24,"losses":19,"wins":31},"tencent/hy4-preview":{"draws":16,"losses":36,"wins":36},"thinkingmachines/inkling":{"draws":47,"losses":29,"wins":110},"thinkingmachines/inkling-small":{"draws":36,"losses":18,"wins":84},"unbiased/pareto-26.10":{"draws":3,"losses":41,"wins":2},"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":29,"losses":55,"wins":54},"x-ai/grok-4.6":{"draws":39,"losses":65,"wins":34},"x-ai/grok-4.7":{"draws":12,"losses":74,"wins":34},"x-ai/grok-build-0.1":{"draws":12,"losses":8,"wins":26},"xiaomi/mimo-v2.5":{"draws":55,"losses":32,"wins":125},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":15,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":35,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":43,"wins":34},"z-ai/glm-5.2":{"draws":55,"losses":70,"wins":151},"z-ai/glm-5.3":{"draws":19,"losses":84,"wins":29},"z-ai/glm-5.3-flash":{"draws":19,"losses":65,"wins":54},"z-ai/glm-5.3-flashx":{"draws":32,"losses":51,"wins":55}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":57,"losses":73,"wins":48},"claude-fable-5":{"draws":37,"losses":143,"wins":12},"claude-fable-5-1":{"draws":8,"losses":209,"wins":1},"claude-haiku-5-5":{"draws":50,"losses":109,"wins":23},"claude-opus-4-5":{"draws":100,"losses":163,"wins":47},"claude-opus-4-8":{"draws":42,"losses":108,"wins":22},"claude-opus-5":{"draws":47,"losses":261,"wins":30},"claude-opus-5-5":{"draws":19,"losses":185,"wins":0},"claude-sonnet-5":{"draws":61,"losses":103,"wins":28},"claude-sonnet-5-5":{"draws":41,"losses":111,"wins":40},"cohere/north-mini-code":{"draws":16,"losses":23,"wins":33},"deepseek/deepseek-v4-flash":{"draws":83,"losses":102,"wins":99},"deepseek/deepseek-v4-pro":{"draws":56,"losses":93,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":51,"losses":80,"wins":45},"deepseek/deepseek-v4.1-flash":{"draws":61,"losses":100,"wins":31},"deepseek/deepseek-v4.1-flash-1017":{"draws":46,"losses":121,"wins":25},"elorian/glimpse":{"draws":27,"losses":53,"wins":26},"fireworks/ember-1":{"draws":57,"losses":107,"wins":28},"gemini-3.1-pro-preview":{"draws":59,"losses":85,"wins":48},"gemini-4-argon":{"draws":17,"losses":164,"wins":11},"google/gemini-3.1-flash-lite":{"draws":33,"losses":35,"wins":58},"google/gemini-3.5-flash":{"draws":47,"losses":144,"wins":49},"google/gemini-3.5-flash-lite":{"draws":86,"losses":140,"wins":112},"google/gemini-3.6-flash":{"draws":103,"losses":218,"wins":51},"google/gemini-3.8-flash":{"draws":47,"losses":125,"wins":20},"google/gemma-4-31b-it":{"draws":39,"losses":32,"wins":37},"gpt-4.1":{"draws":16,"losses":28,"wins":20},"gpt-4.1-nano":{"draws":14,"losses":1,"wins":7},"gpt-5":{"draws":37,"losses":96,"wins":39},"gpt-5.4":{"draws":46,"losses":110,"wins":30},"gpt-5.4-mini":{"draws":45,"losses":47,"wins":36},"gpt-5.4-nano":{"draws":38,"losses":79,"wins":71},"gpt-5.5":{"draws":55,"losses":98,"wins":27},"gpt-5.6-luna":{"draws":58,"losses":88,"wins":46},"gpt-5.6-sol":{"draws":27,"losses":148,"wins":17},"gpt-5.6-terra":{"draws":53,"losses":91,"wins":38},"gpt-6-astra":{"draws":12,"losses":179,"wins":1},"gpt-6-luna":{"draws":56,"losses":95,"wins":41},"gpt-6-sol":{"draws":25,"losses":154,"wins":13},"gpt-6.1-sol":{"draws":12,"losses":175,"wins":5},"gpt-6.1-terra":{"draws":24,"losses":161,"wins":7},"gpt-6.1-terra-pro":{"draws":24,"losses":164,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":7,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":48,"losses":34,"wins":46},"inception/mercury-3":{"draws":44,"losses":56,"wins":26},"inclusionai/ling-3.0-flash":{"draws":47,"losses":31,"wins":52},"inclusionai/ling-3.1-flash":{"draws":18,"losses":15,"wins":5},"meituan/longcat-2.0":{"draws":50,"losses":77,"wins":79},"meta/muse-glimmer-30b":{"draws":56,"losses":61,"wins":57},"meta/muse-spark-1.2":{"draws":49,"losses":104,"wins":33},"meta/muse-spark-1.3":{"draws":34,"losses":139,"wins":19},"meta/muse-spark-open":{"draws":45,"losses":124,"wins":23},"meta/muse-wonder":{"draws":44,"losses":126,"wins":22},"minimax/minimax-m3":{"draws":24,"losses":35,"wins":45},"minimax/minimax-m3.1-flash":{"draws":41,"losses":81,"wins":52},"mistralai/mistral-large-4-0":{"draws":42,"losses":58,"wins":22},"mistralai/mistral-medium-3-5":{"draws":35,"losses":26,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":6,"wins":1},"moonshotai/kimi-k3":{"draws":53,"losses":93,"wins":40},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":163,"wins":10},"nex-agi/nex-n2-pro":{"draws":23,"losses":28,"wins":43},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":17,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":47,"losses":59,"wins":42},"nvidia/nemotron-3.5-super-vl":{"draws":25,"losses":42,"wins":19},"o3":{"draws":38,"losses":170,"wins":58},"openai/gpt-oss-120b":{"draws":42,"losses":61,"wins":65},"poolside/laguna-s-2.1":{"draws":52,"losses":82,"wins":54},"qwen/qwen3.7-max":{"draws":29,"losses":62,"wins":19},"qwen/qwen3.7-plus":{"draws":25,"losses":40,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":58,"losses":109,"wins":25},"qwen/qwen3.8-27b":{"draws":37,"losses":71,"wins":30},"qwen/qwen3.8-flash":{"draws":40,"losses":63,"wins":25},"qwen/qwen3.8-max":{"draws":55,"losses":107,"wins":30},"qwen/qwen3.8-max-0902":{"draws":54,"losses":108,"wins":30},"recursive/flint-v1.0":{"draws":16,"losses":14,"wins":24},"reflection/beam-1.0-501b-a23b":{"draws":52,"losses":91,"wins":33},"stealth/ox-alpha":{"draws":156,"losses":377,"wins":125},"stealth/space-bunny-alpha":{"draws":48,"losses":60,"wins":46},"stepfun/step-3.7-flash":{"draws":34,"losses":64,"wins":40},"stepfun/step-5-preview":{"draws":5,"losses":31,"wins":4},"tencent/hy3-preview":{"draws":30,"losses":48,"wins":26},"tencent/hy4-preview":{"draws":47,"losses":110,"wins":29},"thinkingmachines/inkling":{"draws":68,"losses":68,"wins":68},"thinkingmachines/inkling-small":{"draws":66,"losses":50,"wins":76},"unbiased/pareto-26.10":{"draws":1,"losses":63,"wins":0},"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":54,"losses":114,"wins":24},"x-ai/grok-4.6":{"draws":63,"losses":109,"wins":20},"x-ai/grok-4.7":{"draws":21,"losses":134,"wins":13},"x-ai/grok-build-0.1":{"draws":20,"losses":28,"wins":16},"xiaomi/mimo-v2.5":{"draws":88,"losses":120,"wins":82},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":37,"wins":33},"xiaomi/mimo-v2.6-flash":{"draws":29,"losses":69,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":91,"wins":13},"z-ai/glm-5.2":{"draws":110,"losses":179,"wins":95},"z-ai/glm-5.3":{"draws":33,"losses":126,"wins":23},"z-ai/glm-5.3-flash":{"draws":38,"losses":124,"wins":30},"z-ai/glm-5.3-flashx":{"draws":41,"losses":125,"wins":26}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":42,"losses":60,"wins":30},"claude-fable-5":{"draws":23,"losses":107,"wins":14},"claude-fable-5-1":{"draws":13,"losses":149,"wins":0},"claude-haiku-5-5":{"draws":33,"losses":92,"wins":13},"claude-opus-4-5":{"draws":70,"losses":132,"wins":32},"claude-opus-4-8":{"draws":34,"losses":85,"wins":13},"claude-opus-5":{"draws":40,"losses":195,"wins":11},"claude-opus-5-5":{"draws":10,"losses":146,"wins":0},"claude-sonnet-5":{"draws":41,"losses":79,"wins":24},"claude-sonnet-5-5":{"draws":31,"losses":92,"wins":21},"cohere/north-mini-code":{"draws":15,"losses":17,"wins":22},"deepseek/deepseek-v4-flash":{"draws":78,"losses":90,"wins":48},"deepseek/deepseek-v4-pro":{"draws":41,"losses":71,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":70,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":82,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":105,"wins":14},"elorian/glimpse":{"draws":18,"losses":48,"wins":12},"fireworks/ember-1":{"draws":41,"losses":82,"wins":21},"gemini-3.1-pro-preview":{"draws":37,"losses":78,"wins":29},"gemini-4-argon":{"draws":16,"losses":124,"wins":4},"google/gemini-3.1-flash-lite":{"draws":26,"losses":33,"wins":37},"google/gemini-3.5-flash":{"draws":41,"losses":104,"wins":35},"google/gemini-3.5-flash-lite":{"draws":65,"losses":108,"wins":79},"google/gemini-3.6-flash":{"draws":72,"losses":156,"wins":48},"google/gemini-3.8-flash":{"draws":34,"losses":90,"wins":20},"google/gemma-4-31b-it":{"draws":35,"losses":24,"wins":25},"gpt-4.1":{"draws":13,"losses":20,"wins":15},"gpt-4.1-nano":{"draws":11,"losses":2,"wins":5},"gpt-5":{"draws":38,"losses":65,"wins":23},"gpt-5.4":{"draws":37,"losses":84,"wins":17},"gpt-5.4-mini":{"draws":37,"losses":32,"wins":27},"gpt-5.4-nano":{"draws":40,"losses":63,"wins":41},"gpt-5.5":{"draws":42,"losses":69,"wins":21},"gpt-5.6-luna":{"draws":51,"losses":55,"wins":38},"gpt-5.6-sol":{"draws":22,"losses":109,"wins":13},"gpt-5.6-terra":{"draws":37,"losses":77,"wins":24},"gpt-6-astra":{"draws":9,"losses":135,"wins":0},"gpt-6-luna":{"draws":39,"losses":72,"wins":33},"gpt-6-sol":{"draws":18,"losses":118,"wins":8},"gpt-6.1-sol":{"draws":6,"losses":138,"wins":0},"gpt-6.1-terra":{"draws":10,"losses":134,"wins":0},"gpt-6.1-terra-pro":{"draws":10,"losses":131,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":40,"losses":29,"wins":33},"inception/mercury-3":{"draws":29,"losses":52,"wins":15},"inclusionai/ling-3.0-flash":{"draws":42,"losses":28,"wins":32},"inclusionai/ling-3.1-flash":{"draws":7,"losses":9,"wins":6},"meituan/longcat-2.0":{"draws":40,"losses":67,"wins":49},"meta/muse-glimmer-30b":{"draws":44,"losses":54,"wins":28},"meta/muse-spark-1.2":{"draws":37,"losses":75,"wins":26},"meta/muse-spark-1.3":{"draws":32,"losses":99,"wins":13},"meta/muse-spark-open":{"draws":35,"losses":93,"wins":16},"meta/muse-wonder":{"draws":33,"losses":96,"wins":15},"minimax/minimax-m3":{"draws":21,"losses":36,"wins":21},"minimax/minimax-m3.1-flash":{"draws":35,"losses":59,"wins":32},"mistralai/mistral-large-4-0":{"draws":31,"losses":45,"wins":14},"mistralai/mistral-medium-3-5":{"draws":33,"losses":19,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":9,"wins":2},"moonshotai/kimi-k3":{"draws":44,"losses":73,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":124,"wins":9},"nex-agi/nex-n2-pro":{"draws":17,"losses":23,"wins":32},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":10,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":41,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":38,"wins":9},"o3":{"draws":34,"losses":120,"wins":44},"openai/gpt-oss-120b":{"draws":38,"losses":54,"wins":34},"poolside/laguna-s-2.1":{"draws":41,"losses":73,"wins":24},"qwen/qwen3.7-max":{"draws":22,"losses":42,"wins":20},"qwen/qwen3.7-plus":{"draws":24,"losses":22,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":44,"losses":83,"wins":17},"qwen/qwen3.8-27b":{"draws":28,"losses":58,"wins":16},"qwen/qwen3.8-flash":{"draws":32,"losses":44,"wins":20},"qwen/qwen3.8-max":{"draws":37,"losses":68,"wins":39},"qwen/qwen3.8-max-0902":{"draws":41,"losses":86,"wins":17},"recursive/flint-v1.0":{"draws":12,"losses":16,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":42,"losses":63,"wins":27},"stealth/ox-alpha":{"draws":116,"losses":284,"wins":74},"stealth/space-bunny-alpha":{"draws":31,"losses":57,"wins":26},"stepfun/step-3.7-flash":{"draws":26,"losses":37,"wins":39},"stepfun/step-5-preview":{"draws":9,"losses":15,"wins":4},"tencent/hy3-preview":{"draws":29,"losses":30,"wins":19},"tencent/hy4-preview":{"draws":36,"losses":84,"wins":18},"thinkingmachines/inkling":{"draws":66,"losses":76,"wins":50},"thinkingmachines/inkling-small":{"draws":34,"losses":31,"wins":31},"unbiased/pareto-26.10":{"draws":3,"losses":45,"wins":0},"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":37,"losses":90,"wins":17},"x-ai/grok-4.6":{"draws":37,"losses":90,"wins":17},"x-ai/grok-4.7":{"draws":14,"losses":111,"wins":1},"x-ai/grok-build-0.1":{"draws":14,"losses":18,"wins":16},"xiaomi/mimo-v2.5":{"draws":77,"losses":87,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":26,"losses":37,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":62,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":70,"wins":13},"z-ai/glm-5.2":{"draws":91,"losses":138,"wins":59},"z-ai/glm-5.3":{"draws":20,"losses":109,"wins":9},"z-ai/glm-5.3-flash":{"draws":30,"losses":92,"wins":22},"z-ai/glm-5.3-flashx":{"draws":26,"losses":95,"wins":23}},"unbiased/pareto-26.10":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":42},"claude-fable-5":{"draws":1,"losses":4,"wins":43},"claude-fable-5-1":{"draws":7,"losses":21,"wins":26},"claude-haiku-5-5":{"draws":4,"losses":4,"wins":38},"claude-opus-4-5":{"draws":6,"losses":0,"wins":72},"claude-opus-4-8":{"draws":4,"losses":4,"wins":36},"claude-opus-5":{"draws":7,"losses":24,"wins":51},"claude-opus-5-5":{"draws":4,"losses":27,"wins":21},"claude-sonnet-5":{"draws":4,"losses":1,"wins":43},"claude-sonnet-5-5":{"draws":4,"losses":8,"wins":36},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":68},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":1,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":1,"wins":44},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":2,"wins":40},"elorian/glimpse":{"draws":1,"losses":0,"wins":25},"fireworks/ember-1":{"draws":2,"losses":1,"wins":45},"gemini-3.1-pro-preview":{"draws":3,"losses":3,"wins":42},"gemini-4-argon":{"draws":4,"losses":13,"wins":31},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":7,"losses":3,"wins":50},"google/gemini-3.5-flash-lite":{"draws":5,"losses":0,"wins":79},"google/gemini-3.6-flash":{"draws":8,"losses":3,"wins":81},"google/gemini-3.8-flash":{"draws":4,"losses":5,"wins":39},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":26},"gpt-4.1":{"draws":1,"losses":1,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":0,"wins":41},"gpt-5.4":{"draws":4,"losses":4,"wins":38},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":30},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":43},"gpt-5.5":{"draws":2,"losses":5,"wins":37},"gpt-5.6-luna":{"draws":3,"losses":1,"wins":44},"gpt-5.6-sol":{"draws":4,"losses":3,"wins":41},"gpt-5.6-terra":{"draws":3,"losses":1,"wins":42},"gpt-6-astra":{"draws":8,"losses":22,"wins":18},"gpt-6-luna":{"draws":3,"losses":1,"wins":44},"gpt-6-sol":{"draws":3,"losses":7,"wins":38},"gpt-6.1-sol":{"draws":6,"losses":17,"wins":25},"gpt-6.1-terra":{"draws":7,"losses":8,"wins":33},"gpt-6.1-terra-pro":{"draws":5,"losses":12,"wins":31},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inception/mercury-3":{"draws":2,"losses":1,"wins":29},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":51},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":40},"meta/muse-spark-1.2":{"draws":2,"losses":0,"wins":44},"meta/muse-spark-1.3":{"draws":3,"losses":0,"wins":45},"meta/muse-spark-open":{"draws":3,"losses":2,"wins":43},"meta/muse-wonder":{"draws":6,"losses":8,"wins":34},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"minimax/minimax-m3.1-flash":{"draws":1,"losses":1,"wins":40},"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":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":3,"losses":1,"wins":42},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":15,"wins":28},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":20},"o3":{"draws":0,"losses":0,"wins":66},"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":5,"losses":1,"wins":42},"qwen/qwen3.8-27b":{"draws":2,"losses":0,"wins":32},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":28},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":47},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":44},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":0,"wins":42},"stealth/ox-alpha":{"draws":11,"losses":4,"wins":143},"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":14},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":25},"tencent/hy4-preview":{"draws":3,"losses":2,"wins":41},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":63},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":45},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":8},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":3,"losses":1,"wins":44},"x-ai/grok-4.6":{"draws":6,"losses":2,"wins":40},"x-ai/grok-4.7":{"draws":5,"losses":10,"wins":27},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":15},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":1,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":30},"z-ai/glm-5.2":{"draws":4,"losses":1,"wins":91},"z-ai/glm-5.3":{"draws":5,"losses":4,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":39},"z-ai/glm-5.3-flashx":{"draws":4,"losses":5,"wins":39}},"unbiased/pareto-26.10-preview":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":42},"claude-fable-5":{"draws":5,"losses":11,"wins":32},"claude-fable-5-1":{"draws":0,"losses":24,"wins":30},"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":1,"losses":2,"wins":41},"claude-opus-5":{"draws":5,"losses":30,"wins":47},"claude-opus-5-5":{"draws":1,"losses":25,"wins":26},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"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":0,"losses":1,"wins":71},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":43},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":10,"wins":37},"elorian/glimpse":{"draws":0,"losses":2,"wins":24},"fireworks/ember-1":{"draws":1,"losses":1,"wins":46},"gemini-3.1-pro-preview":{"draws":1,"losses":1,"wins":46},"gemini-4-argon":{"draws":3,"losses":18,"wins":27},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":2,"losses":5,"wins":53},"google/gemini-3.5-flash-lite":{"draws":3,"losses":0,"wins":81},"google/gemini-3.6-flash":{"draws":1,"losses":9,"wins":82},"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":0,"losses":7,"wins":39},"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":2,"losses":3,"wins":43},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":44},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":39},"gpt-6-astra":{"draws":3,"losses":24,"wins":21},"gpt-6-luna":{"draws":3,"losses":1,"wins":44},"gpt-6-sol":{"draws":2,"losses":11,"wins":35},"gpt-6.1-sol":{"draws":1,"losses":19,"wins":28},"gpt-6.1-terra":{"draws":6,"losses":13,"wins":29},"gpt-6.1-terra-pro":{"draws":4,"losses":18,"wins":26},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inception/mercury-3":{"draws":0,"losses":2,"wins":32},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"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":3,"losses":5,"wins":40},"meta/muse-spark-open":{"draws":0,"losses":3,"wins":45},"meta/muse-wonder":{"draws":2,"losses":9,"wins":37},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"minimax/minimax-m3.1-flash":{"draws":1,"losses":1,"wins":40},"mistralai/mistral-large-4-0":{"draws":2,"losses":3,"wins":25},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":43},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":16,"wins":27},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":37},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":19},"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":1,"losses":5,"wins":26},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":41},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":0,"wins":43},"stealth/ox-alpha":{"draws":8,"losses":8,"wins":142},"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":2,"wins":8},"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},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":8},"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":3,"losses":4,"wins":41},"x-ai/grok-4.7":{"draws":2,"losses":8,"wins":32},"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":0,"wins":28},"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":3,"wins":89},"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":1,"losses":5,"wins":42}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":14,"wins":15},"claude-fable-5":{"draws":3,"losses":29,"wins":4},"claude-fable-5-1":{"draws":2,"losses":38,"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":6,"losses":41,"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":6,"losses":25,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":26,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":31,"wins":1},"elorian/glimpse":{"draws":4,"losses":10,"wins":4},"fireworks/ember-1":{"draws":5,"losses":23,"wins":8},"gemini-3.1-pro-preview":{"draws":5,"losses":18,"wins":13},"gemini-4-argon":{"draws":3,"losses":33,"wins":0},"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":19,"losses":24,"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},"gpt-6.1-terra":{"draws":0,"losses":36,"wins":0},"gpt-6.1-terra-pro":{"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},"inception/mercury-3":{"draws":2,"losses":15,"wins":3},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":11},"inclusionai/ling-3.1-flash":{"draws":0,"losses":5,"wins":3},"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":3,"losses":25,"wins":8},"meta/muse-spark-open":{"draws":2,"losses":29,"wins":5},"meta/muse-wonder":{"draws":3,"losses":32,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":10},"minimax/minimax-m3.1-flash":{"draws":6,"losses":24,"wins":6},"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":3,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":24,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":36,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":10,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":10,"wins":2},"o3":{"draws":9,"losses":40,"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},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":19,"wins":7},"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},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":0},"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":{"draws":0,"losses":12,"wins":0},"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":17,"losses":15,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":9},"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":17,"wins":85},"claude-fable-5":{"draws":24,"losses":73,"wins":47},"claude-fable-5-1":{"draws":12,"losses":139,"wins":11},"claude-haiku-5-5":{"draws":30,"losses":49,"wins":59},"claude-opus-4-5":{"draws":63,"losses":65,"wins":106},"claude-opus-4-8":{"draws":36,"losses":44,"wins":52},"claude-opus-5":{"draws":38,"losses":156,"wins":52},"claude-opus-5-5":{"draws":18,"losses":120,"wins":18},"claude-sonnet-5":{"draws":38,"losses":33,"wins":73},"claude-sonnet-5-5":{"draws":31,"losses":63,"wins":50},"cohere/north-mini-code":{"draws":7,"losses":3,"wins":44},"deepseek/deepseek-v4-flash":{"draws":37,"losses":33,"wins":146},"deepseek/deepseek-v4-pro":{"draws":34,"losses":36,"wins":62},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":44,"wins":60},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":46,"wins":67},"deepseek/deepseek-v4.1-flash-1017":{"draws":27,"losses":61,"wins":56},"elorian/glimpse":{"draws":14,"losses":28,"wins":36},"fireworks/ember-1":{"draws":32,"losses":40,"wins":72},"gemini-3.1-pro-preview":{"draws":30,"losses":44,"wins":70},"gemini-4-argon":{"draws":10,"losses":108,"wins":26},"google/gemini-3.1-flash-lite":{"draws":17,"losses":2,"wins":77},"google/gemini-3.5-flash":{"draws":33,"losses":61,"wins":86},"google/gemini-3.5-flash-lite":{"draws":60,"losses":47,"wins":145},"google/gemini-3.6-flash":{"draws":59,"losses":104,"wins":113},"google/gemini-3.8-flash":{"draws":24,"losses":53,"wins":67},"google/gemma-4-31b-it":{"draws":17,"losses":10,"wins":57},"gpt-4.1":{"draws":11,"losses":9,"wins":28},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":25,"losses":33,"wins":68},"gpt-5.4":{"draws":32,"losses":59,"wins":47},"gpt-5.4-mini":{"draws":28,"losses":16,"wins":52},"gpt-5.4-nano":{"draws":31,"losses":29,"wins":84},"gpt-5.5":{"draws":35,"losses":42,"wins":55},"gpt-5.6-luna":{"draws":36,"losses":36,"wins":72},"gpt-5.6-sol":{"draws":18,"losses":82,"wins":44},"gpt-5.6-terra":{"draws":39,"losses":33,"wins":66},"gpt-6-astra":{"draws":9,"losses":120,"wins":15},"gpt-6-luna":{"draws":33,"losses":45,"wins":66},"gpt-6-sol":{"draws":19,"losses":94,"wins":31},"gpt-6.1-sol":{"draws":10,"losses":116,"wins":18},"gpt-6.1-terra":{"draws":18,"losses":102,"wins":24},"gpt-6.1-terra-pro":{"draws":13,"losses":109,"wins":22},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":34,"losses":4,"wins":64},"inception/mercury-3":{"draws":31,"losses":23,"wins":42},"inclusionai/ling-3.0-flash":{"draws":24,"losses":6,"wins":72},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":30,"losses":25,"wins":101},"meta/muse-glimmer-30b":{"draws":31,"losses":14,"wins":81},"meta/muse-spark-1.2":{"draws":32,"losses":37,"wins":69},"meta/muse-spark-1.3":{"draws":23,"losses":60,"wins":61},"meta/muse-spark-open":{"draws":30,"losses":49,"wins":65},"meta/muse-wonder":{"draws":29,"losses":79,"wins":36},"minimax/minimax-m3":{"draws":14,"losses":5,"wins":59},"minimax/minimax-m3.1-flash":{"draws":32,"losses":31,"wins":63},"mistralai/mistral-large-4-0":{"draws":20,"losses":29,"wins":41},"mistralai/mistral-medium-3-5":{"draws":19,"losses":7,"wins":58},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":28,"losses":44,"wins":66},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":98,"wins":27},"nex-agi/nex-n2-pro":{"draws":12,"losses":9,"wins":51},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":3,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":10,"wins":70},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":10,"wins":37},"o3":{"draws":21,"losses":57,"wins":120},"openai/gpt-oss-120b":{"draws":35,"losses":13,"wins":78},"poolside/laguna-s-2.1":{"draws":35,"losses":19,"wins":84},"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":47,"wins":63},"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":44,"wins":68},"qwen/qwen3.8-max-0902":{"draws":31,"losses":52,"wins":61},"recursive/flint-v1.0":{"draws":12,"losses":0,"wins":30},"reflection/beam-1.0-501b-a23b":{"draws":38,"losses":31,"wins":63},"stealth/ox-alpha":{"draws":98,"losses":165,"wins":211},"stealth/space-bunny-alpha":{"draws":30,"losses":21,"wins":63},"stepfun/step-3.7-flash":{"draws":12,"losses":19,"wins":71},"stepfun/step-5-preview":{"draws":5,"losses":14,"wins":9},"tencent/hy3-preview":{"draws":24,"losses":7,"wins":47},"tencent/hy4-preview":{"draws":29,"losses":54,"wins":55},"thinkingmachines/inkling":{"draws":54,"losses":24,"wins":114},"thinkingmachines/inkling-small":{"draws":37,"losses":17,"wins":90},"unbiased/pareto-26.10":{"draws":3,"losses":44,"wins":1},"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":28,"losses":34,"wins":34},"x-ai/grok-4.6":{"draws":42,"losses":54,"wins":48},"x-ai/grok-4.7":{"draws":16,"losses":83,"wins":27},"x-ai/grok-build-0.1":{"draws":13,"losses":5,"wins":30},"xiaomi/mimo-v2.5":{"draws":59,"losses":18,"wins":145},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":14,"wins":49},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":32,"wins":45},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":43,"wins":37},"z-ai/glm-5.2":{"draws":70,"losses":59,"wins":159},"z-ai/glm-5.3":{"draws":26,"losses":78,"wins":34},"z-ai/glm-5.3-flash":{"draws":18,"losses":64,"wins":62},"z-ai/glm-5.3-flashx":{"draws":24,"losses":61,"wins":59}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":17,"wins":85},"claude-fable-5":{"draws":31,"losses":64,"wins":49},"claude-fable-5-1":{"draws":9,"losses":128,"wins":25},"claude-haiku-5-5":{"draws":36,"losses":42,"wins":60},"claude-opus-4-5":{"draws":55,"losses":55,"wins":124},"claude-opus-4-8":{"draws":31,"losses":44,"wins":57},"claude-opus-5":{"draws":37,"losses":161,"wins":48},"claude-opus-5-5":{"draws":16,"losses":126,"wins":14},"claude-sonnet-5":{"draws":36,"losses":34,"wins":74},"claude-sonnet-5-5":{"draws":22,"losses":61,"wins":61},"cohere/north-mini-code":{"draws":9,"losses":2,"wins":43},"deepseek/deepseek-v4-flash":{"draws":50,"losses":25,"wins":141},"deepseek/deepseek-v4-pro":{"draws":31,"losses":27,"wins":74},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":29,"wins":66},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":47,"wins":61},"deepseek/deepseek-v4.1-flash-1017":{"draws":40,"losses":57,"wins":47},"elorian/glimpse":{"draws":20,"losses":25,"wins":33},"fireworks/ember-1":{"draws":36,"losses":43,"wins":65},"gemini-3.1-pro-preview":{"draws":34,"losses":30,"wins":80},"gemini-4-argon":{"draws":19,"losses":105,"wins":20},"google/gemini-3.1-flash-lite":{"draws":17,"losses":4,"wins":75},"google/gemini-3.5-flash":{"draws":40,"losses":39,"wins":101},"google/gemini-3.5-flash-lite":{"draws":56,"losses":33,"wins":163},"google/gemini-3.6-flash":{"draws":64,"losses":82,"wins":130},"google/gemini-3.8-flash":{"draws":38,"losses":54,"wins":52},"google/gemma-4-31b-it":{"draws":24,"losses":6,"wins":54},"gpt-4.1":{"draws":17,"losses":7,"wins":24},"gpt-4.1-nano":{"draws":10,"losses":2,"wins":6},"gpt-5":{"draws":33,"losses":20,"wins":73},"gpt-5.4":{"draws":37,"losses":46,"wins":55},"gpt-5.4-mini":{"draws":31,"losses":12,"wins":53},"gpt-5.4-nano":{"draws":21,"losses":26,"wins":97},"gpt-5.5":{"draws":35,"losses":39,"wins":58},"gpt-5.6-luna":{"draws":32,"losses":22,"wins":90},"gpt-5.6-sol":{"draws":28,"losses":57,"wins":59},"gpt-5.6-terra":{"draws":42,"losses":20,"wins":76},"gpt-6-astra":{"draws":12,"losses":121,"wins":11},"gpt-6-luna":{"draws":36,"losses":25,"wins":83},"gpt-6-sol":{"draws":21,"losses":94,"wins":29},"gpt-6.1-sol":{"draws":17,"losses":115,"wins":12},"gpt-6.1-terra":{"draws":22,"losses":113,"wins":9},"gpt-6.1-terra-pro":{"draws":24,"losses":105,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":27,"losses":7,"wins":68},"inception/mercury-3":{"draws":29,"losses":19,"wins":48},"inclusionai/ling-3.0-flash":{"draws":33,"losses":5,"wins":64},"inclusionai/ling-3.1-flash":{"draws":10,"losses":2,"wins":12},"meituan/longcat-2.0":{"draws":32,"losses":25,"wins":99},"meta/muse-glimmer-30b":{"draws":34,"losses":10,"wins":82},"meta/muse-spark-1.2":{"draws":27,"losses":30,"wins":81},"meta/muse-spark-1.3":{"draws":33,"losses":55,"wins":56},"meta/muse-spark-open":{"draws":34,"losses":43,"wins":67},"meta/muse-wonder":{"draws":40,"losses":63,"wins":41},"minimax/minimax-m3":{"draws":16,"losses":2,"wins":60},"minimax/minimax-m3.1-flash":{"draws":35,"losses":27,"wins":64},"mistralai/mistral-large-4-0":{"draws":30,"losses":17,"wins":43},"mistralai/mistral-medium-3-5":{"draws":21,"losses":7,"wins":56},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":31,"losses":34,"wins":73},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":105,"wins":28},"nex-agi/nex-n2-pro":{"draws":15,"losses":5,"wins":52},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":3,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":12,"wins":61},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":10,"wins":42},"o3":{"draws":33,"losses":45,"wins":120},"openai/gpt-oss-120b":{"draws":33,"losses":12,"wins":81},"poolside/laguna-s-2.1":{"draws":33,"losses":19,"wins":86},"qwen/qwen3.7-max":{"draws":20,"losses":16,"wins":48},"qwen/qwen3.7-plus":{"draws":19,"losses":7,"wins":46},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":50,"wins":61},"qwen/qwen3.8-27b":{"draws":26,"losses":23,"wins":53},"qwen/qwen3.8-flash":{"draws":32,"losses":17,"wins":47},"qwen/qwen3.8-max":{"draws":37,"losses":44,"wins":63},"qwen/qwen3.8-max-0902":{"draws":39,"losses":37,"wins":68},"recursive/flint-v1.0":{"draws":7,"losses":5,"wins":30},"reflection/beam-1.0-501b-a23b":{"draws":35,"losses":28,"wins":69},"stealth/ox-alpha":{"draws":126,"losses":150,"wins":198},"stealth/space-bunny-alpha":{"draws":30,"losses":21,"wins":63},"stepfun/step-3.7-flash":{"draws":21,"losses":14,"wins":67},"stepfun/step-5-preview":{"draws":10,"losses":10,"wins":18},"tencent/hy3-preview":{"draws":21,"losses":12,"wins":45},"tencent/hy4-preview":{"draws":39,"losses":34,"wins":65},"thinkingmachines/inkling":{"draws":63,"losses":20,"wins":109},"thinkingmachines/inkling-small":{"draws":37,"losses":17,"wins":90},"unbiased/pareto-26.10":{"draws":6,"losses":40,"wins":2},"unbiased/pareto-26.10-preview":{"draws":3,"losses":41,"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":15,"losses":79,"wins":32},"x-ai/grok-build-0.1":{"draws":15,"losses":6,"wins":27},"xiaomi/mimo-v2.5":{"draws":67,"losses":21,"wins":134},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":8,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":34,"wins":39},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":42,"wins":33},"z-ai/glm-5.2":{"draws":72,"losses":53,"wins":163},"z-ai/glm-5.3":{"draws":27,"losses":68,"wins":43},"z-ai/glm-5.3-flash":{"draws":33,"losses":52,"wins":59},"z-ai/glm-5.3-flashx":{"draws":26,"losses":55,"wins":63}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":15,"wins":93},"claude-fable-5":{"draws":7,"losses":41,"wins":78},"claude-fable-5-1":{"draws":7,"losses":100,"wins":33},"claude-haiku-5-5":{"draws":12,"losses":18,"wins":92},"claude-opus-4-5":{"draws":16,"losses":36,"wins":154},"claude-opus-4-8":{"draws":15,"losses":32,"wins":71},"claude-opus-5":{"draws":21,"losses":102,"wins":97},"claude-opus-5-5":{"draws":10,"losses":98,"wins":30},"claude-sonnet-5":{"draws":12,"losses":26,"wins":88},"claude-sonnet-5-5":{"draws":14,"losses":48,"wins":64},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":45},"deepseek/deepseek-v4-flash":{"draws":18,"losses":15,"wins":159},"deepseek/deepseek-v4-pro":{"draws":10,"losses":20,"wins":86},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":24,"wins":82},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":32,"wins":82},"deepseek/deepseek-v4.1-flash-1017":{"draws":20,"losses":38,"wins":68},"elorian/glimpse":{"draws":7,"losses":17,"wins":44},"fireworks/ember-1":{"draws":10,"losses":28,"wins":88},"gemini-3.1-pro-preview":{"draws":12,"losses":25,"wins":89},"gemini-4-argon":{"draws":16,"losses":70,"wins":40},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":78},"google/gemini-3.5-flash":{"draws":17,"losses":23,"wins":118},"google/gemini-3.5-flash-lite":{"draws":21,"losses":27,"wins":170},"google/gemini-3.6-flash":{"draws":14,"losses":60,"wins":166},"google/gemini-3.8-flash":{"draws":11,"losses":25,"wins":90},"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":9,"losses":18,"wins":85},"gpt-5.4":{"draws":12,"losses":27,"wins":81},"gpt-5.4-mini":{"draws":13,"losses":5,"wins":66},"gpt-5.4-nano":{"draws":14,"losses":8,"wins":110},"gpt-5.5":{"draws":10,"losses":37,"wins":69},"gpt-5.6-luna":{"draws":13,"losses":17,"wins":96},"gpt-5.6-sol":{"draws":16,"losses":42,"wins":68},"gpt-5.6-terra":{"draws":11,"losses":22,"wins":87},"gpt-6-astra":{"draws":12,"losses":91,"wins":23},"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":82,"wins":38},"gpt-6.1-terra":{"draws":12,"losses":66,"wins":48},"gpt-6.1-terra-pro":{"draws":13,"losses":75,"wins":38},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":72},"inception/mercury-3":{"draws":10,"losses":10,"wins":66},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":73},"inclusionai/ling-3.1-flash":{"draws":4,"losses":2,"wins":12},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":121},"meta/muse-glimmer-30b":{"draws":6,"losses":14,"wins":92},"meta/muse-spark-1.2":{"draws":6,"losses":30,"wins":86},"meta/muse-spark-1.3":{"draws":12,"losses":33,"wins":81},"meta/muse-spark-open":{"draws":9,"losses":26,"wins":89},"meta/muse-wonder":{"draws":16,"losses":38,"wins":72},"minimax/minimax-m3":{"draws":2,"losses":9,"wins":61},"minimax/minimax-m3.1-flash":{"draws":10,"losses":21,"wins":77},"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":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":29,"wins":83},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":69,"wins":46},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":54},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":85},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":11,"wins":43},"o3":{"draws":12,"losses":36,"wins":130},"openai/gpt-oss-120b":{"draws":9,"losses":5,"wins":98},"poolside/laguna-s-2.1":{"draws":12,"losses":13,"wins":99},"qwen/qwen3.7-max":{"draws":10,"losses":16,"wins":50},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":52},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":31,"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":11,"losses":25,"wins":90},"qwen/qwen3.8-max-0902":{"draws":18,"losses":29,"wins":79},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":35},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":10,"wins":93},"stealth/ox-alpha":{"draws":42,"losses":76,"wins":282},"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":2,"losses":7,"wins":23},"tencent/hy3-preview":{"draws":12,"losses":4,"wins":54},"tencent/hy4-preview":{"draws":12,"losses":34,"wins":74},"thinkingmachines/inkling":{"draws":21,"losses":13,"wins":134},"thinkingmachines/inkling-small":{"draws":14,"losses":1,"wins":111},"unbiased/pareto-26.10":{"draws":5,"losses":27,"wins":10},"unbiased/pareto-26.10-preview":{"draws":2,"losses":32,"wins":8},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":23},"x-ai/grok-4.5":{"draws":16,"losses":27,"wins":83},"x-ai/grok-4.6":{"draws":15,"losses":32,"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":4,"losses":4,"wins":46},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":18,"wins":55},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":56},"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":16,"losses":34,"wins":76},"z-ai/glm-5.3-flashx":{"draws":17,"losses":27,"wins":82}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":21,"wins":11},"claude-fable-5":{"draws":8,"losses":34,"wins":6},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":30,"wins":4},"claude-opus-4-5":{"draws":24,"losses":41,"wins":13},"claude-opus-4-8":{"draws":9,"losses":28,"wins":7},"claude-opus-5":{"draws":15,"losses":64,"wins":3},"claude-opus-5-5":{"draws":1,"losses":51,"wins":0},"claude-sonnet-5":{"draws":17,"losses":27,"wins":4},"claude-sonnet-5-5":{"draws":9,"losses":33,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":20,"losses":32,"wins":20},"deepseek/deepseek-v4-pro":{"draws":15,"losses":18,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":26,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":26,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":35,"wins":7},"elorian/glimpse":{"draws":6,"losses":14,"wins":6},"fireworks/ember-1":{"draws":16,"losses":24,"wins":8},"gemini-3.1-pro-preview":{"draws":12,"losses":22,"wins":14},"gemini-4-argon":{"draws":3,"losses":44,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":13,"losses":38,"wins":9},"google/gemini-3.5-flash-lite":{"draws":26,"losses":29,"wins":29},"google/gemini-3.6-flash":{"draws":25,"losses":59,"wins":8},"google/gemini-3.8-flash":{"draws":12,"losses":32,"wins":4},"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":11,"losses":22,"wins":9},"gpt-5.4":{"draws":9,"losses":29,"wins":8},"gpt-5.4-mini":{"draws":9,"losses":14,"wins":9},"gpt-5.4-nano":{"draws":7,"losses":26,"wins":15},"gpt-5.5":{"draws":19,"losses":17,"wins":8},"gpt-5.6-luna":{"draws":15,"losses":22,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":26,"wins":6},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"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},"gpt-6.1-terra":{"draws":5,"losses":41,"wins":2},"gpt-6.1-terra-pro":{"draws":5,"losses":43,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":8,"wins":10},"inception/mercury-3":{"draws":11,"losses":17,"wins":4},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":19},"inclusionai/ling-3.1-flash":{"draws":5,"losses":3,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":19,"wins":19},"meta/muse-glimmer-30b":{"draws":14,"losses":12,"wins":16},"meta/muse-spark-1.2":{"draws":9,"losses":29,"wins":8},"meta/muse-spark-1.3":{"draws":12,"losses":28,"wins":8},"meta/muse-spark-open":{"draws":12,"losses":29,"wins":7},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":6,"losses":9,"wins":11},"minimax/minimax-m3.1-flash":{"draws":13,"losses":18,"wins":11},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":25,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":37,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":11,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":14,"wins":5},"o3":{"draws":11,"losses":38,"wins":17},"openai/gpt-oss-120b":{"draws":13,"losses":12,"wins":17},"poolside/laguna-s-2.1":{"draws":14,"losses":14,"wins":18},"qwen/qwen3.7-max":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.7-plus":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":12,"losses":21,"wins":1},"qwen/qwen3.8-flash":{"draws":13,"losses":13,"wins":6},"qwen/qwen3.8-max":{"draws":15,"losses":26,"wins":7},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":21,"wins":11},"stealth/ox-alpha":{"draws":33,"losses":105,"wins":20},"stealth/space-bunny-alpha":{"draws":9,"losses":19,"wins":10},"stepfun/step-3.7-flash":{"draws":8,"losses":15,"wins":11},"stepfun/step-5-preview":{"draws":3,"losses":9,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":13,"wins":6},"tencent/hy4-preview":{"draws":12,"losses":26,"wins":8},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":28},"thinkingmachines/inkling-small":{"draws":14,"losses":16,"wins":18},"unbiased/pareto-26.10":{"draws":0,"losses":15,"wins":1},"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":28,"losses":20,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":9,"wins":8},"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":36,"losses":38,"wins":22},"z-ai/glm-5.3":{"draws":10,"losses":36,"wins":0},"z-ai/glm-5.3-flash":{"draws":9,"losses":31,"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":64,"losses":83,"wins":57},"claude-fable-5":{"draws":38,"losses":177,"wins":7},"claude-fable-5-1":{"draws":12,"losses":226,"wins":6},"claude-haiku-5-5":{"draws":57,"losses":132,"wins":31},"claude-opus-4-5":{"draws":122,"losses":186,"wins":60},"claude-opus-4-8":{"draws":57,"losses":129,"wins":32},"claude-opus-5":{"draws":56,"losses":299,"wins":23},"claude-opus-5-5":{"draws":13,"losses":225,"wins":4},"claude-sonnet-5":{"draws":68,"losses":109,"wins":45},"claude-sonnet-5-5":{"draws":47,"losses":146,"wins":29},"cohere/north-mini-code":{"draws":17,"losses":32,"wins":31},"deepseek/deepseek-v4-flash":{"draws":104,"losses":118,"wins":112},"deepseek/deepseek-v4-pro":{"draws":67,"losses":99,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":58,"losses":100,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":62,"losses":126,"wins":34},"deepseek/deepseek-v4.1-flash-1017":{"draws":47,"losses":159,"wins":16},"elorian/glimpse":{"draws":34,"losses":64,"wins":20},"fireworks/ember-1":{"draws":69,"losses":115,"wins":38},"gemini-3.1-pro-preview":{"draws":65,"losses":96,"wins":61},"gemini-4-argon":{"draws":16,"losses":205,"wins":1},"google/gemini-3.1-flash-lite":{"draws":45,"losses":40,"wins":77},"google/gemini-3.5-flash":{"draws":70,"losses":155,"wins":59},"google/gemini-3.5-flash-lite":{"draws":109,"losses":139,"wins":144},"google/gemini-3.6-flash":{"draws":113,"losses":248,"wins":63},"google/gemini-3.8-flash":{"draws":55,"losses":147,"wins":20},"google/gemma-4-31b-it":{"draws":60,"losses":33,"wins":41},"gpt-4.1":{"draws":24,"losses":34,"wins":16},"gpt-4.1-nano":{"draws":11,"losses":2,"wins":9},"gpt-5":{"draws":49,"losses":95,"wins":46},"gpt-5.4":{"draws":52,"losses":138,"wins":22},"gpt-5.4-mini":{"draws":49,"losses":57,"wins":42},"gpt-5.4-nano":{"draws":51,"losses":110,"wins":75},"gpt-5.5":{"draws":78,"losses":99,"wins":25},"gpt-5.6-luna":{"draws":71,"losses":93,"wins":58},"gpt-5.6-sol":{"draws":36,"losses":174,"wins":12},"gpt-5.6-terra":{"draws":68,"losses":125,"wins":19},"gpt-6-astra":{"draws":14,"losses":206,"wins":2},"gpt-6-luna":{"draws":74,"losses":116,"wins":32},"gpt-6-sol":{"draws":36,"losses":169,"wins":17},"gpt-6.1-sol":{"draws":18,"losses":196,"wins":8},"gpt-6.1-terra":{"draws":26,"losses":193,"wins":3},"gpt-6.1-terra-pro":{"draws":27,"losses":186,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":12,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":66,"losses":29,"wins":71},"inception/mercury-3":{"draws":52,"losses":70,"wins":24},"inclusionai/ling-3.0-flash":{"draws":68,"losses":38,"wins":54},"inclusionai/ling-3.1-flash":{"draws":9,"losses":13,"wins":8},"meituan/longcat-2.0":{"draws":59,"losses":89,"wins":90},"meta/muse-glimmer-30b":{"draws":66,"losses":61,"wins":65},"meta/muse-spark-1.2":{"draws":59,"losses":126,"wins":27},"meta/muse-spark-1.3":{"draws":45,"losses":151,"wins":26},"meta/muse-spark-open":{"draws":63,"losses":140,"wins":19},"meta/muse-wonder":{"draws":45,"losses":160,"wins":17},"minimax/minimax-m3":{"draws":38,"losses":40,"wins":46},"minimax/minimax-m3.1-flash":{"draws":46,"losses":91,"wins":55},"mistralai/mistral-large-4-0":{"draws":56,"losses":63,"wins":19},"mistralai/mistral-medium-3-5":{"draws":50,"losses":29,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":74,"losses":107,"wins":31},"moonshotai/kimi-k3.1-pro":{"draws":26,"losses":190,"wins":6},"nex-agi/nex-n2-pro":{"draws":21,"losses":34,"wins":47},"nex-agi/nex-n2.5-pro":{"draws":11,"losses":18,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":57,"losses":55,"wins":60},"nvidia/nemotron-3.5-super-vl":{"draws":33,"losses":47,"wins":24},"o3":{"draws":49,"losses":198,"wins":69},"openai/gpt-oss-120b":{"draws":55,"losses":72,"wins":61},"poolside/laguna-s-2.1":{"draws":55,"losses":85,"wins":62},"qwen/qwen3.7-max":{"draws":39,"losses":62,"wins":33},"qwen/qwen3.7-plus":{"draws":39,"losses":45,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":86,"losses":112,"wins":24},"qwen/qwen3.8-27b":{"draws":38,"losses":91,"wins":31},"qwen/qwen3.8-flash":{"draws":49,"losses":64,"wins":35},"qwen/qwen3.8-max":{"draws":69,"losses":114,"wins":39},"qwen/qwen3.8-max-0902":{"draws":72,"losses":119,"wins":31},"recursive/flint-v1.0":{"draws":20,"losses":21,"wins":31},"reflection/beam-1.0-501b-a23b":{"draws":65,"losses":103,"wins":32},"stealth/ox-alpha":{"draws":153,"losses":392,"wins":101},"stealth/space-bunny-alpha":{"draws":60,"losses":75,"wins":43},"stepfun/step-3.7-flash":{"draws":38,"losses":59,"wins":59},"stepfun/step-5-preview":{"draws":4,"losses":30,"wins":10},"tencent/hy3-preview":{"draws":47,"losses":45,"wins":36},"tencent/hy4-preview":{"draws":55,"losses":125,"wins":32},"thinkingmachines/inkling":{"draws":88,"losses":82,"wins":120},"thinkingmachines/inkling-small":{"draws":77,"losses":58,"wins":87},"unbiased/pareto-26.10":{"draws":4,"losses":70,"wins":0},"unbiased/pareto-26.10-preview":{"draws":4,"losses":70,"wins":0},"upstage/solar-mini4":{"draws":17,"losses":30,"wins":15},"x-ai/grok-4.5":{"draws":59,"losses":145,"wins":18},"x-ai/grok-4.6":{"draws":67,"losses":134,"wins":21},"x-ai/grok-4.7":{"draws":22,"losses":160,"wins":16},"x-ai/grok-build-0.1":{"draws":28,"losses":26,"wins":20},"xiaomi/mimo-v2.5":{"draws":108,"losses":98,"wins":98},"xiaomi/mimo-v2.5-pro":{"draws":39,"losses":40,"wins":41},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":92,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":36,"losses":98,"wins":14},"z-ai/glm-5.2":{"draws":149,"losses":199,"wins":96},"z-ai/glm-5.3":{"draws":40,"losses":166,"wins":4},"z-ai/glm-5.3-flash":{"draws":48,"losses":136,"wins":38},"z-ai/glm-5.3-flashx":{"draws":56,"losses":145,"wins":21}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":29,"wins":17},"claude-fable-5":{"draws":11,"losses":61,"wins":8},"claude-fable-5-1":{"draws":2,"losses":80,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":40,"wins":10},"claude-opus-4-5":{"draws":30,"losses":66,"wins":28},"claude-opus-4-8":{"draws":11,"losses":39,"wins":12},"claude-opus-5":{"draws":15,"losses":113,"wins":6},"claude-opus-5-5":{"draws":4,"losses":59,"wins":1},"claude-sonnet-5":{"draws":14,"losses":34,"wins":20},"claude-sonnet-5-5":{"draws":15,"losses":37,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":13,"wins":12},"deepseek/deepseek-v4-flash":{"draws":31,"losses":45,"wins":34},"deepseek/deepseek-v4-pro":{"draws":12,"losses":41,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":43,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":40,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":39,"wins":5},"elorian/glimpse":{"draws":9,"losses":22,"wins":9},"fireworks/ember-1":{"draws":24,"losses":31,"wins":13},"gemini-3.1-pro-preview":{"draws":16,"losses":34,"wins":18},"gemini-4-argon":{"draws":6,"losses":59,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":9,"wins":29},"google/gemini-3.5-flash":{"draws":20,"losses":52,"wins":28},"google/gemini-3.5-flash-lite":{"draws":30,"losses":60,"wins":36},"google/gemini-3.6-flash":{"draws":23,"losses":83,"wins":30},"google/gemini-3.8-flash":{"draws":14,"losses":55,"wins":13},"google/gemma-4-31b-it":{"draws":14,"losses":9,"wins":17},"gpt-4.1":{"draws":6,"losses":13,"wins":9},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":4},"gpt-5":{"draws":14,"losses":35,"wins":21},"gpt-5.4":{"draws":13,"losses":48,"wins":13},"gpt-5.4-mini":{"draws":13,"losses":23,"wins":12},"gpt-5.4-nano":{"draws":16,"losses":40,"wins":28},"gpt-5.5":{"draws":20,"losses":32,"wins":14},"gpt-5.6-luna":{"draws":27,"losses":26,"wins":25},"gpt-5.6-sol":{"draws":10,"losses":58,"wins":10},"gpt-5.6-terra":{"draws":17,"losses":44,"wins":9},"gpt-6-astra":{"draws":7,"losses":69,"wins":0},"gpt-6-luna":{"draws":17,"losses":39,"wins":14},"gpt-6-sol":{"draws":7,"losses":55,"wins":8},"gpt-6.1-sol":{"draws":9,"losses":59,"wins":0},"gpt-6.1-terra":{"draws":9,"losses":49,"wins":2},"gpt-6.1-terra-pro":{"draws":5,"losses":49,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":17,"wins":18},"inception/mercury-3":{"draws":16,"losses":19,"wins":11},"inclusionai/ling-3.0-flash":{"draws":13,"losses":17,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":3,"wins":5},"meituan/longcat-2.0":{"draws":19,"losses":28,"wins":39},"meta/muse-glimmer-30b":{"draws":16,"losses":23,"wins":25},"meta/muse-spark-1.2":{"draws":10,"losses":40,"wins":12},"meta/muse-spark-1.3":{"draws":13,"losses":49,"wins":6},"meta/muse-spark-open":{"draws":15,"losses":44,"wins":5},"meta/muse-wonder":{"draws":11,"losses":45,"wins":10},"minimax/minimax-m3":{"draws":7,"losses":14,"wins":19},"minimax/minimax-m3.1-flash":{"draws":15,"losses":28,"wins":19},"mistralai/mistral-large-4-0":{"draws":9,"losses":21,"wins":8},"mistralai/mistral-medium-3-5":{"draws":11,"losses":12,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":37,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":59,"wins":5},"nex-agi/nex-n2-pro":{"draws":11,"losses":16,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":8,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":24,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":18,"wins":4},"o3":{"draws":11,"losses":70,"wins":23},"openai/gpt-oss-120b":{"draws":17,"losses":28,"wins":23},"poolside/laguna-s-2.1":{"draws":15,"losses":46,"wins":19},"qwen/qwen3.7-max":{"draws":11,"losses":23,"wins":14},"qwen/qwen3.7-plus":{"draws":10,"losses":13,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":51,"wins":15},"qwen/qwen3.8-27b":{"draws":14,"losses":28,"wins":10},"qwen/qwen3.8-flash":{"draws":13,"losses":27,"wins":8},"qwen/qwen3.8-max":{"draws":15,"losses":40,"wins":17},"qwen/qwen3.8-max-0902":{"draws":15,"losses":36,"wins":9},"recursive/flint-v1.0":{"draws":3,"losses":9,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":32,"wins":13},"stealth/ox-alpha":{"draws":45,"losses":151,"wins":50},"stealth/space-bunny-alpha":{"draws":15,"losses":28,"wins":13},"stepfun/step-3.7-flash":{"draws":10,"losses":19,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":22,"wins":8},"tencent/hy3-preview":{"draws":12,"losses":15,"wins":15},"tencent/hy4-preview":{"draws":13,"losses":40,"wins":15},"thinkingmachines/inkling":{"draws":20,"losses":33,"wins":37},"thinkingmachines/inkling-small":{"draws":26,"losses":23,"wins":37},"unbiased/pareto-26.10":{"draws":1,"losses":25,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":28,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":9,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":49,"wins":14},"x-ai/grok-4.6":{"draws":20,"losses":50,"wins":8},"x-ai/grok-4.7":{"draws":4,"losses":46,"wins":4},"x-ai/grok-build-0.1":{"draws":11,"losses":8,"wins":9},"xiaomi/mimo-v2.5":{"draws":39,"losses":41,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":6,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":22,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":28,"wins":7},"z-ai/glm-5.2":{"draws":36,"losses":72,"wins":42},"z-ai/glm-5.3":{"draws":13,"losses":49,"wins":4},"z-ai/glm-5.3-flash":{"draws":11,"losses":54,"wins":13},"z-ai/glm-5.3-flashx":{"draws":15,"losses":47,"wins":10}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":20,"wins":51},"claude-fable-5":{"draws":16,"losses":53,"wins":21},"claude-fable-5-1":{"draws":5,"losses":87,"wins":8},"claude-haiku-5-5":{"draws":22,"losses":37,"wins":27},"claude-opus-4-5":{"draws":30,"losses":45,"wins":71},"claude-opus-4-8":{"draws":14,"losses":26,"wins":42},"claude-opus-5":{"draws":15,"losses":120,"wins":17},"claude-opus-5-5":{"draws":7,"losses":89,"wins":2},"claude-sonnet-5":{"draws":12,"losses":28,"wins":50},"claude-sonnet-5-5":{"draws":10,"losses":47,"wins":33},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":24},"deepseek/deepseek-v4-flash":{"draws":18,"losses":34,"wins":86},"deepseek/deepseek-v4-pro":{"draws":18,"losses":26,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":38,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":40,"wins":34},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":53,"wins":22},"elorian/glimpse":{"draws":5,"losses":17,"wins":26},"fireworks/ember-1":{"draws":11,"losses":37,"wins":42},"gemini-3.1-pro-preview":{"draws":12,"losses":29,"wins":49},"gemini-4-argon":{"draws":3,"losses":79,"wins":8},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":49},"google/gemini-3.5-flash":{"draws":14,"losses":43,"wins":55},"google/gemini-3.5-flash-lite":{"draws":23,"losses":20,"wins":113},"google/gemini-3.6-flash":{"draws":22,"losses":73,"wins":77},"google/gemini-3.8-flash":{"draws":17,"losses":44,"wins":29},"google/gemma-4-31b-it":{"draws":11,"losses":9,"wins":32},"gpt-4.1":{"draws":6,"losses":7,"wins":17},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":7},"gpt-5":{"draws":9,"losses":27,"wins":44},"gpt-5.4":{"draws":22,"losses":39,"wins":25},"gpt-5.4-mini":{"draws":9,"losses":15,"wins":36},"gpt-5.4-nano":{"draws":21,"losses":20,"wins":53},"gpt-5.5":{"draws":20,"losses":37,"wins":25},"gpt-5.6-luna":{"draws":11,"losses":32,"wins":47},"gpt-5.6-sol":{"draws":9,"losses":61,"wins":20},"gpt-5.6-terra":{"draws":17,"losses":33,"wins":36},"gpt-6-astra":{"draws":3,"losses":82,"wins":5},"gpt-6-luna":{"draws":18,"losses":32,"wins":40},"gpt-6-sol":{"draws":9,"losses":62,"wins":19},"gpt-6.1-sol":{"draws":4,"losses":79,"wins":7},"gpt-6.1-terra":{"draws":12,"losses":72,"wins":6},"gpt-6.1-terra-pro":{"draws":9,"losses":74,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":8,"wins":45},"inception/mercury-3":{"draws":12,"losses":29,"wins":23},"inclusionai/ling-3.0-flash":{"draws":17,"losses":5,"wins":42},"inclusionai/ling-3.1-flash":{"draws":5,"losses":4,"wins":7},"meituan/longcat-2.0":{"draws":16,"losses":20,"wins":62},"meta/muse-glimmer-30b":{"draws":13,"losses":14,"wins":51},"meta/muse-spark-1.2":{"draws":9,"losses":45,"wins":32},"meta/muse-spark-1.3":{"draws":9,"losses":51,"wins":30},"meta/muse-spark-open":{"draws":11,"losses":48,"wins":29},"meta/muse-wonder":{"draws":5,"losses":63,"wins":22},"minimax/minimax-m3":{"draws":8,"losses":10,"wins":32},"minimax/minimax-m3.1-flash":{"draws":10,"losses":24,"wins":44},"mistralai/mistral-large-4-0":{"draws":17,"losses":19,"wins":20},"mistralai/mistral-medium-3-5":{"draws":9,"losses":6,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":19,"losses":30,"wins":37},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":70,"wins":10},"nex-agi/nex-n2-pro":{"draws":6,"losses":9,"wins":31},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":14,"wins":45},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":13,"wins":18},"o3":{"draws":12,"losses":36,"wins":80},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":57},"poolside/laguna-s-2.1":{"draws":22,"losses":14,"wins":54},"qwen/qwen3.7-max":{"draws":14,"losses":11,"wins":29},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":32},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":34,"wins":37},"qwen/qwen3.8-27b":{"draws":15,"losses":23,"wins":26},"qwen/qwen3.8-flash":{"draws":12,"losses":27,"wins":21},"qwen/qwen3.8-max":{"draws":18,"losses":36,"wins":36},"qwen/qwen3.8-max-0902":{"draws":13,"losses":36,"wins":41},"recursive/flint-v1.0":{"draws":0,"losses":6,"wins":20},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":35,"wins":35},"stealth/ox-alpha":{"draws":51,"losses":135,"wins":112},"stealth/space-bunny-alpha":{"draws":11,"losses":17,"wins":42},"stepfun/step-3.7-flash":{"draws":13,"losses":7,"wins":46},"stepfun/step-5-preview":{"draws":1,"losses":14,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":13,"wins":26},"tencent/hy4-preview":{"draws":14,"losses":37,"wins":35},"thinkingmachines/inkling":{"draws":29,"losses":22,"wins":69},"thinkingmachines/inkling-small":{"draws":20,"losses":8,"wins":62},"unbiased/pareto-26.10":{"draws":2,"losses":27,"wins":1},"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":45,"wins":32},"x-ai/grok-4.6":{"draws":17,"losses":39,"wins":34},"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":25,"losses":19,"wins":92},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":7,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":13,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":30,"wins":18},"z-ai/glm-5.2":{"draws":28,"losses":56,"wins":96},"z-ai/glm-5.3":{"draws":10,"losses":54,"wins":22},"z-ai/glm-5.3-flash":{"draws":12,"losses":44,"wins":34},"z-ai/glm-5.3-flashx":{"draws":9,"losses":45,"wins":36}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":18,"wins":57},"claude-fable-5":{"draws":8,"losses":48,"wins":40},"claude-fable-5-1":{"draws":13,"losses":84,"wins":11},"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":9,"losses":37,"wins":42},"claude-opus-5":{"draws":25,"losses":98,"wins":41},"claude-opus-5-5":{"draws":10,"losses":80,"wins":14},"claude-sonnet-5":{"draws":15,"losses":25,"wins":56},"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":12,"losses":27,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":31,"wins":43},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":42,"wins":44},"elorian/glimpse":{"draws":8,"losses":22,"wins":22},"fireworks/ember-1":{"draws":21,"losses":29,"wins":46},"gemini-3.1-pro-preview":{"draws":15,"losses":24,"wins":57},"gemini-4-argon":{"draws":9,"losses":64,"wins":23},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":50},"google/gemini-3.5-flash":{"draws":19,"losses":37,"wins":64},"google/gemini-3.5-flash-lite":{"draws":21,"losses":30,"wins":117},"google/gemini-3.6-flash":{"draws":39,"losses":59,"wins":86},"google/gemini-3.8-flash":{"draws":20,"losses":29,"wins":47},"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":10,"losses":23,"wins":51},"gpt-5.4":{"draws":15,"losses":38,"wins":39},"gpt-5.4-mini":{"draws":15,"losses":9,"wins":40},"gpt-5.4-nano":{"draws":14,"losses":16,"wins":66},"gpt-5.5":{"draws":22,"losses":29,"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":23,"wins":45},"gpt-6-astra":{"draws":9,"losses":80,"wins":7},"gpt-6-luna":{"draws":20,"losses":26,"wins":50},"gpt-6-sol":{"draws":18,"losses":52,"wins":26},"gpt-6.1-sol":{"draws":14,"losses":62,"wins":20},"gpt-6.1-terra":{"draws":12,"losses":59,"wins":25},"gpt-6.1-terra-pro":{"draws":16,"losses":65,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":1,"wins":49},"inception/mercury-3":{"draws":14,"losses":18,"wins":32},"inclusionai/ling-3.0-flash":{"draws":14,"losses":5,"wins":49},"inclusionai/ling-3.1-flash":{"draws":6,"losses":4,"wins":4},"meituan/longcat-2.0":{"draws":18,"losses":11,"wins":75},"meta/muse-glimmer-30b":{"draws":15,"losses":13,"wins":56},"meta/muse-spark-1.2":{"draws":10,"losses":27,"wins":55},"meta/muse-spark-1.3":{"draws":15,"losses":32,"wins":49},"meta/muse-spark-open":{"draws":15,"losses":37,"wins":44},"meta/muse-wonder":{"draws":17,"losses":43,"wins":36},"minimax/minimax-m3":{"draws":7,"losses":8,"wins":37},"minimax/minimax-m3.1-flash":{"draws":15,"losses":19,"wins":50},"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":3,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":18,"losses":24,"wins":50},"moonshotai/kimi-k3.1-pro":{"draws":16,"losses":53,"wins":27},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":37},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":1,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":8,"wins":48},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":13,"wins":27},"o3":{"draws":11,"losses":25,"wins":96},"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":8,"losses":13,"wins":35},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":30,"wins":42},"qwen/qwen3.8-27b":{"draws":12,"losses":20,"wins":36},"qwen/qwen3.8-flash":{"draws":14,"losses":14,"wins":36},"qwen/qwen3.8-max":{"draws":25,"losses":19,"wins":52},"qwen/qwen3.8-max-0902":{"draws":15,"losses":29,"wins":52},"recursive/flint-v1.0":{"draws":6,"losses":2,"wins":20},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":26,"wins":47},"stealth/ox-alpha":{"draws":56,"losses":106,"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":9,"wins":15},"tencent/hy3-preview":{"draws":9,"losses":10,"wins":33},"tencent/hy4-preview":{"draws":15,"losses":34,"wins":43},"thinkingmachines/inkling":{"draws":24,"losses":13,"wins":91},"thinkingmachines/inkling-small":{"draws":13,"losses":13,"wins":70},"unbiased/pareto-26.10":{"draws":1,"losses":30,"wins":1},"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":16,"losses":37,"wins":43},"x-ai/grok-4.6":{"draws":21,"losses":33,"wins":42},"x-ai/grok-4.7":{"draws":6,"losses":56,"wins":22},"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":11,"losses":7,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":18,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":15},"z-ai/glm-5.2":{"draws":48,"losses":37,"wins":107},"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":88,"losses":77,"wins":99},"claude-fable-5":{"draws":58,"losses":187,"wins":43},"claude-fable-5-1":{"draws":16,"losses":303,"wins":5},"claude-haiku-5-5":{"draws":64,"losses":147,"wins":65},"claude-opus-4-5":{"draws":135,"losses":196,"wins":137},"claude-opus-4-8":{"draws":69,"losses":134,"wins":61},"claude-opus-5":{"draws":74,"losses":384,"wins":34},"claude-opus-5-5":{"draws":17,"losses":283,"wins":12},"claude-sonnet-5":{"draws":75,"losses":119,"wins":94},"claude-sonnet-5-5":{"draws":55,"losses":168,"wins":65},"cohere/north-mini-code":{"draws":28,"losses":18,"wins":62},"deepseek/deepseek-v4-flash":{"draws":134,"losses":113,"wins":185},"deepseek/deepseek-v4-pro":{"draws":76,"losses":100,"wins":88},"deepseek/deepseek-v4-pro-0813":{"draws":78,"losses":104,"wins":82},"deepseek/deepseek-v4.1-flash":{"draws":96,"losses":125,"wins":67},"deepseek/deepseek-v4.1-flash-1017":{"draws":62,"losses":173,"wins":53},"elorian/glimpse":{"draws":35,"losses":72,"wins":49},"fireworks/ember-1":{"draws":81,"losses":130,"wins":77},"gemini-3.1-pro-preview":{"draws":74,"losses":116,"wins":98},"gemini-4-argon":{"draws":27,"losses":247,"wins":14},"google/gemini-3.1-flash-lite":{"draws":39,"losses":26,"wins":127},"google/gemini-3.5-flash":{"draws":82,"losses":160,"wins":118},"google/gemini-3.5-flash-lite":{"draws":140,"losses":149,"wins":215},"google/gemini-3.6-flash":{"draws":133,"losses":260,"wins":159},"google/gemini-3.8-flash":{"draws":67,"losses":162,"wins":59},"google/gemma-4-31b-it":{"draws":69,"losses":29,"wins":70},"gpt-4.1":{"draws":33,"losses":23,"wins":40},"gpt-4.1-nano":{"draws":21,"losses":0,"wins":15},"gpt-5":{"draws":72,"losses":101,"wins":79},"gpt-5.4":{"draws":74,"losses":141,"wins":61},"gpt-5.4-mini":{"draws":70,"losses":39,"wins":83},"gpt-5.4-nano":{"draws":59,"losses":98,"wins":131},"gpt-5.5":{"draws":91,"losses":123,"wins":50},"gpt-5.6-luna":{"draws":95,"losses":78,"wins":115},"gpt-5.6-sol":{"draws":37,"losses":207,"wins":44},"gpt-5.6-terra":{"draws":99,"losses":104,"wins":73},"gpt-6-astra":{"draws":21,"losses":259,"wins":8},"gpt-6-luna":{"draws":100,"losses":115,"wins":73},"gpt-6-sol":{"draws":42,"losses":211,"wins":35},"gpt-6.1-sol":{"draws":29,"losses":248,"wins":11},"gpt-6.1-terra":{"draws":29,"losses":240,"wins":19},"gpt-6.1-terra-pro":{"draws":32,"losses":239,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":79,"losses":22,"wins":103},"inception/mercury-3":{"draws":64,"losses":80,"wins":48},"inclusionai/ling-3.0-flash":{"draws":85,"losses":41,"wins":78},"inclusionai/ling-3.1-flash":{"draws":13,"losses":17,"wins":12},"meituan/longcat-2.0":{"draws":80,"losses":77,"wins":155},"meta/muse-glimmer-30b":{"draws":94,"losses":51,"wins":107},"meta/muse-spark-1.2":{"draws":66,"losses":137,"wins":73},"meta/muse-spark-1.3":{"draws":57,"losses":163,"wins":68},"meta/muse-spark-open":{"draws":80,"losses":147,"wins":61},"meta/muse-wonder":{"draws":64,"losses":179,"wins":45},"minimax/minimax-m3":{"draws":39,"losses":41,"wins":76},"minimax/minimax-m3.1-flash":{"draws":62,"losses":93,"wins":97},"mistralai/mistral-large-4-0":{"draws":71,"losses":72,"wins":37},"mistralai/mistral-medium-3-5":{"draws":61,"losses":24,"wins":83},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":88,"losses":113,"wins":75},"moonshotai/kimi-k3.1-pro":{"draws":32,"losses":230,"wins":26},"nex-agi/nex-n2-pro":{"draws":43,"losses":28,"wins":73},"nex-agi/nex-n2.5-pro":{"draws":16,"losses":21,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":67,"losses":62,"wins":89},"nvidia/nemotron-3.5-super-vl":{"draws":42,"losses":46,"wins":44},"o3":{"draws":62,"losses":181,"wins":153},"openai/gpt-oss-120b":{"draws":87,"losses":52,"wins":113},"poolside/laguna-s-2.1":{"draws":87,"losses":84,"wins":105},"qwen/qwen3.7-max":{"draws":41,"losses":59,"wins":68},"qwen/qwen3.7-plus":{"draws":36,"losses":34,"wins":74},"qwen/qwen3.8-2.4t-a95b":{"draws":94,"losses":123,"wins":71},"qwen/qwen3.8-27b":{"draws":63,"losses":70,"wins":71},"qwen/qwen3.8-flash":{"draws":59,"losses":71,"wins":62},"qwen/qwen3.8-max":{"draws":82,"losses":126,"wins":80},"qwen/qwen3.8-max-0902":{"draws":91,"losses":138,"wins":59},"recursive/flint-v1.0":{"draws":17,"losses":18,"wins":49},"reflection/beam-1.0-501b-a23b":{"draws":75,"losses":105,"wins":84},"stealth/ox-alpha":{"draws":233,"losses":482,"wins":233},"stealth/space-bunny-alpha":{"draws":75,"losses":76,"wins":77},"stepfun/step-3.7-flash":{"draws":47,"losses":49,"wins":108},"stepfun/step-5-preview":{"draws":8,"losses":26,"wins":24},"tencent/hy3-preview":{"draws":49,"losses":48,"wins":59},"tencent/hy4-preview":{"draws":55,"losses":151,"wins":70},"thinkingmachines/inkling":{"draws":110,"losses":95,"wins":179},"thinkingmachines/inkling-small":{"draws":91,"losses":59,"wins":138},"unbiased/pareto-26.10":{"draws":4,"losses":91,"wins":1},"unbiased/pareto-26.10-preview":{"draws":4,"losses":89,"wins":3},"upstage/solar-mini4":{"draws":8,"losses":16,"wins":48},"x-ai/grok-4.5":{"draws":70,"losses":159,"wins":59},"x-ai/grok-4.6":{"draws":72,"losses":163,"wins":53},"x-ai/grok-4.7":{"draws":29,"losses":186,"wins":37},"x-ai/grok-build-0.1":{"draws":36,"losses":22,"wins":38},"xiaomi/mimo-v2.5":{"draws":149,"losses":96,"wins":199},"xiaomi/mimo-v2.5-pro":{"draws":36,"losses":42,"wins":72},"xiaomi/mimo-v2.6-flash":{"draws":28,"losses":96,"wins":56},"xiaomi/mimo-v2.6-pro":{"draws":48,"losses":107,"wins":37},"z-ai/glm-5.2":{"draws":148,"losses":166,"wins":166},"z-ai/glm-5.3":{"draws":58,"losses":180,"wins":38},"z-ai/glm-5.3-flash":{"draws":59,"losses":162,"wins":67},"z-ai/glm-5.3-flashx":{"draws":71,"losses":148,"wins":69}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":16,"wins":88},"claude-fable-5":{"draws":21,"losses":54,"wins":63},"claude-fable-5-1":{"draws":13,"losses":122,"wins":21},"claude-haiku-5-5":{"draws":23,"losses":33,"wins":76},"claude-opus-4-5":{"draws":46,"losses":31,"wins":147},"claude-opus-4-8":{"draws":20,"losses":30,"wins":76},"claude-opus-5":{"draws":29,"losses":141,"wins":64},"claude-opus-5-5":{"draws":11,"losses":112,"wins":27},"claude-sonnet-5":{"draws":25,"losses":19,"wins":94},"claude-sonnet-5-5":{"draws":21,"losses":54,"wins":63},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":44},"deepseek/deepseek-v4-flash":{"draws":38,"losses":16,"wins":152},"deepseek/deepseek-v4-pro":{"draws":22,"losses":27,"wins":77},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":27,"wins":79},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":29,"wins":88},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":41,"wins":73},"elorian/glimpse":{"draws":13,"losses":15,"wins":46},"fireworks/ember-1":{"draws":23,"losses":26,"wins":89},"gemini-3.1-pro-preview":{"draws":24,"losses":27,"wins":87},"gemini-4-argon":{"draws":15,"losses":83,"wins":40},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":83},"google/gemini-3.5-flash":{"draws":28,"losses":35,"wins":109},"google/gemini-3.5-flash-lite":{"draws":36,"losses":13,"wins":193},"google/gemini-3.6-flash":{"draws":47,"losses":62,"wins":155},"google/gemini-3.8-flash":{"draws":28,"losses":38,"wins":72},"google/gemma-4-31b-it":{"draws":22,"losses":7,"wins":53},"gpt-4.1":{"draws":6,"losses":8,"wins":32},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":11},"gpt-5":{"draws":15,"losses":19,"wins":86},"gpt-5.4":{"draws":23,"losses":39,"wins":70},"gpt-5.4-mini":{"draws":20,"losses":8,"wins":64},"gpt-5.4-nano":{"draws":19,"losses":21,"wins":96},"gpt-5.5":{"draws":27,"losses":23,"wins":76},"gpt-5.6-luna":{"draws":23,"losses":18,"wins":97},"gpt-5.6-sol":{"draws":22,"losses":61,"wins":55},"gpt-5.6-terra":{"draws":29,"losses":21,"wins":82},"gpt-6-astra":{"draws":15,"losses":112,"wins":11},"gpt-6-luna":{"draws":23,"losses":29,"wins":86},"gpt-6-sol":{"draws":20,"losses":73,"wins":45},"gpt-6.1-sol":{"draws":20,"losses":94,"wins":24},"gpt-6.1-terra":{"draws":23,"losses":89,"wins":26},"gpt-6.1-terra-pro":{"draws":18,"losses":92,"wins":28},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":24,"losses":7,"wins":69},"inception/mercury-3":{"draws":22,"losses":21,"wins":49},"inclusionai/ling-3.0-flash":{"draws":21,"losses":3,"wins":72},"inclusionai/ling-3.1-flash":{"draws":7,"losses":4,"wins":13},"meituan/longcat-2.0":{"draws":21,"losses":13,"wins":118},"meta/muse-glimmer-30b":{"draws":22,"losses":9,"wins":89},"meta/muse-spark-1.2":{"draws":23,"losses":42,"wins":67},"meta/muse-spark-1.3":{"draws":22,"losses":40,"wins":76},"meta/muse-spark-open":{"draws":24,"losses":35,"wins":79},"meta/muse-wonder":{"draws":17,"losses":63,"wins":58},"minimax/minimax-m3":{"draws":14,"losses":7,"wins":53},"minimax/minimax-m3.1-flash":{"draws":17,"losses":25,"wins":78},"mistralai/mistral-large-4-0":{"draws":14,"losses":20,"wins":52},"mistralai/mistral-medium-3-5":{"draws":13,"losses":3,"wins":66},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":30,"losses":39,"wins":63},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":81,"wins":38},"nex-agi/nex-n2-pro":{"draws":11,"losses":4,"wins":57},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":6,"wins":78},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":4,"wins":51},"o3":{"draws":14,"losses":34,"wins":140},"openai/gpt-oss-120b":{"draws":26,"losses":5,"wins":91},"poolside/laguna-s-2.1":{"draws":25,"losses":13,"wins":94},"qwen/qwen3.7-max":{"draws":15,"losses":15,"wins":50},"qwen/qwen3.7-plus":{"draws":14,"losses":7,"wins":47},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":30,"wins":83},"qwen/qwen3.8-27b":{"draws":24,"losses":12,"wins":60},"qwen/qwen3.8-flash":{"draws":21,"losses":16,"wins":55},"qwen/qwen3.8-max":{"draws":27,"losses":31,"wins":80},"qwen/qwen3.8-max-0902":{"draws":31,"losses":31,"wins":76},"recursive/flint-v1.0":{"draws":7,"losses":2,"wins":31},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":22,"wins":88},"stealth/ox-alpha":{"draws":81,"losses":118,"wins":259},"stealth/space-bunny-alpha":{"draws":21,"losses":9,"wins":80},"stepfun/step-3.7-flash":{"draws":13,"losses":3,"wins":80},"stepfun/step-5-preview":{"draws":5,"losses":10,"wins":21},"tencent/hy3-preview":{"draws":13,"losses":9,"wins":52},"tencent/hy4-preview":{"draws":19,"losses":29,"wins":84},"thinkingmachines/inkling":{"draws":33,"losses":23,"wins":126},"thinkingmachines/inkling-small":{"draws":20,"losses":9,"wins":109},"unbiased/pareto-26.10":{"draws":5,"losses":37,"wins":4},"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":26,"losses":34,"wins":78},"x-ai/grok-4.6":{"draws":27,"losses":43,"wins":68},"x-ai/grok-4.7":{"draws":16,"losses":71,"wins":33},"x-ai/grok-build-0.1":{"draws":10,"losses":0,"wins":36},"xiaomi/mimo-v2.5":{"draws":40,"losses":4,"wins":166},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":4,"wins":49},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":22,"wins":54},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":34,"wins":43},"z-ai/glm-5.2":{"draws":58,"losses":38,"wins":180},"z-ai/glm-5.3":{"draws":22,"losses":33,"wins":33},"z-ai/glm-5.3-flash":{"draws":29,"losses":34,"wins":75},"z-ai/glm-5.3-flashx":{"draws":19,"losses":36,"wins":83}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":30,"wins":74},"claude-fable-5":{"draws":22,"losses":76,"wins":46},"claude-fable-5-1":{"draws":9,"losses":141,"wins":12},"claude-haiku-5-5":{"draws":27,"losses":55,"wins":56},"claude-opus-4-5":{"draws":50,"losses":56,"wins":128},"claude-opus-4-8":{"draws":19,"losses":50,"wins":63},"claude-opus-5":{"draws":35,"losses":165,"wins":46},"claude-opus-5-5":{"draws":11,"losses":134,"wins":11},"claude-sonnet-5":{"draws":23,"losses":40,"wins":81},"claude-sonnet-5-5":{"draws":19,"losses":70,"wins":55},"cohere/north-mini-code":{"draws":6,"losses":12,"wins":36},"deepseek/deepseek-v4-flash":{"draws":48,"losses":48,"wins":120},"deepseek/deepseek-v4-pro":{"draws":20,"losses":39,"wins":73},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":36,"wins":78},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":58,"wins":61},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":74,"wins":45},"elorian/glimpse":{"draws":12,"losses":31,"wins":35},"fireworks/ember-1":{"draws":23,"losses":47,"wins":74},"gemini-3.1-pro-preview":{"draws":30,"losses":41,"wins":73},"gemini-4-argon":{"draws":15,"losses":110,"wins":19},"google/gemini-3.1-flash-lite":{"draws":17,"losses":14,"wins":65},"google/gemini-3.5-flash":{"draws":21,"losses":57,"wins":102},"google/gemini-3.5-flash-lite":{"draws":45,"losses":48,"wins":159},"google/gemini-3.6-flash":{"draws":41,"losses":92,"wins":143},"google/gemini-3.8-flash":{"draws":18,"losses":72,"wins":54},"google/gemma-4-31b-it":{"draws":25,"losses":14,"wins":45},"gpt-4.1":{"draws":5,"losses":15,"wins":28},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":9},"gpt-5":{"draws":18,"losses":35,"wins":73},"gpt-5.4":{"draws":16,"losses":63,"wins":59},"gpt-5.4-mini":{"draws":21,"losses":21,"wins":54},"gpt-5.4-nano":{"draws":20,"losses":39,"wins":85},"gpt-5.5":{"draws":24,"losses":50,"wins":58},"gpt-5.6-luna":{"draws":33,"losses":30,"wins":81},"gpt-5.6-sol":{"draws":24,"losses":73,"wins":47},"gpt-5.6-terra":{"draws":30,"losses":42,"wins":66},"gpt-6-astra":{"draws":12,"losses":124,"wins":8},"gpt-6-luna":{"draws":39,"losses":34,"wins":71},"gpt-6-sol":{"draws":19,"losses":90,"wins":35},"gpt-6.1-sol":{"draws":12,"losses":116,"wins":16},"gpt-6.1-terra":{"draws":24,"losses":105,"wins":15},"gpt-6.1-terra-pro":{"draws":18,"losses":108,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":23,"losses":12,"wins":67},"inception/mercury-3":{"draws":23,"losses":36,"wins":39},"inclusionai/ling-3.0-flash":{"draws":29,"losses":15,"wins":58},"inclusionai/ling-3.1-flash":{"draws":8,"losses":4,"wins":14},"meituan/longcat-2.0":{"draws":24,"losses":34,"wins":98},"meta/muse-glimmer-30b":{"draws":25,"losses":18,"wins":83},"meta/muse-spark-1.2":{"draws":21,"losses":57,"wins":60},"meta/muse-spark-1.3":{"draws":27,"losses":50,"wins":67},"meta/muse-spark-open":{"draws":25,"losses":60,"wins":59},"meta/muse-wonder":{"draws":31,"losses":71,"wins":42},"minimax/minimax-m3":{"draws":15,"losses":15,"wins":48},"minimax/minimax-m3.1-flash":{"draws":16,"losses":43,"wins":67},"mistralai/mistral-large-4-0":{"draws":26,"losses":22,"wins":42},"mistralai/mistral-medium-3-5":{"draws":21,"losses":10,"wins":53},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":0},"moonshotai/kimi-k3":{"draws":27,"losses":43,"wins":68},"moonshotai/kimi-k3.1-pro":{"draws":16,"losses":104,"wins":24},"nex-agi/nex-n2-pro":{"draws":12,"losses":10,"wins":50},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":5,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":29,"wins":60},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":21,"wins":35},"o3":{"draws":20,"losses":77,"wins":101},"openai/gpt-oss-120b":{"draws":23,"losses":22,"wins":81},"poolside/laguna-s-2.1":{"draws":27,"losses":34,"wins":77},"qwen/qwen3.7-max":{"draws":21,"losses":20,"wins":43},"qwen/qwen3.7-plus":{"draws":15,"losses":15,"wins":42},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":48,"wins":68},"qwen/qwen3.8-27b":{"draws":19,"losses":32,"wins":51},"qwen/qwen3.8-flash":{"draws":18,"losses":35,"wins":43},"qwen/qwen3.8-max":{"draws":27,"losses":59,"wins":58},"qwen/qwen3.8-max-0902":{"draws":38,"losses":53,"wins":53},"recursive/flint-v1.0":{"draws":9,"losses":9,"wins":24},"reflection/beam-1.0-501b-a23b":{"draws":23,"losses":39,"wins":70},"stealth/ox-alpha":{"draws":71,"losses":187,"wins":216},"stealth/space-bunny-alpha":{"draws":26,"losses":20,"wins":68},"stepfun/step-3.7-flash":{"draws":15,"losses":20,"wins":67},"stepfun/step-5-preview":{"draws":5,"losses":16,"wins":15},"tencent/hy3-preview":{"draws":22,"losses":14,"wins":42},"tencent/hy4-preview":{"draws":19,"losses":54,"wins":65},"thinkingmachines/inkling":{"draws":38,"losses":30,"wins":124},"thinkingmachines/inkling-small":{"draws":30,"losses":22,"wins":92},"unbiased/pareto-26.10":{"draws":3,"losses":39,"wins":6},"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":18,"losses":62,"wins":64},"x-ai/grok-4.6":{"draws":33,"losses":59,"wins":52},"x-ai/grok-4.7":{"draws":16,"losses":76,"wins":34},"x-ai/grok-build-0.1":{"draws":9,"losses":8,"wins":31},"xiaomi/mimo-v2.5":{"draws":48,"losses":38,"wins":136},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":13,"wins":54},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":34,"wins":44},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":50,"wins":30},"z-ai/glm-5.2":{"draws":59,"losses":67,"wins":162},"z-ai/glm-5.3":{"draws":29,"losses":75,"wins":34},"z-ai/glm-5.3-flash":{"draws":12,"losses":42,"wins":42},"z-ai/glm-5.3-flashx":{"draws":26,"losses":58,"wins":60}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":26,"wins":86},"claude-fable-5":{"draws":22,"losses":79,"wins":43},"claude-fable-5-1":{"draws":10,"losses":138,"wins":14},"claude-haiku-5-5":{"draws":29,"losses":57,"wins":52},"claude-opus-4-5":{"draws":51,"losses":55,"wins":128},"claude-opus-4-8":{"draws":21,"losses":58,"wins":53},"claude-opus-5":{"draws":40,"losses":165,"wins":41},"claude-opus-5-5":{"draws":15,"losses":132,"wins":9},"claude-sonnet-5":{"draws":31,"losses":35,"wins":78},"claude-sonnet-5-5":{"draws":24,"losses":66,"wins":54},"cohere/north-mini-code":{"draws":9,"losses":5,"wins":40},"deepseek/deepseek-v4-flash":{"draws":42,"losses":43,"wins":131},"deepseek/deepseek-v4-pro":{"draws":31,"losses":41,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":41,"wins":69},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":52,"wins":68},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":72,"wins":48},"elorian/glimpse":{"draws":17,"losses":29,"wins":32},"fireworks/ember-1":{"draws":28,"losses":49,"wins":67},"gemini-3.1-pro-preview":{"draws":28,"losses":41,"wins":75},"gemini-4-argon":{"draws":12,"losses":110,"wins":22},"google/gemini-3.1-flash-lite":{"draws":21,"losses":9,"wins":66},"google/gemini-3.5-flash":{"draws":33,"losses":52,"wins":95},"google/gemini-3.5-flash-lite":{"draws":58,"losses":47,"wins":147},"google/gemini-3.6-flash":{"draws":62,"losses":101,"wins":113},"google/gemini-3.8-flash":{"draws":27,"losses":66,"wins":51},"google/gemma-4-31b-it":{"draws":28,"losses":11,"wins":45},"gpt-4.1":{"draws":8,"losses":10,"wins":30},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":13},"gpt-5":{"draws":27,"losses":35,"wins":64},"gpt-5.4":{"draws":28,"losses":55,"wins":55},"gpt-5.4-mini":{"draws":24,"losses":13,"wins":59},"gpt-5.4-nano":{"draws":28,"losses":36,"wins":80},"gpt-5.5":{"draws":34,"losses":47,"wins":51},"gpt-5.6-luna":{"draws":31,"losses":36,"wins":77},"gpt-5.6-sol":{"draws":24,"losses":79,"wins":41},"gpt-5.6-terra":{"draws":32,"losses":42,"wins":64},"gpt-6-astra":{"draws":15,"losses":121,"wins":8},"gpt-6-luna":{"draws":27,"losses":46,"wins":71},"gpt-6-sol":{"draws":16,"losses":86,"wins":42},"gpt-6.1-sol":{"draws":15,"losses":111,"wins":18},"gpt-6.1-terra":{"draws":18,"losses":109,"wins":17},"gpt-6.1-terra-pro":{"draws":14,"losses":116,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":21,"losses":9,"wins":72},"inception/mercury-3":{"draws":21,"losses":33,"wins":42},"inclusionai/ling-3.0-flash":{"draws":33,"losses":8,"wins":61},"inclusionai/ling-3.1-flash":{"draws":6,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":23,"losses":19,"wins":114},"meta/muse-glimmer-30b":{"draws":28,"losses":20,"wins":78},"meta/muse-spark-1.2":{"draws":28,"losses":52,"wins":58},"meta/muse-spark-1.3":{"draws":22,"losses":62,"wins":60},"meta/muse-spark-open":{"draws":30,"losses":55,"wins":57},"meta/muse-wonder":{"draws":32,"losses":74,"wins":38},"minimax/minimax-m3":{"draws":15,"losses":12,"wins":51},"minimax/minimax-m3.1-flash":{"draws":22,"losses":29,"wins":75},"mistralai/mistral-large-4-0":{"draws":29,"losses":27,"wins":34},"mistralai/mistral-medium-3-5":{"draws":15,"losses":9,"wins":60},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":4},"moonshotai/kimi-k3":{"draws":33,"losses":39,"wins":66},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":110,"wins":22},"nex-agi/nex-n2-pro":{"draws":10,"losses":10,"wins":52},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":8,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":15,"wins":73},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":14,"wins":39},"o3":{"draws":16,"losses":59,"wins":123},"openai/gpt-oss-120b":{"draws":25,"losses":16,"wins":85},"poolside/laguna-s-2.1":{"draws":36,"losses":26,"wins":76},"qwen/qwen3.7-max":{"draws":18,"losses":19,"wins":47},"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":22,"losses":26,"wins":54},"qwen/qwen3.8-flash":{"draws":26,"losses":25,"wins":45},"qwen/qwen3.8-max":{"draws":35,"losses":52,"wins":57},"qwen/qwen3.8-max-0902":{"draws":30,"losses":53,"wins":61},"recursive/flint-v1.0":{"draws":10,"losses":3,"wins":29},"reflection/beam-1.0-501b-a23b":{"draws":23,"losses":41,"wins":68},"stealth/ox-alpha":{"draws":79,"losses":168,"wins":227},"stealth/space-bunny-alpha":{"draws":24,"losses":24,"wins":66},"stepfun/step-3.7-flash":{"draws":13,"losses":14,"wins":75},"stepfun/step-5-preview":{"draws":3,"losses":15,"wins":16},"tencent/hy3-preview":{"draws":16,"losses":13,"wins":49},"tencent/hy4-preview":{"draws":32,"losses":55,"wins":51},"thinkingmachines/inkling":{"draws":41,"losses":26,"wins":125},"thinkingmachines/inkling-small":{"draws":26,"losses":23,"wins":95},"unbiased/pareto-26.10":{"draws":4,"losses":39,"wins":5},"unbiased/pareto-26.10-preview":{"draws":1,"losses":42,"wins":5},"upstage/solar-mini4":{"draws":5,"losses":4,"wins":27},"x-ai/grok-4.5":{"draws":24,"losses":59,"wins":61},"x-ai/grok-4.6":{"draws":26,"losses":63,"wins":55},"x-ai/grok-4.7":{"draws":17,"losses":82,"wins":27},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":30},"xiaomi/mimo-v2.5":{"draws":56,"losses":21,"wins":145},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":10,"wins":47},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":36,"wins":45},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":44,"wins":35},"z-ai/glm-5.2":{"draws":71,"losses":69,"wins":148},"z-ai/glm-5.3":{"draws":19,"losses":83,"wins":36},"z-ai/glm-5.3-flash":{"draws":26,"losses":60,"wins":58},"z-ai/glm-5.3-flashx":{"draws":20,"losses":38,"wins":38}}},"versus_totals_tracks":{"highest":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":9,"wins":9},"claude-fable-5":{"draws":8,"losses":35,"wins":5},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":27,"wins":5},"claude-opus-4-5":{"draws":29,"losses":31,"wins":18},"claude-opus-4-8":{"draws":14,"losses":24,"wins":6},"claude-opus-5":{"draws":10,"losses":63,"wins":9},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":15,"losses":23,"wins":10},"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":22,"losses":19,"wins":31},"deepseek/deepseek-v4-pro":{"draws":8,"losses":21,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":16,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":23,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":31,"wins":7},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":16,"losses":24,"wins":8},"gemini-3.1-pro-preview":{"draws":16,"losses":18,"wins":14},"gemini-4-argon":{"draws":2,"losses":43,"wins":3},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":19},"google/gemini-3.5-flash":{"draws":14,"losses":29,"wins":17},"google/gemini-3.5-flash-lite":{"draws":35,"losses":18,"wins":31},"google/gemini-3.6-flash":{"draws":22,"losses":45,"wins":25},"google/gemini-3.8-flash":{"draws":10,"losses":29,"wins":9},"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":15,"losses":15,"wins":12},"gpt-5.4":{"draws":10,"losses":26,"wins":10},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":12,"losses":17,"wins":19},"gpt-5.5":{"draws":18,"losses":14,"wins":12},"gpt-5.6-luna":{"draws":22,"losses":13,"wins":13},"gpt-5.6-sol":{"draws":10,"losses":32,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":21,"wins":12},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":15,"losses":17,"wins":16},"gpt-6-sol":{"draws":7,"losses":37,"wins":4},"gpt-6.1-sol":{"draws":5,"losses":40,"wins":3},"gpt-6.1-terra":{"draws":6,"losses":38,"wins":4},"gpt-6.1-terra-pro":{"draws":7,"losses":38,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":6,"wins":13},"inception/mercury-3":{"draws":15,"losses":7,"wins":10},"inclusionai/ling-3.0-flash":{"draws":15,"losses":3,"wins":16},"inclusionai/ling-3.1-flash":{"draws":7,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":11,"wins":28},"meta/muse-glimmer-30b":{"draws":15,"losses":9,"wins":18},"meta/muse-spark-1.2":{"draws":14,"losses":21,"wins":11},"meta/muse-spark-1.3":{"draws":16,"losses":25,"wins":7},"meta/muse-spark-open":{"draws":12,"losses":25,"wins":11},"meta/muse-wonder":{"draws":12,"losses":29,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":17},"minimax/minimax-m3.1-flash":{"draws":10,"losses":16,"wins":16},"mistralai/mistral-large-4-0":{"draws":12,"losses":9,"wins":9},"mistralai/mistral-medium-3-5":{"draws":12,"losses":4,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":22,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":35,"wins":5},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":11,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":5,"wins":7},"o3":{"draws":14,"losses":29,"wins":23},"openai/gpt-oss-120b":{"draws":17,"losses":7,"wins":18},"poolside/laguna-s-2.1":{"draws":17,"losses":8,"wins":21},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":7,"losses":5,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":16,"wins":17},"qwen/qwen3.8-27b":{"draws":8,"losses":19,"wins":7},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":14,"losses":16,"wins":18},"qwen/qwen3.8-max-0902":{"draws":15,"losses":23,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":19,"wins":11},"stealth/ox-alpha":{"draws":36,"losses":87,"wins":35},"stealth/space-bunny-alpha":{"draws":18,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":7,"losses":10,"wins":17},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":8,"wins":8},"tencent/hy4-preview":{"draws":15,"losses":23,"wins":8},"thinkingmachines/inkling":{"draws":25,"losses":11,"wins":28},"thinkingmachines/inkling-small":{"draws":18,"losses":8,"wins":22},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":28,"wins":6},"x-ai/grok-4.6":{"draws":9,"losses":34,"wins":5},"x-ai/grok-4.7":{"draws":2,"losses":33,"wins":7},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":26,"losses":14,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":20,"wins":8},"z-ai/glm-5.2":{"draws":35,"losses":30,"wins":31},"z-ai/glm-5.3":{"draws":9,"losses":34,"wins":3},"z-ai/glm-5.3-flash":{"draws":11,"losses":25,"wins":12},"z-ai/glm-5.3-flashx":{"draws":10,"losses":29,"wins":9}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":6,"wins":36},"claude-fable-5":{"draws":2,"losses":12,"wins":18},"claude-fable-5-1":{"draws":5,"losses":40,"wins":9},"claude-haiku-5-5":{"draws":8,"losses":12,"wins":26},"claude-opus-4-5":{"draws":1,"losses":12,"wins":65},"claude-opus-4-8":{"draws":1,"losses":12,"wins":31},"claude-opus-5":{"draws":10,"losses":40,"wins":32},"claude-opus-5-5":{"draws":6,"losses":38,"wins":8},"claude-sonnet-5":{"draws":3,"losses":5,"wins":40},"claude-sonnet-5-5":{"draws":1,"losses":20,"wins":27},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":4,"losses":4,"wins":64},"deepseek/deepseek-v4-pro":{"draws":2,"losses":9,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":7,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":7,"wins":35},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":15,"wins":27},"elorian/glimpse":{"draws":0,"losses":6,"wins":20},"fireworks/ember-1":{"draws":6,"losses":5,"wins":37},"gemini-3.1-pro-preview":{"draws":6,"losses":7,"wins":35},"gemini-4-argon":{"draws":7,"losses":28,"wins":13},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":30},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":54},"google/gemini-3.5-flash-lite":{"draws":2,"losses":4,"wins":78},"google/gemini-3.6-flash":{"draws":5,"losses":18,"wins":69},"google/gemini-3.8-flash":{"draws":4,"losses":19,"wins":25},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":24},"gpt-4.1":{"draws":2,"losses":5,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":9,"wins":32},"gpt-5.4":{"draws":7,"losses":16,"wins":23},"gpt-5.4-mini":{"draws":3,"losses":4,"wins":25},"gpt-5.4-nano":{"draws":1,"losses":6,"wins":41},"gpt-5.5":{"draws":3,"losses":18,"wins":23},"gpt-5.6-luna":{"draws":2,"losses":5,"wins":41},"gpt-5.6-sol":{"draws":6,"losses":16,"wins":26},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":35},"gpt-6-astra":{"draws":5,"losses":37,"wins":6},"gpt-6-luna":{"draws":5,"losses":10,"wins":33},"gpt-6-sol":{"draws":4,"losses":27,"wins":17},"gpt-6.1-sol":{"draws":1,"losses":33,"wins":14},"gpt-6.1-terra":{"draws":8,"losses":26,"wins":14},"gpt-6.1-terra-pro":{"draws":3,"losses":32,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":1,"wins":31},"inception/mercury-3":{"draws":3,"losses":3,"wins":26},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":1,"losses":5,"wins":46},"meta/muse-glimmer-30b":{"draws":3,"losses":1,"wins":38},"meta/muse-spark-1.2":{"draws":1,"losses":8,"wins":37},"meta/muse-spark-1.3":{"draws":2,"losses":8,"wins":38},"meta/muse-spark-open":{"draws":2,"losses":11,"wins":35},"meta/muse-wonder":{"draws":6,"losses":15,"wins":27},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":20},"minimax/minimax-m3.1-flash":{"draws":3,"losses":4,"wins":35},"mistralai/mistral-large-4-0":{"draws":6,"losses":3,"wins":21},"mistralai/mistral-medium-3-5":{"draws":1,"losses":2,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":8,"wins":35},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":29,"wins":16},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":5,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":1,"wins":21},"o3":{"draws":4,"losses":11,"wins":51},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":38},"poolside/laguna-s-2.1":{"draws":1,"losses":3,"wins":42},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":11,"wins":35},"qwen/qwen3.8-27b":{"draws":1,"losses":3,"wins":30},"qwen/qwen3.8-flash":{"draws":4,"losses":5,"wins":23},"qwen/qwen3.8-max":{"draws":4,"losses":9,"wins":35},"qwen/qwen3.8-max-0902":{"draws":4,"losses":10,"wins":34},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":8,"wins":33},"stealth/ox-alpha":{"draws":11,"losses":23,"wins":124},"stealth/space-bunny-alpha":{"draws":5,"losses":2,"wins":31},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":19},"tencent/hy4-preview":{"draws":2,"losses":6,"wins":38},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":56},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":44},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":3},"unbiased/pareto-26.10-preview":{"draws":3,"losses":8,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":3,"losses":10,"wins":35},"x-ai/grok-4.6":{"draws":8,"losses":13,"wins":27},"x-ai/grok-4.7":{"draws":4,"losses":24,"wins":14},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":14},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":67},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":20},"z-ai/glm-5.2":{"draws":8,"losses":10,"wins":78},"z-ai/glm-5.3":{"draws":6,"losses":13,"wins":27},"z-ai/glm-5.3-flash":{"draws":7,"losses":7,"wins":34},"z-ai/glm-5.3-flashx":{"draws":3,"losses":11,"wins":34}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":3,"wins":56},"claude-fable-5":{"draws":0,"losses":3,"wins":63},"claude-fable-5-1":{"draws":3,"losses":11,"wins":42},"claude-haiku-5-5":{"draws":4,"losses":1,"wins":57},"claude-opus-4-5":{"draws":0,"losses":3,"wins":103},"claude-opus-4-8":{"draws":2,"losses":3,"wins":53},"claude-opus-5":{"draws":7,"losses":15,"wins":92},"claude-opus-5-5":{"draws":7,"losses":27,"wins":36},"claude-sonnet-5":{"draws":0,"losses":1,"wins":65},"claude-sonnet-5-5":{"draws":1,"losses":12,"wins":53},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":25},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":95},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":1,"wins":61},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":4,"wins":61},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":5,"wins":60},"elorian/glimpse":{"draws":1,"losses":2,"wins":35},"fireworks/ember-1":{"draws":1,"losses":1,"wins":64},"gemini-3.1-pro-preview":{"draws":2,"losses":1,"wins":63},"gemini-4-argon":{"draws":3,"losses":13,"wins":50},"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":1,"losses":3,"wins":112},"google/gemini-3.6-flash":{"draws":1,"losses":5,"wins":122},"google/gemini-3.8-flash":{"draws":5,"losses":1,"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":0,"losses":3,"wins":61},"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":3,"losses":4,"wins":59},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":64},"gpt-6-astra":{"draws":6,"losses":20,"wins":40},"gpt-6-luna":{"draws":1,"losses":2,"wins":63},"gpt-6-sol":{"draws":0,"losses":12,"wins":54},"gpt-6.1-sol":{"draws":5,"losses":23,"wins":38},"gpt-6.1-terra":{"draws":5,"losses":13,"wins":48},"gpt-6.1-terra-pro":{"draws":8,"losses":19,"wins":39},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":45},"inception/mercury-3":{"draws":0,"losses":0,"wins":42},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":45},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":8},"meituan/longcat-2.0":{"draws":0,"losses":4,"wins":68},"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":1,"losses":3,"wins":62},"meta/muse-spark-open":{"draws":0,"losses":3,"wins":63},"meta/muse-wonder":{"draws":2,"losses":7,"wins":57},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":33},"minimax/minimax-m3.1-flash":{"draws":0,"losses":1,"wins":59},"mistralai/mistral-large-4-0":{"draws":1,"losses":4,"wins":37},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":61},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":8,"wins":54},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":34},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":42},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":32},"o3":{"draws":0,"losses":1,"wins":85},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":56},"poolside/laguna-s-2.1":{"draws":1,"losses":2,"wins":57},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":35},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":29},"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":2,"losses":3,"wins":61},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":18},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":1,"wins":61},"stealth/ox-alpha":{"draws":5,"losses":6,"wins":223},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":54},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":46},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":16},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":33},"tencent/hy4-preview":{"draws":2,"losses":1,"wins":61},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":89},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":65},"unbiased/pareto-26.10":{"draws":5,"losses":7,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":14},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":16},"x-ai/grok-4.5":{"draws":1,"losses":2,"wins":63},"x-ai/grok-4.6":{"draws":3,"losses":6,"wins":57},"x-ai/grok-4.7":{"draws":3,"losses":3,"wins":50},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":94},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":32},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":38},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":4,"wins":36},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":132},"z-ai/glm-5.3":{"draws":5,"losses":3,"wins":56},"z-ai/glm-5.3-flash":{"draws":2,"losses":2,"wins":62},"z-ai/glm-5.3-flashx":{"draws":1,"losses":4,"wins":61}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":3,"wins":33},"claude-fable-5":{"draws":7,"losses":13,"wins":22},"claude-fable-5-1":{"draws":4,"losses":36,"wins":6},"claude-haiku-5-5":{"draws":5,"losses":5,"wins":18},"claude-opus-4-5":{"draws":12,"losses":6,"wins":52},"claude-opus-4-8":{"draws":6,"losses":10,"wins":26},"claude-opus-5":{"draws":13,"losses":36,"wins":21},"claude-opus-5-5":{"draws":6,"losses":33,"wins":7},"claude-sonnet-5":{"draws":5,"losses":4,"wins":33},"claude-sonnet-5-5":{"draws":4,"losses":14,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":10,"losses":3,"wins":51},"deepseek/deepseek-v4-pro":{"draws":5,"losses":5,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":4,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":9,"wins":26},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":10,"wins":23},"elorian/glimpse":{"draws":2,"losses":6,"wins":14},"fireworks/ember-1":{"draws":6,"losses":8,"wins":28},"gemini-3.1-pro-preview":{"draws":6,"losses":9,"wins":27},"gemini-4-argon":{"draws":8,"losses":16,"wins":18},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":4,"losses":9,"wins":41},"google/gemini-3.5-flash-lite":{"draws":5,"losses":5,"wins":64},"google/gemini-3.6-flash":{"draws":8,"losses":18,"wins":54},"google/gemini-3.8-flash":{"draws":8,"losses":8,"wins":26},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":24},"gpt-4.1":{"draws":0,"losses":1,"wins":13},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":3,"losses":3,"wins":30},"gpt-5.4":{"draws":2,"losses":10,"wins":28},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":22},"gpt-5.4-nano":{"draws":4,"losses":4,"wins":38},"gpt-5.5":{"draws":5,"losses":10,"wins":23},"gpt-5.6-luna":{"draws":5,"losses":2,"wins":35},"gpt-5.6-sol":{"draws":5,"losses":15,"wins":22},"gpt-5.6-terra":{"draws":4,"losses":10,"wins":26},"gpt-6-astra":{"draws":2,"losses":35,"wins":5},"gpt-6-luna":{"draws":5,"losses":6,"wins":31},"gpt-6-sol":{"draws":10,"losses":16,"wins":16},"gpt-6.1-sol":{"draws":3,"losses":31,"wins":8},"gpt-6.1-terra":{"draws":2,"losses":28,"wins":12},"gpt-6.1-terra-pro":{"draws":3,"losses":31,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":29},"inception/mercury-3":{"draws":5,"losses":4,"wins":19},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":26},"inclusionai/ling-3.1-flash":{"draws":1,"losses":3,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":4,"wins":40},"meta/muse-glimmer-30b":{"draws":3,"losses":2,"wins":31},"meta/muse-spark-1.2":{"draws":6,"losses":5,"wins":29},"meta/muse-spark-1.3":{"draws":5,"losses":4,"wins":33},"meta/muse-spark-open":{"draws":4,"losses":8,"wins":30},"meta/muse-wonder":{"draws":9,"losses":16,"wins":17},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":21},"minimax/minimax-m3.1-flash":{"draws":2,"losses":2,"wins":32},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":15},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":5},"moonshotai/kimi-k3":{"draws":2,"losses":8,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":22,"wins":12},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":4,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":3,"wins":16},"o3":{"draws":2,"losses":11,"wins":49},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":32},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":30},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":17},"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":7,"wins":20},"qwen/qwen3.8-flash":{"draws":3,"losses":3,"wins":22},"qwen/qwen3.8-max":{"draws":3,"losses":8,"wins":31},"qwen/qwen3.8-max-0902":{"draws":6,"losses":9,"wins":27},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":4,"wins":31},"stealth/ox-alpha":{"draws":15,"losses":21,"wins":82},"stealth/space-bunny-alpha":{"draws":3,"losses":5,"wins":26},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":27},"stepfun/step-5-preview":{"draws":1,"losses":4,"wins":7},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":4,"losses":9,"wins":27},"thinkingmachines/inkling":{"draws":8,"losses":2,"wins":44},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":40},"unbiased/pareto-26.10":{"draws":3,"losses":8,"wins":3},"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":24,"wins":10},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":7,"losses":6,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":7,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":7,"wins":16},"z-ai/glm-5.2":{"draws":5,"losses":10,"wins":69},"z-ai/glm-5.3":{"draws":4,"losses":16,"wins":20},"z-ai/glm-5.3-flash":{"draws":3,"losses":9,"wins":30},"z-ai/glm-5.3-flashx":{"draws":5,"losses":10,"wins":27}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":8,"wins":28},"claude-fable-5":{"draws":7,"losses":32,"wins":9},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":14,"losses":16,"wins":16},"claude-opus-4-5":{"draws":20,"losses":19,"wins":23},"claude-opus-4-8":{"draws":11,"losses":17,"wins":16},"claude-opus-5":{"draws":9,"losses":65,"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":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":15,"losses":12,"wins":45},"deepseek/deepseek-v4-pro":{"draws":10,"losses":14,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":18,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":19,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":28,"wins":12},"elorian/glimpse":{"draws":6,"losses":11,"wins":9},"fireworks/ember-1":{"draws":14,"losses":16,"wins":18},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":27},"gemini-4-argon":{"draws":2,"losses":42,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":8,"losses":25,"wins":27},"google/gemini-3.5-flash-lite":{"draws":21,"losses":18,"wins":45},"google/gemini-3.6-flash":{"draws":18,"losses":44,"wins":30},"google/gemini-3.8-flash":{"draws":11,"losses":29,"wins":8},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":13,"wins":20},"gpt-5.4":{"draws":11,"losses":23,"wins":12},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":11,"losses":12,"wins":25},"gpt-5.5":{"draws":14,"losses":20,"wins":10},"gpt-5.6-luna":{"draws":14,"losses":10,"wins":24},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":12},"gpt-5.6-terra":{"draws":14,"losses":12,"wins":20},"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},"gpt-6.1-terra":{"draws":5,"losses":40,"wins":3},"gpt-6.1-terra-pro":{"draws":6,"losses":38,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":2,"wins":18},"inception/mercury-3":{"draws":9,"losses":12,"wins":11},"inclusionai/ling-3.0-flash":{"draws":12,"losses":5,"wins":17},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":7,"losses":11,"wins":34},"meta/muse-glimmer-30b":{"draws":12,"losses":3,"wins":27},"meta/muse-spark-1.2":{"draws":10,"losses":25,"wins":11},"meta/muse-spark-1.3":{"draws":10,"losses":26,"wins":12},"meta/muse-spark-open":{"draws":10,"losses":23,"wins":15},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":16},"minimax/minimax-m3.1-flash":{"draws":8,"losses":12,"wins":22},"mistralai/mistral-large-4-0":{"draws":11,"losses":11,"wins":8},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":13,"losses":18,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":41,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":7,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":7,"wins":7},"o3":{"draws":5,"losses":20,"wins":41},"openai/gpt-oss-120b":{"draws":9,"losses":5,"wins":28},"poolside/laguna-s-2.1":{"draws":9,"losses":7,"wins":30},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":15},"qwen/qwen3.7-plus":{"draws":6,"losses":4,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":15},"qwen/qwen3.8-flash":{"draws":6,"losses":14,"wins":12},"qwen/qwen3.8-max":{"draws":12,"losses":23,"wins":13},"qwen/qwen3.8-max-0902":{"draws":14,"losses":20,"wins":14},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":15,"wins":16},"stealth/ox-alpha":{"draws":32,"losses":63,"wins":63},"stealth/space-bunny-alpha":{"draws":8,"losses":8,"wins":22},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":11,"losses":20,"wins":15},"thinkingmachines/inkling":{"draws":17,"losses":9,"wins":38},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":26},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":14,"losses":21,"wins":13},"x-ai/grok-4.6":{"draws":12,"losses":27,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":23,"losses":11,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":16},"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":23,"losses":24,"wins":49},"z-ai/glm-5.3":{"draws":8,"losses":27,"wins":11},"z-ai/glm-5.3-flash":{"draws":7,"losses":27,"wins":14},"z-ai/glm-5.3-flashx":{"draws":16,"losses":20,"wins":12}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":5,"wins":29},"claude-fable-5":{"draws":4,"losses":15,"wins":23},"claude-fable-5-1":{"draws":5,"losses":31,"wins":10},"claude-haiku-5-5":{"draws":6,"losses":10,"wins":26},"claude-opus-4-5":{"draws":14,"losses":9,"wins":47},"claude-opus-4-8":{"draws":4,"losses":3,"wins":21},"claude-opus-5":{"draws":12,"losses":40,"wins":18},"claude-opus-5-5":{"draws":6,"losses":29,"wins":11},"claude-sonnet-5":{"draws":8,"losses":4,"wins":30},"claude-sonnet-5-5":{"draws":9,"losses":12,"wins":21},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":6,"losses":3,"wins":55},"deepseek/deepseek-v4-pro":{"draws":3,"losses":7,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":6,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":13,"wins":26},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":13,"wins":25},"elorian/glimpse":{"draws":3,"losses":8,"wins":11},"fireworks/ember-1":{"draws":9,"losses":7,"wins":26},"gemini-3.1-pro-preview":{"draws":6,"losses":7,"wins":29},"gemini-4-argon":{"draws":4,"losses":22,"wins":16},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":37},"google/gemini-3.5-flash-lite":{"draws":8,"losses":4,"wins":62},"google/gemini-3.6-flash":{"draws":14,"losses":20,"wins":46},"google/gemini-3.8-flash":{"draws":7,"losses":12,"wins":23},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":20},"gpt-4.1":{"draws":2,"losses":0,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":2,"losses":5,"wins":29},"gpt-5.4":{"draws":5,"losses":14,"wins":21},"gpt-5.4-mini":{"draws":2,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":6,"losses":3,"wins":37},"gpt-5.5":{"draws":6,"losses":14,"wins":18},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":32},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":22},"gpt-5.6-terra":{"draws":3,"losses":6,"wins":31},"gpt-6-astra":{"draws":5,"losses":32,"wins":5},"gpt-6-luna":{"draws":5,"losses":6,"wins":31},"gpt-6-sol":{"draws":5,"losses":19,"wins":18},"gpt-6.1-sol":{"draws":4,"losses":28,"wins":10},"gpt-6.1-terra":{"draws":3,"losses":24,"wins":15},"gpt-6.1-terra-pro":{"draws":6,"losses":26,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":1,"wins":25},"inception/mercury-3":{"draws":4,"losses":2,"wins":22},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":27},"inclusionai/ling-3.1-flash":{"draws":1,"losses":2,"wins":5},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":38},"meta/muse-glimmer-30b":{"draws":2,"losses":1,"wins":33},"meta/muse-spark-1.2":{"draws":4,"losses":8,"wins":28},"meta/muse-spark-1.3":{"draws":6,"losses":10,"wins":26},"meta/muse-spark-open":{"draws":6,"losses":5,"wins":31},"meta/muse-wonder":{"draws":7,"losses":14,"wins":21},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":19},"minimax/minimax-m3.1-flash":{"draws":7,"losses":4,"wins":25},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":16},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":10,"wins":22},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":27,"wins":12},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":17},"o3":{"draws":4,"losses":7,"wins":51},"openai/gpt-oss-120b":{"draws":5,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":32},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":17},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":11,"wins":20},"qwen/qwen3.8-27b":{"draws":4,"losses":5,"wins":21},"qwen/qwen3.8-flash":{"draws":4,"losses":5,"wins":19},"qwen/qwen3.8-max":{"draws":1,"losses":10,"wins":31},"qwen/qwen3.8-max-0902":{"draws":9,"losses":13,"wins":20},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":5,"wins":30},"stealth/ox-alpha":{"draws":19,"losses":23,"wins":76},"stealth/space-bunny-alpha":{"draws":5,"losses":5,"wins":24},"stepfun/step-3.7-flash":{"draws":1,"losses":5,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":19},"tencent/hy4-preview":{"draws":5,"losses":9,"wins":26},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":45},"thinkingmachines/inkling-small":{"draws":3,"losses":3,"wins":36},"unbiased/pareto-26.10":{"draws":4,"losses":7,"wins":3},"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":11,"losses":9,"wins":22},"x-ai/grok-4.6":{"draws":8,"losses":12,"wins":22},"x-ai/grok-4.7":{"draws":7,"losses":17,"wins":14},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":14,"losses":4,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":9,"wins":19},"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":3,"losses":14,"wins":25},"z-ai/glm-5.3-flashx":{"draws":7,"losses":6,"wins":29}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":8,"wins":60},"claude-fable-5":{"draws":5,"losses":21,"wins":52},"claude-fable-5-1":{"draws":8,"losses":42,"wins":38},"claude-haiku-5-5":{"draws":8,"losses":9,"wins":57},"claude-opus-4-5":{"draws":9,"losses":9,"wins":108},"claude-opus-4-8":{"draws":2,"losses":11,"wins":57},"claude-opus-5":{"draws":13,"losses":38,"wins":75},"claude-opus-5-5":{"draws":5,"losses":42,"wins":39},"claude-sonnet-5":{"draws":6,"losses":6,"wins":66},"claude-sonnet-5-5":{"draws":2,"losses":18,"wins":58},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":26},"deepseek/deepseek-v4-flash":{"draws":2,"losses":8,"wins":104},"deepseek/deepseek-v4-pro":{"draws":3,"losses":5,"wins":66},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":3,"wins":64},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":8,"wins":62},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":12,"wins":60},"elorian/glimpse":{"draws":3,"losses":8,"wins":33},"fireworks/ember-1":{"draws":2,"losses":12,"wins":64},"gemini-3.1-pro-preview":{"draws":2,"losses":6,"wins":70},"gemini-4-argon":{"draws":6,"losses":23,"wins":49},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":42},"google/gemini-3.5-flash":{"draws":7,"losses":4,"wins":85},"google/gemini-3.5-flash-lite":{"draws":2,"losses":6,"wins":126},"google/gemini-3.6-flash":{"draws":7,"losses":22,"wins":119},"google/gemini-3.8-flash":{"draws":4,"losses":11,"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":1,"losses":3,"wins":66},"gpt-5.4":{"draws":3,"losses":8,"wins":63},"gpt-5.4-mini":{"draws":1,"losses":3,"wins":48},"gpt-5.4-nano":{"draws":3,"losses":6,"wins":65},"gpt-5.5":{"draws":5,"losses":7,"wins":62},"gpt-5.6-luna":{"draws":3,"losses":4,"wins":71},"gpt-5.6-sol":{"draws":7,"losses":16,"wins":55},"gpt-5.6-terra":{"draws":4,"losses":5,"wins":65},"gpt-6-astra":{"draws":6,"losses":51,"wins":21},"gpt-6-luna":{"draws":8,"losses":6,"wins":64},"gpt-6-sol":{"draws":11,"losses":22,"wins":45},"gpt-6.1-sol":{"draws":13,"losses":34,"wins":31},"gpt-6.1-terra":{"draws":9,"losses":31,"wins":38},"gpt-6.1-terra-pro":{"draws":11,"losses":27,"wins":40},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":3,"losses":2,"wins":47},"inception/mercury-3":{"draws":3,"losses":2,"wins":47},"inclusionai/ling-3.0-flash":{"draws":2,"losses":4,"wins":46},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":10},"meituan/longcat-2.0":{"draws":1,"losses":6,"wins":73},"meta/muse-glimmer-30b":{"draws":3,"losses":2,"wins":69},"meta/muse-spark-1.2":{"draws":4,"losses":6,"wins":68},"meta/muse-spark-1.3":{"draws":1,"losses":11,"wins":66},"meta/muse-spark-open":{"draws":2,"losses":8,"wins":68},"meta/muse-wonder":{"draws":6,"losses":17,"wins":55},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":41},"minimax/minimax-m3.1-flash":{"draws":5,"losses":5,"wins":56},"mistralai/mistral-large-4-0":{"draws":4,"losses":6,"wins":42},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":40},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":7,"wins":65},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":25,"wins":43},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":36},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":56},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":5,"wins":30},"o3":{"draws":1,"losses":6,"wins":89},"openai/gpt-oss-120b":{"draws":2,"losses":4,"wins":64},"poolside/laguna-s-2.1":{"draws":3,"losses":4,"wins":73},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":38},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":9,"wins":66},"qwen/qwen3.8-27b":{"draws":3,"losses":3,"wins":46},"qwen/qwen3.8-flash":{"draws":3,"losses":2,"wins":47},"qwen/qwen3.8-max":{"draws":1,"losses":5,"wins":72},"qwen/qwen3.8-max-0902":{"draws":6,"losses":8,"wins":64},"recursive/flint-v1.0":{"draws":0,"losses":1,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":3,"wins":68},"stealth/ox-alpha":{"draws":21,"losses":24,"wins":221},"stealth/space-bunny-alpha":{"draws":4,"losses":2,"wins":56},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":45},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":18},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":39},"tencent/hy4-preview":{"draws":2,"losses":8,"wins":64},"thinkingmachines/inkling":{"draws":5,"losses":7,"wins":96},"thinkingmachines/inkling-small":{"draws":7,"losses":6,"wins":65},"unbiased/pareto-26.10":{"draws":3,"losses":13,"wins":10},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":14},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":13},"x-ai/grok-4.5":{"draws":10,"losses":13,"wins":55},"x-ai/grok-4.6":{"draws":5,"losses":11,"wins":62},"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":0,"losses":1,"wins":41},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":44},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":40},"z-ai/glm-5.2":{"draws":9,"losses":10,"wins":137},"z-ai/glm-5.3":{"draws":6,"losses":7,"wins":61},"z-ai/glm-5.3-flash":{"draws":8,"losses":7,"wins":63},"z-ai/glm-5.3-flashx":{"draws":8,"losses":6,"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":5,"losses":8,"wins":41},"claude-haiku-5-5":{"draws":2,"losses":0,"wins":44},"claude-opus-4-5":{"draws":0,"losses":1,"wins":77},"claude-opus-4-8":{"draws":2,"losses":2,"wins":40},"claude-opus-5":{"draws":4,"losses":9,"wins":69},"claude-opus-5-5":{"draws":2,"losses":9,"wins":25},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":3,"losses":3,"wins":42},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":4,"wins":44},"elorian/glimpse":{"draws":0,"losses":2,"wins":24},"fireworks/ember-1":{"draws":0,"losses":2,"wins":46},"gemini-3.1-pro-preview":{"draws":0,"losses":0,"wins":48},"gemini-4-argon":{"draws":1,"losses":5,"wins":42},"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":4,"wins":87},"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":0,"losses":2,"wins":46},"gpt-5.6-sol":{"draws":1,"losses":2,"wins":45},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":46},"gpt-6-astra":{"draws":5,"losses":13,"wins":30},"gpt-6-luna":{"draws":0,"losses":0,"wins":48},"gpt-6-sol":{"draws":3,"losses":1,"wins":44},"gpt-6.1-sol":{"draws":7,"losses":8,"wins":33},"gpt-6.1-terra":{"draws":1,"losses":5,"wins":42},"gpt-6.1-terra-pro":{"draws":2,"losses":4,"wins":42},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":34},"inception/mercury-3":{"draws":0,"losses":0,"wins":32},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":8},"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-spark-open":{"draws":0,"losses":3,"wins":45},"meta/muse-wonder":{"draws":1,"losses":3,"wins":44},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"minimax/minimax-m3.1-flash":{"draws":0,"losses":0,"wins":42},"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":0,"wins":4},"moonshotai/kimi-k3":{"draws":0,"losses":3,"wins":43},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":6,"wins":38},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":2,"wins":20},"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":0,"losses":0,"wins":24},"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":0,"losses":1,"wins":47},"qwen/qwen3.8-max-0902":{"draws":3,"losses":2,"wins":43},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":1,"wins":42},"stealth/ox-alpha":{"draws":1,"losses":0,"wins":157},"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":17},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":26},"tencent/hy4-preview":{"draws":0,"losses":2,"wins":44},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":62},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10":{"draws":2,"losses":4,"wins":10},"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":3,"losses":3,"wins":42},"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":16},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":3,"wins":29},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":94},"z-ai/glm-5.3":{"draws":2,"losses":2,"wins":42},"z-ai/glm-5.3-flash":{"draws":1,"losses":1,"wins":46},"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":25,"wins":15},"claude-fable-5-1":{"draws":1,"losses":51,"wins":2},"claude-haiku-5-5":{"draws":6,"losses":17,"wins":23},"claude-opus-4-5":{"draws":23,"losses":19,"wins":36},"claude-opus-4-8":{"draws":9,"losses":16,"wins":19},"claude-opus-5":{"draws":14,"losses":57,"wins":11},"claude-opus-5-5":{"draws":4,"losses":43,"wins":5},"claude-sonnet-5":{"draws":8,"losses":5,"wins":19},"claude-sonnet-5-5":{"draws":6,"losses":22,"wins":20},"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":13,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":15,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":19,"wins":19},"elorian/glimpse":{"draws":5,"losses":10,"wins":11},"fireworks/ember-1":{"draws":11,"losses":17,"wins":20},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":25},"gemini-4-argon":{"draws":6,"losses":36,"wins":6},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":23},"google/gemini-3.5-flash":{"draws":15,"losses":21,"wins":24},"google/gemini-3.5-flash-lite":{"draws":19,"losses":11,"wins":54},"google/gemini-3.6-flash":{"draws":14,"losses":32,"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":3,"losses":4,"wins":9},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":8,"wins":23},"gpt-5.4":{"draws":11,"losses":21,"wins":14},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":16},"gpt-5.4-nano":{"draws":9,"losses":11,"wins":28},"gpt-5.5":{"draws":11,"losses":17,"wins":16},"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":43,"wins":3},"gpt-6-luna":{"draws":10,"losses":18,"wins":20},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":6},"gpt-6.1-terra":{"draws":4,"losses":37,"wins":7},"gpt-6.1-terra-pro":{"draws":4,"losses":40,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":3,"wins":21},"inception/mercury-3":{"draws":10,"losses":7,"wins":15},"inclusionai/ling-3.0-flash":{"draws":10,"losses":2,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":3,"wins":3},"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":15,"losses":15,"wins":16},"meta/muse-spark-1.3":{"draws":9,"losses":23,"wins":16},"meta/muse-spark-open":{"draws":12,"losses":20,"wins":16},"meta/muse-wonder":{"draws":11,"losses":23,"wins":14},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"minimax/minimax-m3.1-flash":{"draws":11,"losses":13,"wins":18},"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":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":40,"wins":4},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":7,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":12},"o3":{"draws":6,"losses":23,"wins":37},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":29},"poolside/laguna-s-2.1":{"draws":8,"losses":3,"wins":35},"qwen/qwen3.7-max":{"draws":6,"losses":8,"wins":14},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":18,"wins":18},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":16},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":13},"qwen/qwen3.8-max":{"draws":11,"losses":14,"wins":23},"qwen/qwen3.8-max-0902":{"draws":11,"losses":20,"wins":17},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":10,"wins":21},"stealth/ox-alpha":{"draws":32,"losses":64,"wins":62},"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":2,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":5,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":17,"wins":21},"thinkingmachines/inkling":{"draws":19,"losses":7,"wins":38},"thinkingmachines/inkling-small":{"draws":11,"losses":7,"wins":30},"unbiased/pareto-26.10":{"draws":2,"losses":13,"wins":1},"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":15,"losses":20,"wins":13},"x-ai/grok-4.6":{"draws":11,"losses":22,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":20,"wins":17},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":19,"losses":8,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"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":4,"losses":2,"wins":42},"claude-fable-5-1":{"draws":4,"losses":17,"wins":33},"claude-haiku-5-5":{"draws":3,"losses":3,"wins":40},"claude-opus-4-5":{"draws":8,"losses":2,"wins":68},"claude-opus-4-8":{"draws":4,"losses":1,"wins":39},"claude-opus-5":{"draws":7,"losses":14,"wins":61},"claude-opus-5-5":{"draws":8,"losses":18,"wins":26},"claude-sonnet-5":{"draws":1,"losses":0,"wins":47},"claude-sonnet-5-5":{"draws":0,"losses":2,"wins":30},"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":1,"losses":0,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":2,"wins":41},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":2,"wins":40},"elorian/glimpse":{"draws":1,"losses":0,"wins":25},"fireworks/ember-1":{"draws":5,"losses":0,"wins":43},"gemini-3.1-pro-preview":{"draws":1,"losses":3,"wins":44},"gemini-4-argon":{"draws":7,"losses":7,"wins":34},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":53},"google/gemini-3.5-flash-lite":{"draws":3,"losses":2,"wins":79},"google/gemini-3.6-flash":{"draws":7,"losses":5,"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":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":0,"wins":40},"gpt-5.4":{"draws":8,"losses":0,"wins":38},"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":5,"losses":15,"wins":28},"gpt-6-luna":{"draws":8,"losses":1,"wins":39},"gpt-6-sol":{"draws":4,"losses":6,"wins":38},"gpt-6.1-sol":{"draws":1,"losses":15,"wins":32},"gpt-6.1-terra":{"draws":6,"losses":11,"wins":31},"gpt-6.1-terra-pro":{"draws":4,"losses":9,"wins":35},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inception/mercury-3":{"draws":4,"losses":0,"wins":28},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"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":4,"losses":0,"wins":42},"meta/muse-spark-1.3":{"draws":2,"losses":1,"wins":45},"meta/muse-spark-open":{"draws":4,"losses":1,"wins":43},"meta/muse-wonder":{"draws":6,"losses":1,"wins":41},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":23},"minimax/minimax-m3.1-flash":{"draws":2,"losses":0,"wins":40},"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":4},"moonshotai/kimi-k3":{"draws":4,"losses":1,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":5,"wins":35},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":1,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":19},"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":6,"losses":2,"wins":40},"recursive/flint-v1.0":{"draws":0,"losses":1,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":0,"wins":40},"stealth/ox-alpha":{"draws":10,"losses":3,"wins":145},"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":14},"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":{"draws":2,"losses":7,"wins":7},"unbiased/pareto-26.10-preview":{"draws":2,"losses":4,"wins":10},"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":2,"losses":0,"wins":16},"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":6,"losses":0,"wins":90},"z-ai/glm-5.3":{"draws":6,"losses":4,"wins":36},"z-ai/glm-5.3-flash":{"draws":4,"losses":4,"wins":40},"z-ai/glm-5.3-flashx":{"draws":5,"losses":3,"wins":40}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":9,"wins":14},"claude-fable-5":{"draws":8,"losses":28,"wins":6},"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":20,"losses":31,"wins":17},"claude-opus-4-8":{"draws":8,"losses":21,"wins":9},"claude-opus-5":{"draws":13,"losses":49,"wins":8},"claude-opus-5-5":{"draws":2,"losses":41,"wins":3},"claude-sonnet-5":{"draws":12,"losses":19,"wins":11},"claude-sonnet-5-5":{"draws":9,"losses":27,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":8},"deepseek/deepseek-v4-flash":{"draws":13,"losses":16,"wins":21},"deepseek/deepseek-v4-pro":{"draws":13,"losses":15,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":10,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":18,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":25,"wins":7},"elorian/glimpse":{"draws":6,"losses":10,"wins":8},"fireworks/ember-1":{"draws":13,"losses":19,"wins":10},"gemini-3.1-pro-preview":{"draws":13,"losses":12,"wins":17},"gemini-4-argon":{"draws":8,"losses":34,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":16},"google/gemini-3.5-flash":{"draws":15,"losses":20,"wins":17},"google/gemini-3.5-flash-lite":{"draws":21,"losses":24,"wins":27},"google/gemini-3.6-flash":{"draws":21,"losses":45,"wins":14},"google/gemini-3.8-flash":{"draws":10,"losses":27,"wins":5},"google/gemma-4-31b-it":{"draws":14,"losses":1,"wins":9},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":15,"wins":10},"gpt-5.4":{"draws":14,"losses":17,"wins":9},"gpt-5.4-mini":{"draws":12,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":12},"gpt-5.5":{"draws":14,"losses":18,"wins":6},"gpt-5.6-luna":{"draws":16,"losses":9,"wins":17},"gpt-5.6-sol":{"draws":7,"losses":28,"wins":7},"gpt-5.6-terra":{"draws":14,"losses":14,"wins":14},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":17,"losses":13,"wins":12},"gpt-6-sol":{"draws":9,"losses":28,"wins":5},"gpt-6.1-sol":{"draws":7,"losses":34,"wins":1},"gpt-6.1-terra":{"draws":4,"losses":37,"wins":1},"gpt-6.1-terra-pro":{"draws":1,"losses":40,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":14},"inception/mercury-3":{"draws":11,"losses":10,"wins":11},"inclusionai/ling-3.0-flash":{"draws":15,"losses":9,"wins":10},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":9,"wins":23},"meta/muse-glimmer-30b":{"draws":19,"losses":5,"wins":12},"meta/muse-spark-1.2":{"draws":12,"losses":22,"wins":6},"meta/muse-spark-1.3":{"draws":9,"losses":26,"wins":7},"meta/muse-spark-open":{"draws":12,"losses":22,"wins":8},"meta/muse-wonder":{"draws":8,"losses":25,"wins":9},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":9},"minimax/minimax-m3.1-flash":{"draws":7,"losses":12,"wins":17},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":5},"mistralai/mistral-medium-3-5":{"draws":13,"losses":3,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":17,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":34,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":5,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":6,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":9},"o3":{"draws":11,"losses":22,"wins":21},"openai/gpt-oss-120b":{"draws":12,"losses":12,"wins":12},"poolside/laguna-s-2.1":{"draws":17,"losses":11,"wins":10},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":15,"wins":10},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":9,"losses":14,"wins":5},"qwen/qwen3.8-max":{"draws":13,"losses":22,"wins":7},"qwen/qwen3.8-max-0902":{"draws":14,"losses":16,"wins":12},"recursive/flint-v1.0":{"draws":1,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":17,"wins":11},"stealth/ox-alpha":{"draws":35,"losses":72,"wins":33},"stealth/space-bunny-alpha":{"draws":13,"losses":8,"wins":11},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":15},"stepfun/step-5-preview":{"draws":1,"losses":10,"wins":5},"tencent/hy3-preview":{"draws":4,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":17,"wins":11},"thinkingmachines/inkling":{"draws":26,"losses":11,"wins":17},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":10,"losses":23,"wins":9},"x-ai/grok-4.6":{"draws":13,"losses":21,"wins":8},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":26,"losses":15,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":12,"wins":8},"z-ai/glm-5.2":{"draws":33,"losses":27,"wins":24},"z-ai/glm-5.3":{"draws":6,"losses":30,"wins":4},"z-ai/glm-5.3-flash":{"draws":14,"losses":20,"wins":8},"z-ai/glm-5.3-flashx":{"draws":11,"losses":21,"wins":10}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":10,"wins":24},"claude-fable-5":{"draws":9,"losses":29,"wins":10},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":16,"wins":16},"claude-opus-4-5":{"draws":18,"losses":29,"wins":31},"claude-opus-4-8":{"draws":7,"losses":21,"wins":16},"claude-opus-5":{"draws":8,"losses":65,"wins":9},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":11,"losses":22,"wins":15},"claude-sonnet-5-5":{"draws":12,"losses":24,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":17,"losses":19,"wins":36},"deepseek/deepseek-v4-pro":{"draws":10,"losses":7,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":16,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":17,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":24,"wins":10},"elorian/glimpse":{"draws":9,"losses":13,"wins":4},"fireworks/ember-1":{"draws":15,"losses":16,"wins":17},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"gemini-4-argon":{"draws":7,"losses":34,"wins":7},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":16,"losses":23,"wins":21},"google/gemini-3.5-flash-lite":{"draws":20,"losses":27,"wins":37},"google/gemini-3.6-flash":{"draws":21,"losses":41,"wins":30},"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":5,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":12,"wins":21},"gpt-5.4":{"draws":15,"losses":21,"wins":10},"gpt-5.4-mini":{"draws":9,"losses":12,"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":15,"losses":13,"wins":20},"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":4,"losses":43,"wins":1},"gpt-6.1-terra":{"draws":8,"losses":39,"wins":1},"gpt-6.1-terra-pro":{"draws":5,"losses":41,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":2,"wins":16},"inception/mercury-3":{"draws":10,"losses":10,"wins":12},"inclusionai/ling-3.0-flash":{"draws":11,"losses":7,"wins":16},"inclusionai/ling-3.1-flash":{"draws":3,"losses":4,"wins":3},"meituan/longcat-2.0":{"draws":9,"losses":15,"wins":28},"meta/muse-glimmer-30b":{"draws":10,"losses":13,"wins":19},"meta/muse-spark-1.2":{"draws":10,"losses":22,"wins":14},"meta/muse-spark-1.3":{"draws":6,"losses":30,"wins":12},"meta/muse-spark-open":{"draws":11,"losses":25,"wins":12},"meta/muse-wonder":{"draws":12,"losses":24,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":17},"minimax/minimax-m3.1-flash":{"draws":13,"losses":6,"wins":23},"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":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":23,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":36,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":8,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":6,"wins":11},"o3":{"draws":8,"losses":23,"wins":35},"openai/gpt-oss-120b":{"draws":10,"losses":11,"wins":21},"poolside/laguna-s-2.1":{"draws":11,"losses":19,"wins":16},"qwen/qwen3.7-max":{"draws":4,"losses":7,"wins":17},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":25,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":16,"wins":8},"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":23,"wins":14},"recursive/flint-v1.0":{"draws":3,"losses":3,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":18,"wins":14},"stealth/ox-alpha":{"draws":33,"losses":81,"wins":44},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"wins":18},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":8,"wins":3},"tencent/hy3-preview":{"draws":8,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":9,"losses":22,"wins":15},"thinkingmachines/inkling":{"draws":17,"losses":11,"wins":36},"thinkingmachines/inkling-small":{"draws":14,"losses":2,"wins":32},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":25,"losses":16,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":3,"wins":18},"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":28,"losses":33,"wins":35},"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":7,"losses":28,"wins":13},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":21,"wins":14},"claude-opus-4-5":{"draws":15,"losses":20,"wins":43},"claude-opus-4-8":{"draws":9,"losses":15,"wins":20},"claude-opus-5":{"draws":5,"losses":67,"wins":10},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":11,"losses":13,"wins":24},"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":13,"losses":17,"wins":42},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":8,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":24,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":25,"wins":16},"elorian/glimpse":{"draws":3,"losses":9,"wins":14},"fireworks/ember-1":{"draws":10,"losses":14,"wins":24},"gemini-3.1-pro-preview":{"draws":9,"losses":14,"wins":25},"gemini-4-argon":{"draws":4,"losses":40,"wins":4},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":12,"losses":21,"wins":27},"google/gemini-3.5-flash-lite":{"draws":18,"losses":8,"wins":58},"google/gemini-3.6-flash":{"draws":16,"losses":36,"wins":40},"google/gemini-3.8-flash":{"draws":7,"losses":21,"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":13,"wins":27},"gpt-5.5":{"draws":8,"losses":22,"wins":14},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":27},"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":2,"losses":46,"wins":0},"gpt-6.1-terra":{"draws":6,"losses":41,"wins":1},"gpt-6.1-terra-pro":{"draws":3,"losses":43,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":4,"wins":19},"inception/mercury-3":{"draws":6,"losses":14,"wins":12},"inclusionai/ling-3.0-flash":{"draws":9,"losses":4,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":4,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":10,"wins":35},"meta/muse-glimmer-30b":{"draws":7,"losses":5,"wins":30},"meta/muse-spark-1.2":{"draws":10,"losses":16,"wins":20},"meta/muse-spark-1.3":{"draws":11,"losses":18,"wins":19},"meta/muse-spark-open":{"draws":8,"losses":20,"wins":20},"meta/muse-wonder":{"draws":7,"losses":29,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"minimax/minimax-m3.1-flash":{"draws":5,"losses":11,"wins":26},"mistralai/mistral-large-4-0":{"draws":10,"losses":7,"wins":13},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":13,"losses":10,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":39,"wins":6},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":8,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":10},"o3":{"draws":8,"losses":12,"wins":46},"openai/gpt-oss-120b":{"draws":9,"losses":9,"wins":24},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":33},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.7-plus":{"draws":3,"losses":6,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":18,"wins":21},"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":12,"losses":14,"wins":22},"qwen/qwen3.8-max-0902":{"draws":11,"losses":16,"wins":21},"recursive/flint-v1.0":{"draws":3,"losses":4,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":18,"wins":18},"stealth/ox-alpha":{"draws":27,"losses":55,"wins":76},"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":5,"wins":2},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":4,"losses":18,"wins":24},"thinkingmachines/inkling":{"draws":10,"losses":15,"wins":39},"thinkingmachines/inkling-small":{"draws":12,"losses":8,"wins":28},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":9,"losses":18,"wins":21},"x-ai/grok-4.6":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":12},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":18,"losses":11,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":7,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":19,"wins":11},"z-ai/glm-5.2":{"draws":20,"losses":30,"wins":46},"z-ai/glm-5.3":{"draws":5,"losses":26,"wins":15},"z-ai/glm-5.3-flash":{"draws":6,"losses":27,"wins":15},"z-ai/glm-5.3-flashx":{"draws":9,"losses":19,"wins":20}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":7,"wins":33},"claude-fable-5":{"draws":10,"losses":18,"wins":20},"claude-fable-5-1":{"draws":5,"losses":42,"wins":7},"claude-haiku-5-5":{"draws":13,"losses":11,"wins":22},"claude-opus-4-5":{"draws":13,"losses":12,"wins":53},"claude-opus-4-8":{"draws":4,"losses":12,"wins":28},"claude-opus-5":{"draws":9,"losses":54,"wins":19},"claude-opus-5-5":{"draws":4,"losses":41,"wins":7},"claude-sonnet-5":{"draws":9,"losses":7,"wins":32},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":19},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":14,"losses":1,"wins":57},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":6,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":11,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":14,"wins":25},"elorian/glimpse":{"draws":3,"losses":7,"wins":16},"fireworks/ember-1":{"draws":8,"losses":10,"wins":30},"gemini-3.1-pro-preview":{"draws":5,"losses":13,"wins":30},"gemini-4-argon":{"draws":4,"losses":32,"wins":12},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":10,"losses":9,"wins":41},"google/gemini-3.5-flash-lite":{"draws":11,"losses":7,"wins":66},"google/gemini-3.6-flash":{"draws":16,"losses":25,"wins":51},"google/gemini-3.8-flash":{"draws":8,"losses":11,"wins":29},"google/gemma-4-31b-it":{"draws":7,"losses":1,"wins":20},"gpt-4.1":{"draws":1,"losses":1,"wins":14},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":4,"wins":28},"gpt-5.4":{"draws":8,"losses":13,"wins":25},"gpt-5.4-mini":{"draws":11,"losses":2,"wins":19},"gpt-5.4-nano":{"draws":6,"losses":6,"wins":36},"gpt-5.5":{"draws":8,"losses":9,"wins":27},"gpt-5.6-luna":{"draws":9,"losses":3,"wins":36},"gpt-5.6-sol":{"draws":5,"losses":20,"wins":23},"gpt-5.6-terra":{"draws":13,"losses":4,"wins":29},"gpt-6-astra":{"draws":4,"losses":39,"wins":5},"gpt-6-luna":{"draws":10,"losses":7,"wins":31},"gpt-6-sol":{"draws":8,"losses":28,"wins":12},"gpt-6.1-sol":{"draws":2,"losses":38,"wins":8},"gpt-6.1-terra":{"draws":8,"losses":34,"wins":6},"gpt-6.1-terra-pro":{"draws":4,"losses":38,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":1,"wins":24},"inception/mercury-3":{"draws":5,"losses":6,"wins":21},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":29},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":42},"meta/muse-glimmer-30b":{"draws":9,"losses":3,"wins":30},"meta/muse-spark-1.2":{"draws":8,"losses":13,"wins":25},"meta/muse-spark-1.3":{"draws":10,"losses":12,"wins":26},"meta/muse-spark-open":{"draws":4,"losses":13,"wins":29},"meta/muse-wonder":{"draws":11,"losses":18,"wins":19},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"minimax/minimax-m3.1-flash":{"draws":8,"losses":4,"wins":30},"mistralai/mistral-large-4-0":{"draws":9,"losses":6,"wins":15},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":28,"wins":13},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":1,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":1,"wins":20},"o3":{"draws":8,"losses":13,"wins":45},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":37},"poolside/laguna-s-2.1":{"draws":13,"losses":4,"wins":29},"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":7,"wins":29},"qwen/qwen3.8-27b":{"draws":6,"losses":4,"wins":24},"qwen/qwen3.8-flash":{"draws":7,"losses":4,"wins":21},"qwen/qwen3.8-max":{"draws":10,"losses":13,"wins":25},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":26},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":10,"wins":28},"stealth/ox-alpha":{"draws":26,"losses":42,"wins":90},"stealth/space-bunny-alpha":{"draws":3,"losses":5,"wins":30},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":7},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":20},"tencent/hy4-preview":{"draws":8,"losses":14,"wins":24},"thinkingmachines/inkling":{"draws":16,"losses":5,"wins":43},"thinkingmachines/inkling-small":{"draws":6,"losses":3,"wins":39},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":7,"losses":13,"wins":28},"x-ai/grok-4.6":{"draws":8,"losses":11,"wins":29},"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":13,"losses":3,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":5,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":20,"losses":10,"wins":66},"z-ai/glm-5.3":{"draws":6,"losses":27,"wins":13},"z-ai/glm-5.3-flash":{"draws":7,"losses":13,"wins":28},"z-ai/glm-5.3-flashx":{"draws":8,"losses":13,"wins":27}},"deepseek/deepseek-v4.1-flash-1017":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":8,"wins":31},"claude-fable-5":{"draws":10,"losses":14,"wins":24},"claude-fable-5-1":{"draws":5,"losses":40,"wins":9},"claude-haiku-5-5":{"draws":10,"losses":10,"wins":26},"claude-opus-4-5":{"draws":11,"losses":11,"wins":56},"claude-opus-4-8":{"draws":9,"losses":9,"wins":26},"claude-opus-5":{"draws":10,"losses":50,"wins":22},"claude-opus-5-5":{"draws":4,"losses":38,"wins":10},"claude-sonnet-5":{"draws":7,"losses":9,"wins":32},"claude-sonnet-5-5":{"draws":3,"losses":21,"wins":24},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":7,"losses":5,"wins":60},"deepseek/deepseek-v4-pro":{"draws":7,"losses":5,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":12,"wins":30},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":6,"wins":21},"elorian/glimpse":{"draws":5,"losses":8,"wins":13},"fireworks/ember-1":{"draws":9,"losses":8,"wins":31},"gemini-3.1-pro-preview":{"draws":4,"losses":7,"wins":37},"gemini-4-argon":{"draws":9,"losses":31,"wins":8},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":30},"google/gemini-3.5-flash":{"draws":8,"losses":12,"wins":40},"google/gemini-3.5-flash-lite":{"draws":7,"losses":6,"wins":71},"google/gemini-3.6-flash":{"draws":8,"losses":23,"wins":61},"google/gemini-3.8-flash":{"draws":8,"losses":8,"wins":32},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":24},"gpt-4.1":{"draws":1,"losses":2,"wins":13},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":8,"wins":29},"gpt-5.4":{"draws":6,"losses":11,"wins":29},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":27},"gpt-5.4-nano":{"draws":4,"losses":4,"wins":40},"gpt-5.5":{"draws":10,"losses":13,"wins":21},"gpt-5.6-luna":{"draws":4,"losses":6,"wins":38},"gpt-5.6-sol":{"draws":9,"losses":21,"wins":18},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":37},"gpt-6-astra":{"draws":7,"losses":36,"wins":5},"gpt-6-luna":{"draws":9,"losses":8,"wins":31},"gpt-6-sol":{"draws":5,"losses":26,"wins":17},"gpt-6.1-sol":{"draws":3,"losses":34,"wins":11},"gpt-6.1-terra":{"draws":6,"losses":30,"wins":12},"gpt-6.1-terra-pro":{"draws":8,"losses":33,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":23},"inception/mercury-3":{"draws":9,"losses":2,"wins":21},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":30},"inclusionai/ling-3.1-flash":{"draws":2,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":9,"losses":5,"wins":38},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":30},"meta/muse-spark-1.2":{"draws":8,"losses":14,"wins":24},"meta/muse-spark-1.3":{"draws":3,"losses":15,"wins":30},"meta/muse-spark-open":{"draws":8,"losses":8,"wins":32},"meta/muse-wonder":{"draws":12,"losses":14,"wins":22},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"minimax/minimax-m3.1-flash":{"draws":12,"losses":2,"wins":28},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":20},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":3,"losses":10,"wins":33},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":30,"wins":13},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":4,"wins":14},"o3":{"draws":6,"losses":13,"wins":47},"openai/gpt-oss-120b":{"draws":4,"losses":6,"wins":32},"poolside/laguna-s-2.1":{"draws":6,"losses":4,"wins":36},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":21},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":8,"wins":36},"qwen/qwen3.8-27b":{"draws":6,"losses":5,"wins":23},"qwen/qwen3.8-flash":{"draws":7,"losses":6,"wins":19},"qwen/qwen3.8-max":{"draws":5,"losses":10,"wins":33},"qwen/qwen3.8-max-0902":{"draws":7,"losses":9,"wins":32},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":4,"wins":32},"stealth/ox-alpha":{"draws":20,"losses":43,"wins":95},"stealth/space-bunny-alpha":{"draws":5,"losses":7,"wins":26},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":27},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":7},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":17},"tencent/hy4-preview":{"draws":6,"losses":8,"wins":32},"thinkingmachines/inkling":{"draws":17,"losses":6,"wins":41},"thinkingmachines/inkling-small":{"draws":5,"losses":2,"wins":41},"unbiased/pareto-26.10":{"draws":3,"losses":13,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":4,"losses":15,"wins":29},"x-ai/grok-4.6":{"draws":12,"losses":12,"wins":24},"x-ai/grok-4.7":{"draws":8,"losses":20,"wins":14},"x-ai/grok-build-0.1":{"draws":0,"losses":3,"wins":13},"xiaomi/mimo-v2.5":{"draws":14,"losses":2,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":2,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":6,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":14,"wins":16},"z-ai/glm-5.2":{"draws":14,"losses":16,"wins":66},"z-ai/glm-5.3":{"draws":10,"losses":17,"wins":19},"z-ai/glm-5.3-flash":{"draws":4,"losses":10,"wins":34},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":30}},"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":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":8,"losses":14,"wins":24},"claude-opus-4-5":{"draws":19,"losses":14,"wins":45},"claude-opus-4-8":{"draws":9,"losses":12,"wins":23},"claude-opus-5":{"draws":8,"losses":51,"wins":23},"claude-opus-5-5":{"draws":3,"losses":41,"wins":8},"claude-sonnet-5":{"draws":9,"losses":7,"wins":32},"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":15,"losses":7,"wins":50},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":6,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":9,"wins":27},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":20,"wins":21},"elorian/glimpse":{"draws":5,"losses":8,"wins":13},"fireworks/ember-1":{"draws":6,"losses":6,"wins":20},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":30},"gemini-4-argon":{"draws":4,"losses":32,"wins":12},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":9,"losses":15,"wins":36},"google/gemini-3.5-flash-lite":{"draws":20,"losses":12,"wins":52},"google/gemini-3.6-flash":{"draws":17,"losses":26,"wins":49},"google/gemini-3.8-flash":{"draws":11,"losses":14,"wins":23},"google/gemma-4-31b-it":{"draws":7,"losses":3,"wins":18},"gpt-4.1":{"draws":5,"losses":1,"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":16,"wins":22},"gpt-5.4-mini":{"draws":10,"losses":1,"wins":21},"gpt-5.4-nano":{"draws":6,"losses":9,"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":23,"wins":18},"gpt-5.6-terra":{"draws":10,"losses":9,"wins":27},"gpt-6-astra":{"draws":4,"losses":41,"wins":3},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":8,"losses":29,"wins":11},"gpt-6.1-sol":{"draws":1,"losses":37,"wins":10},"gpt-6.1-terra":{"draws":4,"losses":35,"wins":9},"gpt-6.1-terra-pro":{"draws":6,"losses":37,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inception/mercury-3":{"draws":8,"losses":5,"wins":19},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":26},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":10,"wins":34},"meta/muse-glimmer-30b":{"draws":5,"losses":4,"wins":33},"meta/muse-spark-1.2":{"draws":9,"losses":9,"wins":28},"meta/muse-spark-1.3":{"draws":7,"losses":18,"wins":23},"meta/muse-spark-open":{"draws":11,"losses":12,"wins":25},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":20},"minimax/minimax-m3.1-flash":{"draws":9,"losses":8,"wins":25},"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":1,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":9,"wins":29},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":37,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":2,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":5,"wins":12},"o3":{"draws":7,"losses":5,"wins":54},"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":14,"losses":10,"wins":24},"qwen/qwen3.8-27b":{"draws":6,"losses":11,"wins":17},"qwen/qwen3.8-flash":{"draws":6,"losses":9,"wins":17},"qwen/qwen3.8-max":{"draws":10,"losses":14,"wins":24},"qwen/qwen3.8-max-0902":{"draws":8,"losses":15,"wins":25},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":12,"wins":22},"stealth/ox-alpha":{"draws":22,"losses":44,"wins":92},"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":5,"wins":9},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":16},"tencent/hy4-preview":{"draws":8,"losses":14,"wins":24},"thinkingmachines/inkling":{"draws":12,"losses":4,"wins":48},"thinkingmachines/inkling-small":{"draws":12,"losses":1,"wins":35},"unbiased/pareto-26.10":{"draws":0,"losses":15,"wins":1},"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":27,"wins":13},"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":4,"losses":2,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":10,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":17},"z-ai/glm-5.2":{"draws":18,"losses":16,"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":4,"losses":7,"wins":33},"claude-fable-5":{"draws":6,"losses":23,"wins":19},"claude-fable-5-1":{"draws":5,"losses":43,"wins":6},"claude-haiku-5-5":{"draws":6,"losses":14,"wins":26},"claude-opus-4-5":{"draws":12,"losses":18,"wins":48},"claude-opus-4-8":{"draws":4,"losses":14,"wins":26},"claude-opus-5":{"draws":9,"losses":51,"wins":22},"claude-opus-5-5":{"draws":3,"losses":41,"wins":8},"claude-sonnet-5":{"draws":7,"losses":11,"wins":30},"claude-sonnet-5-5":{"draws":6,"losses":19,"wins":23},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":16},"deepseek/deepseek-v4-flash":{"draws":11,"losses":10,"wins":51},"deepseek/deepseek-v4-pro":{"draws":6,"losses":6,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":8,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":14,"wins":28},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":15,"wins":25},"elorian/glimpse":{"draws":4,"losses":6,"wins":16},"fireworks/ember-1":{"draws":3,"losses":15,"wins":30},"gemini-3.1-pro-preview":{"draws":4,"losses":6,"wins":22},"gemini-4-argon":{"draws":3,"losses":35,"wins":10},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":24},"google/gemini-3.5-flash":{"draws":7,"losses":14,"wins":39},"google/gemini-3.5-flash-lite":{"draws":16,"losses":12,"wins":56},"google/gemini-3.6-flash":{"draws":12,"losses":24,"wins":56},"google/gemini-3.8-flash":{"draws":7,"losses":13,"wins":28},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":20},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":6,"losses":5,"wins":31},"gpt-5.4":{"draws":5,"losses":15,"wins":26},"gpt-5.4-mini":{"draws":6,"losses":3,"wins":23},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":34},"gpt-5.5":{"draws":4,"losses":16,"wins":24},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":30},"gpt-5.6-sol":{"draws":3,"losses":20,"wins":25},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":26},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":7,"losses":9,"wins":32},"gpt-6-sol":{"draws":3,"losses":26,"wins":19},"gpt-6.1-sol":{"draws":1,"losses":34,"wins":13},"gpt-6.1-terra":{"draws":4,"losses":31,"wins":13},"gpt-6.1-terra-pro":{"draws":2,"losses":36,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":4,"wins":24},"inception/mercury-3":{"draws":9,"losses":7,"wins":16},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":27},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":38},"meta/muse-glimmer-30b":{"draws":5,"losses":4,"wins":33},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":29},"meta/muse-spark-1.3":{"draws":3,"losses":19,"wins":26},"meta/muse-spark-open":{"draws":8,"losses":11,"wins":29},"meta/muse-wonder":{"draws":4,"losses":23,"wins":21},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":21},"minimax/minimax-m3.1-flash":{"draws":6,"losses":8,"wins":28},"mistralai/mistral-large-4-0":{"draws":5,"losses":6,"wins":19},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":7,"losses":15,"wins":24},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":29,"wins":15},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":3,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":3,"wins":16},"o3":{"draws":2,"losses":15,"wins":49},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":8,"losses":3,"wins":35},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":17},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":13,"wins":28},"qwen/qwen3.8-27b":{"draws":5,"losses":9,"wins":20},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":20},"qwen/qwen3.8-max":{"draws":10,"losses":12,"wins":26},"qwen/qwen3.8-max-0902":{"draws":10,"losses":14,"wins":24},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":6,"wins":31},"stealth/ox-alpha":{"draws":20,"losses":47,"wins":91},"stealth/space-bunny-alpha":{"draws":5,"losses":7,"wins":26},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":9},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":20},"tencent/hy4-preview":{"draws":4,"losses":13,"wins":29},"thinkingmachines/inkling":{"draws":15,"losses":7,"wins":42},"thinkingmachines/inkling-small":{"draws":7,"losses":4,"wins":37},"unbiased/pareto-26.10":{"draws":2,"losses":11,"wins":3},"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":5,"losses":14,"wins":29},"x-ai/grok-4.6":{"draws":9,"losses":17,"wins":22},"x-ai/grok-4.7":{"draws":3,"losses":25,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":12,"losses":8,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":14,"wins":14},"z-ai/glm-5.2":{"draws":15,"losses":16,"wins":65},"z-ai/glm-5.3":{"draws":6,"losses":19,"wins":21},"z-ai/glm-5.3-flash":{"draws":6,"losses":18,"wins":24},"z-ai/glm-5.3-flashx":{"draws":7,"losses":13,"wins":28}},"gemini-4-argon":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":43},"claude-fable-5":{"draws":4,"losses":5,"wins":39},"claude-fable-5-1":{"draws":4,"losses":19,"wins":31},"claude-haiku-5-5":{"draws":2,"losses":8,"wins":36},"claude-opus-4-5":{"draws":1,"losses":2,"wins":75},"claude-opus-4-8":{"draws":0,"losses":5,"wins":39},"claude-opus-5":{"draws":8,"losses":19,"wins":55},"claude-opus-5-5":{"draws":5,"losses":24,"wins":23},"claude-sonnet-5":{"draws":1,"losses":2,"wins":45},"claude-sonnet-5-5":{"draws":2,"losses":9,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":16},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":70},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":43},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":3,"wins":40},"elorian/glimpse":{"draws":0,"losses":4,"wins":22},"fireworks/ember-1":{"draws":1,"losses":6,"wins":41},"gemini-3.1-pro-preview":{"draws":1,"losses":4,"wins":43},"gemini-4-argon":{"draws":3,"losses":5,"wins":24},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":56},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":81},"google/gemini-3.6-flash":{"draws":1,"losses":6,"wins":85},"google/gemini-3.8-flash":{"draws":4,"losses":3,"wins":41},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":27},"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":1,"losses":4,"wins":41},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":27},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":2,"losses":5,"wins":37},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":47},"gpt-5.6-sol":{"draws":3,"losses":4,"wins":41},"gpt-5.6-terra":{"draws":3,"losses":0,"wins":43},"gpt-6-astra":{"draws":3,"losses":22,"wins":23},"gpt-6-luna":{"draws":0,"losses":1,"wins":47},"gpt-6-sol":{"draws":4,"losses":8,"wins":36},"gpt-6.1-sol":{"draws":9,"losses":13,"wins":26},"gpt-6.1-terra":{"draws":6,"losses":17,"wins":25},"gpt-6.1-terra-pro":{"draws":5,"losses":14,"wins":29},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":34},"inception/mercury-3":{"draws":2,"losses":1,"wins":29},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":31},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":1,"losses":4,"wins":47},"meta/muse-glimmer-30b":{"draws":3,"losses":4,"wins":35},"meta/muse-spark-1.2":{"draws":1,"losses":4,"wins":41},"meta/muse-spark-1.3":{"draws":0,"losses":3,"wins":45},"meta/muse-spark-open":{"draws":1,"losses":2,"wins":43},"meta/muse-wonder":{"draws":2,"losses":6,"wins":40},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"minimax/minimax-m3.1-flash":{"draws":3,"losses":3,"wins":36},"mistralai/mistral-large-4-0":{"draws":2,"losses":0,"wins":28},"mistralai/mistral-medium-3-5":{"draws":1,"losses":2,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":1,"losses":4,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":7,"wins":38},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":4,"wins":17},"o3":{"draws":0,"losses":0,"wins":66},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":40},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":44},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":27},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":4,"wins":44},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":32},"qwen/qwen3.8-flash":{"draws":4,"losses":2,"wins":26},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":44},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":1,"wins":43},"stealth/ox-alpha":{"draws":10,"losses":10,"wins":138},"stealth/space-bunny-alpha":{"draws":1,"losses":1,"wins":36},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":21},"tencent/hy4-preview":{"draws":3,"losses":4,"wins":39},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":56},"thinkingmachines/inkling-small":{"draws":2,"losses":3,"wins":43},"unbiased/pareto-26.10":{"draws":2,"losses":9,"wins":5},"unbiased/pareto-26.10-preview":{"draws":2,"losses":6,"wins":8},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":0,"losses":8,"wins":40},"x-ai/grok-4.6":{"draws":4,"losses":1,"wins":43},"x-ai/grok-4.7":{"draws":4,"losses":8,"wins":30},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":71},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":29},"z-ai/glm-5.2":{"draws":3,"losses":4,"wins":89},"z-ai/glm-5.3":{"draws":3,"losses":7,"wins":36},"z-ai/glm-5.3-flash":{"draws":5,"losses":4,"wins":39},"z-ai/glm-5.3-flashx":{"draws":1,"losses":3,"wins":44}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":16,"wins":5},"claude-fable-5":{"draws":2,"losses":25,"wins":3},"claude-fable-5-1":{"draws":3,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":20,"wins":4},"claude-opus-4-5":{"draws":9,"losses":37,"wins":4},"claude-opus-4-8":{"draws":4,"losses":23,"wins":3},"claude-opus-5":{"draws":6,"losses":38,"wins":2},"claude-opus-5-5":{"draws":2,"losses":32,"wins":0},"claude-sonnet-5":{"draws":6,"losses":23,"wins":1},"claude-sonnet-5-5":{"draws":3,"losses":25,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":7},"deepseek/deepseek-v4-flash":{"draws":6,"losses":25,"wins":13},"deepseek/deepseek-v4-pro":{"draws":8,"losses":18,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":19,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":23,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":24,"wins":3},"elorian/glimpse":{"draws":4,"losses":9,"wins":3},"fireworks/ember-1":{"draws":5,"losses":23,"wins":2},"gemini-3.1-pro-preview":{"draws":4,"losses":19,"wins":7},"gemini-4-argon":{"draws":2,"losses":28,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":9,"losses":28,"wins":3},"google/gemini-3.5-flash-lite":{"draws":12,"losses":30,"wins":14},"google/gemini-3.6-flash":{"draws":10,"losses":41,"wins":7},"google/gemini-3.8-flash":{"draws":5,"losses":22,"wins":3},"google/gemma-4-31b-it":{"draws":8,"losses":8,"wins":4},"gpt-4.1":{"draws":2,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":5,"losses":16,"wins":5},"gpt-5.4":{"draws":8,"losses":17,"wins":5},"gpt-5.4-mini":{"draws":6,"losses":12,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":22,"wins":6},"gpt-5.5":{"draws":6,"losses":21,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":15,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":25,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":20,"wins":2},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":6,"losses":18,"wins":6},"gpt-6-sol":{"draws":3,"losses":27,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":30,"wins":0},"gpt-6.1-terra":{"draws":0,"losses":30,"wins":0},"gpt-6.1-terra-pro":{"draws":1,"losses":29,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":6,"losses":9,"wins":9},"inception/mercury-3":{"draws":2,"losses":16,"wins":0},"inclusionai/ling-3.0-flash":{"draws":8,"losses":4,"wins":8},"inclusionai/ling-3.1-flash":{"draws":0,"losses":3,"wins":1},"meituan/longcat-2.0":{"draws":4,"losses":20,"wins":14},"meta/muse-glimmer-30b":{"draws":6,"losses":12,"wins":8},"meta/muse-spark-1.2":{"draws":6,"losses":20,"wins":2},"meta/muse-spark-1.3":{"draws":2,"losses":24,"wins":4},"meta/muse-spark-open":{"draws":4,"losses":21,"wins":5},"meta/muse-wonder":{"draws":1,"losses":28,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":6},"minimax/minimax-m3.1-flash":{"draws":5,"losses":17,"wins":4},"mistralai/mistral-large-4-0":{"draws":7,"losses":9,"wins":2},"mistralai/mistral-medium-3-5":{"draws":6,"losses":9,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":14,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":27,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":10,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":10,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":10,"wins":3},"o3":{"draws":8,"losses":35,"wins":7},"openai/gpt-oss-120b":{"draws":3,"losses":10,"wins":13},"poolside/laguna-s-2.1":{"draws":8,"losses":12,"wins":6},"qwen/qwen3.7-max":{"draws":2,"losses":12,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":7,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":19,"wins":5},"qwen/qwen3.8-27b":{"draws":4,"losses":13,"wins":3},"qwen/qwen3.8-flash":{"draws":7,"losses":9,"wins":4},"qwen/qwen3.8-max":{"draws":7,"losses":22,"wins":1},"qwen/qwen3.8-max-0902":{"draws":5,"losses":22,"wins":3},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":18,"wins":7},"stealth/ox-alpha":{"draws":15,"losses":62,"wins":9},"stealth/space-bunny-alpha":{"draws":6,"losses":14,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":12,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":5},"tencent/hy4-preview":{"draws":7,"losses":20,"wins":3},"thinkingmachines/inkling":{"draws":9,"losses":16,"wins":13},"thinkingmachines/inkling-small":{"draws":7,"losses":10,"wins":13},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"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":25,"wins":0},"x-ai/grok-4.6":{"draws":5,"losses":25,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":25,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":14,"losses":27,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":17,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":14,"wins":4},"z-ai/glm-5.2":{"draws":14,"losses":39,"wins":7},"z-ai/glm-5.3":{"draws":3,"losses":27,"wins":0},"z-ai/glm-5.3-flash":{"draws":5,"losses":19,"wins":6},"z-ai/glm-5.3-flashx":{"draws":4,"losses":22,"wins":4}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":31},"claude-fable-5":{"draws":7,"losses":26,"wins":15},"claude-fable-5-1":{"draws":1,"losses":47,"wins":6},"claude-haiku-5-5":{"draws":8,"losses":17,"wins":21},"claude-opus-4-5":{"draws":21,"losses":10,"wins":47},"claude-opus-4-8":{"draws":8,"losses":14,"wins":22},"claude-opus-5":{"draws":11,"losses":54,"wins":17},"claude-opus-5-5":{"draws":2,"losses":43,"wins":7},"claude-sonnet-5":{"draws":9,"losses":9,"wins":30},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":17},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":10,"losses":8,"wins":54},"deepseek/deepseek-v4-pro":{"draws":7,"losses":13,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":13,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":16,"wins":27},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":7,"losses":14,"wins":27},"gemini-3.1-pro-preview":{"draws":8,"losses":9,"wins":31},"gemini-4-argon":{"draws":5,"losses":38,"wins":5},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":8,"losses":4,"wins":32},"google/gemini-3.5-flash-lite":{"draws":16,"losses":8,"wins":60},"google/gemini-3.6-flash":{"draws":12,"losses":22,"wins":58},"google/gemini-3.8-flash":{"draws":6,"losses":18,"wins":24},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":3,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":8,"wins":26},"gpt-5.4":{"draws":5,"losses":17,"wins":24},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":20},"gpt-5.4-nano":{"draws":4,"losses":7,"wins":37},"gpt-5.5":{"draws":8,"losses":14,"wins":22},"gpt-5.6-luna":{"draws":10,"losses":8,"wins":30},"gpt-5.6-sol":{"draws":5,"losses":24,"wins":19},"gpt-5.6-terra":{"draws":9,"losses":15,"wins":22},"gpt-6-astra":{"draws":4,"losses":41,"wins":3},"gpt-6-luna":{"draws":10,"losses":14,"wins":24},"gpt-6-sol":{"draws":4,"losses":30,"wins":14},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":12},"gpt-6.1-terra":{"draws":3,"losses":37,"wins":8},"gpt-6.1-terra-pro":{"draws":3,"losses":37,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":4,"wins":20},"inception/mercury-3":{"draws":6,"losses":4,"wins":22},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":27},"inclusionai/ling-3.1-flash":{"draws":2,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":6,"losses":5,"wins":41},"meta/muse-glimmer-30b":{"draws":9,"losses":3,"wins":30},"meta/muse-spark-1.2":{"draws":8,"losses":15,"wins":23},"meta/muse-spark-1.3":{"draws":8,"losses":20,"wins":20},"meta/muse-spark-open":{"draws":8,"losses":16,"wins":24},"meta/muse-wonder":{"draws":9,"losses":24,"wins":15},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":22},"minimax/minimax-m3.1-flash":{"draws":8,"losses":7,"wins":27},"mistralai/mistral-large-4-0":{"draws":9,"losses":9,"wins":12},"mistralai/mistral-medium-3-5":{"draws":4,"losses":1,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":16,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":35,"wins":10},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":12},"o3":{"draws":6,"losses":11,"wins":49},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":31},"poolside/laguna-s-2.1":{"draws":1,"losses":4,"wins":41},"qwen/qwen3.7-max":{"draws":7,"losses":5,"wins":16},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":14,"wins":24},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":21},"qwen/qwen3.8-flash":{"draws":4,"losses":9,"wins":19},"qwen/qwen3.8-max":{"draws":11,"losses":13,"wins":24},"qwen/qwen3.8-max-0902":{"draws":10,"losses":24,"wins":14},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":12,"wins":24},"stealth/ox-alpha":{"draws":23,"losses":50,"wins":85},"stealth/space-bunny-alpha":{"draws":10,"losses":4,"wins":24},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":25},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":8},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":18},"tencent/hy4-preview":{"draws":7,"losses":19,"wins":20},"thinkingmachines/inkling":{"draws":10,"losses":5,"wins":49},"thinkingmachines/inkling-small":{"draws":7,"losses":3,"wins":38},"unbiased/pareto-26.10":{"draws":2,"losses":12,"wins":2},"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":8,"losses":15,"wins":25},"x-ai/grok-4.6":{"draws":9,"losses":19,"wins":20},"x-ai/grok-4.7":{"draws":5,"losses":25,"wins":12},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":12,"losses":2,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":8,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":15},"z-ai/glm-5.2":{"draws":16,"losses":21,"wins":59},"z-ai/glm-5.3":{"draws":6,"losses":25,"wins":15},"z-ai/glm-5.3-flash":{"draws":3,"losses":20,"wins":25},"z-ai/glm-5.3-flashx":{"draws":11,"losses":17,"wins":20}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":26,"wins":26},"claude-fable-5":{"draws":11,"losses":57,"wins":10},"claude-fable-5-1":{"draws":4,"losses":86,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":50,"wins":11},"claude-opus-4-5":{"draws":34,"losses":61,"wins":31},"claude-opus-4-8":{"draws":13,"losses":46,"wins":11},"claude-opus-5":{"draws":11,"losses":105,"wins":12},"claude-opus-5-5":{"draws":7,"losses":75,"wins":0},"claude-sonnet-5":{"draws":16,"losses":40,"wins":22},"claude-sonnet-5-5":{"draws":15,"losses":50,"wins":13},"cohere/north-mini-code":{"draws":8,"losses":10,"wins":14},"deepseek/deepseek-v4-flash":{"draws":23,"losses":43,"wins":48},"deepseek/deepseek-v4-pro":{"draws":16,"losses":35,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":35,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":33,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":61,"wins":7},"elorian/glimpse":{"draws":11,"losses":22,"wins":9},"fireworks/ember-1":{"draws":24,"losses":38,"wins":16},"gemini-3.1-pro-preview":{"draws":17,"losses":37,"wins":24},"gemini-4-argon":{"draws":5,"losses":68,"wins":5},"google/gemini-3.1-flash-lite":{"draws":11,"losses":13,"wins":30},"google/gemini-3.5-flash":{"draws":20,"losses":54,"wins":24},"google/gemini-3.5-flash-lite":{"draws":20,"losses":47,"wins":47},"google/gemini-3.6-flash":{"draws":27,"losses":87,"wins":38},"google/gemini-3.8-flash":{"draws":11,"losses":58,"wins":9},"google/gemma-4-31b-it":{"draws":17,"losses":10,"wins":19},"gpt-4.1":{"draws":9,"losses":8,"wins":9},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":5},"gpt-5":{"draws":12,"losses":38,"wins":18},"gpt-5.4":{"draws":10,"losses":46,"wins":20},"gpt-5.4-mini":{"draws":17,"losses":17,"wins":18},"gpt-5.4-nano":{"draws":9,"losses":27,"wins":38},"gpt-5.5":{"draws":20,"losses":36,"wins":16},"gpt-5.6-luna":{"draws":19,"losses":33,"wins":26},"gpt-5.6-sol":{"draws":13,"losses":58,"wins":7},"gpt-5.6-terra":{"draws":16,"losses":38,"wins":20},"gpt-6-astra":{"draws":5,"losses":73,"wins":0},"gpt-6-luna":{"draws":21,"losses":40,"wins":17},"gpt-6-sol":{"draws":9,"losses":64,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":75,"wins":0},"gpt-6.1-terra":{"draws":9,"losses":67,"wins":2},"gpt-6.1-terra-pro":{"draws":3,"losses":72,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":20,"losses":11,"wins":25},"inception/mercury-3":{"draws":10,"losses":26,"wins":12},"inclusionai/ling-3.0-flash":{"draws":12,"losses":14,"wins":26},"inclusionai/ling-3.1-flash":{"draws":6,"losses":6,"wins":4},"meituan/longcat-2.0":{"draws":21,"losses":29,"wins":38},"meta/muse-glimmer-30b":{"draws":16,"losses":23,"wins":29},"meta/muse-spark-1.2":{"draws":20,"losses":38,"wins":16},"meta/muse-spark-1.3":{"draws":14,"losses":49,"wins":15},"meta/muse-spark-open":{"draws":13,"losses":48,"wins":17},"meta/muse-wonder":{"draws":11,"losses":57,"wins":10},"minimax/minimax-m3":{"draws":11,"losses":14,"wins":15},"minimax/minimax-m3.1-flash":{"draws":16,"losses":33,"wins":23},"mistralai/mistral-large-4-0":{"draws":13,"losses":22,"wins":13},"mistralai/mistral-medium-3-5":{"draws":8,"losses":11,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":40,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":66,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":12,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":8,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":18,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":13,"wins":11},"o3":{"draws":14,"losses":63,"wins":33},"openai/gpt-oss-120b":{"draws":19,"losses":22,"wins":27},"poolside/laguna-s-2.1":{"draws":17,"losses":33,"wins":22},"qwen/qwen3.7-max":{"draws":8,"losses":22,"wins":14},"qwen/qwen3.7-plus":{"draws":8,"losses":11,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":41,"wins":15},"qwen/qwen3.8-27b":{"draws":8,"losses":35,"wins":13},"qwen/qwen3.8-flash":{"draws":14,"losses":27,"wins":11},"qwen/qwen3.8-max":{"draws":19,"losses":44,"wins":15},"qwen/qwen3.8-max-0902":{"draws":22,"losses":43,"wins":13},"recursive/flint-v1.0":{"draws":7,"losses":4,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":35,"wins":22},"stealth/ox-alpha":{"draws":42,"losses":162,"wins":64},"stealth/space-bunny-alpha":{"draws":13,"losses":31,"wins":20},"stepfun/step-3.7-flash":{"draws":11,"losses":17,"wins":28},"stepfun/step-5-preview":{"draws":3,"losses":11,"wins":4},"tencent/hy3-preview":{"draws":10,"losses":18,"wins":12},"tencent/hy4-preview":{"draws":13,"losses":47,"wins":16},"thinkingmachines/inkling":{"draws":27,"losses":33,"wins":46},"thinkingmachines/inkling-small":{"draws":19,"losses":32,"wins":27},"unbiased/pareto-26.10":{"draws":1,"losses":25,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":26,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":7,"wins":9},"x-ai/grok-4.5":{"draws":18,"losses":41,"wins":19},"x-ai/grok-4.6":{"draws":18,"losses":50,"wins":10},"x-ai/grok-4.7":{"draws":4,"losses":53,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":9,"wins":11},"xiaomi/mimo-v2.5":{"draws":34,"losses":41,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":31,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":37,"wins":10},"z-ai/glm-5.2":{"draws":29,"losses":73,"wins":54},"z-ai/glm-5.3":{"draws":9,"losses":60,"wins":7},"z-ai/glm-5.3-flash":{"draws":12,"losses":54,"wins":12},"z-ai/glm-5.3-flashx":{"draws":14,"losses":49,"wins":15}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":13,"wins":62},"claude-fable-5":{"draws":12,"losses":45,"wins":39},"claude-fable-5-1":{"draws":5,"losses":96,"wins":7},"claude-haiku-5-5":{"draws":21,"losses":24,"wins":47},"claude-opus-4-5":{"draws":34,"losses":28,"wins":94},"claude-opus-4-8":{"draws":15,"losses":26,"wins":47},"claude-opus-5":{"draws":25,"losses":101,"wins":38},"claude-opus-5-5":{"draws":12,"losses":82,"wins":10},"claude-sonnet-5":{"draws":15,"losses":23,"wins":58},"claude-sonnet-5-5":{"draws":20,"losses":37,"wins":39},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":30},"deepseek/deepseek-v4-flash":{"draws":24,"losses":8,"wins":112},"deepseek/deepseek-v4-pro":{"draws":17,"losses":15,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":20,"wins":53},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":21,"wins":51},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":36,"wins":46},"elorian/glimpse":{"draws":10,"losses":16,"wins":26},"fireworks/ember-1":{"draws":24,"losses":25,"wins":47},"gemini-3.1-pro-preview":{"draws":20,"losses":27,"wins":49},"gemini-4-argon":{"draws":6,"losses":79,"wins":11},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":55},"google/gemini-3.5-flash":{"draws":18,"losses":35,"wins":67},"google/gemini-3.5-flash-lite":{"draws":33,"losses":18,"wins":117},"google/gemini-3.6-flash":{"draws":27,"losses":39,"wins":86},"google/gemini-3.8-flash":{"draws":19,"losses":38,"wins":39},"google/gemma-4-31b-it":{"draws":13,"losses":1,"wins":42},"gpt-4.1":{"draws":6,"losses":5,"wins":21},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":9},"gpt-5":{"draws":10,"losses":20,"wins":54},"gpt-5.4":{"draws":17,"losses":31,"wins":44},"gpt-5.4-mini":{"draws":16,"losses":7,"wins":41},"gpt-5.4-nano":{"draws":14,"losses":13,"wins":69},"gpt-5.5":{"draws":18,"losses":31,"wins":39},"gpt-5.6-luna":{"draws":16,"losses":17,"wins":63},"gpt-5.6-sol":{"draws":11,"losses":45,"wins":40},"gpt-5.6-terra":{"draws":16,"losses":15,"wins":61},"gpt-6-astra":{"draws":6,"losses":79,"wins":11},"gpt-6-luna":{"draws":23,"losses":21,"wins":52},"gpt-6-sol":{"draws":12,"losses":54,"wins":30},"gpt-6.1-sol":{"draws":9,"losses":77,"wins":10},"gpt-6.1-terra":{"draws":12,"losses":71,"wins":13},"gpt-6.1-terra-pro":{"draws":11,"losses":70,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":4,"wins":47},"inception/mercury-3":{"draws":14,"losses":9,"wins":41},"inclusionai/ling-3.0-flash":{"draws":18,"losses":4,"wins":46},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":12},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":80},"meta/muse-glimmer-30b":{"draws":16,"losses":9,"wins":59},"meta/muse-spark-1.2":{"draws":19,"losses":25,"wins":48},"meta/muse-spark-1.3":{"draws":15,"losses":40,"wins":41},"meta/muse-spark-open":{"draws":14,"losses":31,"wins":49},"meta/muse-wonder":{"draws":20,"losses":47,"wins":29},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":35},"minimax/minimax-m3.1-flash":{"draws":17,"losses":14,"wins":53},"mistralai/mistral-large-4-0":{"draws":13,"losses":14,"wins":33},"mistralai/mistral-medium-3-5":{"draws":13,"losses":1,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":22,"losses":21,"wins":49},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":66,"wins":21},"nex-agi/nex-n2-pro":{"draws":6,"losses":6,"wins":36},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":9,"wins":50},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":4,"wins":30},"o3":{"draws":14,"losses":23,"wins":95},"openai/gpt-oss-120b":{"draws":12,"losses":8,"wins":64},"poolside/laguna-s-2.1":{"draws":19,"losses":13,"wins":60},"qwen/qwen3.7-max":{"draws":18,"losses":6,"wins":32},"qwen/qwen3.7-plus":{"draws":7,"losses":5,"wins":36},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":28,"wins":53},"qwen/qwen3.8-27b":{"draws":16,"losses":12,"wins":40},"qwen/qwen3.8-flash":{"draws":14,"losses":14,"wins":36},"qwen/qwen3.8-max":{"draws":18,"losses":19,"wins":59},"qwen/qwen3.8-max-0902":{"draws":26,"losses":32,"wins":38},"recursive/flint-v1.0":{"draws":8,"losses":3,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":16,"losses":16,"wins":56},"stealth/ox-alpha":{"draws":50,"losses":103,"wins":163},"stealth/space-bunny-alpha":{"draws":15,"losses":9,"wins":52},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":58},"stepfun/step-5-preview":{"draws":2,"losses":8,"wins":14},"tencent/hy3-preview":{"draws":13,"losses":7,"wins":32},"tencent/hy4-preview":{"draws":13,"losses":21,"wins":58},"thinkingmachines/inkling":{"draws":34,"losses":12,"wins":82},"thinkingmachines/inkling-small":{"draws":25,"losses":7,"wins":64},"unbiased/pareto-26.10":{"draws":3,"losses":28,"wins":1},"unbiased/pareto-26.10-preview":{"draws":1,"losses":26,"wins":5},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":19},"x-ai/grok-4.5":{"draws":17,"losses":31,"wins":48},"x-ai/grok-4.6":{"draws":21,"losses":33,"wins":42},"x-ai/grok-4.7":{"draws":7,"losses":50,"wins":27},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":23},"xiaomi/mimo-v2.5":{"draws":31,"losses":7,"wins":110},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":31},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":22,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":29,"wins":21},"z-ai/glm-5.2":{"draws":40,"losses":26,"wins":126},"z-ai/glm-5.3":{"draws":16,"losses":40,"wins":36},"z-ai/glm-5.3-flash":{"draws":16,"losses":40,"wins":40},"z-ai/glm-5.3-flashx":{"draws":23,"losses":34,"wins":39}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":6,"wins":35},"claude-fable-5":{"draws":6,"losses":21,"wins":21},"claude-fable-5-1":{"draws":6,"losses":41,"wins":7},"claude-haiku-5-5":{"draws":10,"losses":14,"wins":22},"claude-opus-4-5":{"draws":9,"losses":20,"wins":49},"claude-opus-4-8":{"draws":3,"losses":14,"wins":27},"claude-opus-5":{"draws":4,"losses":57,"wins":21},"claude-opus-5-5":{"draws":4,"losses":36,"wins":12},"claude-sonnet-5":{"draws":2,"losses":13,"wins":33},"claude-sonnet-5-5":{"draws":3,"losses":22,"wins":23},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":5,"losses":3,"wins":64},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":13,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":16,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":21,"wins":20},"elorian/glimpse":{"draws":1,"losses":7,"wins":18},"fireworks/ember-1":{"draws":4,"losses":18,"wins":26},"gemini-3.1-pro-preview":{"draws":4,"losses":11,"wins":33},"gemini-4-argon":{"draws":2,"losses":31,"wins":15},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":27},"google/gemini-3.5-flash":{"draws":9,"losses":7,"wins":44},"google/gemini-3.5-flash-lite":{"draws":4,"losses":10,"wins":70},"google/gemini-3.6-flash":{"draws":7,"losses":28,"wins":57},"google/gemini-3.8-flash":{"draws":4,"losses":12,"wins":16},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":21},"gpt-4.1":{"draws":2,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":1,"losses":9,"wins":32},"gpt-5.4":{"draws":3,"losses":19,"wins":24},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":28},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":34},"gpt-5.5":{"draws":4,"losses":19,"wins":21},"gpt-5.6-luna":{"draws":5,"losses":8,"wins":35},"gpt-5.6-sol":{"draws":4,"losses":22,"wins":22},"gpt-5.6-terra":{"draws":7,"losses":15,"wins":24},"gpt-6-astra":{"draws":5,"losses":40,"wins":3},"gpt-6-luna":{"draws":9,"losses":7,"wins":32},"gpt-6-sol":{"draws":7,"losses":27,"wins":14},"gpt-6.1-sol":{"draws":5,"losses":33,"wins":10},"gpt-6.1-terra":{"draws":7,"losses":29,"wins":12},"gpt-6.1-terra-pro":{"draws":6,"losses":38,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":3,"wins":26},"inception/mercury-3":{"draws":5,"losses":8,"wins":19},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":28},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":42},"meta/muse-glimmer-30b":{"draws":2,"losses":8,"wins":32},"meta/muse-spark-1.2":{"draws":2,"losses":16,"wins":28},"meta/muse-spark-1.3":{"draws":9,"losses":19,"wins":20},"meta/muse-spark-open":{"draws":1,"losses":16,"wins":31},"meta/muse-wonder":{"draws":12,"losses":21,"wins":15},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":22},"minimax/minimax-m3.1-flash":{"draws":5,"losses":11,"wins":26},"mistralai/mistral-large-4-0":{"draws":9,"losses":7,"wins":14},"mistralai/mistral-medium-3-5":{"draws":1,"losses":5,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":10,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":33,"wins":12},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":7,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":9,"wins":12},"o3":{"draws":4,"losses":11,"wins":51},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":38},"poolside/laguna-s-2.1":{"draws":1,"losses":7,"wins":38},"qwen/qwen3.7-max":{"draws":7,"losses":9,"wins":12},"qwen/qwen3.7-plus":{"draws":0,"losses":5,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":14,"wins":31},"qwen/qwen3.8-27b":{"draws":2,"losses":9,"wins":23},"qwen/qwen3.8-flash":{"draws":3,"losses":10,"wins":19},"qwen/qwen3.8-max":{"draws":4,"losses":21,"wins":23},"qwen/qwen3.8-max-0902":{"draws":9,"losses":15,"wins":24},"recursive/flint-v1.0":{"draws":0,"losses":1,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":8,"wins":31},"stealth/ox-alpha":{"draws":20,"losses":44,"wins":94},"stealth/space-bunny-alpha":{"draws":2,"losses":8,"wins":28},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":28},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":5,"losses":20,"wins":21},"thinkingmachines/inkling":{"draws":9,"losses":7,"wins":48},"thinkingmachines/inkling-small":{"draws":5,"losses":11,"wins":32},"unbiased/pareto-26.10":{"draws":2,"losses":12,"wins":2},"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":2,"losses":17,"wins":29},"x-ai/grok-4.7":{"draws":3,"losses":32,"wins":7},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":5,"losses":15,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":5,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":5,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":17,"wins":10},"z-ai/glm-5.2":{"draws":10,"losses":18,"wins":68},"z-ai/glm-5.3":{"draws":9,"losses":24,"wins":13},"z-ai/glm-5.3-flash":{"draws":6,"losses":15,"wins":27},"z-ai/glm-5.3-flashx":{"draws":7,"losses":14,"wins":27}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":11,"wins":17},"claude-fable-5":{"draws":8,"losses":30,"wins":10},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":23,"wins":10},"claude-opus-4-5":{"draws":33,"losses":18,"wins":27},"claude-opus-4-8":{"draws":12,"losses":17,"wins":15},"claude-opus-5":{"draws":10,"losses":64,"wins":8},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":14,"losses":15,"wins":19},"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":19,"losses":8,"wins":45},"deepseek/deepseek-v4-pro":{"draws":13,"losses":17,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":20,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":26,"wins":12},"elorian/glimpse":{"draws":6,"losses":12,"wins":8},"fireworks/ember-1":{"draws":12,"losses":19,"wins":17},"gemini-3.1-pro-preview":{"draws":12,"losses":24,"wins":12},"gemini-4-argon":{"draws":1,"losses":45,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":22},"google/gemini-3.5-flash":{"draws":14,"losses":24,"wins":22},"google/gemini-3.5-flash-lite":{"draws":26,"losses":21,"wins":37},"google/gemini-3.6-flash":{"draws":23,"losses":44,"wins":25},"google/gemini-3.8-flash":{"draws":10,"losses":26,"wins":12},"google/gemma-4-31b-it":{"draws":13,"losses":1,"wins":14},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":5,"wins":13},"gpt-5.4":{"draws":7,"losses":20,"wins":19},"gpt-5.4-mini":{"draws":9,"losses":9,"wins":14},"gpt-5.4-nano":{"draws":8,"losses":9,"wins":31},"gpt-5.5":{"draws":17,"losses":15,"wins":12},"gpt-5.6-luna":{"draws":14,"losses":12,"wins":22},"gpt-5.6-sol":{"draws":8,"losses":33,"wins":7},"gpt-5.6-terra":{"draws":12,"losses":16,"wins":18},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":17,"losses":14,"wins":17},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"gpt-6.1-terra":{"draws":6,"losses":41,"wins":1},"gpt-6.1-terra-pro":{"draws":4,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":20},"inception/mercury-3":{"draws":11,"losses":8,"wins":13},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":4,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":18,"wins":26},"meta/muse-glimmer-30b":{"draws":15,"losses":6,"wins":21},"meta/muse-spark-1.2":{"draws":12,"losses":19,"wins":15},"meta/muse-spark-1.3":{"draws":13,"losses":21,"wins":14},"meta/muse-spark-open":{"draws":17,"losses":19,"wins":12},"meta/muse-wonder":{"draws":9,"losses":32,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":17},"minimax/minimax-m3.1-flash":{"draws":11,"losses":12,"wins":19},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":10,"losses":5,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":17,"losses":13,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":42,"wins":1},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":3,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":7,"wins":7},"o3":{"draws":9,"losses":24,"wins":33},"openai/gpt-oss-120b":{"draws":12,"losses":7,"wins":23},"poolside/laguna-s-2.1":{"draws":16,"losses":16,"wins":14},"qwen/qwen3.7-max":{"draws":11,"losses":6,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"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":7,"losses":12,"wins":13},"qwen/qwen3.8-max":{"draws":23,"losses":13,"wins":12},"qwen/qwen3.8-max-0902":{"draws":11,"losses":23,"wins":14},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":15,"wins":15},"stealth/ox-alpha":{"draws":38,"losses":69,"wins":51},"stealth/space-bunny-alpha":{"draws":9,"losses":12,"wins":17},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":20},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":10,"wins":10},"tencent/hy4-preview":{"draws":16,"losses":16,"wins":14},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":36},"thinkingmachines/inkling-small":{"draws":16,"losses":7,"wins":25},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":24,"wins":12},"x-ai/grok-4.6":{"draws":15,"losses":25,"wins":8},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":22,"losses":16,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":6,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":9},"z-ai/glm-5.2":{"draws":35,"losses":23,"wins":38},"z-ai/glm-5.3":{"draws":6,"losses":33,"wins":7},"z-ai/glm-5.3-flash":{"draws":11,"losses":25,"wins":12},"z-ai/glm-5.3-flashx":{"draws":13,"losses":17,"wins":18}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":27},"claude-fable-5":{"draws":11,"losses":13,"wins":18},"claude-fable-5-1":{"draws":2,"losses":38,"wins":8},"claude-haiku-5-5":{"draws":6,"losses":11,"wins":23},"claude-opus-4-5":{"draws":11,"losses":8,"wins":49},"claude-opus-4-8":{"draws":4,"losses":9,"wins":25},"claude-opus-5":{"draws":8,"losses":46,"wins":16},"claude-opus-5-5":{"draws":3,"losses":36,"wins":7},"claude-sonnet-5":{"draws":6,"losses":5,"wins":31},"claude-sonnet-5-5":{"draws":9,"losses":13,"wins":20},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":9,"losses":2,"wins":51},"deepseek/deepseek-v4-pro":{"draws":9,"losses":7,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":6,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":8,"wins":26},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":11,"wins":25},"elorian/glimpse":{"draws":3,"losses":6,"wins":15},"fireworks/ember-1":{"draws":3,"losses":8,"wins":31},"gemini-3.1-pro-preview":{"draws":2,"losses":10,"wins":30},"gemini-4-argon":{"draws":3,"losses":27,"wins":12},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":6,"losses":6,"wins":42},"google/gemini-3.5-flash-lite":{"draws":11,"losses":7,"wins":58},"google/gemini-3.6-flash":{"draws":11,"losses":19,"wins":52},"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":2,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":4,"wins":32},"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":8,"losses":10,"wins":22},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":33},"gpt-5.6-sol":{"draws":7,"losses":14,"wins":21},"gpt-5.6-terra":{"draws":3,"losses":5,"wins":32},"gpt-6-astra":{"draws":2,"losses":34,"wins":6},"gpt-6-luna":{"draws":8,"losses":9,"wins":25},"gpt-6-sol":{"draws":2,"losses":29,"wins":11},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":9},"gpt-6.1-terra":{"draws":1,"losses":29,"wins":12},"gpt-6.1-terra-pro":{"draws":3,"losses":29,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":19},"inception/mercury-3":{"draws":1,"losses":4,"wins":21},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":24},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":8},"meituan/longcat-2.0":{"draws":4,"losses":3,"wins":41},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":33},"meta/muse-spark-1.2":{"draws":5,"losses":8,"wins":27},"meta/muse-spark-1.3":{"draws":8,"losses":6,"wins":28},"meta/muse-spark-open":{"draws":8,"losses":9,"wins":25},"meta/muse-wonder":{"draws":5,"losses":17,"wins":20},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":16},"minimax/minimax-m3.1-flash":{"draws":4,"losses":5,"wins":29},"mistralai/mistral-large-4-0":{"draws":4,"losses":3,"wins":19},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":27,"wins":13},"nex-agi/nex-n2-pro":{"draws":1,"losses":4,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":1,"wins":15},"o3":{"draws":2,"losses":8,"wins":54},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":30},"poolside/laguna-s-2.1":{"draws":5,"losses":1,"wins":34},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":20},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":10,"wins":26},"qwen/qwen3.8-27b":{"draws":5,"losses":2,"wins":23},"qwen/qwen3.8-flash":{"draws":4,"losses":3,"wins":21},"qwen/qwen3.8-max":{"draws":6,"losses":11,"wins":25},"qwen/qwen3.8-max-0902":{"draws":5,"losses":10,"wins":27},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":7,"wins":23},"stealth/ox-alpha":{"draws":30,"losses":29,"wins":83},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":28},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":28},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":9},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":17},"tencent/hy4-preview":{"draws":4,"losses":8,"wins":30},"thinkingmachines/inkling":{"draws":11,"losses":8,"wins":39},"thinkingmachines/inkling-small":{"draws":6,"losses":3,"wins":33},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":4},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":8,"losses":9,"wins":25},"x-ai/grok-4.6":{"draws":8,"losses":9,"wins":25},"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":9,"losses":2,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":3,"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":3,"losses":10,"wins":29},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":24}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":5,"wins":26},"claude-fable-5":{"draws":7,"losses":18,"wins":17},"claude-fable-5-1":{"draws":1,"losses":36,"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":6,"wins":25},"claude-opus-5":{"draws":4,"losses":36,"wins":30},"claude-opus-5-5":{"draws":1,"losses":36,"wins":9},"claude-sonnet-5":{"draws":7,"losses":8,"wins":27},"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":9,"losses":2,"wins":51},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":9,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":10,"wins":22},"elorian/glimpse":{"draws":6,"losses":5,"wins":13},"fireworks/ember-1":{"draws":8,"losses":8,"wins":26},"gemini-3.1-pro-preview":{"draws":6,"losses":7,"wins":29},"gemini-4-argon":{"draws":3,"losses":21,"wins":18},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":9,"losses":8,"wins":37},"google/gemini-3.5-flash-lite":{"draws":16,"losses":5,"wins":55},"google/gemini-3.6-flash":{"draws":17,"losses":14,"wins":51},"google/gemini-3.8-flash":{"draws":9,"losses":11,"wins":22},"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":8,"losses":5,"wins":25},"gpt-5.4":{"draws":11,"losses":14,"wins":17},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":19},"gpt-5.4-nano":{"draws":0,"losses":6,"wins":36},"gpt-5.5":{"draws":8,"losses":6,"wins":12},"gpt-5.6-luna":{"draws":10,"losses":6,"wins":26},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":22},"gpt-5.6-terra":{"draws":7,"losses":6,"wins":27},"gpt-6-astra":{"draws":1,"losses":37,"wins":4},"gpt-6-luna":{"draws":11,"losses":5,"wins":26},"gpt-6-sol":{"draws":3,"losses":23,"wins":16},"gpt-6.1-sol":{"draws":1,"losses":25,"wins":16},"gpt-6.1-terra":{"draws":3,"losses":28,"wins":11},"gpt-6.1-terra-pro":{"draws":1,"losses":32,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":19},"inception/mercury-3":{"draws":4,"losses":3,"wins":19},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":22},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":5,"wins":35},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":4,"losses":6,"wins":30},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":24},"meta/muse-spark-open":{"draws":3,"losses":10,"wins":29},"meta/muse-wonder":{"draws":7,"losses":15,"wins":20},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":16},"minimax/minimax-m3.1-flash":{"draws":10,"losses":8,"wins":20},"mistralai/mistral-large-4-0":{"draws":4,"losses":7,"wins":15},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":7,"losses":14,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":24,"wins":16},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":0,"wins":15},"o3":{"draws":6,"losses":6,"wins":52},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":25},"poolside/laguna-s-2.1":{"draws":5,"losses":5,"wins":30},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":19},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":8,"wins":26},"qwen/qwen3.8-27b":{"draws":4,"losses":4,"wins":22},"qwen/qwen3.8-flash":{"draws":6,"losses":2,"wins":20},"qwen/qwen3.8-max":{"draws":10,"losses":10,"wins":22},"qwen/qwen3.8-max-0902":{"draws":8,"losses":10,"wins":24},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":7,"wins":25},"stealth/ox-alpha":{"draws":28,"losses":33,"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":0,"losses":1,"wins":9},"tencent/hy3-preview":{"draws":8,"losses":0,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":11,"wins":23},"thinkingmachines/inkling":{"draws":9,"losses":5,"wins":44},"thinkingmachines/inkling-small":{"draws":8,"losses":2,"wins":32},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":2},"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":7,"wins":23},"x-ai/grok-4.6":{"draws":9,"losses":12,"wins":21},"x-ai/grok-4.7":{"draws":3,"losses":17,"wins":16},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":20,"losses":1,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":4,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":13},"z-ai/glm-5.2":{"draws":21,"losses":7,"wins":56},"z-ai/glm-5.3":{"draws":6,"losses":24,"wins":10},"z-ai/glm-5.3-flash":{"draws":3,"losses":19,"wins":20},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":24}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":9,"wins":21},"claude-fable-5":{"draws":7,"losses":29,"wins":12},"claude-fable-5-1":{"draws":3,"losses":45,"wins":6},"claude-haiku-5-5":{"draws":14,"losses":17,"wins":15},"claude-opus-4-5":{"draws":26,"losses":19,"wins":33},"claude-opus-4-8":{"draws":12,"losses":10,"wins":22},"claude-opus-5":{"draws":9,"losses":64,"wins":9},"claude-opus-5-5":{"draws":7,"losses":41,"wins":4},"claude-sonnet-5":{"draws":9,"losses":15,"wins":24},"claude-sonnet-5-5":{"draws":11,"losses":23,"wins":14},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":23,"losses":8,"wins":41},"deepseek/deepseek-v4-pro":{"draws":12,"losses":9,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":9,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":23,"wins":16},"elorian/glimpse":{"draws":8,"losses":8,"wins":10},"fireworks/ember-1":{"draws":14,"losses":9,"wins":25},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":25},"gemini-4-argon":{"draws":5,"losses":37,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":19,"losses":10,"wins":31},"google/gemini-3.5-flash-lite":{"draws":23,"losses":12,"wins":49},"google/gemini-3.6-flash":{"draws":20,"losses":35,"wins":37},"google/gemini-3.8-flash":{"draws":11,"losses":19,"wins":18},"google/gemma-4-31b-it":{"draws":12,"losses":2,"wins":14},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":10,"wins":22},"gpt-5.4":{"draws":16,"losses":19,"wins":11},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":6,"losses":11,"wins":31},"gpt-5.5":{"draws":15,"losses":16,"wins":13},"gpt-5.6-luna":{"draws":10,"losses":7,"wins":15},"gpt-5.6-sol":{"draws":10,"losses":23,"wins":15},"gpt-5.6-terra":{"draws":13,"losses":8,"wins":25},"gpt-6-astra":{"draws":2,"losses":43,"wins":3},"gpt-6-luna":{"draws":12,"losses":17,"wins":19},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":8},"gpt-6.1-terra":{"draws":6,"losses":36,"wins":6},"gpt-6.1-terra-pro":{"draws":2,"losses":43,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":18},"inception/mercury-3":{"draws":9,"losses":10,"wins":13},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":17},"inclusionai/ling-3.1-flash":{"draws":3,"losses":2,"wins":3},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":35},"meta/muse-glimmer-30b":{"draws":10,"losses":4,"wins":28},"meta/muse-spark-1.2":{"draws":9,"losses":20,"wins":17},"meta/muse-spark-1.3":{"draws":12,"losses":20,"wins":16},"meta/muse-spark-open":{"draws":16,"losses":14,"wins":18},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":13},"minimax/minimax-m3.1-flash":{"draws":10,"losses":10,"wins":22},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":11,"losses":1,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":13,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":39,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":1,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":5,"wins":9},"o3":{"draws":15,"losses":17,"wins":34},"openai/gpt-oss-120b":{"draws":15,"losses":6,"wins":21},"poolside/laguna-s-2.1":{"draws":17,"losses":5,"wins":24},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":15},"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":14,"losses":19,"wins":15},"qwen/qwen3.8-max-0902":{"draws":15,"losses":12,"wins":21},"recursive/flint-v1.0":{"draws":1,"losses":3,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":12,"wins":18},"stealth/ox-alpha":{"draws":42,"losses":57,"wins":59},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":19},"stepfun/step-5-preview":{"draws":1,"losses":7,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":16,"losses":13,"wins":17},"thinkingmachines/inkling":{"draws":19,"losses":6,"wins":39},"thinkingmachines/inkling-small":{"draws":17,"losses":6,"wins":25},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":13,"wins":26},"x-ai/grok-4.6":{"draws":10,"losses":23,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":20,"losses":8,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":2,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":10,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":10},"z-ai/glm-5.2":{"draws":31,"losses":27,"wins":38},"z-ai/glm-5.3":{"draws":8,"losses":28,"wins":10},"z-ai/glm-5.3-flash":{"draws":11,"losses":23,"wins":14},"z-ai/glm-5.3-flashx":{"draws":8,"losses":20,"wins":20}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":38},"claude-fable-5":{"draws":2,"losses":13,"wins":33},"claude-fable-5-1":{"draws":6,"losses":34,"wins":14},"claude-haiku-5-5":{"draws":7,"losses":5,"wins":34},"claude-opus-4-5":{"draws":6,"losses":12,"wins":60},"claude-opus-4-8":{"draws":6,"losses":4,"wins":34},"claude-opus-5":{"draws":6,"losses":36,"wins":40},"claude-opus-5-5":{"draws":5,"losses":33,"wins":14},"claude-sonnet-5":{"draws":0,"losses":2,"wins":46},"claude-sonnet-5-5":{"draws":2,"losses":13,"wins":33},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":3,"losses":2,"wins":67},"deepseek/deepseek-v4-pro":{"draws":1,"losses":5,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":2,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":3,"wins":40},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":8,"wins":33},"elorian/glimpse":{"draws":2,"losses":6,"wins":18},"fireworks/ember-1":{"draws":5,"losses":6,"wins":37},"gemini-3.1-pro-preview":{"draws":3,"losses":3,"wins":42},"gemini-4-argon":{"draws":1,"losses":30,"wins":17},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":3,"losses":6,"wins":51},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":78},"google/gemini-3.6-flash":{"draws":7,"losses":15,"wins":70},"google/gemini-3.8-flash":{"draws":4,"losses":8,"wins":36},"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":3,"losses":1,"wins":44},"gpt-5.5":{"draws":6,"losses":10,"wins":28},"gpt-5.6-luna":{"draws":2,"losses":7,"wins":39},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":26},"gpt-5.6-terra":{"draws":2,"losses":4,"wins":40},"gpt-6-astra":{"draws":5,"losses":32,"wins":11},"gpt-6-luna":{"draws":9,"losses":1,"wins":38},"gpt-6-sol":{"draws":6,"losses":17,"wins":25},"gpt-6.1-sol":{"draws":5,"losses":29,"wins":14},"gpt-6.1-terra":{"draws":8,"losses":28,"wins":12},"gpt-6.1-terra-pro":{"draws":7,"losses":28,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inception/mercury-3":{"draws":2,"losses":1,"wins":29},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":1,"wins":5},"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":10,"wins":33},"meta/muse-spark-open":{"draws":3,"losses":7,"wins":38},"meta/muse-wonder":{"draws":2,"losses":16,"wins":30},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"minimax/minimax-m3.1-flash":{"draws":1,"losses":3,"wins":38},"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":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":42},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":25,"wins":20},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":19},"o3":{"draws":1,"losses":7,"wins":58},"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":3,"losses":6,"wins":39},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":27},"qwen/qwen3.8-flash":{"draws":3,"losses":4,"wins":25},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":42},"qwen/qwen3.8-max-0902":{"draws":2,"losses":7,"wins":39},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":7,"wins":31},"stealth/ox-alpha":{"draws":15,"losses":17,"wins":126},"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":2,"losses":2,"wins":8},"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":{"draws":3,"losses":11,"wins":2},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":37},"x-ai/grok-4.6":{"draws":6,"losses":14,"wins":28},"x-ai/grok-4.7":{"draws":5,"losses":17,"wins":20},"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":0,"losses":1,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":5,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":7,"wins":22},"z-ai/glm-5.2":{"draws":5,"losses":3,"wins":88},"z-ai/glm-5.3":{"draws":6,"losses":13,"wins":27},"z-ai/glm-5.3-flash":{"draws":4,"losses":12,"wins":32},"z-ai/glm-5.3-flashx":{"draws":6,"losses":9,"wins":33}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":5,"wins":28},"claude-fable-5":{"draws":12,"losses":25,"wins":11},"claude-fable-5-1":{"draws":1,"losses":50,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":24,"losses":26,"wins":28},"claude-opus-4-8":{"draws":5,"losses":19,"wins":20},"claude-opus-5":{"draws":10,"losses":64,"wins":8},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":17,"losses":12,"wins":19},"claude-sonnet-5-5":{"draws":11,"losses":24,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":14,"losses":10,"wins":48},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":10,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":21,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":27,"wins":11},"elorian/glimpse":{"draws":6,"losses":9,"wins":11},"fireworks/ember-1":{"draws":13,"losses":15,"wins":20},"gemini-3.1-pro-preview":{"draws":12,"losses":15,"wins":21},"gemini-4-argon":{"draws":3,"losses":40,"wins":5},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":13,"losses":15,"wins":32},"google/gemini-3.5-flash-lite":{"draws":20,"losses":12,"wins":52},"google/gemini-3.6-flash":{"draws":24,"losses":38,"wins":30},"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":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":10,"losses":11,"wins":21},"gpt-5.4":{"draws":12,"losses":21,"wins":13},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":17},"gpt-5.4-nano":{"draws":5,"losses":8,"wins":35},"gpt-5.5":{"draws":10,"losses":21,"wins":13},"gpt-5.6-luna":{"draws":11,"losses":15,"wins":22},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":12},"gpt-5.6-terra":{"draws":9,"losses":10,"wins":11},"gpt-6-astra":{"draws":3,"losses":44,"wins":1},"gpt-6-luna":{"draws":13,"losses":17,"wins":18},"gpt-6-sol":{"draws":10,"losses":29,"wins":9},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":4},"gpt-6.1-terra":{"draws":6,"losses":38,"wins":4},"gpt-6.1-terra-pro":{"draws":2,"losses":43,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":4,"wins":19},"inception/mercury-3":{"draws":7,"losses":10,"wins":15},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":24},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":9,"wins":30},"meta/muse-glimmer-30b":{"draws":13,"losses":7,"wins":22},"meta/muse-spark-1.2":{"draws":12,"losses":22,"wins":12},"meta/muse-spark-1.3":{"draws":12,"losses":20,"wins":16},"meta/muse-spark-open":{"draws":16,"losses":19,"wins":13},"meta/muse-wonder":{"draws":8,"losses":27,"wins":13},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":19},"minimax/minimax-m3.1-flash":{"draws":9,"losses":11,"wins":22},"mistralai/mistral-large-4-0":{"draws":15,"losses":8,"wins":7},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":16,"losses":11,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":38,"wins":8},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":6,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":9,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":3,"wins":10},"o3":{"draws":9,"losses":18,"wins":39},"openai/gpt-oss-120b":{"draws":9,"losses":5,"wins":28},"poolside/laguna-s-2.1":{"draws":9,"losses":6,"wins":31},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":19},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":22,"wins":15},"qwen/qwen3.8-27b":{"draws":11,"losses":8,"wins":15},"qwen/qwen3.8-flash":{"draws":5,"losses":8,"wins":19},"qwen/qwen3.8-max":{"draws":14,"losses":19,"wins":15},"qwen/qwen3.8-max-0902":{"draws":10,"losses":22,"wins":16},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":15,"wins":21},"stealth/ox-alpha":{"draws":34,"losses":66,"wins":58},"stealth/space-bunny-alpha":{"draws":11,"losses":7,"wins":20},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":25},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":8},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":13},"tencent/hy4-preview":{"draws":8,"losses":18,"wins":20},"thinkingmachines/inkling":{"draws":16,"losses":9,"wins":39},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":32},"unbiased/pareto-26.10":{"draws":2,"losses":13,"wins":1},"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":13,"losses":27,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":29,"wins":11},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":23,"losses":2,"wins":49},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":14,"wins":11},"z-ai/glm-5.2":{"draws":30,"losses":22,"wins":44},"z-ai/glm-5.3":{"draws":9,"losses":24,"wins":13},"z-ai/glm-5.3-flash":{"draws":8,"losses":20,"wins":20},"z-ai/glm-5.3-flashx":{"draws":11,"losses":20,"wins":17}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":43},"claude-fable-5":{"draws":1,"losses":7,"wins":40},"claude-fable-5-1":{"draws":6,"losses":16,"wins":32},"claude-haiku-5-5":{"draws":0,"losses":3,"wins":43},"claude-opus-4-5":{"draws":0,"losses":1,"wins":77},"claude-opus-4-8":{"draws":3,"losses":1,"wins":40},"claude-opus-5":{"draws":3,"losses":10,"wins":69},"claude-opus-5-5":{"draws":3,"losses":16,"wins":33},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":1,"losses":11,"wins":36},"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":3,"losses":2,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":2,"wins":46},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":1,"wins":45},"elorian/glimpse":{"draws":0,"losses":2,"wins":24},"fireworks/ember-1":{"draws":0,"losses":0,"wins":48},"gemini-3.1-pro-preview":{"draws":0,"losses":2,"wins":46},"gemini-4-argon":{"draws":6,"losses":9,"wins":33},"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":1,"losses":0,"wins":83},"google/gemini-3.6-flash":{"draws":3,"losses":5,"wins":84},"google/gemini-3.8-flash":{"draws":2,"losses":2,"wins":44},"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":5,"wins":41},"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":3,"wins":41},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":47},"gpt-5.6-sol":{"draws":3,"losses":5,"wins":40},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":46},"gpt-6-astra":{"draws":2,"losses":5,"wins":25},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":8,"losses":4,"wins":36},"gpt-6.1-sol":{"draws":6,"losses":9,"wins":33},"gpt-6.1-terra":{"draws":5,"losses":4,"wins":39},"gpt-6.1-terra-pro":{"draws":3,"losses":9,"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},"inception/mercury-3":{"draws":1,"losses":1,"wins":30},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"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":0,"wins":45},"meta/muse-spark-1.3":{"draws":0,"losses":2,"wins":46},"meta/muse-spark-open":{"draws":2,"losses":0,"wins":44},"meta/muse-wonder":{"draws":3,"losses":2,"wins":43},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"minimax/minimax-m3.1-flash":{"draws":0,"losses":0,"wins":42},"mistralai/mistral-large-4-0":{"draws":1,"losses":2,"wins":27},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":0,"wins":46},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":7,"wins":39},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":22},"o3":{"draws":1,"losses":0,"wins":65},"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":1,"wins":46},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":46},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":1,"wins":43},"stealth/ox-alpha":{"draws":6,"losses":3,"wins":149},"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":0,"wins":16},"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":{"draws":4,"losses":1,"wins":11},"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":1,"losses":3,"wins":44},"x-ai/grok-4.6":{"draws":0,"losses":0,"wins":48},"x-ai/grok-4.7":{"draws":4,"losses":2,"wins":36},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":15},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":72},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":24},"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":0,"wins":95},"z-ai/glm-5.3":{"draws":2,"losses":3,"wins":41},"z-ai/glm-5.3-flash":{"draws":2,"losses":1,"wins":45},"z-ai/glm-5.3-flashx":{"draws":1,"losses":3,"wins":44}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":13,"wins":24},"claude-fable-5":{"draws":9,"losses":27,"wins":12},"claude-fable-5-1":{"draws":6,"losses":43,"wins":5},"claude-haiku-5-5":{"draws":4,"losses":21,"wins":21},"claude-opus-4-5":{"draws":15,"losses":26,"wins":37},"claude-opus-4-8":{"draws":5,"losses":16,"wins":23},"claude-opus-5":{"draws":8,"losses":59,"wins":15},"claude-opus-5-5":{"draws":6,"losses":43,"wins":3},"claude-sonnet-5":{"draws":8,"losses":16,"wins":24},"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":9,"losses":13,"wins":50},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":13,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":19,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":23,"wins":14},"elorian/glimpse":{"draws":3,"losses":14,"wins":9},"fireworks/ember-1":{"draws":6,"losses":21,"wins":21},"gemini-3.1-pro-preview":{"draws":4,"losses":19,"wins":25},"gemini-4-argon":{"draws":6,"losses":36,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":28},"google/gemini-3.5-flash":{"draws":9,"losses":20,"wins":31},"google/gemini-3.5-flash-lite":{"draws":9,"losses":20,"wins":55},"google/gemini-3.6-flash":{"draws":12,"losses":34,"wins":46},"google/gemini-3.8-flash":{"draws":7,"losses":21,"wins":20},"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":4,"losses":14,"wins":24},"gpt-5.4":{"draws":11,"losses":15,"wins":20},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":4,"losses":12,"wins":32},"gpt-5.5":{"draws":5,"losses":20,"wins":19},"gpt-5.6-luna":{"draws":9,"losses":11,"wins":28},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":13},"gpt-5.6-terra":{"draws":8,"losses":14,"wins":24},"gpt-6-astra":{"draws":6,"losses":37,"wins":5},"gpt-6-luna":{"draws":5,"losses":13,"wins":14},"gpt-6-sol":{"draws":5,"losses":35,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":39,"wins":4},"gpt-6.1-terra":{"draws":6,"losses":38,"wins":4},"gpt-6.1-terra-pro":{"draws":5,"losses":41,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":24},"inception/mercury-3":{"draws":6,"losses":8,"wins":18},"inclusionai/ling-3.0-flash":{"draws":2,"losses":6,"wins":26},"inclusionai/ling-3.1-flash":{"draws":3,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":9,"wins":38},"meta/muse-glimmer-30b":{"draws":4,"losses":8,"wins":30},"meta/muse-spark-1.2":{"draws":9,"losses":18,"wins":19},"meta/muse-spark-1.3":{"draws":8,"losses":20,"wins":20},"meta/muse-spark-open":{"draws":6,"losses":20,"wins":20},"meta/muse-wonder":{"draws":7,"losses":26,"wins":15},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":18},"minimax/minimax-m3.1-flash":{"draws":7,"losses":14,"wins":21},"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":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":8,"losses":16,"wins":22},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":39,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":13},"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":1,"losses":8,"wins":19},"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":7,"losses":19,"wins":22},"qwen/qwen3.8-max-0902":{"draws":9,"losses":16,"wins":23},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":14,"wins":26},"stealth/ox-alpha":{"draws":25,"losses":58,"wins":75},"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":1,"losses":7,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":16},"tencent/hy4-preview":{"draws":7,"losses":17,"wins":22},"thinkingmachines/inkling":{"draws":8,"losses":12,"wins":44},"thinkingmachines/inkling-small":{"draws":4,"losses":10,"wins":34},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"unbiased/pareto-26.10-preview":{"draws":2,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":7,"losses":21,"wins":20},"x-ai/grok-4.6":{"draws":9,"losses":27,"wins":12},"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":12,"wins":49},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":12,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":18,"wins":9},"z-ai/glm-5.2":{"draws":20,"losses":26,"wins":50},"z-ai/glm-5.3":{"draws":6,"losses":26,"wins":14},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":21}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":8,"wins":35},"claude-fable-5":{"draws":3,"losses":11,"wins":34},"claude-fable-5-1":{"draws":3,"losses":24,"wins":27},"claude-haiku-5-5":{"draws":5,"losses":7,"wins":34},"claude-opus-4-5":{"draws":3,"losses":11,"wins":64},"claude-opus-4-8":{"draws":2,"losses":10,"wins":32},"claude-opus-5":{"draws":14,"losses":25,"wins":43},"claude-opus-5-5":{"draws":6,"losses":26,"wins":20},"claude-sonnet-5":{"draws":1,"losses":6,"wins":41},"claude-sonnet-5-5":{"draws":4,"losses":11,"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":4,"losses":6,"wins":38},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":8,"wins":37},"elorian/glimpse":{"draws":1,"losses":5,"wins":20},"fireworks/ember-1":{"draws":3,"losses":6,"wins":39},"gemini-3.1-pro-preview":{"draws":4,"losses":8,"wins":36},"gemini-4-argon":{"draws":3,"losses":20,"wins":25},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":28},"google/gemini-3.5-flash":{"draws":4,"losses":11,"wins":45},"google/gemini-3.5-flash-lite":{"draws":4,"losses":10,"wins":70},"google/gemini-3.6-flash":{"draws":4,"losses":19,"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":1,"losses":6,"wins":39},"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":9,"wins":36},"gpt-5.6-terra":{"draws":3,"losses":6,"wins":37},"gpt-6-astra":{"draws":5,"losses":33,"wins":10},"gpt-6-luna":{"draws":5,"losses":4,"wins":39},"gpt-6-sol":{"draws":3,"losses":9,"wins":20},"gpt-6.1-sol":{"draws":3,"losses":24,"wins":21},"gpt-6.1-terra":{"draws":4,"losses":17,"wins":27},"gpt-6.1-terra-pro":{"draws":11,"losses":24,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":2,"wins":31},"inception/mercury-3":{"draws":2,"losses":5,"wins":25},"inclusionai/ling-3.0-flash":{"draws":4,"losses":5,"wins":25},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":9},"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-spark-open":{"draws":3,"losses":7,"wins":38},"meta/muse-wonder":{"draws":2,"losses":8,"wins":38},"minimax/minimax-m3":{"draws":1,"losses":4,"wins":21},"minimax/minimax-m3.1-flash":{"draws":1,"losses":4,"wins":37},"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":0,"wins":4},"moonshotai/kimi-k3":{"draws":0,"losses":7,"wins":39},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":18,"wins":23},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":19},"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},"recursive/flint-v1.0":{"draws":0,"losses":2,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":5,"wins":36},"stealth/ox-alpha":{"draws":13,"losses":19,"wins":126},"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":0,"wins":12},"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":{"draws":2,"losses":8,"wins":6},"unbiased/pareto-26.10-preview":{"draws":0,"losses":9,"wins":7},"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":1,"losses":2,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":3,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":23},"z-ai/glm-5.2":{"draws":5,"losses":14,"wins":77},"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":5,"losses":7,"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":5,"losses":17,"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":3,"losses":21,"wins":28},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":1,"losses":9,"wins":38},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":70},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":44},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":5,"wins":42},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":5,"wins":43},"elorian/glimpse":{"draws":0,"losses":3,"wins":23},"fireworks/ember-1":{"draws":0,"losses":3,"wins":45},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":47},"gemini-4-argon":{"draws":2,"losses":11,"wins":35},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":0,"losses":3,"wins":57},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":84},"google/gemini-3.6-flash":{"draws":3,"losses":5,"wins":84},"google/gemini-3.8-flash":{"draws":2,"losses":3,"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":3,"losses":5,"wins":38},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":31},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":0,"losses":6,"wins":38},"gpt-5.6-luna":{"draws":0,"losses":3,"wins":45},"gpt-5.6-sol":{"draws":2,"losses":9,"wins":37},"gpt-5.6-terra":{"draws":0,"losses":3,"wins":43},"gpt-6-astra":{"draws":8,"losses":14,"wins":26},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":2,"losses":6,"wins":40},"gpt-6.1-sol":{"draws":0,"losses":8,"wins":24},"gpt-6.1-terra":{"draws":5,"losses":7,"wins":36},"gpt-6.1-terra-pro":{"draws":2,"losses":9,"wins":37},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":34},"inception/mercury-3":{"draws":0,"losses":4,"wins":28},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":50},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":1,"losses":4,"wins":41},"meta/muse-spark-1.3":{"draws":1,"losses":0,"wins":47},"meta/muse-spark-open":{"draws":0,"losses":3,"wins":45},"meta/muse-wonder":{"draws":2,"losses":6,"wins":40},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"minimax/minimax-m3.1-flash":{"draws":0,"losses":0,"wins":42},"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":0},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":43},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":7,"wins":36},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":18},"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":0,"losses":3,"wins":45},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":32},"qwen/qwen3.8-flash":{"draws":1,"losses":2,"wins":29},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":47},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":45},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":0,"wins":44},"stealth/ox-alpha":{"draws":2,"losses":6,"wins":150},"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":12},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":26},"tencent/hy4-preview":{"draws":1,"losses":3,"wins":42},"thinkingmachines/inkling":{"draws":1,"losses":1,"wins":62},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":8},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":10},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":0,"losses":4,"wins":44},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":42},"x-ai/grok-4.7":{"draws":2,"losses":5,"wins":35},"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":24},"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":0,"losses":2,"wins":94},"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":1,"losses":4,"wins":43}},"gpt-6.1-terra":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":42},"claude-fable-5":{"draws":4,"losses":11,"wins":33},"claude-fable-5-1":{"draws":6,"losses":23,"wins":25},"claude-haiku-5-5":{"draws":4,"losses":5,"wins":37},"claude-opus-4-5":{"draws":4,"losses":0,"wins":74},"claude-opus-4-8":{"draws":1,"losses":5,"wins":38},"claude-opus-5":{"draws":6,"losses":28,"wins":48},"claude-opus-5-5":{"draws":4,"losses":26,"wins":22},"claude-sonnet-5":{"draws":1,"losses":1,"wins":46},"claude-sonnet-5-5":{"draws":4,"losses":10,"wins":34},"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":5,"losses":0,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":3,"wins":39},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":9,"wins":29},"elorian/glimpse":{"draws":0,"losses":4,"wins":22},"fireworks/ember-1":{"draws":1,"losses":3,"wins":44},"gemini-3.1-pro-preview":{"draws":6,"losses":3,"wins":39},"gemini-4-argon":{"draws":9,"losses":14,"wins":25},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":56},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":78},"google/gemini-3.6-flash":{"draws":5,"losses":8,"wins":79},"google/gemini-3.8-flash":{"draws":7,"losses":8,"wins":33},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":25},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":0,"losses":0,"wins":42},"gpt-5.4":{"draws":3,"losses":5,"wins":38},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":27},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":43},"gpt-5.5":{"draws":1,"losses":5,"wins":38},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":41},"gpt-5.6-sol":{"draws":6,"losses":5,"wins":37},"gpt-5.6-terra":{"draws":6,"losses":1,"wins":39},"gpt-6-astra":{"draws":3,"losses":30,"wins":15},"gpt-6-luna":{"draws":4,"losses":1,"wins":43},"gpt-6-sol":{"draws":3,"losses":12,"wins":33},"gpt-6.1-sol":{"draws":8,"losses":22,"wins":18},"gpt-6.1-terra":{"draws":4,"losses":7,"wins":21},"gpt-6.1-terra-pro":{"draws":5,"losses":21,"wins":22},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":32},"inception/mercury-3":{"draws":5,"losses":1,"wins":26},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":3,"losses":1,"wins":48},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":37},"meta/muse-spark-1.2":{"draws":1,"losses":3,"wins":42},"meta/muse-spark-1.3":{"draws":4,"losses":6,"wins":38},"meta/muse-spark-open":{"draws":5,"losses":3,"wins":38},"meta/muse-wonder":{"draws":12,"losses":3,"wins":33},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":23},"minimax/minimax-m3.1-flash":{"draws":5,"losses":2,"wins":35},"mistralai/mistral-large-4-0":{"draws":2,"losses":3,"wins":25},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":36},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":15,"wins":24},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":37},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":1,"wins":19},"o3":{"draws":1,"losses":3,"wins":62},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":38},"poolside/laguna-s-2.1":{"draws":5,"losses":0,"wins":41},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":26},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":42},"qwen/qwen3.8-27b":{"draws":3,"losses":1,"wins":30},"qwen/qwen3.8-flash":{"draws":2,"losses":3,"wins":27},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-max-0902":{"draws":7,"losses":5,"wins":36},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":1,"wins":42},"stealth/ox-alpha":{"draws":13,"losses":8,"wins":137},"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":8},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":5,"losses":3,"wins":38},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":56},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":45},"unbiased/pareto-26.10":{"draws":2,"losses":9,"wins":5},"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":6,"losses":5,"wins":37},"x-ai/grok-4.6":{"draws":6,"losses":6,"wins":36},"x-ai/grok-4.7":{"draws":4,"losses":11,"wins":27},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":15},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":5,"wins":26},"z-ai/glm-5.2":{"draws":5,"losses":3,"wins":88},"z-ai/glm-5.3":{"draws":2,"losses":8,"wins":36},"z-ai/glm-5.3-flash":{"draws":3,"losses":7,"wins":38},"z-ai/glm-5.3-flashx":{"draws":4,"losses":5,"wins":39}},"gpt-6.1-terra-pro":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":5,"wins":37},"claude-fable-5":{"draws":1,"losses":12,"wins":35},"claude-fable-5-1":{"draws":6,"losses":19,"wins":29},"claude-haiku-5-5":{"draws":3,"losses":7,"wins":36},"claude-opus-4-5":{"draws":1,"losses":10,"wins":67},"claude-opus-4-8":{"draws":1,"losses":6,"wins":37},"claude-opus-5":{"draws":6,"losses":28,"wins":48},"claude-opus-5-5":{"draws":3,"losses":30,"wins":19},"claude-sonnet-5":{"draws":1,"losses":5,"wins":42},"claude-sonnet-5-5":{"draws":1,"losses":15,"wins":32},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":4,"wins":68},"deepseek/deepseek-v4-pro":{"draws":0,"losses":3,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":4,"wins":39},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":5,"wins":41},"elorian/glimpse":{"draws":3,"losses":2,"wins":21},"fireworks/ember-1":{"draws":1,"losses":6,"wins":41},"gemini-3.1-pro-preview":{"draws":0,"losses":7,"wins":41},"gemini-4-argon":{"draws":3,"losses":13,"wins":32},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":0,"losses":6,"wins":54},"google/gemini-3.5-flash-lite":{"draws":1,"losses":4,"wins":79},"google/gemini-3.6-flash":{"draws":5,"losses":13,"wins":74},"google/gemini-3.8-flash":{"draws":5,"losses":5,"wins":38},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":2,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":2,"wins":37},"gpt-5.4":{"draws":0,"losses":9,"wins":37},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":29},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":45},"gpt-5.5":{"draws":4,"losses":5,"wins":35},"gpt-5.6-luna":{"draws":3,"losses":1,"wins":44},"gpt-5.6-sol":{"draws":2,"losses":8,"wins":38},"gpt-5.6-terra":{"draws":1,"losses":4,"wins":41},"gpt-6-astra":{"draws":4,"losses":28,"wins":16},"gpt-6-luna":{"draws":3,"losses":4,"wins":41},"gpt-6-sol":{"draws":6,"losses":5,"wins":37},"gpt-6.1-sol":{"draws":3,"losses":17,"wins":28},"gpt-6.1-terra":{"draws":4,"losses":18,"wins":26},"gpt-6.1-terra-pro":{"draws":4,"losses":6,"wins":22},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":32},"inception/mercury-3":{"draws":1,"losses":3,"wins":28},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":49},"meta/muse-glimmer-30b":{"draws":0,"losses":1,"wins":41},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":42},"meta/muse-spark-1.3":{"draws":3,"losses":5,"wins":40},"meta/muse-spark-open":{"draws":3,"losses":4,"wins":39},"meta/muse-wonder":{"draws":2,"losses":8,"wins":38},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":24},"minimax/minimax-m3.1-flash":{"draws":1,"losses":2,"wins":39},"mistralai/mistral-large-4-0":{"draws":3,"losses":3,"wins":24},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k3":{"draws":3,"losses":6,"wins":37},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":14,"wins":31},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":2,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":22},"o3":{"draws":0,"losses":8,"wins":58},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":40},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":42},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":25},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":4,"wins":44},"qwen/qwen3.8-27b":{"draws":2,"losses":4,"wins":28},"qwen/qwen3.8-flash":{"draws":3,"losses":4,"wins":25},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":42},"qwen/qwen3.8-max-0902":{"draws":0,"losses":6,"wins":42},"recursive/flint-v1.0":{"draws":1,"losses":1,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":2,"wins":39},"stealth/ox-alpha":{"draws":12,"losses":11,"wins":135},"stealth/space-bunny-alpha":{"draws":0,"losses":3,"wins":35},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":9},"tencent/hy3-preview":{"draws":1,"losses":4,"wins":21},"tencent/hy4-preview":{"draws":3,"losses":4,"wins":39},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":60},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10":{"draws":2,"losses":9,"wins":5},"unbiased/pareto-26.10-preview":{"draws":1,"losses":8,"wins":7},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":0,"losses":9,"wins":39},"x-ai/grok-4.6":{"draws":5,"losses":7,"wins":36},"x-ai/grok-4.7":{"draws":2,"losses":11,"wins":29},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":8,"losses":5,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":3,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":5,"wins":24},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":86},"z-ai/glm-5.3":{"draws":2,"losses":11,"wins":33},"z-ai/glm-5.3-flash":{"draws":4,"losses":8,"wins":36},"z-ai/glm-5.3-flashx":{"draws":7,"losses":3,"wins":38}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":12,"wins":8},"claude-fable-5":{"draws":9,"losses":27,"wins":0},"claude-fable-5-1":{"draws":2,"losses":38,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":25,"wins":0},"claude-opus-4-5":{"draws":28,"losses":30,"wins":2},"claude-opus-4-8":{"draws":9,"losses":23,"wins":4},"claude-opus-5":{"draws":12,"losses":44,"wins":2},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":11,"losses":24,"wins":1},"claude-sonnet-5-5":{"draws":11,"losses":24,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":4},"deepseek/deepseek-v4-flash":{"draws":20,"losses":29,"wins":7},"deepseek/deepseek-v4-pro":{"draws":13,"losses":17,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":17,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":19,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":26,"wins":0},"elorian/glimpse":{"draws":4,"losses":12,"wins":4},"fireworks/ember-1":{"draws":13,"losses":20,"wins":3},"gemini-3.1-pro-preview":{"draws":12,"losses":15,"wins":9},"gemini-4-argon":{"draws":4,"losses":32,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":6,"wins":10},"google/gemini-3.5-flash":{"draws":16,"losses":27,"wins":3},"google/gemini-3.5-flash-lite":{"draws":26,"losses":28,"wins":8},"google/gemini-3.6-flash":{"draws":21,"losses":43,"wins":4},"google/gemini-3.8-flash":{"draws":8,"losses":27,"wins":1},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":8},"gpt-4.1":{"draws":4,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":11,"losses":17,"wins":2},"gpt-5.4":{"draws":11,"losses":21,"wins":2},"gpt-5.4-mini":{"draws":9,"losses":10,"wins":5},"gpt-5.4-nano":{"draws":15,"losses":19,"wins":4},"gpt-5.5":{"draws":12,"losses":16,"wins":4},"gpt-5.6-luna":{"draws":14,"losses":13,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":0},"gpt-5.6-terra":{"draws":11,"losses":23,"wins":2},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":15,"losses":18,"wins":3},"gpt-6-sol":{"draws":3,"losses":31,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"gpt-6.1-terra":{"draws":2,"losses":34,"wins":0},"gpt-6.1-terra-pro":{"draws":5,"losses":31,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":6,"wins":2},"inception/mercury-3":{"draws":12,"losses":12,"wins":2},"inclusionai/ling-3.0-flash":{"draws":13,"losses":11,"wins":6},"inclusionai/ling-3.1-flash":{"draws":3,"losses":3,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":17,"wins":9},"meta/muse-glimmer-30b":{"draws":12,"losses":10,"wins":8},"meta/muse-spark-1.2":{"draws":12,"losses":20,"wins":2},"meta/muse-spark-1.3":{"draws":10,"losses":23,"wins":3},"meta/muse-spark-open":{"draws":11,"losses":25,"wins":0},"meta/muse-wonder":{"draws":8,"losses":28,"wins":0},"minimax/minimax-m3":{"draws":10,"losses":7,"wins":3},"minimax/minimax-m3.1-flash":{"draws":10,"losses":18,"wins":2},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":3},"mistralai/mistral-medium-3-5":{"draws":9,"losses":6,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":18,"losses":12,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":29,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":7,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":10,"wins":3},"o3":{"draws":9,"losses":37,"wins":4},"openai/gpt-oss-120b":{"draws":10,"losses":9,"wins":11},"poolside/laguna-s-2.1":{"draws":14,"losses":10,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":3},"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":9,"losses":13,"wins":2},"qwen/qwen3.8-max":{"draws":15,"losses":19,"wins":2},"qwen/qwen3.8-max-0902":{"draws":15,"losses":18,"wins":3},"recursive/flint-v1.0":{"draws":4,"losses":6,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":17,"wins":1},"stealth/ox-alpha":{"draws":28,"losses":61,"wins":11},"stealth/space-bunny-alpha":{"draws":12,"losses":12,"wins":4},"stepfun/step-3.7-flash":{"draws":8,"losses":13,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":4},"tencent/hy4-preview":{"draws":14,"losses":18,"wins":2},"thinkingmachines/inkling":{"draws":17,"losses":20,"wins":7},"thinkingmachines/inkling-small":{"draws":14,"losses":13,"wins":9},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":11,"losses":23,"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":24,"losses":27,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":0},"z-ai/glm-5.2":{"draws":30,"losses":36,"wins":6},"z-ai/glm-5.3":{"draws":8,"losses":24,"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}},"inception/mercury-3":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":5,"wins":14},"claude-fable-5":{"draws":10,"losses":14,"wins":6},"claude-fable-5-1":{"draws":2,"losses":30,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":9,"wins":12},"claude-opus-4-5":{"draws":15,"losses":12,"wins":21},"claude-opus-4-8":{"draws":9,"losses":9,"wins":8},"claude-opus-5":{"draws":5,"losses":37,"wins":8},"claude-opus-5-5":{"draws":2,"losses":31,"wins":1},"claude-sonnet-5":{"draws":11,"losses":6,"wins":13},"claude-sonnet-5-5":{"draws":7,"losses":15,"wins":8},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":29},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":3,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":7,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":11,"wins":6},"elorian/glimpse":{"draws":2,"losses":7,"wins":7},"fireworks/ember-1":{"draws":13,"losses":7,"wins":10},"gemini-3.1-pro-preview":{"draws":9,"losses":4,"wins":17},"gemini-4-argon":{"draws":5,"losses":24,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":10,"losses":7,"wins":19},"google/gemini-3.5-flash-lite":{"draws":16,"losses":4,"wins":30},"google/gemini-3.6-flash":{"draws":12,"losses":24,"wins":20},"google/gemini-3.8-flash":{"draws":8,"losses":10,"wins":12},"google/gemma-4-31b-it":{"draws":7,"losses":0,"wins":9},"gpt-4.1":{"draws":4,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":4,"wins":17},"gpt-5.4":{"draws":7,"losses":12,"wins":9},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":14},"gpt-5.4-nano":{"draws":11,"losses":6,"wins":15},"gpt-5.5":{"draws":10,"losses":8,"wins":8},"gpt-5.6-luna":{"draws":12,"losses":4,"wins":14},"gpt-5.6-sol":{"draws":6,"losses":16,"wins":8},"gpt-5.6-terra":{"draws":10,"losses":6,"wins":14},"gpt-6-astra":{"draws":4,"losses":24,"wins":2},"gpt-6-luna":{"draws":9,"losses":6,"wins":15},"gpt-6-sol":{"draws":6,"losses":17,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":20,"wins":6},"gpt-6.1-terra":{"draws":8,"losses":18,"wins":4},"gpt-6.1-terra-pro":{"draws":8,"losses":18,"wins":4},"inception/mercury-2.5-preview":{"draws":10,"losses":0,"wins":10},"inception/mercury-3":{"draws":6,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":16},"inclusionai/ling-3.1-flash":{"draws":0,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":0,"wins":22},"meta/muse-glimmer-30b":{"draws":9,"losses":1,"wins":14},"meta/muse-spark-1.2":{"draws":9,"losses":10,"wins":9},"meta/muse-spark-1.3":{"draws":7,"losses":15,"wins":8},"meta/muse-spark-open":{"draws":8,"losses":12,"wins":8},"meta/muse-wonder":{"draws":7,"losses":11,"wins":12},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":9},"minimax/minimax-m3.1-flash":{"draws":7,"losses":5,"wins":12},"mistralai/mistral-large-4-0":{"draws":6,"losses":0,"wins":12},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":4,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":20,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":2,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"wins":8},"o3":{"draws":5,"losses":3,"wins":30},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":13},"poolside/laguna-s-2.1":{"draws":15,"losses":1,"wins":16},"qwen/qwen3.7-max":{"draws":7,"losses":1,"wins":10},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":9,"wins":11},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":11},"qwen/qwen3.8-flash":{"draws":6,"losses":7,"wins":7},"qwen/qwen3.8-max":{"draws":10,"losses":9,"wins":11},"qwen/qwen3.8-max-0902":{"draws":9,"losses":11,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":1,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":4,"wins":12},"stealth/ox-alpha":{"draws":28,"losses":34,"wins":42},"stealth/space-bunny-alpha":{"draws":8,"losses":2,"wins":10},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":15},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":7},"tencent/hy4-preview":{"draws":9,"losses":9,"wins":10},"thinkingmachines/inkling":{"draws":17,"losses":2,"wins":19},"thinkingmachines/inkling-small":{"draws":9,"losses":1,"wins":20},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":9,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":10},"x-ai/grok-4.6":{"draws":13,"losses":9,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":18,"wins":5},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":5},"xiaomi/mimo-v2.5":{"draws":18,"losses":2,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":5,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":12,"wins":5},"z-ai/glm-5.2":{"draws":22,"losses":7,"wins":31},"z-ai/glm-5.3":{"draws":6,"losses":13,"wins":9},"z-ai/glm-5.3-flash":{"draws":6,"losses":10,"wins":14},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":12}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":17},"claude-fable-5":{"draws":8,"losses":32,"wins":2},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":17,"wins":8},"claude-opus-4-5":{"draws":27,"losses":28,"wins":13},"claude-opus-4-8":{"draws":10,"losses":19,"wins":9},"claude-opus-5":{"draws":10,"losses":64,"wins":6},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":12,"losses":21,"wins":9},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":12},"cohere/north-mini-code":{"draws":6,"losses":5,"wins":5},"deepseek/deepseek-v4-flash":{"draws":25,"losses":16,"wins":21},"deepseek/deepseek-v4-pro":{"draws":12,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":18,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":16,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":28,"wins":4},"elorian/glimpse":{"draws":5,"losses":12,"wins":7},"fireworks/ember-1":{"draws":13,"losses":18,"wins":11},"gemini-3.1-pro-preview":{"draws":11,"losses":18,"wins":13},"gemini-4-argon":{"draws":5,"losses":36,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":14},"google/gemini-3.5-flash":{"draws":15,"losses":24,"wins":13},"google/gemini-3.5-flash-lite":{"draws":21,"losses":21,"wins":30},"google/gemini-3.6-flash":{"draws":24,"losses":34,"wins":22},"google/gemini-3.8-flash":{"draws":10,"losses":26,"wins":6},"google/gemma-4-31b-it":{"draws":15,"losses":4,"wins":5},"gpt-4.1":{"draws":5,"losses":6,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":14,"losses":16,"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":19,"losses":18,"wins":3},"gpt-5.6-luna":{"draws":16,"losses":14,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":30,"wins":5},"gpt-5.6-terra":{"draws":18,"losses":15,"wins":7},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":15,"losses":18,"wins":9},"gpt-6-sol":{"draws":4,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"gpt-6.1-terra":{"draws":5,"losses":35,"wins":2},"gpt-6.1-terra-pro":{"draws":4,"losses":34,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":6,"wins":10},"inception/mercury-3":{"draws":9,"losses":12,"wins":7},"inclusionai/ling-3.0-flash":{"draws":19,"losses":6,"wins":3},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":17,"losses":10,"wins":17},"meta/muse-glimmer-30b":{"draws":15,"losses":2,"wins":9},"meta/muse-spark-1.2":{"draws":14,"losses":21,"wins":7},"meta/muse-spark-1.3":{"draws":12,"losses":22,"wins":8},"meta/muse-spark-open":{"draws":11,"losses":20,"wins":11},"meta/muse-wonder":{"draws":12,"losses":25,"wins":5},"minimax/minimax-m3":{"draws":10,"losses":4,"wins":10},"minimax/minimax-m3.1-flash":{"draws":9,"losses":15,"wins":12},"mistralai/mistral-large-4-0":{"draws":10,"losses":11,"wins":7},"mistralai/mistral-medium-3-5":{"draws":12,"losses":2,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":21,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":34,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":11,"wins":4},"o3":{"draws":9,"losses":29,"wins":16},"openai/gpt-oss-120b":{"draws":12,"losses":12,"wins":14},"poolside/laguna-s-2.1":{"draws":18,"losses":12,"wins":12},"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":8,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":11},"qwen/qwen3.8-max-0902":{"draws":12,"losses":24,"wins":6},"recursive/flint-v1.0":{"draws":5,"losses":2,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":18,"wins":8},"stealth/ox-alpha":{"draws":33,"losses":81,"wins":28},"stealth/space-bunny-alpha":{"draws":11,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":18},"stepfun/step-5-preview":{"draws":0,"losses":10,"wins":4},"tencent/hy3-preview":{"draws":9,"losses":9,"wins":6},"tencent/hy4-preview":{"draws":15,"losses":20,"wins":5},"thinkingmachines/inkling":{"draws":21,"losses":14,"wins":23},"thinkingmachines/inkling-small":{"draws":18,"losses":4,"wins":20},"unbiased/pareto-26.10":{"draws":2,"losses":12,"wins":0},"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":10,"losses":28,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":29,"wins":7},"x-ai/grok-build-0.1":{"draws":8,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":22,"losses":16,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":2,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":17,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":6},"z-ai/glm-5.2":{"draws":39,"losses":30,"wins":15},"z-ai/glm-5.3":{"draws":11,"losses":25,"wins":4},"z-ai/glm-5.3-flash":{"draws":10,"losses":25,"wins":7},"z-ai/glm-5.3-flashx":{"draws":8,"losses":24,"wins":10}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":9,"wins":28},"claude-fable-5":{"draws":6,"losses":28,"wins":14},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":9,"losses":19,"wins":18},"claude-opus-4-5":{"draws":18,"losses":18,"wins":42},"claude-opus-4-8":{"draws":5,"losses":16,"wins":23},"claude-opus-5":{"draws":13,"losses":60,"wins":9},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":11,"losses":7,"wins":30},"claude-sonnet-5-5":{"draws":7,"losses":21,"wins":20},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":15},"deepseek/deepseek-v4-flash":{"draws":15,"losses":9,"wins":48},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":8,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":15,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":19,"wins":20},"elorian/glimpse":{"draws":5,"losses":9,"wins":12},"fireworks/ember-1":{"draws":10,"losses":15,"wins":23},"gemini-3.1-pro-preview":{"draws":8,"losses":16,"wins":24},"gemini-4-argon":{"draws":3,"losses":41,"wins":4},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":7,"losses":19,"wins":34},"google/gemini-3.5-flash-lite":{"draws":15,"losses":18,"wins":51},"google/gemini-3.6-flash":{"draws":19,"losses":26,"wins":47},"google/gemini-3.8-flash":{"draws":5,"losses":19,"wins":24},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":16},"gpt-4.1":{"draws":8,"losses":2,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":7,"losses":5,"wins":30},"gpt-5.4":{"draws":8,"losses":21,"wins":17},"gpt-5.4-mini":{"draws":7,"losses":5,"wins":20},"gpt-5.4-nano":{"draws":6,"losses":15,"wins":27},"gpt-5.5":{"draws":7,"losses":21,"wins":16},"gpt-5.6-luna":{"draws":13,"losses":11,"wins":24},"gpt-5.6-sol":{"draws":8,"losses":26,"wins":14},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":24},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":11,"losses":12,"wins":25},"gpt-6-sol":{"draws":6,"losses":31,"wins":11},"gpt-6.1-sol":{"draws":3,"losses":35,"wins":10},"gpt-6.1-terra":{"draws":4,"losses":40,"wins":4},"gpt-6.1-terra-pro":{"draws":4,"losses":40,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":9,"losses":7,"wins":18},"inception/mercury-3":{"draws":8,"losses":5,"wins":21},"inclusionai/ling-3.0-flash":{"draws":7,"losses":3,"wins":24},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":6,"losses":3,"wins":43},"meta/muse-glimmer-30b":{"draws":10,"losses":4,"wins":28},"meta/muse-spark-1.2":{"draws":8,"losses":7,"wins":15},"meta/muse-spark-1.3":{"draws":10,"losses":18,"wins":20},"meta/muse-spark-open":{"draws":6,"losses":20,"wins":20},"meta/muse-wonder":{"draws":9,"losses":20,"wins":19},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":20},"minimax/minimax-m3.1-flash":{"draws":7,"losses":12,"wins":23},"mistralai/mistral-large-4-0":{"draws":5,"losses":7,"wins":18},"mistralai/mistral-medium-3-5":{"draws":5,"losses":4,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":15,"wins":25},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":37,"wins":6},"nex-agi/nex-n2-pro":{"draws":3,"losses":4,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":7,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":2,"wins":14},"o3":{"draws":5,"losses":22,"wins":39},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":27},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":34},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":18},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":15,"wins":22},"qwen/qwen3.8-27b":{"draws":6,"losses":8,"wins":20},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":20},"qwen/qwen3.8-max":{"draws":12,"losses":14,"wins":22},"qwen/qwen3.8-max-0902":{"draws":11,"losses":16,"wins":21},"recursive/flint-v1.0":{"draws":1,"losses":1,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":13,"wins":23},"stealth/ox-alpha":{"draws":23,"losses":60,"wins":75},"stealth/space-bunny-alpha":{"draws":8,"losses":10,"wins":20},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":2,"wins":17},"tencent/hy4-preview":{"draws":7,"losses":16,"wins":23},"thinkingmachines/inkling":{"draws":12,"losses":12,"wins":40},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":29},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":8,"losses":24,"wins":16},"x-ai/grok-4.7":{"draws":2,"losses":29,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":18,"losses":6,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":11,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":15,"wins":13},"z-ai/glm-5.2":{"draws":21,"losses":24,"wins":51},"z-ai/glm-5.3":{"draws":7,"losses":18,"wins":21},"z-ai/glm-5.3-flash":{"draws":5,"losses":18,"wins":25},"z-ai/glm-5.3-flashx":{"draws":10,"losses":18,"wins":20}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":6,"wins":33},"claude-fable-5":{"draws":6,"losses":23,"wins":19},"claude-fable-5-1":{"draws":3,"losses":43,"wins":8},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":13,"losses":9,"wins":56},"claude-opus-4-8":{"draws":7,"losses":10,"wins":27},"claude-opus-5":{"draws":9,"losses":52,"wins":21},"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":20,"wins":23},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":9,"losses":2,"wins":61},"deepseek/deepseek-v4-pro":{"draws":3,"losses":6,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":8,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":10,"wins":28},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":18,"wins":24},"elorian/glimpse":{"draws":3,"losses":6,"wins":17},"fireworks/ember-1":{"draws":8,"losses":7,"wins":33},"gemini-3.1-pro-preview":{"draws":6,"losses":11,"wins":31},"gemini-4-argon":{"draws":2,"losses":35,"wins":11},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":25},"google/gemini-3.5-flash":{"draws":8,"losses":12,"wins":40},"google/gemini-3.5-flash-lite":{"draws":13,"losses":5,"wins":66},"google/gemini-3.6-flash":{"draws":9,"losses":22,"wins":61},"google/gemini-3.8-flash":{"draws":11,"losses":14,"wins":23},"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":3,"losses":1,"wins":28},"gpt-5.4-nano":{"draws":3,"losses":6,"wins":39},"gpt-5.5":{"draws":6,"losses":12,"wins":26},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":33},"gpt-5.6-sol":{"draws":7,"losses":14,"wins":27},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":30},"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},"gpt-6.1-terra":{"draws":4,"losses":35,"wins":9},"gpt-6.1-terra-pro":{"draws":4,"losses":37,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":4,"wins":26},"inception/mercury-3":{"draws":4,"losses":4,"wins":24},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":30},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":6},"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":7,"losses":10,"wins":29},"meta/muse-spark-1.3":{"draws":6,"losses":3,"wins":23},"meta/muse-spark-open":{"draws":5,"losses":9,"wins":32},"meta/muse-wonder":{"draws":8,"losses":22,"wins":18},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":23},"minimax/minimax-m3.1-flash":{"draws":5,"losses":6,"wins":31},"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":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":10,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":31,"wins":11},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":3,"wins":17},"o3":{"draws":3,"losses":8,"wins":55},"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":4,"losses":2,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":13,"wins":27},"qwen/qwen3.8-27b":{"draws":6,"losses":6,"wins":22},"qwen/qwen3.8-flash":{"draws":4,"losses":8,"wins":20},"qwen/qwen3.8-max":{"draws":6,"losses":13,"wins":29},"qwen/qwen3.8-max-0902":{"draws":11,"losses":15,"wins":22},"recursive/flint-v1.0":{"draws":0,"losses":2,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":8,"wins":31},"stealth/ox-alpha":{"draws":24,"losses":31,"wins":103},"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":1,"losses":4,"wins":7},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":19},"tencent/hy4-preview":{"draws":7,"losses":12,"wins":27},"thinkingmachines/inkling":{"draws":5,"losses":6,"wins":53},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":43},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":12,"wins":2},"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":10,"losses":13,"wins":25},"x-ai/grok-4.7":{"draws":5,"losses":23,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":13},"xiaomi/mimo-v2.5":{"draws":9,"losses":4,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":16},"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":11,"losses":14,"wins":71},"z-ai/glm-5.3":{"draws":9,"losses":16,"wins":21},"z-ai/glm-5.3-flash":{"draws":8,"losses":15,"wins":25},"z-ai/glm-5.3-flashx":{"draws":5,"losses":14,"wins":29}},"meta/muse-spark-open":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":26},"claude-fable-5":{"draws":4,"losses":29,"wins":15},"claude-fable-5-1":{"draws":3,"losses":42,"wins":9},"claude-haiku-5-5":{"draws":6,"losses":22,"wins":18},"claude-opus-4-5":{"draws":18,"losses":16,"wins":44},"claude-opus-4-8":{"draws":9,"losses":16,"wins":19},"claude-opus-5":{"draws":5,"losses":62,"wins":15},"claude-opus-5-5":{"draws":3,"losses":39,"wins":10},"claude-sonnet-5":{"draws":10,"losses":10,"wins":28},"claude-sonnet-5-5":{"draws":6,"losses":19,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":8,"wins":51},"deepseek/deepseek-v4-pro":{"draws":10,"losses":7,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":13,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":16,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":20,"wins":18},"elorian/glimpse":{"draws":2,"losses":12,"wins":10},"fireworks/ember-1":{"draws":8,"losses":15,"wins":25},"gemini-3.1-pro-preview":{"draws":7,"losses":11,"wins":28},"gemini-4-argon":{"draws":6,"losses":30,"wins":10},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":11,"losses":16,"wins":33},"google/gemini-3.5-flash-lite":{"draws":11,"losses":14,"wins":59},"google/gemini-3.6-flash":{"draws":10,"losses":31,"wins":49},"google/gemini-3.8-flash":{"draws":8,"losses":16,"wins":24},"google/gemma-4-31b-it":{"draws":7,"losses":3,"wins":18},"gpt-4.1":{"draws":3,"losses":2,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":2},"gpt-5":{"draws":6,"losses":8,"wins":28},"gpt-5.4":{"draws":9,"losses":16,"wins":21},"gpt-5.4-mini":{"draws":9,"losses":6,"wins":17},"gpt-5.4-nano":{"draws":7,"losses":8,"wins":33},"gpt-5.5":{"draws":7,"losses":13,"wins":24},"gpt-5.6-luna":{"draws":12,"losses":10,"wins":26},"gpt-5.6-sol":{"draws":8,"losses":20,"wins":20},"gpt-5.6-terra":{"draws":14,"losses":6,"wins":26},"gpt-6-astra":{"draws":2,"losses":42,"wins":2},"gpt-6-luna":{"draws":8,"losses":13,"wins":23},"gpt-6-sol":{"draws":4,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":7},"gpt-6.1-terra":{"draws":1,"losses":36,"wins":7},"gpt-6.1-terra-pro":{"draws":4,"losses":34,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":3,"wins":22},"inception/mercury-3":{"draws":3,"losses":9,"wins":16},"inclusionai/ling-3.0-flash":{"draws":3,"losses":4,"wins":27},"inclusionai/ling-3.1-flash":{"draws":2,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":12,"losses":7,"wins":33},"meta/muse-glimmer-30b":{"draws":11,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":8,"losses":11,"wins":25},"meta/muse-spark-1.3":{"draws":6,"losses":16,"wins":24},"meta/muse-spark-open":{"draws":4,"losses":10,"wins":14},"meta/muse-wonder":{"draws":9,"losses":19,"wins":18},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":20},"minimax/minimax-m3.1-flash":{"draws":7,"losses":12,"wins":21},"mistralai/mistral-large-4-0":{"draws":4,"losses":9,"wins":15},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":35,"wins":10},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":7,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":2,"wins":15},"o3":{"draws":3,"losses":10,"wins":51},"openai/gpt-oss-120b":{"draws":10,"losses":4,"wins":28},"poolside/laguna-s-2.1":{"draws":8,"losses":4,"wins":34},"qwen/qwen3.7-max":{"draws":5,"losses":6,"wins":17},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":17,"wins":23},"qwen/qwen3.8-27b":{"draws":6,"losses":7,"wins":19},"qwen/qwen3.8-flash":{"draws":8,"losses":11,"wins":13},"qwen/qwen3.8-max":{"draws":11,"losses":14,"wins":23},"qwen/qwen3.8-max-0902":{"draws":10,"losses":17,"wins":21},"recursive/flint-v1.0":{"draws":1,"losses":3,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":10,"wins":23},"stealth/ox-alpha":{"draws":30,"losses":42,"wins":86},"stealth/space-bunny-alpha":{"draws":8,"losses":7,"wins":23},"stepfun/step-3.7-flash":{"draws":1,"losses":7,"wins":24},"stepfun/step-5-preview":{"draws":1,"losses":4,"wins":5},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":19},"tencent/hy4-preview":{"draws":6,"losses":17,"wins":23},"thinkingmachines/inkling":{"draws":15,"losses":7,"wins":42},"thinkingmachines/inkling-small":{"draws":9,"losses":7,"wins":32},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":5,"wins":7},"x-ai/grok-4.5":{"draws":5,"losses":23,"wins":20},"x-ai/grok-4.6":{"draws":10,"losses":22,"wins":16},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":11},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":16,"losses":11,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":7,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":15},"z-ai/glm-5.2":{"draws":20,"losses":21,"wins":55},"z-ai/glm-5.3":{"draws":6,"losses":28,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":21,"wins":20},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":22}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":2,"wins":35},"claude-fable-5":{"draws":6,"losses":16,"wins":26},"claude-fable-5-1":{"draws":6,"losses":34,"wins":14},"claude-haiku-5-5":{"draws":7,"losses":6,"wins":33},"claude-opus-4-5":{"draws":9,"losses":9,"wins":60},"claude-opus-4-8":{"draws":9,"losses":8,"wins":27},"claude-opus-5":{"draws":9,"losses":35,"wins":38},"claude-opus-5-5":{"draws":4,"losses":36,"wins":12},"claude-sonnet-5":{"draws":6,"losses":5,"wins":37},"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":4,"wins":60},"deepseek/deepseek-v4-pro":{"draws":5,"losses":4,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":4,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":5,"wins":32},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":11,"wins":24},"elorian/glimpse":{"draws":4,"losses":4,"wins":18},"fireworks/ember-1":{"draws":12,"losses":5,"wins":31},"gemini-3.1-pro-preview":{"draws":6,"losses":8,"wins":34},"gemini-4-argon":{"draws":6,"losses":23,"wins":19},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":7,"losses":4,"wins":49},"google/gemini-3.5-flash-lite":{"draws":9,"losses":5,"wins":70},"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":6,"losses":7,"wins":33},"gpt-5.4-mini":{"draws":6,"losses":1,"wins":25},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":42},"gpt-5.5":{"draws":7,"losses":10,"wins":27},"gpt-5.6-luna":{"draws":7,"losses":6,"wins":35},"gpt-5.6-sol":{"draws":5,"losses":13,"wins":30},"gpt-5.6-terra":{"draws":9,"losses":4,"wins":33},"gpt-6-astra":{"draws":7,"losses":35,"wins":6},"gpt-6-luna":{"draws":7,"losses":5,"wins":36},"gpt-6-sol":{"draws":3,"losses":23,"wins":22},"gpt-6.1-sol":{"draws":6,"losses":27,"wins":15},"gpt-6.1-terra":{"draws":10,"losses":22,"wins":16},"gpt-6.1-terra-pro":{"draws":10,"losses":24,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":25},"inception/mercury-3":{"draws":8,"losses":1,"wins":23},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":11},"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":5,"wins":37},"meta/muse-spark-open":{"draws":8,"losses":9,"wins":31},"meta/muse-wonder":{"draws":6,"losses":7,"wins":19},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":21},"minimax/minimax-m3.1-flash":{"draws":4,"losses":1,"wins":37},"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":5},"moonshotai/kimi-k3":{"draws":7,"losses":6,"wins":33},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":20,"wins":21},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":1,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":19},"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":5,"losses":11,"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},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":4,"wins":35},"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":2,"losses":0,"wins":10},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":22},"tencent/hy4-preview":{"draws":6,"losses":7,"wins":33},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":52},"thinkingmachines/inkling-small":{"draws":6,"losses":2,"wins":40},"unbiased/pareto-26.10":{"draws":4,"losses":10,"wins":2},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"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":13,"losses":7,"wins":28},"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":2,"losses":0,"wins":18},"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":14,"losses":5,"wins":77},"z-ai/glm-5.3":{"draws":2,"losses":15,"wins":29},"z-ai/glm-5.3-flash":{"draws":12,"losses":9,"wins":27},"z-ai/glm-5.3-flashx":{"draws":7,"losses":7,"wins":34}},"minimax/minimax-m3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":10,"wins":20},"claude-fable-5":{"draws":9,"losses":24,"wins":9},"claude-fable-5-1":{"draws":2,"losses":44,"wins":2},"claude-haiku-5-5":{"draws":7,"losses":26,"wins":7},"claude-opus-4-5":{"draws":20,"losses":24,"wins":24},"claude-opus-4-8":{"draws":12,"losses":15,"wins":11},"claude-opus-5":{"draws":17,"losses":45,"wins":8},"claude-opus-5-5":{"draws":2,"losses":40,"wins":0},"claude-sonnet-5":{"draws":12,"losses":16,"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":15,"losses":18,"wins":29},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":18,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":24,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":19,"wins":9},"elorian/glimpse":{"draws":7,"losses":10,"wins":5},"fireworks/ember-1":{"draws":9,"losses":20,"wins":13},"gemini-3.1-pro-preview":{"draws":12,"losses":15,"wins":15},"gemini-4-argon":{"draws":6,"losses":31,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":18},"google/gemini-3.5-flash":{"draws":11,"losses":20,"wins":21},"google/gemini-3.5-flash-lite":{"draws":20,"losses":24,"wins":30},"google/gemini-3.6-flash":{"draws":20,"losses":40,"wins":22},"google/gemini-3.8-flash":{"draws":9,"losses":25,"wins":8},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":12},"gpt-4.1":{"draws":4,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":9,"losses":11,"wins":16},"gpt-5.4":{"draws":7,"losses":20,"wins":13},"gpt-5.4-mini":{"draws":12,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":7,"losses":18,"wins":15},"gpt-5.5":{"draws":15,"losses":10,"wins":13},"gpt-5.6-luna":{"draws":8,"losses":17,"wins":17},"gpt-5.6-sol":{"draws":4,"losses":27,"wins":11},"gpt-5.6-terra":{"draws":9,"losses":15,"wins":16},"gpt-6-astra":{"draws":1,"losses":41,"wins":0},"gpt-6-luna":{"draws":10,"losses":15,"wins":17},"gpt-6-sol":{"draws":5,"losses":34,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":39,"wins":1},"gpt-6.1-terra":{"draws":4,"losses":36,"wins":2},"gpt-6.1-terra-pro":{"draws":5,"losses":37,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":14},"inception/mercury-3":{"draws":6,"losses":12,"wins":8},"inclusionai/ling-3.0-flash":{"draws":8,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":10,"losses":10,"wins":24},"meta/muse-glimmer-30b":{"draws":11,"losses":6,"wins":19},"meta/muse-spark-1.2":{"draws":10,"losses":14,"wins":16},"meta/muse-spark-1.3":{"draws":8,"losses":25,"wins":9},"meta/muse-spark-open":{"draws":5,"losses":21,"wins":14},"meta/muse-wonder":{"draws":9,"losses":25,"wins":8},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":13},"minimax/minimax-m3.1-flash":{"draws":6,"losses":12,"wins":8},"mistralai/mistral-large-4-0":{"draws":7,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":17,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":34,"wins":6},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":7,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":5,"wins":8},"o3":{"draws":8,"losses":23,"wins":25},"openai/gpt-oss-120b":{"draws":9,"losses":9,"wins":18},"poolside/laguna-s-2.1":{"draws":8,"losses":13,"wins":17},"qwen/qwen3.7-max":{"draws":4,"losses":11,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":18,"wins":13},"qwen/qwen3.8-27b":{"draws":7,"losses":17,"wins":8},"qwen/qwen3.8-flash":{"draws":11,"losses":7,"wins":10},"qwen/qwen3.8-max":{"draws":10,"losses":17,"wins":15},"qwen/qwen3.8-max-0902":{"draws":14,"losses":19,"wins":9},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":12,"wins":16},"stealth/ox-alpha":{"draws":28,"losses":73,"wins":41},"stealth/space-bunny-alpha":{"draws":9,"losses":10,"wins":15},"stepfun/step-3.7-flash":{"draws":4,"losses":10,"wins":16},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":5,"wins":10},"tencent/hy4-preview":{"draws":11,"losses":16,"wins":13},"thinkingmachines/inkling":{"draws":15,"losses":15,"wins":28},"thinkingmachines/inkling-small":{"draws":13,"losses":10,"wins":19},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":10,"losses":22,"wins":10},"x-ai/grok-4.6":{"draws":8,"losses":23,"wins":11},"x-ai/grok-4.7":{"draws":4,"losses":26,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":16,"losses":17,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":14,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":18,"wins":5},"z-ai/glm-5.2":{"draws":23,"losses":24,"wins":37},"z-ai/glm-5.3":{"draws":8,"losses":22,"wins":10},"z-ai/glm-5.3-flash":{"draws":7,"losses":25,"wins":10},"z-ai/glm-5.3-flashx":{"draws":8,"losses":26,"wins":8}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":10,"wins":23},"claude-fable-5":{"draws":12,"losses":24,"wins":12},"claude-fable-5-1":{"draws":3,"losses":45,"wins":6},"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":14,"losses":56,"wins":12},"claude-opus-5-5":{"draws":10,"losses":38,"wins":4},"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":17,"losses":8,"wins":47},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":22,"wins":19},"elorian/glimpse":{"draws":7,"losses":6,"wins":13},"fireworks/ember-1":{"draws":10,"losses":14,"wins":24},"gemini-3.1-pro-preview":{"draws":7,"losses":15,"wins":26},"gemini-4-argon":{"draws":7,"losses":33,"wins":8},"google/gemini-3.1-flash-lite":{"draws":10,"losses":0,"wins":22},"google/gemini-3.5-flash":{"draws":18,"losses":15,"wins":27},"google/gemini-3.5-flash-lite":{"draws":17,"losses":13,"wins":54},"google/gemini-3.6-flash":{"draws":14,"losses":31,"wins":47},"google/gemini-3.8-flash":{"draws":15,"losses":15,"wins":18},"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":12,"losses":5,"wins":15},"gpt-5.4-nano":{"draws":8,"losses":10,"wins":30},"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":6,"losses":36,"wins":6},"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},"gpt-6.1-terra":{"draws":9,"losses":31,"wins":8},"gpt-6.1-terra-pro":{"draws":6,"losses":35,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"inception/mercury-3":{"draws":6,"losses":14,"wins":12},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":4,"losses":2,"wins":4},"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":7,"losses":21,"wins":18},"meta/muse-spark-1.3":{"draws":13,"losses":18,"wins":17},"meta/muse-spark-open":{"draws":7,"losses":25,"wins":14},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":19},"minimax/minimax-m3.1-flash":{"draws":6,"losses":10,"wins":26},"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":2,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":15,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":36,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":11,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":3,"wins":12},"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},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":13,"wins":20},"stealth/ox-alpha":{"draws":49,"losses":53,"wins":56},"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":2,"losses":5,"wins":7},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":8,"losses":18,"wins":20},"thinkingmachines/inkling":{"draws":18,"losses":7,"wins":39},"thinkingmachines/inkling-small":{"draws":14,"losses":3,"wins":31},"unbiased/pareto-26.10":{"draws":2,"losses":13,"wins":1},"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":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":25,"losses":8,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":15},"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":5,"losses":28,"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":15,"losses":12,"wins":11},"claude-fable-5":{"draws":12,"losses":26,"wins":4},"claude-fable-5-1":{"draws":3,"losses":44,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":28,"wins":2},"claude-opus-4-5":{"draws":18,"losses":40,"wins":10},"claude-opus-4-8":{"draws":10,"losses":26,"wins":2},"claude-opus-5":{"draws":13,"losses":51,"wins":6},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":13,"losses":20,"wins":9},"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":20,"losses":22,"wins":20},"deepseek/deepseek-v4-pro":{"draws":12,"losses":22,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":20,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":27,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":30,"wins":2},"elorian/glimpse":{"draws":5,"losses":12,"wins":5},"fireworks/ember-1":{"draws":11,"losses":25,"wins":6},"gemini-3.1-pro-preview":{"draws":11,"losses":21,"wins":10},"gemini-4-argon":{"draws":1,"losses":39,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":15},"google/gemini-3.5-flash":{"draws":13,"losses":28,"wins":11},"google/gemini-3.5-flash-lite":{"draws":23,"losses":31,"wins":20},"google/gemini-3.6-flash":{"draws":20,"losses":50,"wins":10},"google/gemini-3.8-flash":{"draws":9,"losses":28,"wins":5},"google/gemma-4-31b-it":{"draws":11,"losses":10,"wins":5},"gpt-4.1":{"draws":4,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":17,"wins":9},"gpt-5.4":{"draws":12,"losses":23,"wins":5},"gpt-5.4-mini":{"draws":9,"losses":14,"wins":5},"gpt-5.4-nano":{"draws":7,"losses":20,"wins":13},"gpt-5.5":{"draws":12,"losses":22,"wins":4},"gpt-5.6-luna":{"draws":15,"losses":23,"wins":4},"gpt-5.6-sol":{"draws":9,"losses":31,"wins":2},"gpt-5.6-terra":{"draws":10,"losses":22,"wins":8},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":12,"losses":25,"wins":5},"gpt-6-sol":{"draws":4,"losses":35,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":0},"gpt-6.1-terra":{"draws":3,"losses":36,"wins":3},"gpt-6.1-terra-pro":{"draws":4,"losses":38,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":8,"wins":13},"inception/mercury-3":{"draws":8,"losses":16,"wins":4},"inclusionai/ling-3.0-flash":{"draws":10,"losses":8,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":14,"losses":21,"wins":13},"meta/muse-glimmer-30b":{"draws":12,"losses":16,"wins":8},"meta/muse-spark-1.2":{"draws":12,"losses":20,"wins":8},"meta/muse-spark-1.3":{"draws":9,"losses":30,"wins":3},"meta/muse-spark-open":{"draws":12,"losses":24,"wins":6},"meta/muse-wonder":{"draws":8,"losses":31,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":8},"minimax/minimax-m3.1-flash":{"draws":11,"losses":18,"wins":7},"mistralai/mistral-large-4-0":{"draws":11,"losses":12,"wins":3},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":39,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":6,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":11,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":11,"wins":2},"o3":{"draws":12,"losses":36,"wins":8},"openai/gpt-oss-120b":{"draws":15,"losses":10,"wins":13},"poolside/laguna-s-2.1":{"draws":14,"losses":18,"wins":8},"qwen/qwen3.7-max":{"draws":8,"losses":13,"wins":3},"qwen/qwen3.7-plus":{"draws":8,"losses":7,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":27,"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":14,"losses":22,"wins":6},"qwen/qwen3.8-max-0902":{"draws":11,"losses":25,"wins":6},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":24,"wins":5},"stealth/ox-alpha":{"draws":35,"losses":80,"wins":27},"stealth/space-bunny-alpha":{"draws":8,"losses":19,"wins":7},"stepfun/step-3.7-flash":{"draws":11,"losses":12,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":21,"wins":7},"thinkingmachines/inkling":{"draws":16,"losses":22,"wins":16},"thinkingmachines/inkling-small":{"draws":17,"losses":18,"wins":7},"unbiased/pareto-26.10":{"draws":2,"losses":12,"wins":0},"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":10,"losses":28,"wins":4},"x-ai/grok-4.6":{"draws":10,"losses":29,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":1},"x-ai/grok-build-0.1":{"draws":5,"losses":6,"wins":3},"xiaomi/mimo-v2.5":{"draws":24,"losses":22,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":8,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":20,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":32,"losses":39,"wins":13},"z-ai/glm-5.3":{"draws":7,"losses":33,"wins":2},"z-ai/glm-5.3-flash":{"draws":8,"losses":29,"wins":5},"z-ai/glm-5.3-flashx":{"draws":10,"losses":27,"wins":5}},"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":17,"wins":13},"claude-opus-4-5":{"draws":19,"losses":23,"wins":26},"claude-opus-4-8":{"draws":8,"losses":17,"wins":13},"claude-opus-5":{"draws":12,"losses":52,"wins":16},"claude-opus-5-5":{"draws":3,"losses":40,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":21,"wins":15},"elorian/glimpse":{"draws":4,"losses":7,"wins":13},"fireworks/ember-1":{"draws":13,"losses":14,"wins":15},"gemini-3.1-pro-preview":{"draws":13,"losses":10,"wins":19},"gemini-4-argon":{"draws":3,"losses":31,"wins":8},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":16},"google/gemini-3.5-flash":{"draws":17,"losses":13,"wins":22},"google/gemini-3.5-flash-lite":{"draws":27,"losses":11,"wins":34},"google/gemini-3.6-flash":{"draws":17,"losses":31,"wins":32},"google/gemini-3.8-flash":{"draws":8,"losses":19,"wins":15},"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},"gpt-6.1-terra":{"draws":2,"losses":35,"wins":5},"gpt-6.1-terra-pro":{"draws":3,"losses":36,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":3,"wins":10},"inception/mercury-3":{"draws":2,"losses":11,"wins":15},"inclusionai/ling-3.0-flash":{"draws":9,"losses":7,"wins":12},"inclusionai/ling-3.1-flash":{"draws":0,"losses":1,"wins":1},"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":5,"losses":18,"wins":19},"meta/muse-spark-1.3":{"draws":10,"losses":17,"wins":15},"meta/muse-spark-open":{"draws":8,"losses":13,"wins":19},"meta/muse-wonder":{"draws":6,"losses":27,"wins":9},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":12},"minimax/minimax-m3.1-flash":{"draws":6,"losses":11,"wins":19},"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":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":7,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":32,"wins":8},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":13,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":6,"wins":9},"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},"recursive/flint-v1.0":{"draws":3,"losses":3,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":10,"wins":19},"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":8},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":9,"losses":16,"wins":15},"thinkingmachines/inkling":{"draws":14,"losses":12,"wins":32},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":12,"wins":1},"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":21,"wins":13},"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":2,"losses":3,"wins":9},"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}},"moonshotai/kimi-k3.1-pro":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":0,"wins":41},"claude-fable-5":{"draws":2,"losses":9,"wins":37},"claude-fable-5-1":{"draws":4,"losses":30,"wins":20},"claude-haiku-5-5":{"draws":4,"losses":4,"wins":38},"claude-opus-4-5":{"draws":4,"losses":4,"wins":70},"claude-opus-4-8":{"draws":2,"losses":2,"wins":40},"claude-opus-5":{"draws":8,"losses":32,"wins":42},"claude-opus-5-5":{"draws":7,"losses":27,"wins":18},"claude-sonnet-5":{"draws":4,"losses":0,"wins":44},"claude-sonnet-5-5":{"draws":5,"losses":13,"wins":30},"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":6,"losses":3,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":1,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":3,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":5,"wins":37},"elorian/glimpse":{"draws":2,"losses":4,"wins":20},"fireworks/ember-1":{"draws":4,"losses":3,"wins":41},"gemini-3.1-pro-preview":{"draws":6,"losses":6,"wins":36},"gemini-4-argon":{"draws":8,"losses":19,"wins":21},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":52},"google/gemini-3.5-flash-lite":{"draws":5,"losses":2,"wins":77},"google/gemini-3.6-flash":{"draws":6,"losses":10,"wins":76},"google/gemini-3.8-flash":{"draws":5,"losses":7,"wins":36},"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":3,"losses":2,"wins":37},"gpt-5.4":{"draws":4,"losses":6,"wins":36},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":28},"gpt-5.4-nano":{"draws":1,"losses":1,"wins":46},"gpt-5.5":{"draws":2,"losses":8,"wins":34},"gpt-5.6-luna":{"draws":2,"losses":3,"wins":43},"gpt-5.6-sol":{"draws":7,"losses":7,"wins":34},"gpt-5.6-terra":{"draws":4,"losses":4,"wins":38},"gpt-6-astra":{"draws":8,"losses":25,"wins":15},"gpt-6-luna":{"draws":4,"losses":1,"wins":43},"gpt-6-sol":{"draws":5,"losses":14,"wins":29},"gpt-6.1-sol":{"draws":6,"losses":26,"wins":16},"gpt-6.1-terra":{"draws":8,"losses":23,"wins":17},"gpt-6.1-terra-pro":{"draws":5,"losses":27,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":30},"inception/mercury-3":{"draws":5,"losses":3,"wins":24},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.1-flash":{"draws":2,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":47},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":35},"meta/muse-spark-1.2":{"draws":5,"losses":2,"wins":39},"meta/muse-spark-1.3":{"draws":3,"losses":4,"wins":41},"meta/muse-spark-open":{"draws":3,"losses":3,"wins":42},"meta/muse-wonder":{"draws":9,"losses":11,"wins":28},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"minimax/minimax-m3.1-flash":{"draws":5,"losses":2,"wins":35},"mistralai/mistral-large-4-0":{"draws":2,"losses":2,"wins":26},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":3,"losses":4,"wins":39},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":13,"wins":16},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":21},"o3":{"draws":0,"losses":1,"wins":65},"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":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":6,"wins":39},"qwen/qwen3.8-27b":{"draws":2,"losses":1,"wins":31},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":24},"qwen/qwen3.8-max":{"draws":1,"losses":6,"wins":41},"qwen/qwen3.8-max-0902":{"draws":4,"losses":3,"wins":41},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":1,"wins":42},"stealth/ox-alpha":{"draws":13,"losses":8,"wins":137},"stealth/space-bunny-alpha":{"draws":0,"losses":1,"wins":37},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":13},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":25},"tencent/hy4-preview":{"draws":5,"losses":9,"wins":32},"thinkingmachines/inkling":{"draws":7,"losses":0,"wins":57},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":44},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":4},"unbiased/pareto-26.10-preview":{"draws":3,"losses":7,"wins":6},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":37},"x-ai/grok-4.6":{"draws":1,"losses":7,"wins":40},"x-ai/grok-4.7":{"draws":7,"losses":14,"wins":21},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":67},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":1,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":8,"wins":19},"z-ai/glm-5.2":{"draws":5,"losses":3,"wins":88},"z-ai/glm-5.3":{"draws":6,"losses":11,"wins":29},"z-ai/glm-5.3-flash":{"draws":5,"losses":6,"wins":37},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":42}},"nex-agi/nex-n2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":3},"claude-fable-5":{"draws":0,"losses":4,"wins":2},"claude-fable-5-1":{"draws":0,"losses":8,"wins":0},"claude-haiku-5-5":{"draws":0,"losses":4,"wins":2},"claude-opus-4-5":{"draws":0,"losses":7,"wins":3},"claude-opus-4-8":{"draws":0,"losses":6,"wins":0},"claude-opus-5":{"draws":0,"losses":7,"wins":1},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":0,"losses":4,"wins":2},"claude-sonnet-5-5":{"draws":0,"losses":5,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":0,"losses":3,"wins":7},"deepseek/deepseek-v4-pro":{"draws":0,"losses":6,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":4,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":4,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":5,"wins":1},"elorian/glimpse":{"draws":0,"losses":3,"wins":1},"fireworks/ember-1":{"draws":0,"losses":4,"wins":2},"gemini-3.1-pro-preview":{"draws":0,"losses":4,"wins":2},"gemini-4-argon":{"draws":0,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":6},"google/gemini-3.5-flash-lite":{"draws":0,"losses":3,"wins":7},"google/gemini-3.6-flash":{"draws":0,"losses":8,"wins":4},"google/gemini-3.8-flash":{"draws":0,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":0,"losses":5,"wins":1},"gpt-5.4":{"draws":0,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":3},"gpt-5.4-nano":{"draws":0,"losses":1,"wins":5},"gpt-5.5":{"draws":0,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":4},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":0,"losses":4,"wins":2},"gpt-6-sol":{"draws":0,"losses":4,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-terra":{"draws":0,"losses":6,"wins":0},"gpt-6.1-terra-pro":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":1,"wins":3},"inception/mercury-3":{"draws":0,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":1},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":4,"wins":4},"meta/muse-glimmer-30b":{"draws":0,"losses":3,"wins":3},"meta/muse-spark-1.2":{"draws":0,"losses":5,"wins":1},"meta/muse-spark-1.3":{"draws":0,"losses":4,"wins":2},"meta/muse-spark-open":{"draws":0,"losses":5,"wins":1},"meta/muse-wonder":{"draws":0,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"minimax/minimax-m3.1-flash":{"draws":0,"losses":4,"wins":2},"mistralai/mistral-large-4-0":{"draws":0,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":3,"wins":1},"o3":{"draws":0,"losses":2,"wins":10},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-max":{"draws":0,"losses":6,"wins":0},"qwen/qwen3.8-max-0902":{"draws":0,"losses":2,"wins":4},"recursive/flint-v1.0":{"draws":0,"losses":1,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":0,"wins":6},"stealth/ox-alpha":{"draws":0,"losses":13,"wins":5},"stealth/space-bunny-alpha":{"draws":0,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":1},"tencent/hy4-preview":{"draws":0,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":8},"thinkingmachines/inkling-small":{"draws":0,"losses":2,"wins":4},"unbiased/pareto-26.10":{"draws":0,"losses":2,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":5,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":5,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":8,"wins":4},"z-ai/glm-5.3":{"draws":0,"losses":5,"wins":1},"z-ai/glm-5.3-flash":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.3-flashx":{"draws":0,"losses":5,"wins":1}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":16,"wins":15},"claude-fable-5":{"draws":10,"losses":40,"wins":4},"claude-fable-5-1":{"draws":6,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":16,"losses":31,"wins":7},"claude-opus-4-5":{"draws":35,"losses":45,"wins":10},"claude-opus-4-8":{"draws":12,"losses":33,"wins":9},"claude-opus-5":{"draws":13,"losses":83,"wins":2},"claude-opus-5-5":{"draws":2,"losses":59,"wins":1},"claude-sonnet-5":{"draws":21,"losses":26,"wins":7},"claude-sonnet-5-5":{"draws":12,"losses":33,"wins":9},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":31,"losses":30,"wins":21},"deepseek/deepseek-v4-pro":{"draws":15,"losses":25,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":24,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":25,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":40,"wins":2},"elorian/glimpse":{"draws":7,"losses":19,"wins":0},"fireworks/ember-1":{"draws":22,"losses":26,"wins":6},"gemini-3.1-pro-preview":{"draws":19,"losses":20,"wins":15},"gemini-4-argon":{"draws":6,"losses":47,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":9,"wins":19},"google/gemini-3.5-flash":{"draws":18,"losses":32,"wins":18},"google/gemini-3.5-flash-lite":{"draws":30,"losses":32,"wins":32},"google/gemini-3.6-flash":{"draws":33,"losses":56,"wins":11},"google/gemini-3.8-flash":{"draws":19,"losses":33,"wins":2},"google/gemma-4-31b-it":{"draws":21,"losses":7,"wins":6},"gpt-4.1":{"draws":8,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":25,"wins":6},"gpt-5.4":{"draws":13,"losses":32,"wins":5},"gpt-5.4-mini":{"draws":16,"losses":12,"wins":8},"gpt-5.4-nano":{"draws":17,"losses":27,"wins":18},"gpt-5.5":{"draws":20,"losses":25,"wins":3},"gpt-5.6-luna":{"draws":18,"losses":25,"wins":11},"gpt-5.6-sol":{"draws":9,"losses":43,"wins":2},"gpt-5.6-terra":{"draws":18,"losses":25,"wins":7},"gpt-6-astra":{"draws":4,"losses":50,"wins":0},"gpt-6-luna":{"draws":18,"losses":28,"wins":8},"gpt-6-sol":{"draws":6,"losses":46,"wins":2},"gpt-6.1-sol":{"draws":5,"losses":49,"wins":0},"gpt-6.1-terra":{"draws":6,"losses":48,"wins":0},"gpt-6.1-terra-pro":{"draws":6,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":19,"losses":12,"wins":11},"inception/mercury-3":{"draws":16,"losses":17,"wins":5},"inclusionai/ling-3.0-flash":{"draws":21,"losses":6,"wins":9},"inclusionai/ling-3.1-flash":{"draws":3,"losses":3,"wins":2},"meituan/longcat-2.0":{"draws":18,"losses":18,"wins":22},"meta/muse-glimmer-30b":{"draws":20,"losses":15,"wins":11},"meta/muse-spark-1.2":{"draws":16,"losses":31,"wins":5},"meta/muse-spark-1.3":{"draws":15,"losses":38,"wins":1},"meta/muse-spark-open":{"draws":16,"losses":35,"wins":3},"meta/muse-wonder":{"draws":20,"losses":33,"wins":1},"minimax/minimax-m3":{"draws":11,"losses":7,"wins":14},"minimax/minimax-m3.1-flash":{"draws":16,"losses":16,"wins":10},"mistralai/mistral-large-4-0":{"draws":12,"losses":17,"wins":5},"mistralai/mistral-medium-3-5":{"draws":13,"losses":8,"wins":13},"moonshotai/kimi-k3":{"draws":19,"losses":24,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":47,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":11,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":14,"wins":4},"o3":{"draws":15,"losses":45,"wins":14},"openai/gpt-oss-120b":{"draws":17,"losses":14,"wins":17},"poolside/laguna-s-2.1":{"draws":22,"losses":20,"wins":14},"qwen/qwen3.7-max":{"draws":16,"losses":10,"wins":8},"qwen/qwen3.7-plus":{"draws":12,"losses":14,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":26,"wins":3},"qwen/qwen3.8-27b":{"draws":14,"losses":17,"wins":5},"qwen/qwen3.8-flash":{"draws":13,"losses":18,"wins":5},"qwen/qwen3.8-max":{"draws":22,"losses":28,"wins":4},"qwen/qwen3.8-max-0902":{"draws":24,"losses":25,"wins":5},"recursive/flint-v1.0":{"draws":5,"losses":7,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":29,"wins":6},"stealth/ox-alpha":{"draws":42,"losses":93,"wins":15},"stealth/space-bunny-alpha":{"draws":16,"losses":19,"wins":7},"stepfun/step-3.7-flash":{"draws":9,"losses":13,"wins":12},"stepfun/step-5-preview":{"draws":1,"losses":11,"wins":2},"tencent/hy3-preview":{"draws":15,"losses":12,"wins":7},"tencent/hy4-preview":{"draws":16,"losses":28,"wins":6},"thinkingmachines/inkling":{"draws":23,"losses":19,"wins":26},"thinkingmachines/inkling-small":{"draws":21,"losses":15,"wins":18},"unbiased/pareto-26.10":{"draws":2,"losses":16,"wins":0},"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":14,"losses":37,"wins":3},"x-ai/grok-4.6":{"draws":20,"losses":28,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":43,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":39,"losses":30,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":8,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":24,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":25,"wins":3},"z-ai/glm-5.2":{"draws":41,"losses":49,"wins":18},"z-ai/glm-5.3":{"draws":11,"losses":40,"wins":1},"z-ai/glm-5.3-flash":{"draws":14,"losses":25,"wins":15},"z-ai/glm-5.3-flashx":{"draws":13,"losses":36,"wins":5}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":36,"wins":59},"claude-fable-5":{"draws":2,"losses":93,"wins":19},"claude-fable-5-1":{"draws":0,"losses":116,"wins":8},"claude-haiku-5-5":{"draws":11,"losses":57,"wins":44},"claude-opus-4-5":{"draws":9,"losses":123,"wins":56},"claude-opus-4-8":{"draws":7,"losses":67,"wins":36},"claude-opus-5":{"draws":6,"losses":154,"wins":12},"claude-opus-5-5":{"draws":2,"losses":122,"wins":2},"claude-sonnet-5":{"draws":6,"losses":52,"wins":56},"claude-sonnet-5-5":{"draws":4,"losses":82,"wins":28},"cohere/north-mini-code":{"draws":4,"losses":11,"wins":39},"deepseek/deepseek-v4-flash":{"draws":7,"losses":58,"wins":115},"deepseek/deepseek-v4-pro":{"draws":1,"losses":55,"wins":50},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":65,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":57,"wins":42},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":73,"wins":37},"elorian/glimpse":{"draws":4,"losses":33,"wins":23},"fireworks/ember-1":{"draws":4,"losses":72,"wins":38},"gemini-3.1-pro-preview":{"draws":7,"losses":48,"wins":59},"gemini-4-argon":{"draws":0,"losses":108,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":12,"wins":82},"google/gemini-3.5-flash":{"draws":3,"losses":91,"wins":56},"google/gemini-3.5-flash-lite":{"draws":11,"losses":63,"wins":132},"google/gemini-3.6-flash":{"draws":7,"losses":133,"wins":82},"google/gemini-3.8-flash":{"draws":2,"losses":78,"wins":34},"google/gemma-4-31b-it":{"draws":9,"losses":13,"wins":46},"gpt-4.1":{"draws":2,"losses":20,"wins":16},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":7},"gpt-5":{"draws":1,"losses":63,"wins":42},"gpt-5.4":{"draws":1,"losses":84,"wins":29},"gpt-5.4-mini":{"draws":6,"losses":18,"wins":52},"gpt-5.4-nano":{"draws":1,"losses":67,"wins":70},"gpt-5.5":{"draws":12,"losses":66,"wins":28},"gpt-5.6-luna":{"draws":12,"losses":45,"wins":57},"gpt-5.6-sol":{"draws":2,"losses":90,"wins":22},"gpt-5.6-terra":{"draws":8,"losses":54,"wins":44},"gpt-6-astra":{"draws":4,"losses":110,"wins":0},"gpt-6-luna":{"draws":14,"losses":61,"wins":39},"gpt-6-sol":{"draws":2,"losses":100,"wins":12},"gpt-6.1-sol":{"draws":0,"losses":108,"wins":6},"gpt-6.1-terra":{"draws":5,"losses":104,"wins":5},"gpt-6.1-terra-pro":{"draws":2,"losses":102,"wins":10},"inception/mercury-2.5-preview":{"draws":8,"losses":11,"wins":57},"inception/mercury-3":{"draws":5,"losses":46,"wins":27},"inclusionai/ling-3.0-flash":{"draws":6,"losses":18,"wins":56},"inclusionai/ling-3.1-flash":{"draws":0,"losses":10,"wins":10},"meituan/longcat-2.0":{"draws":8,"losses":43,"wins":87},"meta/muse-glimmer-30b":{"draws":8,"losses":21,"wins":69},"meta/muse-spark-1.2":{"draws":3,"losses":49,"wins":54},"meta/muse-spark-1.3":{"draws":2,"losses":73,"wins":39},"meta/muse-spark-open":{"draws":3,"losses":82,"wins":29},"meta/muse-wonder":{"draws":4,"losses":86,"wins":24},"minimax/minimax-m3":{"draws":1,"losses":19,"wins":46},"minimax/minimax-m3.1-flash":{"draws":1,"losses":45,"wins":56},"mistralai/mistral-large-4-0":{"draws":10,"losses":34,"wins":24},"mistralai/mistral-medium-3-5":{"draws":4,"losses":8,"wins":50},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":5,"losses":53,"wins":48},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":96,"wins":16},"nex-agi/nex-n2-pro":{"draws":1,"losses":17,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":9,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":31,"wins":57},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":30,"wins":21},"o3":{"draws":8,"losses":78,"wins":84},"openai/gpt-oss-120b":{"draws":4,"losses":22,"wins":74},"poolside/laguna-s-2.1":{"draws":5,"losses":45,"wins":64},"qwen/qwen3.7-max":{"draws":2,"losses":33,"wins":39},"qwen/qwen3.7-plus":{"draws":0,"losses":17,"wins":49},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":68,"wins":39},"qwen/qwen3.8-27b":{"draws":2,"losses":44,"wins":38},"qwen/qwen3.8-flash":{"draws":1,"losses":38,"wins":37},"qwen/qwen3.8-max":{"draws":9,"losses":64,"wins":41},"qwen/qwen3.8-max-0902":{"draws":11,"losses":57,"wins":46},"recursive/flint-v1.0":{"draws":0,"losses":3,"wins":33},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":49,"wins":45},"stealth/ox-alpha":{"draws":18,"losses":176,"wins":150},"stealth/space-bunny-alpha":{"draws":5,"losses":37,"wins":50},"stepfun/step-3.7-flash":{"draws":7,"losses":32,"wins":59},"stepfun/step-5-preview":{"draws":1,"losses":7,"wins":6},"tencent/hy3-preview":{"draws":7,"losses":22,"wins":29},"tencent/hy4-preview":{"draws":7,"losses":64,"wins":43},"thinkingmachines/inkling":{"draws":9,"losses":35,"wins":110},"thinkingmachines/inkling-small":{"draws":9,"losses":30,"wins":75},"unbiased/pareto-26.10":{"draws":0,"losses":38,"wins":0},"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":72,"wins":37},"x-ai/grok-4.6":{"draws":12,"losses":71,"wins":31},"x-ai/grok-4.7":{"draws":3,"losses":76,"wins":25},"x-ai/grok-build-0.1":{"draws":3,"losses":13,"wins":22},"xiaomi/mimo-v2.5":{"draws":9,"losses":38,"wins":133},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":14,"wins":49},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":49,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":52,"wins":20},"z-ai/glm-5.2":{"draws":12,"losses":99,"wins":117},"z-ai/glm-5.3":{"draws":1,"losses":84,"wins":23},"z-ai/glm-5.3-flash":{"draws":0,"losses":58,"wins":56},"z-ai/glm-5.3-flashx":{"draws":3,"losses":71,"wins":40}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":14,"wins":13},"claude-fable-5":{"draws":10,"losses":25,"wins":7},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":26,"wins":4},"claude-opus-4-5":{"draws":17,"losses":33,"wins":18},"claude-opus-4-8":{"draws":12,"losses":16,"wins":10},"claude-opus-5":{"draws":11,"losses":57,"wins":2},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":11,"losses":24,"wins":7},"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":20,"losses":19,"wins":23},"deepseek/deepseek-v4-pro":{"draws":11,"losses":14,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":16,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":17,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":26,"wins":7},"elorian/glimpse":{"draws":7,"losses":9,"wins":6},"fireworks/ember-1":{"draws":12,"losses":20,"wins":10},"gemini-3.1-pro-preview":{"draws":13,"losses":14,"wins":15},"gemini-4-argon":{"draws":2,"losses":39,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":18},"google/gemini-3.5-flash":{"draws":14,"losses":20,"wins":18},"google/gemini-3.5-flash-lite":{"draws":23,"losses":18,"wins":33},"google/gemini-3.6-flash":{"draws":18,"losses":47,"wins":15},"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":18,"losses":10,"wins":14},"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},"gpt-6.1-terra":{"draws":6,"losses":36,"wins":0},"gpt-6.1-terra-pro":{"draws":2,"losses":40,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":9,"wins":12},"inception/mercury-3":{"draws":7,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":18},"inclusionai/ling-3.1-flash":{"draws":0,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":11,"losses":18,"wins":19},"meta/muse-glimmer-30b":{"draws":11,"losses":8,"wins":17},"meta/muse-spark-1.2":{"draws":11,"losses":21,"wins":8},"meta/muse-spark-1.3":{"draws":6,"losses":30,"wins":6},"meta/muse-spark-open":{"draws":12,"losses":25,"wins":5},"meta/muse-wonder":{"draws":9,"losses":29,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":13},"minimax/minimax-m3.1-flash":{"draws":12,"losses":16,"wins":8},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":7},"mistralai/mistral-medium-3-5":{"draws":13,"losses":3,"wins":10},"moonshotai/kimi-k3":{"draws":11,"losses":22,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":35,"wins":3},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":8,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":11,"wins":4},"o3":{"draws":6,"losses":33,"wins":17},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":12},"poolside/laguna-s-2.1":{"draws":12,"losses":7,"wins":21},"qwen/qwen3.7-max":{"draws":8,"losses":9,"wins":7},"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},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":19,"wins":8},"stealth/ox-alpha":{"draws":32,"losses":75,"wins":35},"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":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":7},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":9},"thinkingmachines/inkling":{"draws":13,"losses":16,"wins":25},"thinkingmachines/inkling-small":{"draws":13,"losses":11,"wins":18},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":11,"losses":26,"wins":5},"x-ai/grok-4.6":{"draws":10,"losses":24,"wins":8},"x-ai/grok-4.7":{"draws":1,"losses":32,"wins":3},"x-ai/grok-build-0.1":{"draws":3,"losses":5,"wins":6},"xiaomi/mimo-v2.5":{"draws":20,"losses":10,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":10},"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":26,"losses":36,"wins":22},"z-ai/glm-5.3":{"draws":9,"losses":31,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":25,"wins":10},"z-ai/glm-5.3-flashx":{"draws":11,"losses":26,"wins":5}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":3,"wins":30},"claude-fable-5":{"draws":11,"losses":13,"wins":24},"claude-fable-5-1":{"draws":5,"losses":44,"wins":5},"claude-haiku-5-5":{"draws":11,"losses":10,"wins":25},"claude-opus-4-5":{"draws":22,"losses":7,"wins":49},"claude-opus-4-8":{"draws":10,"losses":5,"wins":29},"claude-opus-5":{"draws":10,"losses":52,"wins":20},"claude-opus-5-5":{"draws":3,"losses":39,"wins":10},"claude-sonnet-5":{"draws":12,"losses":6,"wins":30},"claude-sonnet-5-5":{"draws":9,"losses":17,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":16,"losses":4,"wins":52},"deepseek/deepseek-v4-pro":{"draws":10,"losses":4,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":20,"wins":21},"elorian/glimpse":{"draws":5,"losses":8,"wins":13},"fireworks/ember-1":{"draws":11,"losses":8,"wins":29},"gemini-3.1-pro-preview":{"draws":8,"losses":9,"wins":31},"gemini-4-argon":{"draws":4,"losses":31,"wins":13},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":27},"google/gemini-3.5-flash":{"draws":12,"losses":9,"wins":39},"google/gemini-3.5-flash-lite":{"draws":18,"losses":5,"wins":61},"google/gemini-3.6-flash":{"draws":21,"losses":21,"wins":50},"google/gemini-3.8-flash":{"draws":12,"losses":13,"wins":23},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":21},"gpt-4.1":{"draws":6,"losses":0,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":10,"losses":6,"wins":26},"gpt-5.4":{"draws":8,"losses":11,"wins":27},"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":12,"wins":21},"gpt-5.6-luna":{"draws":9,"losses":6,"wins":33},"gpt-5.6-sol":{"draws":7,"losses":19,"wins":22},"gpt-5.6-terra":{"draws":12,"losses":6,"wins":28},"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":1,"losses":34,"wins":13},"gpt-6.1-terra":{"draws":4,"losses":32,"wins":12},"gpt-6.1-terra-pro":{"draws":2,"losses":38,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":23},"inception/mercury-3":{"draws":11,"losses":3,"wins":18},"inclusionai/ling-3.0-flash":{"draws":9,"losses":0,"wins":25},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"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":9,"losses":11,"wins":28},"meta/muse-spark-open":{"draws":13,"losses":10,"wins":25},"meta/muse-wonder":{"draws":7,"losses":16,"wins":25},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":19},"minimax/minimax-m3.1-flash":{"draws":10,"losses":4,"wins":28},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":19},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":22},"moonshotai/kimi-k3":{"draws":12,"losses":8,"wins":26},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":31,"wins":11},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":2,"wins":14},"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":6,"wins":21},"qwen/qwen3.8-27b":{"draws":13,"losses":3,"wins":18},"qwen/qwen3.8-flash":{"draws":6,"losses":6,"wins":20},"qwen/qwen3.8-max":{"draws":13,"losses":11,"wins":24},"qwen/qwen3.8-max-0902":{"draws":13,"losses":10,"wins":25},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":5,"wins":32},"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":4,"wins":6},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":16},"tencent/hy4-preview":{"draws":10,"losses":14,"wins":22},"thinkingmachines/inkling":{"draws":19,"losses":2,"wins":43},"thinkingmachines/inkling-small":{"draws":14,"losses":5,"wins":29},"unbiased/pareto-26.10":{"draws":0,"losses":15,"wins":1},"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":11,"wins":24},"x-ai/grok-4.6":{"draws":8,"losses":13,"wins":27},"x-ai/grok-4.7":{"draws":1,"losses":26,"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":3,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":6,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":11,"wins":14},"z-ai/glm-5.2":{"draws":27,"losses":12,"wins":57},"z-ai/glm-5.3":{"draws":10,"losses":20,"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":3,"losses":7,"wins":24},"claude-fable-5":{"draws":3,"losses":22,"wins":11},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":4,"losses":13,"wins":19},"claude-opus-4-5":{"draws":5,"losses":16,"wins":39},"claude-opus-4-8":{"draws":4,"losses":14,"wins":18},"claude-opus-5":{"draws":8,"losses":44,"wins":6},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":4,"losses":11,"wins":21},"claude-sonnet-5-5":{"draws":3,"losses":17,"wins":16},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":12},"deepseek/deepseek-v4-flash":{"draws":2,"losses":13,"wins":39},"deepseek/deepseek-v4-pro":{"draws":2,"losses":11,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":9,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":21,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":23,"wins":11},"elorian/glimpse":{"draws":2,"losses":7,"wins":11},"fireworks/ember-1":{"draws":2,"losses":11,"wins":23},"gemini-3.1-pro-preview":{"draws":4,"losses":9,"wins":23},"gemini-4-argon":{"draws":3,"losses":29,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":2,"losses":13,"wins":33},"google/gemini-3.5-flash-lite":{"draws":5,"losses":7,"wins":54},"google/gemini-3.6-flash":{"draws":4,"losses":27,"wins":39},"google/gemini-3.8-flash":{"draws":2,"losses":17,"wins":17},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":16},"gpt-4.1":{"draws":1,"losses":1,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":1,"losses":8,"wins":23},"gpt-5.4":{"draws":3,"losses":22,"wins":11},"gpt-5.4-mini":{"draws":0,"losses":4,"wins":20},"gpt-5.4-nano":{"draws":0,"losses":13,"wins":27},"gpt-5.5":{"draws":1,"losses":16,"wins":17},"gpt-5.6-luna":{"draws":6,"losses":9,"wins":21},"gpt-5.6-sol":{"draws":3,"losses":23,"wins":10},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":18},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":2,"losses":13,"wins":21},"gpt-6-sol":{"draws":4,"losses":24,"wins":8},"gpt-6.1-sol":{"draws":1,"losses":31,"wins":4},"gpt-6.1-terra":{"draws":0,"losses":34,"wins":2},"gpt-6.1-terra-pro":{"draws":0,"losses":32,"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},"inception/mercury-3":{"draws":1,"losses":7,"wins":14},"inclusionai/ling-3.0-flash":{"draws":1,"losses":3,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":2,"losses":5,"wins":35},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":29},"meta/muse-spark-1.2":{"draws":2,"losses":10,"wins":22},"meta/muse-spark-1.3":{"draws":4,"losses":12,"wins":20},"meta/muse-spark-open":{"draws":2,"losses":17,"wins":17},"meta/muse-wonder":{"draws":3,"losses":28,"wins":5},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":18},"minimax/minimax-m3.1-flash":{"draws":3,"losses":12,"wins":17},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":12},"mistralai/mistral-medium-3-5":{"draws":1,"losses":1,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":16,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":29,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":3,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":5,"wins":13},"o3":{"draws":1,"losses":19,"wins":40},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":23},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":28},"qwen/qwen3.7-max":{"draws":1,"losses":9,"wins":12},"qwen/qwen3.7-plus":{"draws":0,"losses":7,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":13,"wins":17},"qwen/qwen3.8-27b":{"draws":1,"losses":7,"wins":6},"qwen/qwen3.8-flash":{"draws":1,"losses":9,"wins":14},"qwen/qwen3.8-max":{"draws":5,"losses":12,"wins":19},"qwen/qwen3.8-max-0902":{"draws":4,"losses":15,"wins":17},"recursive/flint-v1.0":{"draws":0,"losses":2,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":9,"wins":22},"stealth/ox-alpha":{"draws":14,"losses":38,"wins":50},"stealth/space-bunny-alpha":{"draws":2,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":0,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":0,"wins":7},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":14},"tencent/hy4-preview":{"draws":5,"losses":13,"wins":18},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":38},"thinkingmachines/inkling-small":{"draws":1,"losses":1,"wins":34},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":5,"losses":17,"wins":14},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":1,"losses":6,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":17},"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":10,"losses":21,"wins":41},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":5},"z-ai/glm-5.3-flash":{"draws":4,"losses":11,"wins":21},"z-ai/glm-5.3-flashx":{"draws":3,"losses":15,"wins":18}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":14,"wins":19},"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":23,"wins":10},"claude-opus-4-5":{"draws":23,"losses":20,"wins":35},"claude-opus-4-8":{"draws":6,"losses":19,"wins":19},"claude-opus-5":{"draws":7,"losses":63,"wins":12},"claude-opus-5-5":{"draws":3,"losses":47,"wins":2},"claude-sonnet-5":{"draws":12,"losses":14,"wins":22},"claude-sonnet-5-5":{"draws":6,"losses":25,"wins":17},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":11,"losses":15,"wins":46},"deepseek/deepseek-v4-pro":{"draws":9,"losses":11,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":11,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":15,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":29,"wins":11},"elorian/glimpse":{"draws":5,"losses":10,"wins":11},"fireworks/ember-1":{"draws":8,"losses":19,"wins":21},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":25},"gemini-4-argon":{"draws":6,"losses":38,"wins":4},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":13,"losses":24,"wins":23},"google/gemini-3.5-flash-lite":{"draws":14,"losses":13,"wins":57},"google/gemini-3.6-flash":{"draws":13,"losses":36,"wins":43},"google/gemini-3.8-flash":{"draws":10,"losses":22,"wins":16},"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":9,"losses":14,"wins":19},"gpt-5.4":{"draws":8,"losses":18,"wins":20},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":15},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":28},"gpt-5.5":{"draws":12,"losses":14,"wins":18},"gpt-5.6-luna":{"draws":10,"losses":8,"wins":30},"gpt-5.6-sol":{"draws":10,"losses":30,"wins":8},"gpt-5.6-terra":{"draws":16,"losses":12,"wins":18},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":9,"losses":17,"wins":22},"gpt-6-sol":{"draws":5,"losses":36,"wins":7},"gpt-6.1-sol":{"draws":2,"losses":43,"wins":3},"gpt-6.1-terra":{"draws":8,"losses":34,"wins":6},"gpt-6.1-terra-pro":{"draws":2,"losses":40,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":22},"inception/mercury-3":{"draws":9,"losses":9,"wins":16},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":20},"inclusionai/ling-3.1-flash":{"draws":1,"losses":3,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":36},"meta/muse-glimmer-30b":{"draws":9,"losses":8,"wins":25},"meta/muse-spark-1.2":{"draws":11,"losses":21,"wins":14},"meta/muse-spark-1.3":{"draws":13,"losses":21,"wins":14},"meta/muse-spark-open":{"draws":5,"losses":22,"wins":21},"meta/muse-wonder":{"draws":9,"losses":27,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":17},"minimax/minimax-m3.1-flash":{"draws":8,"losses":12,"wins":22},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":9},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":16,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":38,"wins":10},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":13},"o3":{"draws":6,"losses":24,"wins":36},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":29},"poolside/laguna-s-2.1":{"draws":6,"losses":9,"wins":31},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":15},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":15,"wins":20},"qwen/qwen3.8-27b":{"draws":7,"losses":10,"wins":17},"qwen/qwen3.8-flash":{"draws":5,"losses":8,"wins":19},"qwen/qwen3.8-max":{"draws":8,"losses":10,"wins":14},"qwen/qwen3.8-max-0902":{"draws":8,"losses":23,"wins":17},"recursive/flint-v1.0":{"draws":1,"losses":2,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":15,"wins":22},"stealth/ox-alpha":{"draws":36,"losses":63,"wins":59},"stealth/space-bunny-alpha":{"draws":8,"losses":9,"wins":21},"stepfun/step-3.7-flash":{"draws":6,"losses":5,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":9},"tencent/hy3-preview":{"draws":10,"losses":2,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":19,"wins":19},"thinkingmachines/inkling":{"draws":18,"losses":8,"wins":38},"thinkingmachines/inkling-small":{"draws":11,"losses":10,"wins":27},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":20,"wins":19},"x-ai/grok-4.6":{"draws":12,"losses":17,"wins":19},"x-ai/grok-4.7":{"draws":5,"losses":26,"wins":11},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":22,"losses":8,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":5,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":19,"wins":6},"z-ai/glm-5.2":{"draws":22,"losses":30,"wins":44},"z-ai/glm-5.3":{"draws":5,"losses":30,"wins":11},"z-ai/glm-5.3-flash":{"draws":11,"losses":13,"wins":24},"z-ai/glm-5.3-flashx":{"draws":14,"losses":17,"wins":17}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":4,"wins":33},"claude-fable-5":{"draws":10,"losses":17,"wins":21},"claude-fable-5-1":{"draws":3,"losses":37,"wins":14},"claude-haiku-5-5":{"draws":11,"losses":9,"wins":26},"claude-opus-4-5":{"draws":14,"losses":12,"wins":52},"claude-opus-4-8":{"draws":4,"losses":14,"wins":26},"claude-opus-5":{"draws":11,"losses":42,"wins":29},"claude-opus-5-5":{"draws":8,"losses":36,"wins":8},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":16,"wins":20},"elorian/glimpse":{"draws":6,"losses":5,"wins":15},"fireworks/ember-1":{"draws":11,"losses":10,"wins":27},"gemini-3.1-pro-preview":{"draws":11,"losses":6,"wins":31},"gemini-4-argon":{"draws":7,"losses":32,"wins":9},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":28},"google/gemini-3.5-flash":{"draws":12,"losses":5,"wins":43},"google/gemini-3.5-flash-lite":{"draws":13,"losses":4,"wins":67},"google/gemini-3.6-flash":{"draws":19,"losses":17,"wins":56},"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":5,"losses":8,"wins":35},"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},"gpt-6.1-terra":{"draws":6,"losses":32,"wins":10},"gpt-6.1-terra-pro":{"draws":6,"losses":35,"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},"inception/mercury-3":{"draws":8,"losses":7,"wins":17},"inclusionai/ling-3.0-flash":{"draws":9,"losses":0,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":4},"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-spark-open":{"draws":7,"losses":8,"wins":33},"meta/muse-wonder":{"draws":13,"losses":19,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":22},"minimax/minimax-m3.1-flash":{"draws":9,"losses":6,"wins":27},"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":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":8,"wins":29},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":30,"wins":13},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":2,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":19},"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},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":7,"wins":30},"stealth/ox-alpha":{"draws":31,"losses":41,"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":0,"losses":3,"wins":5},"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":{"draws":2,"losses":12,"wins":2},"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":20,"losses":4,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":2,"wins":14},"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}},"reflection/beam-1.0-501b-a23b":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":11,"wins":27},"claude-fable-5":{"draws":8,"losses":30,"wins":10},"claude-fable-5-1":{"draws":5,"losses":48,"wins":1},"claude-haiku-5-5":{"draws":8,"losses":23,"wins":15},"claude-opus-4-5":{"draws":23,"losses":19,"wins":36},"claude-opus-4-8":{"draws":8,"losses":22,"wins":14},"claude-opus-5":{"draws":10,"losses":63,"wins":9},"claude-opus-5-5":{"draws":7,"losses":45,"wins":0},"claude-sonnet-5":{"draws":11,"losses":13,"wins":24},"claude-sonnet-5-5":{"draws":8,"losses":26,"wins":14},"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":10,"losses":13,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":11,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":23,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":22,"wins":15},"elorian/glimpse":{"draws":5,"losses":12,"wins":9},"fireworks/ember-1":{"draws":9,"losses":15,"wins":24},"gemini-3.1-pro-preview":{"draws":9,"losses":15,"wins":24},"gemini-4-argon":{"draws":3,"losses":38,"wins":7},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":13,"losses":15,"wins":32},"google/gemini-3.5-flash-lite":{"draws":12,"losses":16,"wins":56},"google/gemini-3.6-flash":{"draws":18,"losses":38,"wins":36},"google/gemini-3.8-flash":{"draws":10,"losses":22,"wins":16},"google/gemma-4-31b-it":{"draws":4,"losses":6,"wins":18},"gpt-4.1":{"draws":4,"losses":5,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":5,"losses":12,"wins":25},"gpt-5.4":{"draws":10,"losses":22,"wins":14},"gpt-5.4-mini":{"draws":7,"losses":4,"wins":21},"gpt-5.4-nano":{"draws":5,"losses":10,"wins":33},"gpt-5.5":{"draws":12,"losses":17,"wins":15},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":27},"gpt-5.6-sol":{"draws":7,"losses":29,"wins":12},"gpt-5.6-terra":{"draws":7,"losses":19,"wins":20},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":11,"losses":15,"wins":22},"gpt-6-sol":{"draws":5,"losses":37,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"gpt-6.1-terra":{"draws":2,"losses":44,"wins":2},"gpt-6.1-terra-pro":{"draws":4,"losses":41,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inception/mercury-3":{"draws":11,"losses":5,"wins":16},"inclusionai/ling-3.0-flash":{"draws":6,"losses":6,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":4,"wins":4},"meituan/longcat-2.0":{"draws":7,"losses":9,"wins":36},"meta/muse-glimmer-30b":{"draws":7,"losses":6,"wins":29},"meta/muse-spark-1.2":{"draws":9,"losses":14,"wins":23},"meta/muse-spark-1.3":{"draws":6,"losses":25,"wins":17},"meta/muse-spark-open":{"draws":12,"losses":18,"wins":18},"meta/muse-wonder":{"draws":7,"losses":30,"wins":11},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":21},"minimax/minimax-m3.1-flash":{"draws":7,"losses":14,"wins":21},"mistralai/mistral-large-4-0":{"draws":6,"losses":13,"wins":11},"mistralai/mistral-medium-3-5":{"draws":4,"losses":1,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":11,"losses":14,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":40,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":5,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":4,"wins":17},"o3":{"draws":4,"losses":25,"wins":37},"openai/gpt-oss-120b":{"draws":8,"losses":5,"wins":29},"poolside/laguna-s-2.1":{"draws":7,"losses":8,"wins":31},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":4,"losses":7,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":17,"wins":19},"qwen/qwen3.8-27b":{"draws":6,"losses":11,"wins":17},"qwen/qwen3.8-flash":{"draws":5,"losses":8,"wins":19},"qwen/qwen3.8-max":{"draws":13,"losses":14,"wins":21},"qwen/qwen3.8-max-0902":{"draws":12,"losses":16,"wins":20},"recursive/flint-v1.0":{"draws":1,"losses":1,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":10,"wins":9},"stealth/ox-alpha":{"draws":29,"losses":62,"wins":67},"stealth/space-bunny-alpha":{"draws":9,"losses":3,"wins":26},"stepfun/step-3.7-flash":{"draws":3,"losses":10,"wins":21},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":6,"losses":7,"wins":13},"tencent/hy4-preview":{"draws":10,"losses":20,"wins":16},"thinkingmachines/inkling":{"draws":17,"losses":8,"wins":39},"thinkingmachines/inkling-small":{"draws":12,"losses":8,"wins":28},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":8},"x-ai/grok-4.5":{"draws":12,"losses":18,"wins":18},"x-ai/grok-4.6":{"draws":12,"losses":22,"wins":14},"x-ai/grok-4.7":{"draws":7,"losses":29,"wins":6},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":18,"losses":9,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":12,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":10},"z-ai/glm-5.2":{"draws":17,"losses":26,"wins":53},"z-ai/glm-5.3":{"draws":6,"losses":29,"wins":11},"z-ai/glm-5.3-flash":{"draws":7,"losses":25,"wins":16},"z-ai/glm-5.3-flashx":{"draws":6,"losses":21,"wins":21}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":17,"wins":110},"claude-fable-5":{"draws":16,"losses":74,"wins":60},"claude-fable-5-1":{"draws":12,"losses":143,"wins":17},"claude-haiku-5-5":{"draws":16,"losses":43,"wins":81},"claude-opus-4-5":{"draws":25,"losses":51,"wins":164},"claude-opus-4-8":{"draws":12,"losses":42,"wins":76},"claude-opus-5":{"draws":35,"losses":168,"wins":55},"claude-opus-5-5":{"draws":7,"losses":134,"wins":21},"claude-sonnet-5":{"draws":13,"losses":28,"wins":109},"claude-sonnet-5-5":{"draws":10,"losses":67,"wins":73},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":51},"deepseek/deepseek-v4-flash":{"draws":15,"losses":22,"wins":185},"deepseek/deepseek-v4-pro":{"draws":13,"losses":35,"wins":92},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":33,"wins":91},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":43,"wins":92},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":57,"wins":77},"elorian/glimpse":{"draws":10,"losses":23,"wins":51},"fireworks/ember-1":{"draws":20,"losses":36,"wins":94},"gemini-3.1-pro-preview":{"draws":16,"losses":37,"wins":97},"gemini-4-argon":{"draws":16,"losses":108,"wins":26},"google/gemini-3.1-flash-lite":{"draws":7,"losses":6,"wins":81},"google/gemini-3.5-flash":{"draws":17,"losses":40,"wins":129},"google/gemini-3.5-flash-lite":{"draws":21,"losses":32,"wins":211},"google/gemini-3.6-flash":{"draws":25,"losses":85,"wins":180},"google/gemini-3.8-flash":{"draws":14,"losses":58,"wins":78},"google/gemma-4-31b-it":{"draws":7,"losses":8,"wins":69},"gpt-4.1":{"draws":8,"losses":10,"wins":32},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":15},"gpt-5":{"draws":10,"losses":30,"wins":94},"gpt-5.4":{"draws":18,"losses":48,"wins":80},"gpt-5.4-mini":{"draws":13,"losses":11,"wins":76},"gpt-5.4-nano":{"draws":7,"losses":36,"wins":99},"gpt-5.5":{"draws":16,"losses":41,"wins":83},"gpt-5.6-luna":{"draws":23,"losses":23,"wins":104},"gpt-5.6-sol":{"draws":16,"losses":73,"wins":61},"gpt-5.6-terra":{"draws":15,"losses":39,"wins":90},"gpt-6-astra":{"draws":14,"losses":118,"wins":18},"gpt-6-luna":{"draws":16,"losses":32,"wins":102},"gpt-6-sol":{"draws":18,"losses":93,"wins":39},"gpt-6.1-sol":{"draws":15,"losses":118,"wins":17},"gpt-6.1-terra":{"draws":16,"losses":108,"wins":26},"gpt-6.1-terra-pro":{"draws":14,"losses":110,"wins":26},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":14,"losses":9,"wins":77},"inception/mercury-3":{"draws":8,"losses":26,"wins":64},"inclusionai/ling-3.0-flash":{"draws":7,"losses":6,"wins":93},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":11,"losses":19,"wins":134},"meta/muse-glimmer-30b":{"draws":9,"losses":9,"wins":116},"meta/muse-spark-1.2":{"draws":16,"losses":29,"wins":99},"meta/muse-spark-1.3":{"draws":17,"losses":48,"wins":85},"meta/muse-spark-open":{"draws":13,"losses":50,"wins":87},"meta/muse-wonder":{"draws":11,"losses":77,"wins":62},"minimax/minimax-m3":{"draws":9,"losses":4,"wins":65},"minimax/minimax-m3.1-flash":{"draws":13,"losses":30,"wins":91},"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":1,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":39,"wins":90},"moonshotai/kimi-k3.1-pro":{"draws":21,"losses":101,"wins":28},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":65},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":1,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":14,"wins":81},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":11,"wins":48},"o3":{"draws":7,"losses":41,"wins":156},"openai/gpt-oss-120b":{"draws":13,"losses":8,"wins":111},"poolside/laguna-s-2.1":{"draws":13,"losses":19,"wins":116},"qwen/qwen3.7-max":{"draws":5,"losses":11,"wins":68},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":60},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":45,"wins":86},"qwen/qwen3.8-27b":{"draws":7,"losses":22,"wins":77},"qwen/qwen3.8-flash":{"draws":8,"losses":23,"wins":69},"qwen/qwen3.8-max":{"draws":18,"losses":35,"wins":97},"qwen/qwen3.8-max-0902":{"draws":19,"losses":42,"wins":89},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":36},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":30,"wins":95},"stealth/ox-alpha":{"draws":46,"losses":131,"wins":311},"stealth/space-bunny-alpha":{"draws":11,"losses":16,"wins":91},"stepfun/step-3.7-flash":{"draws":1,"losses":13,"wins":94},"stepfun/step-5-preview":{"draws":2,"losses":10,"wins":16},"tencent/hy3-preview":{"draws":13,"losses":11,"wins":54},"tencent/hy4-preview":{"draws":17,"losses":50,"wins":79},"thinkingmachines/inkling":{"draws":21,"losses":24,"wins":161},"thinkingmachines/inkling-small":{"draws":15,"losses":7,"wins":128},"unbiased/pareto-26.10":{"draws":3,"losses":46,"wins":1},"unbiased/pareto-26.10-preview":{"draws":8,"losses":36,"wins":6},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":33},"x-ai/grok-4.5":{"draws":14,"losses":65,"wins":71},"x-ai/grok-4.6":{"draws":25,"losses":57,"wins":68},"x-ai/grok-4.7":{"draws":8,"losses":78,"wins":42},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":45},"xiaomi/mimo-v2.5":{"draws":24,"losses":18,"wins":174},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":71},"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":28,"losses":49,"wins":223},"z-ai/glm-5.3":{"draws":19,"losses":61,"wins":64},"z-ai/glm-5.3-flash":{"draws":15,"losses":43,"wins":92},"z-ai/glm-5.3-flashx":{"draws":16,"losses":52,"wins":82}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":7,"wins":17},"claude-fable-5":{"draws":9,"losses":22,"wins":5},"claude-fable-5-1":{"draws":0,"losses":38,"wins":2},"claude-haiku-5-5":{"draws":7,"losses":18,"wins":11},"claude-opus-4-5":{"draws":17,"losses":29,"wins":14},"claude-opus-4-8":{"draws":6,"losses":15,"wins":15},"claude-opus-5":{"draws":11,"losses":41,"wins":6},"claude-opus-5-5":{"draws":1,"losses":38,"wins":1},"claude-sonnet-5":{"draws":3,"losses":13,"wins":20},"claude-sonnet-5-5":{"draws":3,"losses":19,"wins":14},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":11,"losses":15,"wins":28},"deepseek/deepseek-v4-pro":{"draws":8,"losses":12,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":14,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":18,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":26,"wins":6},"elorian/glimpse":{"draws":2,"losses":11,"wins":7},"fireworks/ember-1":{"draws":5,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":3,"losses":11,"wins":22},"gemini-4-argon":{"draws":1,"losses":31,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":22},"google/gemini-3.5-flash":{"draws":9,"losses":19,"wins":20},"google/gemini-3.5-flash-lite":{"draws":14,"losses":15,"wins":37},"google/gemini-3.6-flash":{"draws":15,"losses":31,"wins":24},"google/gemini-3.8-flash":{"draws":5,"losses":21,"wins":10},"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":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":13,"wins":17},"gpt-5.4":{"draws":3,"losses":26,"wins":7},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":14},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":20},"gpt-5.5":{"draws":10,"losses":15,"wins":9},"gpt-5.6-luna":{"draws":5,"losses":12,"wins":19},"gpt-5.6-sol":{"draws":4,"losses":24,"wins":8},"gpt-5.6-terra":{"draws":7,"losses":15,"wins":12},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":8,"losses":14,"wins":14},"gpt-6-sol":{"draws":1,"losses":27,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":3},"gpt-6.1-terra":{"draws":2,"losses":28,"wins":6},"gpt-6.1-terra-pro":{"draws":0,"losses":30,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":4,"wins":14},"inception/mercury-3":{"draws":3,"losses":11,"wins":8},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":16},"inclusionai/ling-3.1-flash":{"draws":0,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":10,"losses":11,"wins":21},"meta/muse-glimmer-30b":{"draws":7,"losses":2,"wins":23},"meta/muse-spark-1.2":{"draws":5,"losses":14,"wins":15},"meta/muse-spark-1.3":{"draws":4,"losses":16,"wins":16},"meta/muse-spark-open":{"draws":5,"losses":22,"wins":9},"meta/muse-wonder":{"draws":5,"losses":24,"wins":7},"minimax/minimax-m3":{"draws":1,"losses":4,"wins":15},"minimax/minimax-m3.1-flash":{"draws":6,"losses":11,"wins":15},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":15},"moonshotai/kimi-k3":{"draws":7,"losses":16,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":29,"wins":5},"nex-agi/nex-n2-pro":{"draws":3,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":9,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":9},"o3":{"draws":8,"losses":27,"wins":25},"openai/gpt-oss-120b":{"draws":5,"losses":4,"wins":21},"poolside/laguna-s-2.1":{"draws":2,"losses":7,"wins":23},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":12,"wins":14},"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":6,"losses":17,"wins":13},"qwen/qwen3.8-max-0902":{"draws":7,"losses":19,"wins":10},"recursive/flint-v1.0":{"draws":1,"losses":3,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":15,"wins":9},"stealth/ox-alpha":{"draws":19,"losses":47,"wins":36},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":15},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":5,"losses":13,"wins":18},"thinkingmachines/inkling":{"draws":11,"losses":13,"wins":24},"thinkingmachines/inkling-small":{"draws":5,"losses":3,"wins":28},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":7,"losses":22,"wins":7},"x-ai/grok-4.6":{"draws":4,"losses":20,"wins":12},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":1,"losses":4,"wins":7},"xiaomi/mimo-v2.5":{"draws":16,"losses":13,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":10,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":15,"losses":23,"wins":34},"z-ai/glm-5.3":{"draws":4,"losses":23,"wins":7},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":6},"z-ai/glm-5.3-flashx":{"draws":4,"losses":21,"wins":11}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":17,"wins":9},"claude-fable-5":{"draws":0,"losses":28,"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":2,"losses":39,"wins":9},"claude-opus-4-8":{"draws":0,"losses":25,"wins":5},"claude-opus-5":{"draws":1,"losses":44,"wins":1},"claude-opus-5-5":{"draws":0,"losses":34,"wins":0},"claude-sonnet-5":{"draws":0,"losses":24,"wins":6},"claude-sonnet-5-5":{"draws":0,"losses":24,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":0,"losses":34,"wins":14},"deepseek/deepseek-v4-pro":{"draws":0,"losses":25,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":22,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":28,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":28,"wins":2},"elorian/glimpse":{"draws":0,"losses":13,"wins":3},"fireworks/ember-1":{"draws":1,"losses":25,"wins":4},"gemini-3.1-pro-preview":{"draws":0,"losses":19,"wins":11},"gemini-4-argon":{"draws":0,"losses":30,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":7,"wins":17},"google/gemini-3.5-flash":{"draws":2,"losses":28,"wins":10},"google/gemini-3.5-flash-lite":{"draws":0,"losses":38,"wins":16},"google/gemini-3.6-flash":{"draws":1,"losses":51,"wins":6},"google/gemini-3.8-flash":{"draws":0,"losses":29,"wins":1},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":10},"gpt-4.1":{"draws":0,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":27,"wins":1},"gpt-5.4":{"draws":0,"losses":24,"wins":6},"gpt-5.4-mini":{"draws":0,"losses":12,"wins":8},"gpt-5.4-nano":{"draws":0,"losses":25,"wins":13},"gpt-5.5":{"draws":2,"losses":22,"wins":4},"gpt-5.6-luna":{"draws":2,"losses":19,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":28,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":22,"wins":6},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":2,"losses":20,"wins":8},"gpt-6-sol":{"draws":0,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":30,"wins":0},"gpt-6.1-terra":{"draws":0,"losses":30,"wins":0},"gpt-6.1-terra-pro":{"draws":0,"losses":30,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":5,"wins":13},"inception/mercury-3":{"draws":0,"losses":17,"wins":3},"inclusionai/ling-3.0-flash":{"draws":2,"losses":11,"wins":9},"inclusionai/ling-3.1-flash":{"draws":0,"losses":6,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":23,"wins":12},"meta/muse-glimmer-30b":{"draws":0,"losses":19,"wins":7},"meta/muse-spark-1.2":{"draws":1,"losses":20,"wins":7},"meta/muse-spark-1.3":{"draws":0,"losses":30,"wins":0},"meta/muse-spark-open":{"draws":0,"losses":23,"wins":7},"meta/muse-wonder":{"draws":0,"losses":29,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":13,"wins":3},"minimax/minimax-m3.1-flash":{"draws":0,"losses":20,"wins":6},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":5,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":24,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":29,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":10,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":15,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":12,"wins":2},"o3":{"draws":2,"losses":42,"wins":12},"openai/gpt-oss-120b":{"draws":0,"losses":14,"wins":12},"poolside/laguna-s-2.1":{"draws":0,"losses":21,"wins":9},"qwen/qwen3.7-max":{"draws":2,"losses":14,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":12,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":24,"wins":5},"qwen/qwen3.8-27b":{"draws":0,"losses":14,"wins":8},"qwen/qwen3.8-flash":{"draws":0,"losses":14,"wins":6},"qwen/qwen3.8-max":{"draws":1,"losses":28,"wins":1},"qwen/qwen3.8-max-0902":{"draws":4,"losses":19,"wins":7},"recursive/flint-v1.0":{"draws":0,"losses":5,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":18,"wins":8},"stealth/ox-alpha":{"draws":2,"losses":68,"wins":14},"stealth/space-bunny-alpha":{"draws":2,"losses":14,"wins":8},"stepfun/step-3.7-flash":{"draws":2,"losses":11,"wins":3},"stepfun/step-5-preview":{"draws":0,"losses":7,"wins":1},"tencent/hy3-preview":{"draws":2,"losses":9,"wins":5},"tencent/hy4-preview":{"draws":2,"losses":26,"wins":2},"thinkingmachines/inkling":{"draws":3,"losses":14,"wins":23},"thinkingmachines/inkling-small":{"draws":1,"losses":19,"wins":10},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"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":1,"losses":26,"wins":3},"x-ai/grok-4.7":{"draws":0,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":7,"wins":3},"xiaomi/mimo-v2.5":{"draws":2,"losses":31,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":12,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":17,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":19,"wins":1},"z-ai/glm-5.2":{"draws":3,"losses":44,"wins":13},"z-ai/glm-5.3":{"draws":0,"losses":28,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":26,"wins":4},"z-ai/glm-5.3-flashx":{"draws":0,"losses":25,"wins":5}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":12,"wins":15},"claude-fable-5":{"draws":10,"losses":26,"wins":6},"claude-fable-5-1":{"draws":3,"losses":42,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":17,"wins":13},"claude-opus-4-5":{"draws":23,"losses":31,"wins":16},"claude-opus-4-8":{"draws":8,"losses":23,"wins":11},"claude-opus-5":{"draws":12,"losses":55,"wins":3},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":11,"losses":19,"wins":12},"claude-sonnet-5-5":{"draws":7,"losses":30,"wins":5},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":16,"losses":23,"wins":25},"deepseek/deepseek-v4-pro":{"draws":11,"losses":16,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":14,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":24,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":27,"wins":6},"elorian/glimpse":{"draws":6,"losses":9,"wins":7},"fireworks/ember-1":{"draws":14,"losses":20,"wins":8},"gemini-3.1-pro-preview":{"draws":11,"losses":16,"wins":15},"gemini-4-argon":{"draws":3,"losses":38,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":9,"wins":16},"google/gemini-3.5-flash":{"draws":13,"losses":24,"wins":17},"google/gemini-3.5-flash-lite":{"draws":19,"losses":18,"wins":37},"google/gemini-3.6-flash":{"draws":22,"losses":41,"wins":17},"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":4,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":1},"gpt-5":{"draws":9,"losses":10,"wins":17},"gpt-5.4":{"draws":8,"losses":22,"wins":10},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":16,"wins":21},"gpt-5.5":{"draws":15,"losses":19,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":16,"wins":15},"gpt-5.6-sol":{"draws":8,"losses":28,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":18,"wins":10},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":13,"losses":16,"wins":13},"gpt-6-sol":{"draws":5,"losses":34,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":2},"gpt-6.1-terra":{"draws":9,"losses":33,"wins":0},"gpt-6.1-terra-pro":{"draws":4,"losses":34,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":10,"wins":10},"inception/mercury-3":{"draws":8,"losses":13,"wins":7},"inclusionai/ling-3.0-flash":{"draws":8,"losses":7,"wins":15},"inclusionai/ling-3.1-flash":{"draws":4,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":14,"wins":23},"meta/muse-glimmer-30b":{"draws":10,"losses":7,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":22,"wins":7},"meta/muse-spark-1.3":{"draws":5,"losses":28,"wins":9},"meta/muse-spark-open":{"draws":9,"losses":25,"wins":8},"meta/muse-wonder":{"draws":6,"losses":30,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":10},"minimax/minimax-m3.1-flash":{"draws":7,"losses":14,"wins":15},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":37,"wins":1},"nex-agi/nex-n2-pro":{"draws":5,"losses":8,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":8,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":10,"wins":4},"o3":{"draws":10,"losses":25,"wins":27},"openai/gpt-oss-120b":{"draws":10,"losses":10,"wins":16},"poolside/laguna-s-2.1":{"draws":11,"losses":11,"wins":16},"qwen/qwen3.7-max":{"draws":10,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":18,"wins":9},"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":12,"losses":22,"wins":8},"qwen/qwen3.8-max-0902":{"draws":13,"losses":22,"wins":7},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":15,"wins":14},"stealth/ox-alpha":{"draws":33,"losses":61,"wins":24},"stealth/space-bunny-alpha":{"draws":9,"losses":12,"wins":13},"stepfun/step-3.7-flash":{"draws":5,"losses":8,"wins":17},"stepfun/step-5-preview":{"draws":1,"losses":4,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":5},"tencent/hy4-preview":{"draws":11,"losses":17,"wins":12},"thinkingmachines/inkling":{"draws":15,"losses":10,"wins":29},"thinkingmachines/inkling-small":{"draws":12,"losses":13,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":8,"losses":24,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":23,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":9,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":13,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":20,"losses":34,"wins":30},"z-ai/glm-5.3":{"draws":6,"losses":29,"wins":5},"z-ai/glm-5.3-flash":{"draws":10,"losses":24,"wins":8},"z-ai/glm-5.3-flashx":{"draws":6,"losses":28,"wins":8}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":3,"wins":27},"claude-fable-5":{"draws":8,"losses":21,"wins":19},"claude-fable-5-1":{"draws":6,"losses":39,"wins":9},"claude-haiku-5-5":{"draws":14,"losses":15,"wins":17},"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":58,"wins":14},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":10,"losses":7,"wins":31},"claude-sonnet-5-5":{"draws":4,"losses":23,"wins":21},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":14,"losses":11,"wins":47},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":6,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":8,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":17,"wins":24},"elorian/glimpse":{"draws":2,"losses":9,"wins":15},"fireworks/ember-1":{"draws":10,"losses":11,"wins":27},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":23},"gemini-4-argon":{"draws":5,"losses":37,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":13,"losses":9,"wins":38},"google/gemini-3.5-flash-lite":{"draws":22,"losses":12,"wins":50},"google/gemini-3.6-flash":{"draws":14,"losses":35,"wins":43},"google/gemini-3.8-flash":{"draws":9,"losses":14,"wins":25},"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":15,"losses":7,"wins":20},"gpt-5.4":{"draws":9,"losses":16,"wins":21},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":18},"gpt-5.4-nano":{"draws":7,"losses":7,"wins":34},"gpt-5.5":{"draws":13,"losses":10,"wins":21},"gpt-5.6-luna":{"draws":13,"losses":7,"wins":28},"gpt-5.6-sol":{"draws":6,"losses":20,"wins":22},"gpt-5.6-terra":{"draws":9,"losses":12,"wins":25},"gpt-6-astra":{"draws":6,"losses":40,"wins":2},"gpt-6-luna":{"draws":13,"losses":8,"wins":27},"gpt-6-sol":{"draws":7,"losses":26,"wins":15},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":7},"gpt-6.1-terra":{"draws":6,"losses":39,"wins":3},"gpt-6.1-terra-pro":{"draws":3,"losses":40,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":18},"inception/mercury-3":{"draws":7,"losses":8,"wins":17},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":14,"losses":7,"wins":31},"meta/muse-glimmer-30b":{"draws":12,"losses":4,"wins":26},"meta/muse-spark-1.2":{"draws":5,"losses":14,"wins":27},"meta/muse-spark-1.3":{"draws":13,"losses":17,"wins":18},"meta/muse-spark-open":{"draws":4,"losses":15,"wins":29},"meta/muse-wonder":{"draws":9,"losses":21,"wins":18},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":17},"minimax/minimax-m3.1-flash":{"draws":5,"losses":16,"wins":21},"mistralai/mistral-large-4-0":{"draws":11,"losses":4,"wins":15},"mistralai/mistral-medium-3-5":{"draws":5,"losses":5,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":9,"wins":26},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":34,"wins":12},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":8,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":5,"wins":12},"o3":{"draws":12,"losses":15,"wins":39},"openai/gpt-oss-120b":{"draws":15,"losses":6,"wins":21},"poolside/laguna-s-2.1":{"draws":12,"losses":11,"wins":23},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":20},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":17},"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":8,"losses":7,"wins":17},"qwen/qwen3.8-max":{"draws":9,"losses":12,"wins":27},"qwen/qwen3.8-max-0902":{"draws":12,"losses":11,"wins":25},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":10,"wins":23},"stealth/ox-alpha":{"draws":29,"losses":29,"wins":100},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":10,"losses":4,"wins":20},"stepfun/step-5-preview":{"draws":1,"losses":4,"wins":11},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":14},"tencent/hy4-preview":{"draws":5,"losses":7,"wins":18},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":36},"thinkingmachines/inkling-small":{"draws":10,"losses":6,"wins":32},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":2},"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":4,"losses":14,"wins":30},"x-ai/grok-4.6":{"draws":17,"losses":16,"wins":15},"x-ai/grok-4.7":{"draws":4,"losses":24,"wins":14},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":7},"xiaomi/mimo-v2.5":{"draws":18,"losses":9,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":9,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":13},"z-ai/glm-5.2":{"draws":14,"losses":16,"wins":66},"z-ai/glm-5.3":{"draws":7,"losses":25,"wins":14},"z-ai/glm-5.3-flash":{"draws":8,"losses":20,"wins":20},"z-ai/glm-5.3-flashx":{"draws":12,"losses":10,"wins":26}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":36,"wins":20},"claude-fable-5":{"draws":12,"losses":67,"wins":5},"claude-fable-5-1":{"draws":0,"losses":94,"wins":0},"claude-haiku-5-5":{"draws":28,"losses":43,"wins":9},"claude-opus-4-5":{"draws":42,"losses":75,"wins":19},"claude-opus-4-8":{"draws":17,"losses":48,"wins":11},"claude-opus-5":{"draws":20,"losses":121,"wins":9},"claude-opus-5-5":{"draws":7,"losses":85,"wins":0},"claude-sonnet-5":{"draws":27,"losses":44,"wins":13},"claude-sonnet-5-5":{"draws":19,"losses":47,"wins":18},"cohere/north-mini-code":{"draws":5,"losses":10,"wins":17},"deepseek/deepseek-v4-flash":{"draws":34,"losses":40,"wins":54},"deepseek/deepseek-v4-pro":{"draws":22,"losses":41,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":37,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":44,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":21,"losses":50,"wins":13},"elorian/glimpse":{"draws":9,"losses":25,"wins":12},"fireworks/ember-1":{"draws":25,"losses":46,"wins":13},"gemini-3.1-pro-preview":{"draws":30,"losses":34,"wins":20},"gemini-4-argon":{"draws":8,"losses":73,"wins":3},"google/gemini-3.1-flash-lite":{"draws":16,"losses":8,"wins":30},"google/gemini-3.5-flash":{"draws":21,"losses":56,"wins":27},"google/gemini-3.5-flash-lite":{"draws":38,"losses":56,"wins":50},"google/gemini-3.6-flash":{"draws":43,"losses":87,"wins":30},"google/gemini-3.8-flash":{"draws":25,"losses":49,"wins":10},"google/gemma-4-31b-it":{"draws":17,"losses":12,"wins":19},"gpt-4.1":{"draws":7,"losses":11,"wins":10},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":16,"losses":39,"wins":21},"gpt-5.4":{"draws":18,"losses":46,"wins":16},"gpt-5.4-mini":{"draws":21,"losses":19,"wins":16},"gpt-5.4-nano":{"draws":23,"losses":28,"wins":35},"gpt-5.5":{"draws":24,"losses":42,"wins":12},"gpt-5.6-luna":{"draws":26,"losses":37,"wins":21},"gpt-5.6-sol":{"draws":13,"losses":62,"wins":9},"gpt-5.6-terra":{"draws":23,"losses":39,"wins":18},"gpt-6-astra":{"draws":6,"losses":77,"wins":1},"gpt-6-luna":{"draws":23,"losses":40,"wins":21},"gpt-6-sol":{"draws":8,"losses":67,"wins":9},"gpt-6.1-sol":{"draws":6,"losses":74,"wins":4},"gpt-6.1-terra":{"draws":13,"losses":67,"wins":4},"gpt-6.1-terra-pro":{"draws":12,"losses":68,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":25,"losses":12,"wins":19},"inception/mercury-3":{"draws":21,"losses":22,"wins":17},"inclusionai/ling-3.0-flash":{"draws":21,"losses":14,"wins":23},"inclusionai/ling-3.1-flash":{"draws":8,"losses":3,"wins":1},"meituan/longcat-2.0":{"draws":20,"losses":30,"wins":40},"meta/muse-glimmer-30b":{"draws":22,"losses":27,"wins":27},"meta/muse-spark-1.2":{"draws":20,"losses":51,"wins":11},"meta/muse-spark-1.3":{"draws":14,"losses":61,"wins":9},"meta/muse-spark-open":{"draws":21,"losses":55,"wins":8},"meta/muse-wonder":{"draws":24,"losses":52,"wins":8},"minimax/minimax-m3":{"draws":10,"losses":16,"wins":22},"minimax/minimax-m3.1-flash":{"draws":14,"losses":30,"wins":28},"mistralai/mistral-large-4-0":{"draws":19,"losses":25,"wins":10},"mistralai/mistral-medium-3-5":{"draws":13,"losses":11,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":24,"losses":41,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":72,"wins":5},"nex-agi/nex-n2-pro":{"draws":8,"losses":14,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":9,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":25,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":18,"wins":10},"o3":{"draws":21,"losses":63,"wins":32},"openai/gpt-oss-120b":{"draws":19,"losses":23,"wins":34},"poolside/laguna-s-2.1":{"draws":23,"losses":37,"wins":26},"qwen/qwen3.7-max":{"draws":12,"losses":28,"wins":10},"qwen/qwen3.7-plus":{"draws":13,"losses":17,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":48,"wins":8},"qwen/qwen3.8-27b":{"draws":19,"losses":26,"wins":13},"qwen/qwen3.8-flash":{"draws":18,"losses":27,"wins":11},"qwen/qwen3.8-max":{"draws":24,"losses":43,"wins":17},"qwen/qwen3.8-max-0902":{"draws":26,"losses":44,"wins":14},"recursive/flint-v1.0":{"draws":8,"losses":5,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":24,"losses":36,"wins":18},"stealth/ox-alpha":{"draws":65,"losses":159,"wins":58},"stealth/space-bunny-alpha":{"draws":19,"losses":24,"wins":23},"stepfun/step-3.7-flash":{"draws":16,"losses":19,"wins":25},"stepfun/step-5-preview":{"draws":3,"losses":15,"wins":2},"tencent/hy3-preview":{"draws":13,"losses":21,"wins":12},"tencent/hy4-preview":{"draws":15,"losses":47,"wins":18},"thinkingmachines/inkling":{"draws":25,"losses":29,"wins":32},"thinkingmachines/inkling-small":{"draws":30,"losses":16,"wins":38},"unbiased/pareto-26.10":{"draws":0,"losses":28,"wins":0},"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":25,"losses":52,"wins":7},"x-ai/grok-4.7":{"draws":13,"losses":58,"wins":5},"x-ai/grok-build-0.1":{"draws":9,"losses":10,"wins":9},"xiaomi/mimo-v2.5":{"draws":38,"losses":46,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":16,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":25,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":40,"wins":7},"z-ai/glm-5.2":{"draws":37,"losses":80,"wins":51},"z-ai/glm-5.3":{"draws":16,"losses":53,"wins":11},"z-ai/glm-5.3-flash":{"draws":17,"losses":53,"wins":14},"z-ai/glm-5.3-flashx":{"draws":20,"losses":52,"wins":12}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":19,"wins":11},"claude-fable-5":{"draws":7,"losses":36,"wins":5},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":30,"wins":5},"claude-opus-4-5":{"draws":26,"losses":34,"wins":18},"claude-opus-4-8":{"draws":11,"losses":26,"wins":7},"claude-opus-5":{"draws":14,"losses":66,"wins":2},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":11,"losses":27,"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":23,"losses":27,"wins":22},"deepseek/deepseek-v4-pro":{"draws":16,"losses":20,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":23,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":27,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":37,"wins":4},"elorian/glimpse":{"draws":7,"losses":16,"wins":3},"fireworks/ember-1":{"draws":14,"losses":24,"wins":10},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":17},"gemini-4-argon":{"draws":4,"losses":44,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":17},"google/gemini-3.5-flash":{"draws":14,"losses":32,"wins":14},"google/gemini-3.5-flash-lite":{"draws":19,"losses":27,"wins":38},"google/gemini-3.6-flash":{"draws":28,"losses":48,"wins":16},"google/gemini-3.8-flash":{"draws":12,"losses":28,"wins":8},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":10},"gpt-4.1":{"draws":3,"losses":6,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":21,"wins":9},"gpt-5.4":{"draws":10,"losses":30,"wins":6},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":11},"gpt-5.4-nano":{"draws":16,"losses":14,"wins":18},"gpt-5.5":{"draws":18,"losses":20,"wins":6},"gpt-5.6-luna":{"draws":17,"losses":16,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":6},"gpt-5.6-terra":{"draws":10,"losses":24,"wins":12},"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},"gpt-6.1-terra":{"draws":4,"losses":44,"wins":0},"gpt-6.1-terra-pro":{"draws":2,"losses":45,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":9,"wins":12},"inception/mercury-3":{"draws":10,"losses":14,"wins":8},"inclusionai/ling-3.0-flash":{"draws":15,"losses":6,"wins":13},"inclusionai/ling-3.1-flash":{"draws":5,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":15,"losses":16,"wins":21},"meta/muse-glimmer-30b":{"draws":14,"losses":16,"wins":12},"meta/muse-spark-1.2":{"draws":12,"losses":23,"wins":11},"meta/muse-spark-1.3":{"draws":12,"losses":32,"wins":4},"meta/muse-spark-open":{"draws":11,"losses":28,"wins":9},"meta/muse-wonder":{"draws":11,"losses":30,"wins":7},"minimax/minimax-m3":{"draws":9,"losses":8,"wins":9},"minimax/minimax-m3.1-flash":{"draws":11,"losses":15,"wins":16},"mistralai/mistral-large-4-0":{"draws":9,"losses":16,"wins":5},"mistralai/mistral-medium-3-5":{"draws":9,"losses":3,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":17,"losses":21,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":42,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":6,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":6,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":8,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":13,"wins":3},"o3":{"draws":13,"losses":34,"wins":19},"openai/gpt-oss-120b":{"draws":12,"losses":13,"wins":17},"poolside/laguna-s-2.1":{"draws":16,"losses":20,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":14,"wins":8},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":18,"wins":8},"qwen/qwen3.8-27b":{"draws":12,"losses":16,"wins":6},"qwen/qwen3.8-flash":{"draws":14,"losses":9,"wins":9},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":17},"qwen/qwen3.8-max-0902":{"draws":12,"losses":29,"wins":7},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":17,"losses":17,"wins":10},"stealth/ox-alpha":{"draws":36,"losses":98,"wins":24},"stealth/space-bunny-alpha":{"draws":9,"losses":19,"wins":10},"stepfun/step-3.7-flash":{"draws":9,"losses":9,"wins":16},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":14,"losses":25,"wins":7},"thinkingmachines/inkling":{"draws":20,"losses":17,"wins":27},"thinkingmachines/inkling-small":{"draws":12,"losses":5,"wins":15},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":10,"losses":29,"wins":9},"x-ai/grok-4.6":{"draws":15,"losses":25,"wins":8},"x-ai/grok-4.7":{"draws":5,"losses":36,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":28,"losses":25,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":8,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":22,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":22,"wins":5},"z-ai/glm-5.2":{"draws":30,"losses":40,"wins":26},"z-ai/glm-5.3":{"draws":6,"losses":37,"wins":3},"z-ai/glm-5.3-flash":{"draws":14,"losses":27,"wins":7},"z-ai/glm-5.3-flashx":{"draws":7,"losses":31,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":17,"wins":1},"elorian/glimpse":{"draws":0,"losses":6,"wins":2},"fireworks/ember-1":{"draws":0,"losses":11,"wins":7},"gemini-3.1-pro-preview":{"draws":0,"losses":8,"wins":10},"gemini-4-argon":{"draws":0,"losses":18,"wins":0},"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},"gpt-6.1-terra":{"draws":0,"losses":18,"wins":0},"gpt-6.1-terra-pro":{"draws":0,"losses":18,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":7,"wins":7},"inception/mercury-3":{"draws":0,"losses":7,"wins":3},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":7},"inclusionai/ling-3.1-flash":{"draws":0,"losses":3,"wins":3},"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-spark-open":{"draws":0,"losses":15,"wins":3},"meta/muse-wonder":{"draws":0,"losses":17,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":8},"minimax/minimax-m3.1-flash":{"draws":0,"losses":14,"wins":4},"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":1,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":12,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":18,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":6,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":7,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":6,"wins":2},"o3":{"draws":1,"losses":23,"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},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":10,"wins":6},"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},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"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":{"draws":0,"losses":6,"wins":0},"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":4,"wins":6},"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":2,"wins":32},"claude-fable-5":{"draws":6,"losses":18,"wins":24},"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":17,"losses":22,"wins":39},"claude-opus-4-8":{"draws":11,"losses":14,"wins":19},"claude-opus-5":{"draws":10,"losses":51,"wins":21},"claude-opus-5-5":{"draws":9,"losses":39,"wins":4},"claude-sonnet-5":{"draws":8,"losses":11,"wins":29},"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":8,"wins":55},"deepseek/deepseek-v4-pro":{"draws":13,"losses":8,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":12,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":16,"wins":26},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":16,"wins":25},"elorian/glimpse":{"draws":4,"losses":8,"wins":14},"fireworks/ember-1":{"draws":5,"losses":12,"wins":31},"gemini-3.1-pro-preview":{"draws":8,"losses":14,"wins":26},"gemini-4-argon":{"draws":1,"losses":37,"wins":10},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":8,"losses":17,"wins":35},"google/gemini-3.5-flash-lite":{"draws":13,"losses":19,"wins":52},"google/gemini-3.6-flash":{"draws":14,"losses":31,"wins":47},"google/gemini-3.8-flash":{"draws":4,"losses":17,"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":6,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":10,"losses":9,"wins":29},"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":7,"wins":29},"gpt-6-astra":{"draws":0,"losses":43,"wins":5},"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":36,"wins":10},"gpt-6.1-terra":{"draws":4,"losses":35,"wins":9},"gpt-6.1-terra-pro":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":25},"inception/mercury-3":{"draws":9,"losses":8,"wins":15},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":24},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":8,"losses":4,"wins":40},"meta/muse-glimmer-30b":{"draws":7,"losses":6,"wins":29},"meta/muse-spark-1.2":{"draws":8,"losses":12,"wins":26},"meta/muse-spark-1.3":{"draws":6,"losses":19,"wins":23},"meta/muse-spark-open":{"draws":8,"losses":13,"wins":27},"meta/muse-wonder":{"draws":11,"losses":26,"wins":11},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"minimax/minimax-m3.1-flash":{"draws":9,"losses":10,"wins":23},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":13,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":35,"wins":11},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":2,"wins":16},"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},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":8,"wins":25},"stealth/ox-alpha":{"draws":29,"losses":51,"wins":78},"stealth/space-bunny-alpha":{"draws":8,"losses":7,"wins":23},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":8,"losses":18,"wins":20},"thinkingmachines/inkling":{"draws":15,"losses":7,"wins":42},"thinkingmachines/inkling-small":{"draws":5,"losses":7,"wins":36},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":10,"losses":11,"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":4,"losses":2,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":10,"wins":17},"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":5,"losses":21,"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":7,"losses":7,"wins":30},"claude-fable-5":{"draws":11,"losses":17,"wins":20},"claude-fable-5-1":{"draws":3,"losses":36,"wins":15},"claude-haiku-5-5":{"draws":13,"losses":15,"wins":18},"claude-opus-4-5":{"draws":14,"losses":17,"wins":47},"claude-opus-4-8":{"draws":11,"losses":12,"wins":21},"claude-opus-5":{"draws":9,"losses":52,"wins":21},"claude-opus-5-5":{"draws":7,"losses":39,"wins":6},"claude-sonnet-5":{"draws":9,"losses":8,"wins":31},"claude-sonnet-5-5":{"draws":2,"losses":19,"wins":27},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":16,"losses":4,"wins":52},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":9,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":12,"wins":28},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":19,"wins":19},"elorian/glimpse":{"draws":6,"losses":7,"wins":13},"fireworks/ember-1":{"draws":11,"losses":13,"wins":24},"gemini-3.1-pro-preview":{"draws":7,"losses":9,"wins":32},"gemini-4-argon":{"draws":9,"losses":29,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":10,"losses":11,"wins":39},"google/gemini-3.5-flash-lite":{"draws":17,"losses":10,"wins":57},"google/gemini-3.6-flash":{"draws":14,"losses":24,"wins":54},"google/gemini-3.8-flash":{"draws":12,"losses":13,"wins":23},"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":10,"losses":3,"wins":29},"gpt-5.4":{"draws":12,"losses":11,"wins":23},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":20},"gpt-5.4-nano":{"draws":7,"losses":7,"wins":34},"gpt-5.5":{"draws":9,"losses":7,"wins":28},"gpt-5.6-luna":{"draws":9,"losses":6,"wins":33},"gpt-5.6-sol":{"draws":8,"losses":15,"wins":25},"gpt-5.6-terra":{"draws":8,"losses":3,"wins":35},"gpt-6-astra":{"draws":5,"losses":36,"wins":7},"gpt-6-luna":{"draws":9,"losses":12,"wins":27},"gpt-6-sol":{"draws":3,"losses":36,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"gpt-6.1-terra":{"draws":6,"losses":39,"wins":3},"gpt-6.1-terra-pro":{"draws":9,"losses":32,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":26},"inception/mercury-3":{"draws":9,"losses":3,"wins":20},"inclusionai/ling-3.0-flash":{"draws":10,"losses":1,"wins":23},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":42},"meta/muse-glimmer-30b":{"draws":9,"losses":7,"wins":26},"meta/muse-spark-1.2":{"draws":6,"losses":9,"wins":31},"meta/muse-spark-1.3":{"draws":11,"losses":19,"wins":18},"meta/muse-spark-open":{"draws":7,"losses":13,"wins":28},"meta/muse-wonder":{"draws":11,"losses":20,"wins":17},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":25},"minimax/minimax-m3.1-flash":{"draws":9,"losses":7,"wins":26},"mistralai/mistral-large-4-0":{"draws":11,"losses":4,"wins":15},"mistralai/mistral-medium-3-5":{"draws":1,"losses":1,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":13,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":31,"wins":16},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":1,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":4,"wins":17},"o3":{"draws":12,"losses":17,"wins":37},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":8,"losses":7,"wins":31},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":20,"wins":23},"qwen/qwen3.8-27b":{"draws":6,"losses":7,"wins":21},"qwen/qwen3.8-flash":{"draws":10,"losses":2,"wins":20},"qwen/qwen3.8-max":{"draws":6,"losses":15,"wins":27},"qwen/qwen3.8-max-0902":{"draws":11,"losses":13,"wins":24},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":9,"wins":28},"stealth/ox-alpha":{"draws":38,"losses":47,"wins":73},"stealth/space-bunny-alpha":{"draws":7,"losses":7,"wins":24},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":3,"wins":9},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":18},"tencent/hy4-preview":{"draws":13,"losses":9,"wins":24},"thinkingmachines/inkling":{"draws":19,"losses":5,"wins":40},"thinkingmachines/inkling-small":{"draws":12,"losses":5,"wins":31},"unbiased/pareto-26.10":{"draws":2,"losses":12,"wins":2},"unbiased/pareto-26.10-preview":{"draws":3,"losses":11,"wins":2},"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":3,"losses":3,"wins":10},"xiaomi/mimo-v2.5":{"draws":22,"losses":2,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":7,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":10,"wins":13},"z-ai/glm-5.2":{"draws":17,"losses":16,"wins":63},"z-ai/glm-5.3":{"draws":8,"losses":17,"wins":21},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":25},"z-ai/glm-5.3-flashx":{"draws":8,"losses":14,"wins":26}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":37},"claude-fable-5":{"draws":0,"losses":11,"wins":31},"claude-fable-5-1":{"draws":1,"losses":32,"wins":13},"claude-haiku-5-5":{"draws":0,"losses":4,"wins":36},"claude-opus-4-5":{"draws":1,"losses":6,"wins":61},"claude-opus-4-8":{"draws":3,"losses":8,"wins":27},"claude-opus-5":{"draws":3,"losses":31,"wins":36},"claude-opus-5-5":{"draws":1,"losses":33,"wins":12},"claude-sonnet-5":{"draws":0,"losses":7,"wins":35},"claude-sonnet-5-5":{"draws":0,"losses":15,"wins":27},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":65},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":5,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":8,"wins":27},"elorian/glimpse":{"draws":2,"losses":5,"wins":15},"fireworks/ember-1":{"draws":3,"losses":9,"wins":30},"gemini-3.1-pro-preview":{"draws":2,"losses":5,"wins":35},"gemini-4-argon":{"draws":5,"losses":19,"wins":18},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":2,"losses":2,"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":3,"losses":6,"wins":33},"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":1,"wins":44},"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":3,"losses":3,"wins":34},"gpt-6-astra":{"draws":3,"losses":31,"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":25,"wins":16},"gpt-6.1-terra":{"draws":3,"losses":19,"wins":20},"gpt-6.1-terra-pro":{"draws":6,"losses":21,"wins":15},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":27},"inception/mercury-3":{"draws":2,"losses":1,"wins":27},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":4},"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":3,"losses":6,"wins":33},"meta/muse-spark-open":{"draws":0,"losses":6,"wins":36},"meta/muse-wonder":{"draws":5,"losses":10,"wins":27},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":23},"minimax/minimax-m3.1-flash":{"draws":4,"losses":4,"wins":28},"mistralai/mistral-large-4-0":{"draws":2,"losses":3,"wins":21},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":23},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":34},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":17,"wins":22},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":2,"wins":16},"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":5,"wins":20},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":7,"wins":35},"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":5,"wins":36},"qwen/qwen3.8-max-0902":{"draws":4,"losses":8,"wins":30},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":1,"wins":37},"stealth/ox-alpha":{"draws":5,"losses":16,"wins":119},"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":0,"wins":8},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":18},"tencent/hy4-preview":{"draws":3,"losses":6,"wins":31},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":49},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":39},"unbiased/pareto-26.10":{"draws":1,"losses":8,"wins":5},"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":11,"wins":13},"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":0,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":6,"wins":22},"z-ai/glm-5.2":{"draws":4,"losses":9,"wins":71},"z-ai/glm-5.3":{"draws":3,"losses":6,"wins":31},"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":13,"losses":9,"wins":6},"claude-fable-5":{"draws":9,"losses":21,"wins":0},"claude-fable-5-1":{"draws":1,"losses":30,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":18,"wins":1},"claude-opus-4-5":{"draws":24,"losses":22,"wins":4},"claude-opus-4-8":{"draws":13,"losses":15,"wins":2},"claude-opus-5":{"draws":11,"losses":37,"wins":2},"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":4,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":21,"losses":15,"wins":10},"deepseek/deepseek-v4-pro":{"draws":13,"losses":9,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":11,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":13,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":19,"wins":1},"elorian/glimpse":{"draws":5,"losses":9,"wins":2},"fireworks/ember-1":{"draws":14,"losses":11,"wins":5},"gemini-3.1-pro-preview":{"draws":13,"losses":11,"wins":6},"gemini-4-argon":{"draws":3,"losses":27,"wins":0},"google/gemini-3.1-flash-lite":{"draws":12,"losses":3,"wins":5},"google/gemini-3.5-flash":{"draws":15,"losses":20,"wins":3},"google/gemini-3.5-flash-lite":{"draws":23,"losses":21,"wins":8},"google/gemini-3.6-flash":{"draws":22,"losses":27,"wins":7},"google/gemini-3.8-flash":{"draws":9,"losses":19,"wins":2},"google/gemma-4-31b-it":{"draws":13,"losses":2,"wins":3},"gpt-4.1":{"draws":6,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":12,"wins":2},"gpt-5.4":{"draws":8,"losses":17,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":7,"wins":5},"gpt-5.4-nano":{"draws":8,"losses":19,"wins":5},"gpt-5.5":{"draws":14,"losses":7,"wins":5},"gpt-5.6-luna":{"draws":18,"losses":9,"wins":3},"gpt-5.6-sol":{"draws":8,"losses":20,"wins":2},"gpt-5.6-terra":{"draws":15,"losses":13,"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},"gpt-6.1-terra":{"draws":9,"losses":21,"wins":0},"gpt-6.1-terra-pro":{"draws":10,"losses":19,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":0,"wins":9},"inception/mercury-3":{"draws":12,"losses":9,"wins":1},"inclusionai/ling-3.0-flash":{"draws":13,"losses":7,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":6},"meta/muse-glimmer-30b":{"draws":15,"losses":7,"wins":2},"meta/muse-spark-1.2":{"draws":11,"losses":15,"wins":2},"meta/muse-spark-1.3":{"draws":9,"losses":20,"wins":1},"meta/muse-spark-open":{"draws":13,"losses":15,"wins":2},"meta/muse-wonder":{"draws":9,"losses":17,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":3},"minimax/minimax-m3.1-flash":{"draws":6,"losses":10,"wins":8},"mistralai/mistral-large-4-0":{"draws":12,"losses":6,"wins":0},"mistralai/mistral-medium-3-5":{"draws":11,"losses":4,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":10,"wins":2},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":26,"wins":0},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":5,"wins":5},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":1},"o3":{"draws":9,"losses":21,"wins":8},"openai/gpt-oss-120b":{"draws":13,"losses":8,"wins":3},"poolside/laguna-s-2.1":{"draws":8,"losses":15,"wins":3},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":12,"wins":2},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":4},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":1},"qwen/qwen3.8-max":{"draws":14,"losses":10,"wins":6},"qwen/qwen3.8-max-0902":{"draws":15,"losses":11,"wins":4},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":10,"wins":3},"stealth/ox-alpha":{"draws":29,"losses":42,"wins":11},"stealth/space-bunny-alpha":{"draws":11,"losses":9,"wins":2},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":3},"stepfun/step-5-preview":{"draws":0,"losses":7,"wins":3},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":3},"tencent/hy4-preview":{"draws":10,"losses":13,"wins":5},"thinkingmachines/inkling":{"draws":21,"losses":8,"wins":7},"thinkingmachines/inkling-small":{"draws":17,"losses":6,"wins":7},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"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":13,"losses":15,"wins":2},"x-ai/grok-4.7":{"draws":5,"losses":20,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":23,"losses":13,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":5},"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":26,"losses":26,"wins":8},"z-ai/glm-5.3":{"draws":11,"losses":17,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":20,"wins":4},"z-ai/glm-5.3-flashx":{"draws":15,"losses":14,"wins":1}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":13,"wins":16},"claude-fable-5":{"draws":11,"losses":29,"wins":8},"claude-fable-5-1":{"draws":4,"losses":48,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":24,"wins":9},"claude-opus-4-5":{"draws":15,"losses":36,"wins":27},"claude-opus-4-8":{"draws":10,"losses":20,"wins":14},"claude-opus-5":{"draws":19,"losses":60,"wins":3},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":6,"losses":20,"wins":22},"claude-sonnet-5-5":{"draws":8,"losses":26,"wins":14},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":21,"losses":23,"wins":28},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":18,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":22,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":24,"wins":13},"elorian/glimpse":{"draws":3,"losses":13,"wins":10},"fireworks/ember-1":{"draws":9,"losses":19,"wins":20},"gemini-3.1-pro-preview":{"draws":9,"losses":15,"wins":24},"gemini-4-argon":{"draws":7,"losses":41,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":28},"google/gemini-3.5-flash":{"draws":14,"losses":28,"wins":18},"google/gemini-3.5-flash-lite":{"draws":22,"losses":18,"wins":44},"google/gemini-3.6-flash":{"draws":17,"losses":46,"wins":29},"google/gemini-3.8-flash":{"draws":13,"losses":26,"wins":9},"google/gemma-4-31b-it":{"draws":9,"losses":7,"wins":12},"gpt-4.1":{"draws":4,"losses":6,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":14,"losses":13,"wins":15},"gpt-5.4":{"draws":12,"losses":27,"wins":7},"gpt-5.4-mini":{"draws":10,"losses":5,"wins":17},"gpt-5.4-nano":{"draws":9,"losses":17,"wins":22},"gpt-5.5":{"draws":12,"losses":21,"wins":11},"gpt-5.6-luna":{"draws":10,"losses":14,"wins":24},"gpt-5.6-sol":{"draws":6,"losses":38,"wins":4},"gpt-5.6-terra":{"draws":20,"losses":17,"wins":9},"gpt-6-astra":{"draws":4,"losses":43,"wins":1},"gpt-6-luna":{"draws":16,"losses":22,"wins":10},"gpt-6-sol":{"draws":5,"losses":34,"wins":9},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"gpt-6.1-terra":{"draws":4,"losses":39,"wins":5},"gpt-6.1-terra-pro":{"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":7,"wins":19},"inception/mercury-3":{"draws":8,"losses":15,"wins":9},"inclusionai/ling-3.0-flash":{"draws":17,"losses":4,"wins":13},"inclusionai/ling-3.1-flash":{"draws":3,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":9,"losses":17,"wins":26},"meta/muse-glimmer-30b":{"draws":11,"losses":7,"wins":24},"meta/muse-spark-1.2":{"draws":9,"losses":24,"wins":13},"meta/muse-spark-1.3":{"draws":5,"losses":31,"wins":12},"meta/muse-spark-open":{"draws":13,"losses":24,"wins":11},"meta/muse-wonder":{"draws":9,"losses":31,"wins":8},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":13},"minimax/minimax-m3.1-flash":{"draws":7,"losses":16,"wins":19},"mistralai/mistral-large-4-0":{"draws":13,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":16},"moonshotai/kimi-k3":{"draws":17,"losses":19,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":38,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":4,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":9},"o3":{"draws":11,"losses":32,"wins":23},"openai/gpt-oss-120b":{"draws":8,"losses":7,"wins":27},"poolside/laguna-s-2.1":{"draws":16,"losses":8,"wins":22},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":15},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"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":12,"wins":9},"qwen/qwen3.8-max":{"draws":16,"losses":22,"wins":10},"qwen/qwen3.8-max-0902":{"draws":13,"losses":28,"wins":7},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":20,"wins":15},"stealth/ox-alpha":{"draws":43,"losses":78,"wins":37},"stealth/space-bunny-alpha":{"draws":13,"losses":10,"wins":15},"stepfun/step-3.7-flash":{"draws":7,"losses":9,"wins":18},"stepfun/step-5-preview":{"draws":1,"losses":4,"wins":5},"tencent/hy3-preview":{"draws":5,"losses":9,"wins":12},"tencent/hy4-preview":{"draws":13,"losses":23,"wins":10},"thinkingmachines/inkling":{"draws":16,"losses":18,"wins":30},"thinkingmachines/inkling-small":{"draws":16,"losses":10,"wins":22},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":8,"losses":27,"wins":13},"x-ai/grok-4.6":{"draws":13,"losses":24,"wins":11},"x-ai/grok-4.7":{"draws":5,"losses":32,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":28,"losses":15,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":19,"wins":4},"z-ai/glm-5.2":{"draws":25,"losses":26,"wins":29},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":10,"losses":30,"wins":8},"z-ai/glm-5.3-flashx":{"draws":10,"losses":27,"wins":11}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":2,"wins":34},"claude-fable-5":{"draws":5,"losses":7,"wins":30},"claude-fable-5-1":{"draws":2,"losses":34,"wins":12},"claude-haiku-5-5":{"draws":3,"losses":5,"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":5,"losses":27,"wins":38},"claude-opus-5-5":{"draws":2,"losses":30,"wins":14},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":2,"wins":31},"elorian/glimpse":{"draws":2,"losses":1,"wins":19},"fireworks/ember-1":{"draws":3,"losses":2,"wins":37},"gemini-3.1-pro-preview":{"draws":5,"losses":5,"wins":32},"gemini-4-argon":{"draws":8,"losses":8,"wins":26},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":44},"google/gemini-3.5-flash-lite":{"draws":5,"losses":1,"wins":68},"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":6,"losses":28,"wins":8},"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},"gpt-6.1-terra":{"draws":9,"losses":19,"wins":14},"gpt-6.1-terra-pro":{"draws":9,"losses":20,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":1,"wins":28},"inception/mercury-3":{"draws":5,"losses":3,"wins":20},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"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":7,"losses":3,"wins":30},"meta/muse-spark-1.3":{"draws":7,"losses":6,"wins":29},"meta/muse-spark-open":{"draws":4,"losses":3,"wins":35},"meta/muse-wonder":{"draws":5,"losses":9,"wins":28},"minimax/minimax-m3":{"draws":5,"losses":0,"wins":17},"minimax/minimax-m3.1-flash":{"draws":2,"losses":2,"wins":32},"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":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":17,"wins":15},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":1,"wins":19},"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},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":0,"wins":38},"stealth/ox-alpha":{"draws":16,"losses":11,"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":6},"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":{"draws":2,"losses":10,"wins":2},"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":6,"losses":6,"wins":30},"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":1,"wins":16},"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":2,"wins":71},"z-ai/glm-5.3":{"draws":7,"losses":1,"wins":20},"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":15,"wins":26},"claude-fable-5":{"draws":4,"losses":23,"wins":21},"claude-fable-5-1":{"draws":2,"losses":46,"wins":6},"claude-haiku-5-5":{"draws":6,"losses":18,"wins":22},"claude-opus-4-5":{"draws":11,"losses":18,"wins":49},"claude-opus-4-8":{"draws":5,"losses":17,"wins":22},"claude-opus-5":{"draws":12,"losses":52,"wins":18},"claude-opus-5-5":{"draws":4,"losses":44,"wins":4},"claude-sonnet-5":{"draws":3,"losses":14,"wins":31},"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":5,"losses":21,"wins":46},"deepseek/deepseek-v4-pro":{"draws":2,"losses":15,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":10,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":22,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":24,"wins":18},"elorian/glimpse":{"draws":3,"losses":9,"wins":14},"fireworks/ember-1":{"draws":6,"losses":17,"wins":25},"gemini-3.1-pro-preview":{"draws":10,"losses":12,"wins":26},"gemini-4-argon":{"draws":3,"losses":37,"wins":8},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":22},"google/gemini-3.5-flash":{"draws":4,"losses":21,"wins":35},"google/gemini-3.5-flash-lite":{"draws":10,"losses":19,"wins":55},"google/gemini-3.6-flash":{"draws":6,"losses":32,"wins":54},"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":10,"wins":29},"gpt-5.4":{"draws":2,"losses":20,"wins":24},"gpt-5.4-mini":{"draws":6,"losses":6,"wins":20},"gpt-5.4-nano":{"draws":2,"losses":15,"wins":31},"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":10,"losses":11,"wins":27},"gpt-6-sol":{"draws":5,"losses":34,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":7},"gpt-6.1-terra":{"draws":7,"losses":33,"wins":8},"gpt-6.1-terra-pro":{"draws":8,"losses":33,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":7,"wins":23},"inception/mercury-3":{"draws":6,"losses":11,"wins":17},"inclusionai/ling-3.0-flash":{"draws":7,"losses":9,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":5,"losses":12,"wins":35},"meta/muse-glimmer-30b":{"draws":3,"losses":7,"wins":32},"meta/muse-spark-1.2":{"draws":3,"losses":20,"wins":23},"meta/muse-spark-1.3":{"draws":7,"losses":14,"wins":27},"meta/muse-spark-open":{"draws":4,"losses":20,"wins":24},"meta/muse-wonder":{"draws":7,"losses":24,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":6,"wins":17},"minimax/minimax-m3.1-flash":{"draws":4,"losses":12,"wins":26},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":3,"losses":5,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":14,"wins":26},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":35,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":9,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":6,"wins":15},"o3":{"draws":5,"losses":31,"wins":30},"openai/gpt-oss-120b":{"draws":3,"losses":8,"wins":31},"poolside/laguna-s-2.1":{"draws":3,"losses":13,"wins":30},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":18},"qwen/qwen3.7-plus":{"draws":3,"losses":4,"wins":17},"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":2,"losses":11,"wins":19},"qwen/qwen3.8-max":{"draws":7,"losses":21,"wins":20},"qwen/qwen3.8-max-0902":{"draws":10,"losses":15,"wins":23},"recursive/flint-v1.0":{"draws":2,"losses":4,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":14,"wins":26},"stealth/ox-alpha":{"draws":17,"losses":57,"wins":84},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":22},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":7,"wins":5},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":4,"losses":14,"wins":28},"thinkingmachines/inkling":{"draws":10,"losses":8,"wins":46},"thinkingmachines/inkling-small":{"draws":6,"losses":9,"wins":33},"unbiased/pareto-26.10":{"draws":1,"losses":12,"wins":3},"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":7,"losses":23,"wins":18},"x-ai/grok-4.7":{"draws":3,"losses":24,"wins":15},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":12},"xiaomi/mimo-v2.5":{"draws":6,"losses":21,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":14,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":18,"wins":10},"z-ai/glm-5.2":{"draws":11,"losses":26,"wins":59},"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":4,"losses":7,"wins":33},"claude-fable-5":{"draws":6,"losses":18,"wins":24},"claude-fable-5-1":{"draws":3,"losses":44,"wins":7},"claude-haiku-5-5":{"draws":8,"losses":10,"wins":28},"claude-opus-4-5":{"draws":9,"losses":11,"wins":58},"claude-opus-4-8":{"draws":2,"losses":16,"wins":26},"claude-opus-5":{"draws":11,"losses":51,"wins":20},"claude-opus-5-5":{"draws":7,"losses":39,"wins":6},"claude-sonnet-5":{"draws":6,"losses":7,"wins":35},"claude-sonnet-5-5":{"draws":6,"losses":20,"wins":22},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":8,"losses":9,"wins":55},"deepseek/deepseek-v4-pro":{"draws":6,"losses":9,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":8,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":9,"wins":36},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":18,"wins":25},"elorian/glimpse":{"draws":2,"losses":8,"wins":16},"fireworks/ember-1":{"draws":4,"losses":8,"wins":36},"gemini-3.1-pro-preview":{"draws":7,"losses":10,"wins":31},"gemini-4-argon":{"draws":2,"losses":35,"wins":11},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":26},"google/gemini-3.5-flash":{"draws":4,"losses":10,"wins":46},"google/gemini-3.5-flash-lite":{"draws":16,"losses":8,"wins":60},"google/gemini-3.6-flash":{"draws":17,"losses":24,"wins":51},"google/gemini-3.8-flash":{"draws":3,"losses":16,"wins":29},"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":7,"losses":6,"wins":29},"gpt-5.4":{"draws":5,"losses":11,"wins":30},"gpt-5.4-mini":{"draws":6,"losses":4,"wins":22},"gpt-5.4-nano":{"draws":4,"losses":10,"wins":34},"gpt-5.5":{"draws":8,"losses":12,"wins":24},"gpt-5.6-luna":{"draws":6,"losses":5,"wins":37},"gpt-5.6-sol":{"draws":5,"losses":18,"wins":25},"gpt-5.6-terra":{"draws":7,"losses":8,"wins":31},"gpt-6-astra":{"draws":3,"losses":40,"wins":5},"gpt-6-luna":{"draws":8,"losses":9,"wins":31},"gpt-6-sol":{"draws":4,"losses":24,"wins":20},"gpt-6.1-sol":{"draws":7,"losses":35,"wins":6},"gpt-6.1-terra":{"draws":6,"losses":34,"wins":8},"gpt-6.1-terra-pro":{"draws":4,"losses":37,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":3,"losses":2,"wins":29},"inception/mercury-3":{"draws":4,"losses":8,"wins":20},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":2,"losses":4,"wins":46},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":31},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":29},"meta/muse-spark-1.3":{"draws":6,"losses":13,"wins":29},"meta/muse-spark-open":{"draws":7,"losses":11,"wins":28},"meta/muse-wonder":{"draws":10,"losses":19,"wins":19},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":19},"minimax/minimax-m3.1-flash":{"draws":6,"losses":8,"wins":28},"mistralai/mistral-large-4-0":{"draws":10,"losses":4,"wins":16},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":9,"wins":32},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":39,"wins":8},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":2,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":3,"wins":16},"o3":{"draws":3,"losses":13,"wins":50},"openai/gpt-oss-120b":{"draws":7,"losses":2,"wins":33},"poolside/laguna-s-2.1":{"draws":11,"losses":3,"wins":32},"qwen/qwen3.7-max":{"draws":3,"losses":6,"wins":19},"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":3,"losses":7,"wins":24},"qwen/qwen3.8-flash":{"draws":5,"losses":10,"wins":17},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":25},"qwen/qwen3.8-max-0902":{"draws":7,"losses":10,"wins":31},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":9,"wins":31},"stealth/ox-alpha":{"draws":16,"losses":33,"wins":109},"stealth/space-bunny-alpha":{"draws":3,"losses":6,"wins":29},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":30},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":13},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":21},"tencent/hy4-preview":{"draws":6,"losses":13,"wins":27},"thinkingmachines/inkling":{"draws":7,"losses":10,"wins":47},"thinkingmachines/inkling-small":{"draws":6,"losses":6,"wins":36},"unbiased/pareto-26.10":{"draws":1,"losses":12,"wins":3},"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":3,"losses":14,"wins":31},"x-ai/grok-4.6":{"draws":5,"losses":15,"wins":28},"x-ai/grok-4.7":{"draws":6,"losses":27,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":10,"losses":5,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":5,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":13,"wins":14},"z-ai/glm-5.2":{"draws":15,"losses":14,"wins":67},"z-ai/glm-5.3":{"draws":4,"losses":23,"wins":19},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":27},"z-ai/glm-5.3-flashx":{"draws":6,"losses":6,"wins":20}}},"medium":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":6,"wins":13},"claude-fable-5":{"draws":6,"losses":27,"wins":9},"claude-fable-5-1":{"draws":3,"losses":39,"wins":4},"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":8,"losses":16,"wins":14},"claude-opus-5":{"draws":12,"losses":49,"wins":13},"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":23,"wins":8},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":19,"losses":17,"wins":26},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":15,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":25,"wins":8},"elorian/glimpse":{"draws":6,"losses":10,"wins":6},"fireworks/ember-1":{"draws":10,"losses":19,"wins":13},"gemini-3.1-pro-preview":{"draws":10,"losses":17,"wins":15},"gemini-4-argon":{"draws":1,"losses":38,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":5,"wins":14},"google/gemini-3.5-flash":{"draws":12,"losses":22,"wins":18},"google/gemini-3.5-flash-lite":{"draws":21,"losses":19,"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":17,"wins":9},"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":37,"wins":3},"gpt-6-luna":{"draws":12,"losses":14,"wins":16},"gpt-6-sol":{"draws":4,"losses":30,"wins":8},"gpt-6.1-sol":{"draws":4,"losses":32,"wins":6},"gpt-6.1-terra":{"draws":9,"losses":27,"wins":6},"gpt-6.1-terra-pro":{"draws":5,"losses":31,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":9,"wins":10},"inception/mercury-3":{"draws":7,"losses":8,"wins":13},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":16},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":0},"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":10,"losses":15,"wins":15},"meta/muse-spark-1.3":{"draws":8,"losses":22,"wins":12},"meta/muse-spark-open":{"draws":9,"losses":21,"wins":12},"meta/muse-wonder":{"draws":13,"losses":22,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":13},"minimax/minimax-m3.1-flash":{"draws":9,"losses":12,"wins":15},"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":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":35,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":7,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":6},"o3":{"draws":9,"losses":23,"wins":22},"openai/gpt-oss-120b":{"draws":10,"losses":9,"wins":17},"poolside/laguna-s-2.1":{"draws":12,"losses":13,"wins":17},"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":5,"losses":12,"wins":11},"qwen/qwen3.8-max":{"draws":14,"losses":13,"wins":15},"qwen/qwen3.8-max-0902":{"draws":8,"losses":25,"wins":9},"recursive/flint-v1.0":{"draws":2,"losses":4,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":15,"wins":12},"stealth/ox-alpha":{"draws":33,"losses":72,"wins":35},"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":3,"losses":4,"wins":5},"tencent/hy3-preview":{"draws":8,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":23,"wins":6},"thinkingmachines/inkling":{"draws":18,"losses":13,"wins":25},"thinkingmachines/inkling-small":{"draws":12,"losses":10,"wins":20},"unbiased/pareto-26.10":{"draws":2,"losses":12,"wins":0},"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":8,"losses":4,"wins":14},"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":24,"losses":28,"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":6,"wins":31},"claude-fable-5":{"draws":7,"losses":9,"wins":16},"claude-fable-5-1":{"draws":2,"losses":47,"wins":5},"claude-haiku-5-5":{"draws":8,"losses":13,"wins":25},"claude-opus-4-5":{"draws":16,"losses":12,"wins":50},"claude-opus-4-8":{"draws":10,"losses":8,"wins":26},"claude-opus-5":{"draws":10,"losses":47,"wins":25},"claude-opus-5-5":{"draws":5,"losses":39,"wins":8},"claude-sonnet-5":{"draws":8,"losses":10,"wins":30},"claude-sonnet-5-5":{"draws":11,"losses":16,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":15,"losses":3,"wins":54},"deepseek/deepseek-v4-pro":{"draws":7,"losses":8,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":10,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":14,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":18,"wins":20},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":10,"losses":7,"wins":31},"gemini-3.1-pro-preview":{"draws":12,"losses":7,"wins":29},"gemini-4-argon":{"draws":5,"losses":32,"wins":11},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":12,"losses":13,"wins":35},"google/gemini-3.5-flash-lite":{"draws":15,"losses":12,"wins":57},"google/gemini-3.6-flash":{"draws":15,"losses":30,"wins":47},"google/gemini-3.8-flash":{"draws":7,"losses":15,"wins":26},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":17},"gpt-4.1":{"draws":3,"losses":4,"wins":9},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":8,"wins":28},"gpt-5.4":{"draws":10,"losses":11,"wins":25},"gpt-5.4-mini":{"draws":7,"losses":4,"wins":21},"gpt-5.4-nano":{"draws":5,"losses":4,"wins":39},"gpt-5.5":{"draws":11,"losses":11,"wins":22},"gpt-5.6-luna":{"draws":11,"losses":7,"wins":30},"gpt-5.6-sol":{"draws":3,"losses":23,"wins":22},"gpt-5.6-terra":{"draws":12,"losses":6,"wins":28},"gpt-6-astra":{"draws":2,"losses":37,"wins":9},"gpt-6-luna":{"draws":12,"losses":8,"wins":28},"gpt-6-sol":{"draws":7,"losses":26,"wins":15},"gpt-6.1-sol":{"draws":5,"losses":30,"wins":13},"gpt-6.1-terra":{"draws":7,"losses":29,"wins":12},"gpt-6.1-terra-pro":{"draws":3,"losses":34,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":3,"wins":22},"inception/mercury-3":{"draws":8,"losses":6,"wins":18},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":25},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":6,"wins":41},"meta/muse-glimmer-30b":{"draws":7,"losses":5,"wins":30},"meta/muse-spark-1.2":{"draws":5,"losses":10,"wins":31},"meta/muse-spark-1.3":{"draws":10,"losses":16,"wins":22},"meta/muse-spark-open":{"draws":7,"losses":10,"wins":31},"meta/muse-wonder":{"draws":9,"losses":20,"wins":19},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":16},"minimax/minimax-m3.1-flash":{"draws":9,"losses":6,"wins":27},"mistralai/mistral-large-4-0":{"draws":6,"losses":9,"wins":15},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":7,"losses":10,"wins":29},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":29,"wins":13},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":2,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":3,"wins":14},"o3":{"draws":6,"losses":8,"wins":52},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":25},"poolside/laguna-s-2.1":{"draws":5,"losses":10,"wins":31},"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":11,"wins":22},"qwen/qwen3.8-27b":{"draws":9,"losses":5,"wins":20},"qwen/qwen3.8-flash":{"draws":6,"losses":8,"wins":18},"qwen/qwen3.8-max":{"draws":8,"losses":14,"wins":26},"qwen/qwen3.8-max-0902":{"draws":12,"losses":12,"wins":24},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":8,"wins":24},"stealth/ox-alpha":{"draws":30,"losses":46,"wins":82},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":8},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":16},"tencent/hy4-preview":{"draws":9,"losses":8,"wins":29},"thinkingmachines/inkling":{"draws":15,"losses":4,"wins":45},"thinkingmachines/inkling-small":{"draws":7,"losses":8,"wins":33},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":10,"losses":16,"wins":22},"x-ai/grok-4.6":{"draws":13,"losses":19,"wins":16},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":14},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":16,"losses":2,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":8,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":12,"wins":16},"z-ai/glm-5.2":{"draws":21,"losses":14,"wins":61},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":17},"z-ai/glm-5.3-flash":{"draws":8,"losses":16,"wins":24},"z-ai/glm-5.3-flashx":{"draws":10,"losses":14,"wins":24}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":3,"wins":39},"claude-fable-5":{"draws":3,"losses":11,"wins":34},"claude-fable-5-1":{"draws":3,"losses":23,"wins":12},"claude-haiku-5-5":{"draws":1,"losses":4,"wins":41},"claude-opus-4-5":{"draws":3,"losses":6,"wins":69},"claude-opus-4-8":{"draws":3,"losses":5,"wins":36},"claude-opus-5":{"draws":4,"losses":36,"wins":42},"claude-opus-5-5":{"draws":2,"losses":36,"wins":14},"claude-sonnet-5":{"draws":2,"losses":3,"wins":43},"claude-sonnet-5-5":{"draws":3,"losses":11,"wins":34},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":67},"deepseek/deepseek-v4-pro":{"draws":7,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":1,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":6,"wins":38},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":8,"wins":35},"elorian/glimpse":{"draws":2,"losses":3,"wins":21},"fireworks/ember-1":{"draws":1,"losses":8,"wins":39},"gemini-3.1-pro-preview":{"draws":2,"losses":3,"wins":43},"gemini-4-argon":{"draws":4,"losses":21,"wins":23},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":53},"google/gemini-3.5-flash-lite":{"draws":8,"losses":0,"wins":76},"google/gemini-3.6-flash":{"draws":8,"losses":11,"wins":73},"google/gemini-3.8-flash":{"draws":1,"losses":8,"wins":39},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":26},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":0,"wins":40},"gpt-5.4":{"draws":4,"losses":5,"wins":37},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":29},"gpt-5.4-nano":{"draws":2,"losses":1,"wins":45},"gpt-5.5":{"draws":3,"losses":8,"wins":33},"gpt-5.6-luna":{"draws":5,"losses":3,"wins":40},"gpt-5.6-sol":{"draws":5,"losses":8,"wins":35},"gpt-5.6-terra":{"draws":5,"losses":4,"wins":37},"gpt-6-astra":{"draws":5,"losses":33,"wins":10},"gpt-6-luna":{"draws":5,"losses":3,"wins":40},"gpt-6-sol":{"draws":6,"losses":15,"wins":27},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":15},"gpt-6.1-terra":{"draws":7,"losses":21,"wins":20},"gpt-6.1-terra-pro":{"draws":5,"losses":23,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inception/mercury-3":{"draws":2,"losses":0,"wins":30},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":48},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":36},"meta/muse-spark-1.2":{"draws":4,"losses":4,"wins":38},"meta/muse-spark-1.3":{"draws":3,"losses":7,"wins":38},"meta/muse-spark-open":{"draws":4,"losses":8,"wins":36},"meta/muse-wonder":{"draws":4,"losses":14,"wins":30},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"minimax/minimax-m3.1-flash":{"draws":6,"losses":3,"wins":33},"mistralai/mistral-large-4-0":{"draws":2,"losses":2,"wins":26},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":3,"losses":4,"wins":39},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":16,"wins":24},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":21},"o3":{"draws":2,"losses":6,"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":1,"losses":0,"wins":27},"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":3,"losses":3,"wins":26},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":42},"qwen/qwen3.8-max-0902":{"draws":4,"losses":9,"wins":35},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":1,"wins":42},"stealth/ox-alpha":{"draws":10,"losses":12,"wins":136},"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":1,"losses":0,"wins":11},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":21},"tencent/hy4-preview":{"draws":3,"losses":6,"wins":37},"thinkingmachines/inkling":{"draws":6,"losses":0,"wins":58},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":43},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":8},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":4},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":3,"losses":6,"wins":39},"x-ai/grok-4.6":{"draws":3,"losses":11,"wins":34},"x-ai/grok-4.7":{"draws":2,"losses":14,"wins":26},"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":2,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":2,"wins":25},"z-ai/glm-5.2":{"draws":7,"losses":4,"wins":85},"z-ai/glm-5.3":{"draws":5,"losses":7,"wins":34},"z-ai/glm-5.3-flash":{"draws":3,"losses":8,"wins":37},"z-ai/glm-5.3-flashx":{"draws":4,"losses":6,"wins":38}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":10,"wins":26},"claude-fable-5":{"draws":9,"losses":26,"wins":13},"claude-fable-5-1":{"draws":2,"losses":47,"wins":5},"claude-haiku-5-5":{"draws":5,"losses":14,"wins":11},"claude-opus-4-5":{"draws":22,"losses":19,"wins":37},"claude-opus-4-8":{"draws":6,"losses":20,"wins":18},"claude-opus-5":{"draws":17,"losses":55,"wins":10},"claude-opus-5-5":{"draws":7,"losses":43,"wins":2},"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":18,"losses":8,"wins":46},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":20,"wins":20},"elorian/glimpse":{"draws":3,"losses":9,"wins":14},"fireworks/ember-1":{"draws":14,"losses":11,"wins":23},"gemini-3.1-pro-preview":{"draws":13,"losses":14,"wins":21},"gemini-4-argon":{"draws":4,"losses":39,"wins":5},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":13,"losses":24,"wins":23},"google/gemini-3.5-flash-lite":{"draws":16,"losses":13,"wins":55},"google/gemini-3.6-flash":{"draws":25,"losses":33,"wins":34},"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":14,"losses":11,"wins":23},"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":28,"wins":12},"gpt-5.6-terra":{"draws":18,"losses":9,"wins":19},"gpt-6-astra":{"draws":2,"losses":43,"wins":3},"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},"gpt-6.1-terra":{"draws":8,"losses":35,"wins":5},"gpt-6.1-terra-pro":{"draws":7,"losses":38,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":23},"inception/mercury-3":{"draws":9,"losses":8,"wins":15},"inclusionai/ling-3.0-flash":{"draws":11,"losses":1,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":1,"wins":1},"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-spark-open":{"draws":5,"losses":19,"wins":24},"meta/muse-wonder":{"draws":10,"losses":27,"wins":11},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":20},"minimax/minimax-m3.1-flash":{"draws":8,"losses":10,"wins":24},"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":2,"wins":1},"moonshotai/kimi-k3":{"draws":13,"losses":12,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":37,"wins":9},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":8,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":6,"wins":12},"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},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":12,"wins":26},"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":3,"losses":6,"wins":3},"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":{"draws":0,"losses":15,"wins":1},"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":5,"losses":4,"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":9,"wins":21},"claude-fable-5":{"draws":7,"losses":33,"wins":8},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":11,"losses":20,"wins":15},"claude-opus-4-5":{"draws":20,"losses":14,"wins":28},"claude-opus-4-8":{"draws":13,"losses":16,"wins":15},"claude-opus-5":{"draws":13,"losses":61,"wins":8},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":13,"losses":11,"wins":24},"claude-sonnet-5-5":{"draws":10,"losses":21,"wins":17},"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":10,"losses":13,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":20,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":25,"wins":14},"elorian/glimpse":{"draws":6,"losses":12,"wins":8},"fireworks/ember-1":{"draws":16,"losses":19,"wins":13},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":22},"gemini-4-argon":{"draws":1,"losses":44,"wins":3},"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":42,"wins":27},"google/gemini-3.8-flash":{"draws":11,"losses":24,"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":11,"losses":14,"wins":17},"gpt-5.4":{"draws":13,"losses":24,"wins":9},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":13,"losses":8,"wins":27},"gpt-5.5":{"draws":17,"losses":17,"wins":10},"gpt-5.6-luna":{"draws":18,"losses":10,"wins":20},"gpt-5.6-sol":{"draws":7,"losses":33,"wins":8},"gpt-5.6-terra":{"draws":15,"losses":14,"wins":17},"gpt-6-astra":{"draws":6,"losses":41,"wins":1},"gpt-6-luna":{"draws":15,"losses":12,"wins":21},"gpt-6-sol":{"draws":8,"losses":34,"wins":6},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":4},"gpt-6.1-terra":{"draws":8,"losses":40,"wins":0},"gpt-6.1-terra-pro":{"draws":7,"losses":36,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"inception/mercury-3":{"draws":9,"losses":8,"wins":15},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":24},"inclusionai/ling-3.1-flash":{"draws":3,"losses":2,"wins":3},"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":23,"wins":11},"meta/muse-spark-1.3":{"draws":7,"losses":26,"wins":15},"meta/muse-spark-open":{"draws":15,"losses":19,"wins":14},"meta/muse-wonder":{"draws":11,"losses":25,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":16},"minimax/minimax-m3.1-flash":{"draws":10,"losses":13,"wins":19},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":11},"mistralai/mistral-medium-3-5":{"draws":10,"losses":3,"wins":15},"moonshotai/kimi-k3":{"draws":16,"losses":15,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":39,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":9,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":9},"o3":{"draws":9,"losses":19,"wins":38},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":26},"poolside/laguna-s-2.1":{"draws":14,"losses":6,"wins":26},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":15},"qwen/qwen3.7-plus":{"draws":5,"losses":5,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":20,"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":11,"losses":21,"wins":16},"qwen/qwen3.8-max-0902":{"draws":12,"losses":21,"wins":15},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":17,"losses":14,"wins":13},"stealth/ox-alpha":{"draws":47,"losses":61,"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":3,"losses":3,"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":{"draws":3,"losses":13,"wins":0},"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":13,"losses":21,"wins":14},"x-ai/grok-4.6":{"draws":12,"losses":25,"wins":11},"x-ai/grok-4.7":{"draws":1,"losses":31,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":7},"xiaomi/mimo-v2.5":{"draws":23,"losses":10,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":27,"losses":30,"wins":39},"z-ai/glm-5.3":{"draws":12,"losses":29,"wins":5},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"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":15,"losses":8,"wins":21},"claude-fable-5":{"draws":13,"losses":27,"wins":8},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":24,"losses":26,"wins":28},"claude-opus-4-8":{"draws":5,"losses":15,"wins":8},"claude-opus-5":{"draws":10,"losses":66,"wins":6},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":13,"losses":22,"wins":13},"claude-sonnet-5-5":{"draws":10,"losses":28,"wins":10},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":18,"wins":33},"deepseek/deepseek-v4-pro":{"draws":13,"losses":15,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":24,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":29,"wins":9},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":17,"losses":15,"wins":16},"gemini-3.1-pro-preview":{"draws":11,"losses":20,"wins":17},"gemini-4-argon":{"draws":4,"losses":38,"wins":6},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":17,"losses":19,"wins":24},"google/gemini-3.5-flash-lite":{"draws":21,"losses":14,"wins":49},"google/gemini-3.6-flash":{"draws":20,"losses":45,"wins":27},"google/gemini-3.8-flash":{"draws":11,"losses":25,"wins":12},"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":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":13,"wins":16},"gpt-5.4":{"draws":14,"losses":21,"wins":11},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":11},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":24},"gpt-5.5":{"draws":17,"losses":16,"wins":11},"gpt-5.6-luna":{"draws":17,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":9,"losses":29,"wins":10},"gpt-5.6-terra":{"draws":13,"losses":19,"wins":14},"gpt-6-astra":{"draws":1,"losses":45,"wins":2},"gpt-6-luna":{"draws":15,"losses":16,"wins":17},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":1,"losses":46,"wins":1},"gpt-6.1-terra":{"draws":1,"losses":46,"wins":1},"gpt-6.1-terra-pro":{"draws":1,"losses":45,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":5,"wins":17},"inception/mercury-3":{"draws":11,"losses":12,"wins":9},"inclusionai/ling-3.0-flash":{"draws":17,"losses":0,"wins":17},"inclusionai/ling-3.1-flash":{"draws":1,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":13,"losses":14,"wins":25},"meta/muse-glimmer-30b":{"draws":12,"losses":9,"wins":21},"meta/muse-spark-1.2":{"draws":13,"losses":20,"wins":13},"meta/muse-spark-1.3":{"draws":9,"losses":23,"wins":16},"meta/muse-spark-open":{"draws":15,"losses":20,"wins":13},"meta/muse-wonder":{"draws":11,"losses":26,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":12},"minimax/minimax-m3.1-flash":{"draws":11,"losses":12,"wins":19},"mistralai/mistral-large-4-0":{"draws":9,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":10,"losses":3,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":16,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":43,"wins":1},"nex-agi/nex-n2-pro":{"draws":8,"losses":2,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":12,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":6,"wins":8},"o3":{"draws":14,"losses":20,"wins":32},"openai/gpt-oss-120b":{"draws":12,"losses":10,"wins":20},"poolside/laguna-s-2.1":{"draws":17,"losses":9,"wins":20},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"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":15,"losses":8,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":20,"wins":14},"qwen/qwen3.8-max-0902":{"draws":11,"losses":21,"wins":16},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":15,"wins":15},"stealth/ox-alpha":{"draws":35,"losses":76,"wins":47},"stealth/space-bunny-alpha":{"draws":9,"losses":14,"wins":15},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":20},"stepfun/step-5-preview":{"draws":3,"losses":7,"wins":2},"tencent/hy3-preview":{"draws":9,"losses":9,"wins":8},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":22,"losses":12,"wins":30},"thinkingmachines/inkling-small":{"draws":19,"losses":4,"wins":25},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":13,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":8},"xiaomi/mimo-v2.5":{"draws":23,"losses":15,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":6,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":18,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":12},"z-ai/glm-5.2":{"draws":36,"losses":24,"wins":36},"z-ai/glm-5.3":{"draws":6,"losses":35,"wins":5},"z-ai/glm-5.3-flash":{"draws":9,"losses":26,"wins":13},"z-ai/glm-5.3-flashx":{"draws":8,"losses":25,"wins":15}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":5,"wins":58},"claude-fable-5":{"draws":12,"losses":23,"wins":49},"claude-fable-5-1":{"draws":7,"losses":70,"wins":19},"claude-haiku-5-5":{"draws":14,"losses":14,"wins":52},"claude-opus-4-5":{"draws":26,"losses":8,"wins":102},"claude-opus-4-8":{"draws":13,"losses":10,"wins":53},"claude-opus-5":{"draws":18,"losses":59,"wins":55},"claude-opus-5-5":{"draws":8,"losses":60,"wins":24},"claude-sonnet-5":{"draws":13,"losses":9,"wins":62},"claude-sonnet-5-5":{"draws":8,"losses":30,"wins":46},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":28},"deepseek/deepseek-v4-flash":{"draws":18,"losses":1,"wins":105},"deepseek/deepseek-v4-pro":{"draws":9,"losses":12,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":12,"wins":57},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":16,"wins":54},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":20,"wins":53},"elorian/glimpse":{"draws":8,"losses":9,"wins":31},"fireworks/ember-1":{"draws":10,"losses":12,"wins":62},"gemini-3.1-pro-preview":{"draws":11,"losses":10,"wins":63},"gemini-4-argon":{"draws":11,"losses":46,"wins":27},"google/gemini-3.1-flash-lite":{"draws":11,"losses":1,"wins":40},"google/gemini-3.5-flash":{"draws":14,"losses":7,"wins":83},"google/gemini-3.5-flash-lite":{"draws":22,"losses":10,"wins":112},"google/gemini-3.6-flash":{"draws":20,"losses":29,"wins":111},"google/gemini-3.8-flash":{"draws":7,"losses":19,"wins":58},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":37},"gpt-4.1":{"draws":4,"losses":1,"wins":23},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":6},"gpt-5":{"draws":10,"losses":5,"wins":61},"gpt-5.4":{"draws":9,"losses":14,"wins":57},"gpt-5.4-mini":{"draws":13,"losses":4,"wins":39},"gpt-5.4-nano":{"draws":8,"losses":3,"wins":69},"gpt-5.5":{"draws":11,"losses":22,"wins":47},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":63},"gpt-5.6-sol":{"draws":16,"losses":23,"wins":45},"gpt-5.6-terra":{"draws":11,"losses":8,"wins":61},"gpt-6-astra":{"draws":6,"losses":59,"wins":19},"gpt-6-luna":{"draws":12,"losses":9,"wins":63},"gpt-6-sol":{"draws":13,"losses":29,"wins":42},"gpt-6.1-sol":{"draws":7,"losses":54,"wins":23},"gpt-6.1-terra":{"draws":10,"losses":42,"wins":32},"gpt-6.1-terra-pro":{"draws":8,"losses":50,"wins":26},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":1,"wins":39},"inception/mercury-3":{"draws":5,"losses":6,"wins":45},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":48},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":7,"wins":72},"meta/muse-glimmer-30b":{"draws":5,"losses":9,"wins":66},"meta/muse-spark-1.2":{"draws":12,"losses":14,"wins":58},"meta/muse-spark-1.3":{"draws":13,"losses":17,"wins":54},"meta/muse-spark-open":{"draws":12,"losses":13,"wins":59},"meta/muse-wonder":{"draws":9,"losses":32,"wins":43},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":39},"minimax/minimax-m3.1-flash":{"draws":11,"losses":7,"wins":54},"mistralai/mistral-large-4-0":{"draws":10,"losses":6,"wins":40},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":13,"losses":10,"wins":61},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":34,"wins":42},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":38},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":1,"wins":54},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":26},"o3":{"draws":8,"losses":10,"wins":90},"openai/gpt-oss-120b":{"draws":7,"losses":2,"wins":67},"poolside/laguna-s-2.1":{"draws":5,"losses":3,"wins":76},"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":17,"losses":9,"wins":58},"qwen/qwen3.8-27b":{"draws":11,"losses":6,"wins":39},"qwen/qwen3.8-flash":{"draws":8,"losses":3,"wins":45},"qwen/qwen3.8-max":{"draws":14,"losses":5,"wins":65},"qwen/qwen3.8-max-0902":{"draws":13,"losses":13,"wins":58},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":5,"wins":62},"stealth/ox-alpha":{"draws":45,"losses":28,"wins":211},"stealth/space-bunny-alpha":{"draws":14,"losses":5,"wins":49},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":52},"stepfun/step-5-preview":{"draws":5,"losses":2,"wins":17},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":34},"tencent/hy4-preview":{"draws":4,"losses":13,"wins":63},"thinkingmachines/inkling":{"draws":20,"losses":5,"wins":91},"thinkingmachines/inkling-small":{"draws":15,"losses":2,"wins":67},"unbiased/pareto-26.10":{"draws":1,"losses":19,"wins":8},"unbiased/pareto-26.10-preview":{"draws":3,"losses":16,"wins":9},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":13},"x-ai/grok-4.5":{"draws":13,"losses":17,"wins":54},"x-ai/grok-4.6":{"draws":16,"losses":15,"wins":53},"x-ai/grok-4.7":{"draws":7,"losses":40,"wins":29},"x-ai/grok-build-0.1":{"draws":8,"losses":0,"wins":20},"xiaomi/mimo-v2.5":{"draws":28,"losses":6,"wins":94},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":2,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":40},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":16,"wins":31},"z-ai/glm-5.2":{"draws":23,"losses":11,"wins":134},"z-ai/glm-5.3":{"draws":9,"losses":23,"wins":48},"z-ai/glm-5.3-flash":{"draws":9,"losses":19,"wins":56},"z-ai/glm-5.3-flashx":{"draws":15,"losses":12,"wins":57}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":50},"claude-fable-5":{"draws":3,"losses":2,"wins":49},"claude-fable-5-1":{"draws":6,"losses":23,"wins":31},"claude-haiku-5-5":{"draws":2,"losses":3,"wins":47},"claude-opus-4-5":{"draws":4,"losses":1,"wins":83},"claude-opus-4-8":{"draws":1,"losses":1,"wins":48},"claude-opus-5":{"draws":3,"losses":19,"wins":72},"claude-opus-5-5":{"draws":4,"losses":18,"wins":22},"claude-sonnet-5":{"draws":0,"losses":0,"wins":54},"claude-sonnet-5-5":{"draws":4,"losses":10,"wins":40},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":22},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":81},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":2,"wins":51},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":0,"wins":51},"elorian/glimpse":{"draws":1,"losses":0,"wins":29},"fireworks/ember-1":{"draws":0,"losses":0,"wins":54},"gemini-3.1-pro-preview":{"draws":1,"losses":3,"wins":50},"gemini-4-argon":{"draws":2,"losses":16,"wins":36},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":35},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":68},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":94},"google/gemini-3.6-flash":{"draws":2,"losses":10,"wins":90},"google/gemini-3.8-flash":{"draws":3,"losses":2,"wins":49},"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":0,"wins":48},"gpt-5.4":{"draws":1,"losses":4,"wins":47},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":35},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":56},"gpt-5.5":{"draws":2,"losses":0,"wins":48},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":51},"gpt-5.6-sol":{"draws":1,"losses":5,"wins":48},"gpt-5.6-terra":{"draws":0,"losses":1,"wins":51},"gpt-6-astra":{"draws":3,"losses":24,"wins":27},"gpt-6-luna":{"draws":0,"losses":1,"wins":53},"gpt-6-sol":{"draws":4,"losses":14,"wins":36},"gpt-6.1-sol":{"draws":1,"losses":23,"wins":30},"gpt-6.1-terra":{"draws":7,"losses":14,"wins":33},"gpt-6.1-terra-pro":{"draws":4,"losses":18,"wins":32},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":38},"inception/mercury-3":{"draws":3,"losses":0,"wins":35},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":40},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":10},"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":1,"losses":2,"wins":49},"meta/muse-spark-1.3":{"draws":1,"losses":0,"wins":53},"meta/muse-spark-open":{"draws":0,"losses":0,"wins":54},"meta/muse-wonder":{"draws":3,"losses":6,"wins":45},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":30},"minimax/minimax-m3.1-flash":{"draws":2,"losses":1,"wins":41},"mistralai/mistral-large-4-0":{"draws":3,"losses":2,"wins":29},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":1,"losses":1,"wins":50},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":15,"wins":33},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":27},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":42},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":1,"wins":25},"o3":{"draws":2,"losses":1,"wins":73},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":47},"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":1,"losses":0,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":0,"wins":54},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":35},"qwen/qwen3.8-flash":{"draws":3,"losses":0,"wins":33},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":52},"qwen/qwen3.8-max-0902":{"draws":1,"losses":4,"wins":49},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":16},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":0,"wins":48},"stealth/ox-alpha":{"draws":6,"losses":2,"wins":166},"stealth/space-bunny-alpha":{"draws":1,"losses":1,"wins":40},"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":3,"wins":48},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":68},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":52},"unbiased/pareto-26.10":{"draws":1,"losses":6,"wins":11},"unbiased/pareto-26.10-preview":{"draws":0,"losses":7,"wins":11},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":3,"losses":1,"wins":50},"x-ai/grok-4.6":{"draws":1,"losses":2,"wins":51},"x-ai/grok-4.7":{"draws":1,"losses":6,"wins":41},"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":24},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":34},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":32},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":107},"z-ai/glm-5.3":{"draws":3,"losses":7,"wins":42},"z-ai/glm-5.3-flash":{"draws":4,"losses":3,"wins":47},"z-ai/glm-5.3-flashx":{"draws":2,"losses":1,"wins":51}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":7,"wins":25},"claude-fable-5":{"draws":7,"losses":36,"wins":5},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":25,"losses":28,"wins":25},"claude-opus-4-8":{"draws":12,"losses":20,"wins":12},"claude-opus-5":{"draws":9,"losses":60,"wins":13},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":9,"losses":15,"wins":8},"claude-sonnet-5-5":{"draws":9,"losses":30,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":18,"losses":18,"wins":36},"deepseek/deepseek-v4-pro":{"draws":16,"losses":15,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":20,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":32,"wins":5},"elorian/glimpse":{"draws":8,"losses":11,"wins":7},"fireworks/ember-1":{"draws":11,"losses":22,"wins":15},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"gemini-4-argon":{"draws":4,"losses":42,"wins":2},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":15,"losses":27,"wins":18},"google/gemini-3.5-flash-lite":{"draws":23,"losses":22,"wins":39},"google/gemini-3.6-flash":{"draws":26,"losses":47,"wins":19},"google/gemini-3.8-flash":{"draws":13,"losses":28,"wins":7},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":13},"gpt-4.1":{"draws":5,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":11,"wins":20},"gpt-5.4":{"draws":9,"losses":27,"wins":10},"gpt-5.4-mini":{"draws":16,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":11,"losses":16,"wins":21},"gpt-5.5":{"draws":17,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":17,"wins":19},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":6},"gpt-5.6-terra":{"draws":19,"losses":14,"wins":13},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":13,"losses":17,"wins":18},"gpt-6-sol":{"draws":9,"losses":34,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":44,"wins":0},"gpt-6.1-terra":{"draws":4,"losses":42,"wins":2},"gpt-6.1-terra-pro":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":18},"inception/mercury-3":{"draws":11,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":14,"losses":3,"wins":17},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":12,"wins":26},"meta/muse-glimmer-30b":{"draws":15,"losses":5,"wins":22},"meta/muse-spark-1.2":{"draws":11,"losses":24,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":26,"wins":11},"meta/muse-spark-open":{"draws":11,"losses":28,"wins":9},"meta/muse-wonder":{"draws":10,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":5,"losses":6,"wins":15},"minimax/minimax-m3.1-flash":{"draws":11,"losses":12,"wins":19},"mistralai/mistral-large-4-0":{"draws":12,"losses":11,"wins":7},"mistralai/mistral-medium-3-5":{"draws":11,"losses":3,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":12,"losses":22,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":40,"wins":3},"nex-agi/nex-n2-pro":{"draws":8,"losses":1,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":7,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":8},"o3":{"draws":10,"losses":32,"wins":24},"openai/gpt-oss-120b":{"draws":11,"losses":7,"wins":24},"poolside/laguna-s-2.1":{"draws":18,"losses":10,"wins":18},"qwen/qwen3.7-max":{"draws":10,"losses":7,"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":9,"losses":15,"wins":10},"qwen/qwen3.8-flash":{"draws":11,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":16,"losses":20,"wins":12},"qwen/qwen3.8-max-0902":{"draws":13,"losses":23,"wins":12},"recursive/flint-v1.0":{"draws":5,"losses":0,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":17,"wins":16},"stealth/ox-alpha":{"draws":33,"losses":93,"wins":32},"stealth/space-bunny-alpha":{"draws":8,"losses":15,"wins":15},"stepfun/step-3.7-flash":{"draws":7,"losses":10,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":8,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":14,"losses":25,"wins":7},"thinkingmachines/inkling":{"draws":22,"losses":13,"wins":29},"thinkingmachines/inkling-small":{"draws":17,"losses":7,"wins":24},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":25,"wins":11},"x-ai/grok-4.6":{"draws":11,"losses":25,"wins":12},"x-ai/grok-4.7":{"draws":3,"losses":36,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":24,"losses":18,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":31,"losses":33,"wins":32},"z-ai/glm-5.3":{"draws":8,"losses":36,"wins":2},"z-ai/glm-5.3-flash":{"draws":11,"losses":28,"wins":9},"z-ai/glm-5.3-flashx":{"draws":12,"losses":28,"wins":8}},"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":2,"losses":48,"wins":4},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":22,"losses":24,"wins":32},"claude-opus-4-8":{"draws":10,"losses":19,"wins":15},"claude-opus-5":{"draws":8,"losses":61,"wins":13},"claude-opus-5-5":{"draws":1,"losses":46,"wins":5},"claude-sonnet-5":{"draws":12,"losses":17,"wins":19},"claude-sonnet-5-5":{"draws":4,"losses":17,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":20,"losses":11,"wins":41},"deepseek/deepseek-v4-pro":{"draws":13,"losses":15,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":13,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":14,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":25,"wins":13},"elorian/glimpse":{"draws":9,"losses":8,"wins":9},"fireworks/ember-1":{"draws":12,"losses":22,"wins":14},"gemini-3.1-pro-preview":{"draws":10,"losses":18,"wins":20},"gemini-4-argon":{"draws":3,"losses":38,"wins":7},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":23},"google/gemini-3.5-flash":{"draws":13,"losses":19,"wins":28},"google/gemini-3.5-flash-lite":{"draws":24,"losses":16,"wins":44},"google/gemini-3.6-flash":{"draws":22,"losses":38,"wins":32},"google/gemini-3.8-flash":{"draws":6,"losses":25,"wins":17},"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":13,"losses":18,"wins":15},"gpt-5.4-mini":{"draws":9,"losses":8,"wins":15},"gpt-5.4-nano":{"draws":10,"losses":4,"wins":34},"gpt-5.5":{"draws":11,"losses":21,"wins":12},"gpt-5.6-luna":{"draws":17,"losses":11,"wins":20},"gpt-5.6-sol":{"draws":5,"losses":34,"wins":9},"gpt-5.6-terra":{"draws":15,"losses":14,"wins":17},"gpt-6-astra":{"draws":1,"losses":42,"wins":5},"gpt-6-luna":{"draws":13,"losses":16,"wins":19},"gpt-6-sol":{"draws":3,"losses":34,"wins":11},"gpt-6.1-sol":{"draws":2,"losses":43,"wins":3},"gpt-6.1-terra":{"draws":4,"losses":37,"wins":7},"gpt-6.1-terra-pro":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":5,"wins":17},"inception/mercury-3":{"draws":9,"losses":11,"wins":12},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":20},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":9,"losses":12,"wins":31},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":23},"meta/muse-spark-1.2":{"draws":14,"losses":14,"wins":18},"meta/muse-spark-1.3":{"draws":10,"losses":22,"wins":16},"meta/muse-spark-open":{"draws":12,"losses":23,"wins":13},"meta/muse-wonder":{"draws":11,"losses":21,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":17},"minimax/minimax-m3.1-flash":{"draws":13,"losses":6,"wins":23},"mistralai/mistral-large-4-0":{"draws":9,"losses":9,"wins":12},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":15},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":41,"wins":4},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":8,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":4,"wins":10},"o3":{"draws":7,"losses":15,"wins":44},"openai/gpt-oss-120b":{"draws":14,"losses":7,"wins":21},"poolside/laguna-s-2.1":{"draws":14,"losses":12,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":11},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":21,"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":17,"wins":22},"qwen/qwen3.8-max-0902":{"draws":10,"losses":22,"wins":16},"recursive/flint-v1.0":{"draws":4,"losses":1,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":13,"wins":16},"stealth/ox-alpha":{"draws":31,"losses":69,"wins":58},"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":2,"losses":3,"wins":5},"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":{"draws":1,"losses":14,"wins":1},"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":12,"losses":22,"wins":14},"x-ai/grok-4.6":{"draws":10,"losses":29,"wins":9},"x-ai/grok-4.7":{"draws":7,"losses":26,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":19,"losses":11,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":11},"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":26,"wins":11},"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":1,"losses":40,"wins":1},"claude-haiku-5-5":{"draws":7,"losses":20,"wins":7},"claude-opus-4-5":{"draws":6,"losses":44,"wins":8},"claude-opus-4-8":{"draws":8,"losses":22,"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":5,"losses":23,"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":9,"losses":23,"wins":20},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":21,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":24,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":29,"wins":1},"elorian/glimpse":{"draws":3,"losses":12,"wins":5},"fireworks/ember-1":{"draws":5,"losses":24,"wins":7},"gemini-3.1-pro-preview":{"draws":6,"losses":16,"wins":14},"gemini-4-argon":{"draws":0,"losses":34,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":7,"wins":16},"google/gemini-3.5-flash":{"draws":8,"losses":29,"wins":9},"google/gemini-3.5-flash-lite":{"draws":18,"losses":24,"wins":24},"google/gemini-3.6-flash":{"draws":11,"losses":51,"wins":8},"google/gemini-3.8-flash":{"draws":4,"losses":26,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":11,"wins":5},"gpt-4.1":{"draws":3,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":22,"wins":6},"gpt-5.4":{"draws":5,"losses":21,"wins":10},"gpt-5.4-mini":{"draws":4,"losses":10,"wins":10},"gpt-5.4-nano":{"draws":3,"losses":20,"wins":11},"gpt-5.5":{"draws":8,"losses":22,"wins":4},"gpt-5.6-luna":{"draws":7,"losses":19,"wins":10},"gpt-5.6-sol":{"draws":2,"losses":29,"wins":5},"gpt-5.6-terra":{"draws":5,"losses":21,"wins":8},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":8,"losses":21,"wins":7},"gpt-6-sol":{"draws":4,"losses":31,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"gpt-6.1-terra":{"draws":1,"losses":35,"wins":0},"gpt-6.1-terra-pro":{"draws":0,"losses":36,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":9,"wins":11},"inception/mercury-3":{"draws":2,"losses":16,"wins":4},"inclusionai/ling-3.0-flash":{"draws":6,"losses":9,"wins":9},"inclusionai/ling-3.1-flash":{"draws":3,"losses":3,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":26,"wins":12},"meta/muse-glimmer-30b":{"draws":10,"losses":8,"wins":14},"meta/muse-spark-1.2":{"draws":4,"losses":21,"wins":9},"meta/muse-spark-1.3":{"draws":3,"losses":31,"wins":2},"meta/muse-spark-open":{"draws":6,"losses":23,"wins":7},"meta/muse-wonder":{"draws":3,"losses":29,"wins":4},"minimax/minimax-m3":{"draws":1,"losses":9,"wins":8},"minimax/minimax-m3.1-flash":{"draws":8,"losses":15,"wins":9},"mistralai/mistral-large-4-0":{"draws":6,"losses":11,"wins":5},"mistralai/mistral-medium-3-5":{"draws":5,"losses":8,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":21,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":35,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":10,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":18,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":13,"wins":2},"o3":{"draws":5,"losses":36,"wins":13},"openai/gpt-oss-120b":{"draws":7,"losses":12,"wins":13},"poolside/laguna-s-2.1":{"draws":5,"losses":9,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":29,"wins":3},"qwen/qwen3.8-27b":{"draws":2,"losses":16,"wins":6},"qwen/qwen3.8-flash":{"draws":3,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":5,"losses":28,"wins":3},"qwen/qwen3.8-max-0902":{"draws":4,"losses":27,"wins":5},"recursive/flint-v1.0":{"draws":2,"losses":4,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":21,"wins":9},"stealth/ox-alpha":{"draws":19,"losses":86,"wins":21},"stealth/space-bunny-alpha":{"draws":5,"losses":17,"wins":8},"stepfun/step-3.7-flash":{"draws":4,"losses":15,"wins":7},"stepfun/step-5-preview":{"draws":3,"losses":9,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":8,"wins":6},"tencent/hy4-preview":{"draws":8,"losses":22,"wins":6},"thinkingmachines/inkling":{"draws":13,"losses":20,"wins":15},"thinkingmachines/inkling-small":{"draws":9,"losses":13,"wins":14},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":7,"losses":26,"wins":3},"x-ai/grok-4.6":{"draws":6,"losses":28,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":9,"losses":18,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":16,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":18,"losses":37,"wins":17},"z-ai/glm-5.3":{"draws":5,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":1,"losses":25,"wins":10},"z-ai/glm-5.3-flashx":{"draws":5,"losses":27,"wins":4}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":51,"wins":37},"claude-fable-5":{"draws":20,"losses":104,"wins":8},"claude-fable-5-1":{"draws":3,"losses":141,"wins":2},"claude-haiku-5-5":{"draws":34,"losses":75,"wins":19},"claude-opus-4-5":{"draws":56,"losses":119,"wins":41},"claude-opus-4-8":{"draws":29,"losses":79,"wins":16},"claude-opus-5":{"draws":24,"losses":187,"wins":11},"claude-opus-5-5":{"draws":6,"losses":135,"wins":3},"claude-sonnet-5":{"draws":33,"losses":74,"wins":25},"claude-sonnet-5-5":{"draws":27,"losses":88,"wins":17},"cohere/north-mini-code":{"draws":10,"losses":21,"wins":19},"deepseek/deepseek-v4-flash":{"draws":43,"losses":62,"wins":53},"deepseek/deepseek-v4-pro":{"draws":28,"losses":67,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":65,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":80,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":93,"wins":15},"elorian/glimpse":{"draws":15,"losses":39,"wins":16},"fireworks/ember-1":{"draws":33,"losses":72,"wins":27},"gemini-3.1-pro-preview":{"draws":33,"losses":67,"wins":32},"gemini-4-argon":{"draws":5,"losses":123,"wins":4},"google/gemini-3.1-flash-lite":{"draws":22,"losses":24,"wins":46},"google/gemini-3.5-flash":{"draws":33,"losses":97,"wins":36},"google/gemini-3.5-flash-lite":{"draws":55,"losses":85,"wins":90},"google/gemini-3.6-flash":{"draws":53,"losses":154,"wins":45},"google/gemini-3.8-flash":{"draws":24,"losses":96,"wins":12},"google/gemma-4-31b-it":{"draws":34,"losses":17,"wins":27},"gpt-4.1":{"draws":12,"losses":24,"wins":8},"gpt-4.1-nano":{"draws":10,"losses":3,"wins":3},"gpt-5":{"draws":29,"losses":57,"wins":30},"gpt-5.4":{"draws":30,"losses":78,"wins":18},"gpt-5.4-mini":{"draws":29,"losses":34,"wins":25},"gpt-5.4-nano":{"draws":24,"losses":64,"wins":52},"gpt-5.5":{"draws":37,"losses":70,"wins":13},"gpt-5.6-luna":{"draws":45,"losses":58,"wins":29},"gpt-5.6-sol":{"draws":17,"losses":109,"wins":6},"gpt-5.6-terra":{"draws":33,"losses":75,"wins":18},"gpt-6-astra":{"draws":3,"losses":125,"wins":4},"gpt-6-luna":{"draws":33,"losses":72,"wins":27},"gpt-6-sol":{"draws":18,"losses":106,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":122,"wins":5},"gpt-6.1-terra":{"draws":11,"losses":120,"wins":1},"gpt-6.1-terra-pro":{"draws":7,"losses":119,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":34,"losses":23,"wins":37},"inception/mercury-3":{"draws":23,"losses":48,"wins":21},"inclusionai/ling-3.0-flash":{"draws":32,"losses":26,"wins":36},"inclusionai/ling-3.1-flash":{"draws":9,"losses":5,"wins":4},"meituan/longcat-2.0":{"draws":30,"losses":55,"wins":59},"meta/muse-glimmer-30b":{"draws":36,"losses":30,"wins":48},"meta/muse-spark-1.2":{"draws":33,"losses":75,"wins":18},"meta/muse-spark-1.3":{"draws":23,"losses":92,"wins":17},"meta/muse-spark-open":{"draws":28,"losses":88,"wins":16},"meta/muse-wonder":{"draws":24,"losses":91,"wins":17},"minimax/minimax-m3":{"draws":16,"losses":28,"wins":30},"minimax/minimax-m3.1-flash":{"draws":27,"losses":56,"wins":31},"mistralai/mistral-large-4-0":{"draws":26,"losses":45,"wins":11},"mistralai/mistral-medium-3-5":{"draws":27,"losses":21,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":38,"losses":68,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":118,"wins":5},"nex-agi/nex-n2-pro":{"draws":13,"losses":23,"wins":30},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":14,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":33,"wins":43},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":26,"wins":17},"o3":{"draws":21,"losses":125,"wins":44},"openai/gpt-oss-120b":{"draws":34,"losses":40,"wins":42},"poolside/laguna-s-2.1":{"draws":31,"losses":47,"wins":50},"qwen/qwen3.7-max":{"draws":21,"losses":32,"wins":27},"qwen/qwen3.7-plus":{"draws":17,"losses":27,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":80,"wins":16},"qwen/qwen3.8-27b":{"draws":22,"losses":52,"wins":20},"qwen/qwen3.8-flash":{"draws":22,"losses":43,"wins":23},"qwen/qwen3.8-max":{"draws":34,"losses":74,"wins":24},"qwen/qwen3.8-max-0902":{"draws":32,"losses":80,"wins":20},"recursive/flint-v1.0":{"draws":9,"losses":11,"wins":20},"reflection/beam-1.0-501b-a23b":{"draws":26,"losses":73,"wins":21},"stealth/ox-alpha":{"draws":94,"losses":251,"wins":71},"stealth/space-bunny-alpha":{"draws":31,"losses":49,"wins":24},"stepfun/step-3.7-flash":{"draws":21,"losses":35,"wins":40},"stepfun/step-5-preview":{"draws":5,"losses":23,"wins":6},"tencent/hy3-preview":{"draws":25,"losses":26,"wins":21},"tencent/hy4-preview":{"draws":25,"losses":78,"wins":23},"thinkingmachines/inkling":{"draws":45,"losses":67,"wins":62},"thinkingmachines/inkling-small":{"draws":45,"losses":33,"wins":54},"unbiased/pareto-26.10":{"draws":3,"losses":41,"wins":0},"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":20,"losses":95,"wins":17},"x-ai/grok-4.6":{"draws":29,"losses":92,"wins":11},"x-ai/grok-4.7":{"draws":11,"losses":98,"wins":9},"x-ai/grok-build-0.1":{"draws":11,"losses":13,"wins":20},"xiaomi/mimo-v2.5":{"draws":59,"losses":76,"wins":73},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":27,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":56,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":63,"wins":13},"z-ai/glm-5.2":{"draws":76,"losses":121,"wins":67},"z-ai/glm-5.3":{"draws":25,"losses":93,"wins":8},"z-ai/glm-5.3-flash":{"draws":23,"losses":78,"wins":31},"z-ai/glm-5.3-flashx":{"draws":26,"losses":80,"wins":26}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":6,"wins":28},"claude-fable-5":{"draws":8,"losses":27,"wins":13},"claude-fable-5-1":{"draws":3,"losses":47,"wins":4},"claude-haiku-5-5":{"draws":8,"losses":20,"wins":18},"claude-opus-4-5":{"draws":22,"losses":18,"wins":38},"claude-opus-4-8":{"draws":9,"losses":19,"wins":16},"claude-opus-5":{"draws":8,"losses":58,"wins":16},"claude-opus-5-5":{"draws":3,"losses":45,"wins":4},"claude-sonnet-5":{"draws":14,"losses":12,"wins":22},"claude-sonnet-5-5":{"draws":10,"losses":23,"wins":15},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":16,"losses":16,"wins":40},"deepseek/deepseek-v4-pro":{"draws":9,"losses":7,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":20,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":28,"wins":10},"elorian/glimpse":{"draws":4,"losses":13,"wins":9},"fireworks/ember-1":{"draws":12,"losses":20,"wins":16},"gemini-3.1-pro-preview":{"draws":11,"losses":15,"wins":22},"gemini-4-argon":{"draws":4,"losses":38,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":13,"losses":24,"wins":23},"google/gemini-3.5-flash-lite":{"draws":13,"losses":24,"wins":47},"google/gemini-3.6-flash":{"draws":20,"losses":31,"wins":41},"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":2,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":13,"wins":23},"gpt-5.4":{"draws":7,"losses":23,"wins":16},"gpt-5.4-mini":{"draws":11,"losses":7,"wins":14},"gpt-5.4-nano":{"draws":9,"losses":11,"wins":28},"gpt-5.5":{"draws":9,"losses":20,"wins":15},"gpt-5.6-luna":{"draws":13,"losses":10,"wins":25},"gpt-5.6-sol":{"draws":4,"losses":31,"wins":13},"gpt-5.6-terra":{"draws":10,"losses":16,"wins":20},"gpt-6-astra":{"draws":4,"losses":38,"wins":6},"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},"gpt-6.1-terra":{"draws":8,"losses":34,"wins":6},"gpt-6.1-terra-pro":{"draws":3,"losses":39,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":21},"inception/mercury-3":{"draws":9,"losses":10,"wins":13},"inclusionai/ling-3.0-flash":{"draws":10,"losses":4,"wins":20},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":8,"losses":5,"wins":39},"meta/muse-glimmer-30b":{"draws":10,"losses":6,"wins":26},"meta/muse-spark-1.2":{"draws":9,"losses":15,"wins":22},"meta/muse-spark-1.3":{"draws":7,"losses":24,"wins":17},"meta/muse-spark-open":{"draws":14,"losses":23,"wins":11},"meta/muse-wonder":{"draws":7,"losses":29,"wins":12},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"minimax/minimax-m3.1-flash":{"draws":9,"losses":11,"wins":22},"mistralai/mistral-large-4-0":{"draws":4,"losses":14,"wins":12},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":20,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":39,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":4,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":6,"wins":9},"o3":{"draws":6,"losses":23,"wins":37},"openai/gpt-oss-120b":{"draws":9,"losses":7,"wins":26},"poolside/laguna-s-2.1":{"draws":8,"losses":10,"wins":28},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":19,"wins":16},"qwen/qwen3.8-27b":{"draws":9,"losses":7,"wins":18},"qwen/qwen3.8-flash":{"draws":6,"losses":15,"wins":11},"qwen/qwen3.8-max":{"draws":12,"losses":20,"wins":16},"qwen/qwen3.8-max-0902":{"draws":11,"losses":22,"wins":15},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":12,"wins":20},"stealth/ox-alpha":{"draws":40,"losses":62,"wins":56},"stealth/space-bunny-alpha":{"draws":10,"losses":9,"wins":19},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":22,"wins":16},"thinkingmachines/inkling":{"draws":20,"losses":6,"wins":38},"thinkingmachines/inkling-small":{"draws":14,"losses":7,"wins":27},"unbiased/pareto-26.10":{"draws":0,"losses":15,"wins":1},"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":26,"wins":12},"x-ai/grok-4.6":{"draws":6,"losses":27,"wins":15},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":21,"losses":7,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":2,"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":26,"losses":23,"wins":47},"z-ai/glm-5.3":{"draws":5,"losses":26,"wins":15},"z-ai/glm-5.3-flash":{"draws":8,"losses":22,"wins":18},"z-ai/glm-5.3-flashx":{"draws":10,"losses":21,"wins":17}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":14,"wins":18},"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":21,"losses":30,"wins":27},"claude-opus-4-8":{"draws":12,"losses":15,"wins":17},"claude-opus-5":{"draws":8,"losses":65,"wins":9},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":16,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":9,"losses":28,"wins":11},"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":19,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":12,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":20,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":27,"wins":12},"elorian/glimpse":{"draws":5,"losses":11,"wins":10},"fireworks/ember-1":{"draws":11,"losses":26,"wins":11},"gemini-3.1-pro-preview":{"draws":13,"losses":19,"wins":16},"gemini-4-argon":{"draws":2,"losses":42,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":23},"google/gemini-3.5-flash":{"draws":15,"losses":28,"wins":17},"google/gemini-3.5-flash-lite":{"draws":24,"losses":17,"wins":43},"google/gemini-3.6-flash":{"draws":20,"losses":46,"wins":26},"google/gemini-3.8-flash":{"draws":14,"losses":23,"wins":11},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":13},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":17,"wins":14},"gpt-5.4":{"draws":7,"losses":28,"wins":11},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":24},"gpt-5.5":{"draws":11,"losses":16,"wins":17},"gpt-5.6-luna":{"draws":15,"losses":17,"wins":16},"gpt-5.6-sol":{"draws":4,"losses":35,"wins":9},"gpt-5.6-terra":{"draws":9,"losses":21,"wins":16},"gpt-6-astra":{"draws":1,"losses":47,"wins":0},"gpt-6-luna":{"draws":12,"losses":21,"wins":15},"gpt-6-sol":{"draws":3,"losses":37,"wins":8},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"gpt-6.1-terra":{"draws":6,"losses":39,"wins":3},"gpt-6.1-terra-pro":{"draws":4,"losses":40,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":6,"wins":17},"inception/mercury-3":{"draws":11,"losses":10,"wins":11},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":4,"losses":3,"wins":5},"meituan/longcat-2.0":{"draws":14,"losses":13,"wins":25},"meta/muse-glimmer-30b":{"draws":12,"losses":6,"wins":24},"meta/muse-spark-1.2":{"draws":7,"losses":28,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":24,"wins":13},"meta/muse-spark-open":{"draws":9,"losses":29,"wins":10},"meta/muse-wonder":{"draws":11,"losses":27,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":19},"minimax/minimax-m3.1-flash":{"draws":7,"losses":16,"wins":19},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":6,"losses":5,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":9,"losses":19,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":37,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":4,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":9},"o3":{"draws":10,"losses":22,"wins":34},"openai/gpt-oss-120b":{"draws":12,"losses":11,"wins":19},"poolside/laguna-s-2.1":{"draws":10,"losses":13,"wins":23},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":14},"qwen/qwen3.7-plus":{"draws":8,"losses":7,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":18,"wins":17},"qwen/qwen3.8-27b":{"draws":10,"losses":16,"wins":8},"qwen/qwen3.8-flash":{"draws":9,"losses":16,"wins":7},"qwen/qwen3.8-max":{"draws":18,"losses":20,"wins":10},"qwen/qwen3.8-max-0902":{"draws":17,"losses":21,"wins":10},"recursive/flint-v1.0":{"draws":5,"losses":0,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":19,"wins":14},"stealth/ox-alpha":{"draws":38,"losses":69,"wins":51},"stealth/space-bunny-alpha":{"draws":11,"losses":10,"wins":17},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":11,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":10},"tencent/hy4-preview":{"draws":10,"losses":20,"wins":16},"thinkingmachines/inkling":{"draws":21,"losses":14,"wins":29},"thinkingmachines/inkling-small":{"draws":11,"losses":9,"wins":28},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":1,"wins":8},"x-ai/grok-4.5":{"draws":9,"losses":24,"wins":15},"x-ai/grok-4.6":{"draws":11,"losses":26,"wins":11},"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":23,"losses":14,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":14,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":15,"wins":9},"z-ai/glm-5.2":{"draws":30,"losses":31,"wins":35},"z-ai/glm-5.3":{"draws":10,"losses":26,"wins":10},"z-ai/glm-5.3-flash":{"draws":5,"losses":30,"wins":13},"z-ai/glm-5.3-flashx":{"draws":9,"losses":24,"wins":15}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":7,"wins":24},"claude-fable-5":{"draws":13,"losses":23,"wins":12},"claude-fable-5-1":{"draws":6,"losses":43,"wins":5},"claude-haiku-5-5":{"draws":14,"losses":19,"wins":13},"claude-opus-4-5":{"draws":18,"losses":22,"wins":38},"claude-opus-4-8":{"draws":9,"losses":12,"wins":23},"claude-opus-5":{"draws":17,"losses":52,"wins":13},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":11,"losses":15,"wins":22},"claude-sonnet-5-5":{"draws":9,"losses":21,"wins":18},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":20,"losses":12,"wins":40},"deepseek/deepseek-v4-pro":{"draws":13,"losses":14,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":10,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":13,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":25,"wins":11},"elorian/glimpse":{"draws":7,"losses":11,"wins":8},"fireworks/ember-1":{"draws":15,"losses":16,"wins":17},"gemini-3.1-pro-preview":{"draws":12,"losses":11,"wins":25},"gemini-4-argon":{"draws":8,"losses":35,"wins":5},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":15,"losses":18,"wins":27},"google/gemini-3.5-flash-lite":{"draws":31,"losses":7,"wins":46},"google/gemini-3.6-flash":{"draws":29,"losses":36,"wins":27},"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":13,"losses":11,"wins":18},"gpt-5.4":{"draws":14,"losses":14,"wins":18},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":18,"losses":9,"wins":21},"gpt-5.5":{"draws":13,"losses":17,"wins":14},"gpt-5.6-luna":{"draws":15,"losses":11,"wins":22},"gpt-5.6-sol":{"draws":12,"losses":23,"wins":13},"gpt-5.6-terra":{"draws":17,"losses":11,"wins":18},"gpt-6-astra":{"draws":6,"losses":40,"wins":2},"gpt-6-luna":{"draws":15,"losses":11,"wins":22},"gpt-6-sol":{"draws":7,"losses":30,"wins":11},"gpt-6.1-sol":{"draws":6,"losses":36,"wins":6},"gpt-6.1-terra":{"draws":8,"losses":31,"wins":9},"gpt-6.1-terra-pro":{"draws":9,"losses":34,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":6,"wins":15},"inception/mercury-3":{"draws":11,"losses":6,"wins":15},"inclusionai/ling-3.0-flash":{"draws":19,"losses":3,"wins":12},"inclusionai/ling-3.1-flash":{"draws":7,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":9,"losses":9,"wins":34},"meta/muse-glimmer-30b":{"draws":14,"losses":4,"wins":24},"meta/muse-spark-1.2":{"draws":15,"losses":13,"wins":18},"meta/muse-spark-1.3":{"draws":11,"losses":18,"wins":19},"meta/muse-spark-open":{"draws":14,"losses":13,"wins":21},"meta/muse-wonder":{"draws":16,"losses":19,"wins":13},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"minimax/minimax-m3.1-flash":{"draws":13,"losses":7,"wins":22},"mistralai/mistral-large-4-0":{"draws":14,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":9,"losses":1,"wins":18},"moonshotai/kimi-k3":{"draws":13,"losses":14,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":30,"wins":9},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":8,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":5,"wins":10},"o3":{"draws":15,"losses":16,"wins":35},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":20,"losses":6,"wins":20},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":12},"qwen/qwen3.7-plus":{"draws":11,"losses":1,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":24},"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":12,"losses":17,"wins":19},"qwen/qwen3.8-max-0902":{"draws":18,"losses":15,"wins":15},"recursive/flint-v1.0":{"draws":5,"losses":1,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":10,"wins":23},"stealth/ox-alpha":{"draws":34,"losses":63,"wins":61},"stealth/space-bunny-alpha":{"draws":10,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":8,"losses":4,"wins":22},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":6},"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":17,"losses":5,"wins":26},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":17,"losses":18,"wins":13},"x-ai/grok-4.7":{"draws":8,"losses":24,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":25,"losses":7,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":1,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":10,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":14,"wins":8},"z-ai/glm-5.2":{"draws":39,"losses":18,"wins":39},"z-ai/glm-5.3":{"draws":7,"losses":27,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":18,"wins":23},"z-ai/glm-5.3-flashx":{"draws":7,"losses":23,"wins":18}},"deepseek/deepseek-v4.1-flash-1017":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":32},"claude-fable-5":{"draws":7,"losses":20,"wins":21},"claude-fable-5-1":{"draws":3,"losses":45,"wins":6},"claude-haiku-5-5":{"draws":5,"losses":19,"wins":22},"claude-opus-4-5":{"draws":11,"losses":15,"wins":52},"claude-opus-4-8":{"draws":6,"losses":11,"wins":27},"claude-opus-5":{"draws":11,"losses":56,"wins":15},"claude-opus-5-5":{"draws":4,"losses":43,"wins":5},"claude-sonnet-5":{"draws":10,"losses":9,"wins":29},"claude-sonnet-5-5":{"draws":9,"losses":18,"wins":21},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":12,"losses":10,"wins":50},"deepseek/deepseek-v4-pro":{"draws":9,"losses":6,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":10,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":11,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":14,"wins":16},"elorian/glimpse":{"draws":5,"losses":7,"wins":14},"fireworks/ember-1":{"draws":10,"losses":9,"wins":29},"gemini-3.1-pro-preview":{"draws":10,"losses":14,"wins":24},"gemini-4-argon":{"draws":5,"losses":37,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":9,"losses":14,"wins":37},"google/gemini-3.5-flash-lite":{"draws":9,"losses":10,"wins":65},"google/gemini-3.6-flash":{"draws":16,"losses":33,"wins":43},"google/gemini-3.8-flash":{"draws":7,"losses":13,"wins":28},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":21},"gpt-4.1":{"draws":4,"losses":3,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":6,"wins":28},"gpt-5.4":{"draws":10,"losses":14,"wins":22},"gpt-5.4-mini":{"draws":9,"losses":1,"wins":22},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":33},"gpt-5.5":{"draws":11,"losses":14,"wins":19},"gpt-5.6-luna":{"draws":10,"losses":6,"wins":32},"gpt-5.6-sol":{"draws":7,"losses":21,"wins":20},"gpt-5.6-terra":{"draws":11,"losses":6,"wins":29},"gpt-6-astra":{"draws":2,"losses":43,"wins":3},"gpt-6-luna":{"draws":10,"losses":10,"wins":28},"gpt-6-sol":{"draws":6,"losses":31,"wins":11},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":8},"gpt-6.1-terra":{"draws":5,"losses":38,"wins":5},"gpt-6.1-terra-pro":{"draws":4,"losses":40,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":4,"wins":22},"inception/mercury-3":{"draws":5,"losses":5,"wins":22},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":27},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":5,"losses":5,"wins":42},"meta/muse-glimmer-30b":{"draws":6,"losses":3,"wins":33},"meta/muse-spark-1.2":{"draws":8,"losses":13,"wins":25},"meta/muse-spark-1.3":{"draws":7,"losses":16,"wins":25},"meta/muse-spark-open":{"draws":10,"losses":14,"wins":24},"meta/muse-wonder":{"draws":9,"losses":17,"wins":22},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"minimax/minimax-m3.1-flash":{"draws":5,"losses":7,"wins":30},"mistralai/mistral-large-4-0":{"draws":6,"losses":8,"wins":16},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":27},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":35,"wins":11},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":3,"wins":16},"o3":{"draws":6,"losses":13,"wins":47},"openai/gpt-oss-120b":{"draws":8,"losses":6,"wins":28},"poolside/laguna-s-2.1":{"draws":7,"losses":8,"wins":31},"qwen/qwen3.7-max":{"draws":3,"losses":0,"wins":25},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":23},"qwen/qwen3.8-27b":{"draws":3,"losses":8,"wins":23},"qwen/qwen3.8-flash":{"draws":4,"losses":8,"wins":20},"qwen/qwen3.8-max":{"draws":9,"losses":8,"wins":31},"qwen/qwen3.8-max-0902":{"draws":12,"losses":13,"wins":23},"recursive/flint-v1.0":{"draws":1,"losses":1,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":9,"wins":27},"stealth/ox-alpha":{"draws":21,"losses":54,"wins":83},"stealth/space-bunny-alpha":{"draws":5,"losses":3,"wins":30},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":28},"stepfun/step-5-preview":{"draws":1,"losses":6,"wins":5},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":18},"tencent/hy4-preview":{"draws":9,"losses":14,"wins":23},"thinkingmachines/inkling":{"draws":10,"losses":7,"wins":47},"thinkingmachines/inkling-small":{"draws":6,"losses":4,"wins":38},"unbiased/pareto-26.10":{"draws":3,"losses":12,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":9,"losses":15,"wins":24},"x-ai/grok-4.6":{"draws":9,"losses":15,"wins":24},"x-ai/grok-4.7":{"draws":5,"losses":23,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":12,"losses":4,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":1,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":5,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":12,"wins":16},"z-ai/glm-5.2":{"draws":17,"losses":11,"wins":68},"z-ai/glm-5.3":{"draws":6,"losses":27,"wins":13},"z-ai/glm-5.3-flash":{"draws":11,"losses":14,"wins":23},"z-ai/glm-5.3-flashx":{"draws":10,"losses":8,"wins":30}},"elorian/glimpse":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":7,"wins":28},"claude-fable-5":{"draws":7,"losses":16,"wins":25},"claude-fable-5-1":{"draws":5,"losses":40,"wins":9},"claude-haiku-5-5":{"draws":9,"losses":12,"wins":25},"claude-opus-4-5":{"draws":23,"losses":9,"wins":46},"claude-opus-4-8":{"draws":9,"losses":7,"wins":28},"claude-opus-5":{"draws":10,"losses":49,"wins":23},"claude-opus-5-5":{"draws":2,"losses":43,"wins":7},"claude-sonnet-5":{"draws":9,"losses":11,"wins":28},"claude-sonnet-5-5":{"draws":12,"losses":18,"wins":18},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":16},"deepseek/deepseek-v4-flash":{"draws":18,"losses":8,"wins":46},"deepseek/deepseek-v4-pro":{"draws":11,"losses":6,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":10,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":13,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":16,"wins":19},"elorian/glimpse":{"draws":1,"losses":2,"wins":7},"fireworks/ember-1":{"draws":13,"losses":10,"wins":25},"gemini-3.1-pro-preview":{"draws":13,"losses":10,"wins":25},"gemini-4-argon":{"draws":7,"losses":30,"wins":11},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":13,"losses":12,"wins":35},"google/gemini-3.5-flash-lite":{"draws":23,"losses":4,"wins":57},"google/gemini-3.6-flash":{"draws":19,"losses":25,"wins":48},"google/gemini-3.8-flash":{"draws":10,"losses":12,"wins":26},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":3,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":8,"wins":27},"gpt-5.4":{"draws":13,"losses":17,"wins":16},"gpt-5.4-mini":{"draws":11,"losses":2,"wins":19},"gpt-5.4-nano":{"draws":10,"losses":4,"wins":34},"gpt-5.5":{"draws":12,"losses":11,"wins":21},"gpt-5.6-luna":{"draws":14,"losses":5,"wins":29},"gpt-5.6-sol":{"draws":9,"losses":20,"wins":19},"gpt-5.6-terra":{"draws":13,"losses":7,"wins":26},"gpt-6-astra":{"draws":4,"losses":37,"wins":7},"gpt-6-luna":{"draws":9,"losses":10,"wins":29},"gpt-6-sol":{"draws":8,"losses":26,"wins":14},"gpt-6.1-sol":{"draws":3,"losses":35,"wins":10},"gpt-6.1-terra":{"draws":3,"losses":31,"wins":14},"gpt-6.1-terra-pro":{"draws":10,"losses":31,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":23},"inception/mercury-3":{"draws":8,"losses":5,"wins":19},"inclusionai/ling-3.0-flash":{"draws":9,"losses":2,"wins":23},"inclusionai/ling-3.1-flash":{"draws":0,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":11,"losses":4,"wins":37},"meta/muse-glimmer-30b":{"draws":10,"losses":4,"wins":28},"meta/muse-spark-1.2":{"draws":11,"losses":11,"wins":24},"meta/muse-spark-1.3":{"draws":11,"losses":14,"wins":23},"meta/muse-spark-open":{"draws":9,"losses":7,"wins":30},"meta/muse-wonder":{"draws":12,"losses":18,"wins":18},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":17},"minimax/minimax-m3.1-flash":{"draws":13,"losses":4,"wins":25},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":6,"losses":4,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":7},"moonshotai/kimi-k3":{"draws":15,"losses":7,"wins":24},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":28,"wins":13},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":1,"wins":14},"o3":{"draws":7,"losses":8,"wins":51},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":27},"poolside/laguna-s-2.1":{"draws":13,"losses":5,"wins":28},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":8,"wins":26},"qwen/qwen3.8-27b":{"draws":9,"losses":6,"wins":19},"qwen/qwen3.8-flash":{"draws":8,"losses":6,"wins":18},"qwen/qwen3.8-max":{"draws":12,"losses":11,"wins":25},"qwen/qwen3.8-max-0902":{"draws":16,"losses":9,"wins":23},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":5,"wins":27},"stealth/ox-alpha":{"draws":47,"losses":40,"wins":71},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":14},"tencent/hy4-preview":{"draws":9,"losses":10,"wins":27},"thinkingmachines/inkling":{"draws":21,"losses":3,"wins":40},"thinkingmachines/inkling-small":{"draws":13,"losses":0,"wins":35},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":14,"wins":25},"x-ai/grok-4.6":{"draws":14,"losses":12,"wins":22},"x-ai/grok-4.7":{"draws":5,"losses":22,"wins":15},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":21,"losses":0,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":2,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":12,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":10,"wins":18},"z-ai/glm-5.2":{"draws":27,"losses":14,"wins":55},"z-ai/glm-5.3":{"draws":11,"losses":23,"wins":12},"z-ai/glm-5.3-flash":{"draws":10,"losses":15,"wins":23},"z-ai/glm-5.3-flashx":{"draws":12,"losses":12,"wins":24}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":5,"wins":26},"claude-fable-5":{"draws":13,"losses":30,"wins":5},"claude-fable-5-1":{"draws":1,"losses":49,"wins":4},"claude-haiku-5-5":{"draws":15,"losses":24,"wins":7},"claude-opus-4-5":{"draws":29,"losses":21,"wins":28},"claude-opus-4-8":{"draws":16,"losses":16,"wins":12},"claude-opus-5":{"draws":10,"losses":59,"wins":13},"claude-opus-5-5":{"draws":3,"losses":45,"wins":4},"claude-sonnet-5":{"draws":13,"losses":18,"wins":17},"claude-sonnet-5-5":{"draws":9,"losses":22,"wins":17},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":22,"losses":13,"wins":37},"deepseek/deepseek-v4-pro":{"draws":13,"losses":10,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":27,"wins":7},"elorian/glimpse":{"draws":7,"losses":7,"wins":12},"fireworks/ember-1":{"draws":8,"losses":8,"wins":16},"gemini-3.1-pro-preview":{"draws":9,"losses":13,"wins":26},"gemini-4-argon":{"draws":3,"losses":41,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":17,"losses":18,"wins":25},"google/gemini-3.5-flash-lite":{"draws":31,"losses":8,"wins":45},"google/gemini-3.6-flash":{"draws":27,"losses":29,"wins":36},"google/gemini-3.8-flash":{"draws":7,"losses":22,"wins":19},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":4,"losses":6,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":9,"wins":23},"gpt-5.4":{"draws":11,"losses":21,"wins":14},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":18},"gpt-5.4-nano":{"draws":14,"losses":10,"wins":24},"gpt-5.5":{"draws":17,"losses":14,"wins":13},"gpt-5.6-luna":{"draws":17,"losses":13,"wins":18},"gpt-5.6-sol":{"draws":9,"losses":29,"wins":10},"gpt-5.6-terra":{"draws":12,"losses":8,"wins":26},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":14,"losses":12,"wins":22},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":38,"wins":4},"gpt-6.1-terra":{"draws":4,"losses":41,"wins":3},"gpt-6.1-terra-pro":{"draws":5,"losses":39,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":3,"wins":20},"inception/mercury-3":{"draws":12,"losses":9,"wins":11},"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":11,"losses":9,"wins":32},"meta/muse-glimmer-30b":{"draws":15,"losses":6,"wins":21},"meta/muse-spark-1.2":{"draws":12,"losses":15,"wins":19},"meta/muse-spark-1.3":{"draws":17,"losses":18,"wins":13},"meta/muse-spark-open":{"draws":11,"losses":19,"wins":18},"meta/muse-wonder":{"draws":11,"losses":27,"wins":10},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":23},"minimax/minimax-m3.1-flash":{"draws":11,"losses":10,"wins":21},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":20},"moonshotai/kimi-k3":{"draws":16,"losses":13,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":38,"wins":5},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":3,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":3,"wins":12},"o3":{"draws":11,"losses":16,"wins":39},"openai/gpt-oss-120b":{"draws":13,"losses":3,"wins":26},"poolside/laguna-s-2.1":{"draws":16,"losses":7,"wins":23},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":15},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":19},"qwen/qwen3.8-27b":{"draws":11,"losses":10,"wins":13},"qwen/qwen3.8-flash":{"draws":9,"losses":9,"wins":14},"qwen/qwen3.8-max":{"draws":12,"losses":14,"wins":22},"qwen/qwen3.8-max-0902":{"draws":14,"losses":21,"wins":13},"recursive/flint-v1.0":{"draws":5,"losses":0,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":20,"wins":11},"stealth/ox-alpha":{"draws":44,"losses":53,"wins":61},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"wins":18},"stepfun/step-3.7-flash":{"draws":7,"losses":5,"wins":22},"stepfun/step-5-preview":{"draws":1,"losses":6,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":12},"tencent/hy4-preview":{"draws":11,"losses":21,"wins":14},"thinkingmachines/inkling":{"draws":22,"losses":4,"wins":38},"thinkingmachines/inkling-small":{"draws":13,"losses":8,"wins":27},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":10,"losses":21,"wins":17},"x-ai/grok-4.6":{"draws":15,"losses":20,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":28,"wins":11},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":24,"losses":11,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":2,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":13,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":18,"wins":6},"z-ai/glm-5.2":{"draws":28,"losses":22,"wins":46},"z-ai/glm-5.3":{"draws":9,"losses":29,"wins":8},"z-ai/glm-5.3-flash":{"draws":8,"losses":26,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":20,"wins":17}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":12,"wins":18},"claude-fable-5":{"draws":11,"losses":27,"wins":10},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":19,"wins":13},"claude-opus-4-5":{"draws":23,"losses":37,"wins":18},"claude-opus-4-8":{"draws":14,"losses":23,"wins":7},"claude-opus-5":{"draws":9,"losses":67,"wins":6},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":16,"losses":19,"wins":13},"claude-sonnet-5-5":{"draws":7,"losses":29,"wins":12},"cohere/north-mini-code":{"draws":5,"losses":7,"wins":6},"deepseek/deepseek-v4-flash":{"draws":23,"losses":22,"wins":27},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":19,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":22,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":30,"wins":8},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":13,"losses":25,"wins":10},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":11},"gemini-4-argon":{"draws":6,"losses":37,"wins":5},"google/gemini-3.1-flash-lite":{"draws":6,"losses":6,"wins":20},"google/gemini-3.5-flash":{"draws":13,"losses":33,"wins":14},"google/gemini-3.5-flash-lite":{"draws":34,"losses":22,"wins":28},"google/gemini-3.6-flash":{"draws":21,"losses":46,"wins":25},"google/gemini-3.8-flash":{"draws":10,"losses":32,"wins":6},"google/gemma-4-31b-it":{"draws":13,"losses":5,"wins":10},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":13,"wins":15},"gpt-5.4":{"draws":12,"losses":22,"wins":12},"gpt-5.4-mini":{"draws":12,"losses":10,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":20},"gpt-5.5":{"draws":10,"losses":24,"wins":10},"gpt-5.6-luna":{"draws":13,"losses":19,"wins":16},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":15,"losses":14,"wins":17},"gpt-6-astra":{"draws":3,"losses":44,"wins":1},"gpt-6-luna":{"draws":16,"losses":18,"wins":14},"gpt-6-sol":{"draws":4,"losses":39,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":47,"wins":0},"gpt-6.1-terra":{"draws":6,"losses":41,"wins":1},"gpt-6.1-terra-pro":{"draws":4,"losses":40,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":7,"wins":10},"inception/mercury-3":{"draws":11,"losses":16,"wins":5},"inclusionai/ling-3.0-flash":{"draws":15,"losses":6,"wins":13},"inclusionai/ling-3.1-flash":{"draws":3,"losses":3,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":19,"wins":23},"meta/muse-glimmer-30b":{"draws":19,"losses":5,"wins":18},"meta/muse-spark-1.2":{"draws":11,"losses":20,"wins":15},"meta/muse-spark-1.3":{"draws":11,"losses":27,"wins":10},"meta/muse-spark-open":{"draws":11,"losses":25,"wins":10},"meta/muse-wonder":{"draws":9,"losses":36,"wins":3},"minimax/minimax-m3":{"draws":5,"losses":10,"wins":11},"minimax/minimax-m3.1-flash":{"draws":16,"losses":12,"wins":14},"mistralai/mistral-large-4-0":{"draws":7,"losses":14,"wins":9},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":26,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":35,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":11,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":10,"wins":7},"o3":{"draws":13,"losses":29,"wins":24},"openai/gpt-oss-120b":{"draws":13,"losses":10,"wins":19},"poolside/laguna-s-2.1":{"draws":18,"losses":12,"wins":16},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":24,"wins":13},"qwen/qwen3.8-27b":{"draws":8,"losses":19,"wins":7},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":10,"losses":23,"wins":15},"qwen/qwen3.8-max-0902":{"draws":10,"losses":25,"wins":13},"recursive/flint-v1.0":{"draws":6,"losses":0,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":20,"wins":13},"stealth/ox-alpha":{"draws":40,"losses":78,"wins":40},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":11,"wins":8},"tencent/hy4-preview":{"draws":12,"losses":24,"wins":10},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":28},"thinkingmachines/inkling-small":{"draws":17,"losses":7,"wins":24},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":10,"losses":24,"wins":14},"x-ai/grok-4.6":{"draws":12,"losses":30,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":31,"losses":20,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":20,"wins":5},"z-ai/glm-5.2":{"draws":25,"losses":40,"wins":31},"z-ai/glm-5.3":{"draws":8,"losses":32,"wins":6},"z-ai/glm-5.3-flash":{"draws":13,"losses":23,"wins":12},"z-ai/glm-5.3-flashx":{"draws":12,"losses":28,"wins":8}},"gemini-4-argon":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":3,"wins":38},"claude-fable-5":{"draws":3,"losses":15,"wins":30},"claude-fable-5-1":{"draws":5,"losses":40,"wins":9},"claude-haiku-5-5":{"draws":7,"losses":9,"wins":30},"claude-opus-4-5":{"draws":5,"losses":7,"wins":66},"claude-opus-4-8":{"draws":5,"losses":8,"wins":31},"claude-opus-5":{"draws":12,"losses":43,"wins":27},"claude-opus-5-5":{"draws":1,"losses":38,"wins":13},"claude-sonnet-5":{"draws":7,"losses":4,"wins":37},"claude-sonnet-5-5":{"draws":5,"losses":17,"wins":26},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":7,"losses":2,"wins":63},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":2,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":7,"wins":34},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":10,"wins":29},"elorian/glimpse":{"draws":6,"losses":3,"wins":17},"fireworks/ember-1":{"draws":7,"losses":4,"wins":37},"gemini-3.1-pro-preview":{"draws":5,"losses":5,"wins":38},"gemini-4-argon":{"draws":7,"losses":16,"wins":9},"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":7,"losses":4,"wins":73},"google/gemini-3.6-flash":{"draws":11,"losses":13,"wins":68},"google/gemini-3.8-flash":{"draws":6,"losses":7,"wins":35},"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":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":2,"wins":38},"gpt-5.4":{"draws":8,"losses":13,"wins":25},"gpt-5.4-mini":{"draws":7,"losses":0,"wins":25},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":44},"gpt-5.5":{"draws":5,"losses":8,"wins":31},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":40},"gpt-5.6-sol":{"draws":3,"losses":16,"wins":29},"gpt-5.6-terra":{"draws":7,"losses":3,"wins":36},"gpt-6-astra":{"draws":4,"losses":35,"wins":9},"gpt-6-luna":{"draws":6,"losses":5,"wins":37},"gpt-6-sol":{"draws":5,"losses":25,"wins":18},"gpt-6.1-sol":{"draws":5,"losses":34,"wins":9},"gpt-6.1-terra":{"draws":9,"losses":26,"wins":13},"gpt-6.1-terra-pro":{"draws":5,"losses":34,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":27},"inception/mercury-3":{"draws":6,"losses":4,"wins":22},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":43},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":36},"meta/muse-spark-1.2":{"draws":6,"losses":6,"wins":34},"meta/muse-spark-1.3":{"draws":7,"losses":7,"wins":34},"meta/muse-spark-open":{"draws":5,"losses":11,"wins":32},"meta/muse-wonder":{"draws":10,"losses":16,"wins":22},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":25},"minimax/minimax-m3.1-flash":{"draws":10,"losses":4,"wins":28},"mistralai/mistral-large-4-0":{"draws":2,"losses":4,"wins":24},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":5,"wins":38},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":24,"wins":16},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":18},"o3":{"draws":1,"losses":4,"wins":61},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":40},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":42},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":9,"wins":35},"qwen/qwen3.8-27b":{"draws":5,"losses":2,"wins":27},"qwen/qwen3.8-flash":{"draws":4,"losses":8,"wins":20},"qwen/qwen3.8-max":{"draws":7,"losses":6,"wins":35},"qwen/qwen3.8-max-0902":{"draws":4,"losses":7,"wins":37},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":6,"wins":34},"stealth/ox-alpha":{"draws":18,"losses":22,"wins":118},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":33},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":32},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":8},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":25},"tencent/hy4-preview":{"draws":8,"losses":4,"wins":34},"thinkingmachines/inkling":{"draws":8,"losses":3,"wins":53},"thinkingmachines/inkling-small":{"draws":7,"losses":0,"wins":41},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":4},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":5},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":9,"losses":9,"wins":30},"x-ai/grok-4.6":{"draws":10,"losses":12,"wins":26},"x-ai/grok-4.7":{"draws":8,"losses":16,"wins":18},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":15},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":12,"wins":16},"z-ai/glm-5.2":{"draws":14,"losses":4,"wins":78},"z-ai/glm-5.3":{"draws":5,"losses":19,"wins":22},"z-ai/glm-5.3-flash":{"draws":8,"losses":4,"wins":36},"z-ai/glm-5.3-flashx":{"draws":5,"losses":11,"wins":32}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":15,"wins":10},"claude-fable-5":{"draws":5,"losses":31,"wins":0},"claude-fable-5-1":{"draws":3,"losses":37,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":23,"wins":4},"claude-opus-4-5":{"draws":13,"losses":46,"wins":1},"claude-opus-4-8":{"draws":12,"losses":21,"wins":3},"claude-opus-5":{"draws":8,"losses":48,"wins":2},"claude-opus-5-5":{"draws":5,"losses":35,"wins":0},"claude-sonnet-5":{"draws":14,"losses":21,"wins":1},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":8,"wins":5},"deepseek/deepseek-v4-flash":{"draws":13,"losses":30,"wins":11},"deepseek/deepseek-v4-pro":{"draws":9,"losses":23,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":18,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":17,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":28,"wins":1},"elorian/glimpse":{"draws":7,"losses":11,"wins":2},"fireworks/ember-1":{"draws":6,"losses":26,"wins":4},"gemini-3.1-pro-preview":{"draws":9,"losses":17,"wins":10},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":8,"wins":8},"google/gemini-3.5-flash":{"draws":11,"losses":27,"wins":10},"google/gemini-3.5-flash-lite":{"draws":19,"losses":22,"wins":25},"google/gemini-3.6-flash":{"draws":15,"losses":47,"wins":8},"google/gemini-3.8-flash":{"draws":9,"losses":27,"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":5,"losses":22,"wins":5},"gpt-5.4":{"draws":3,"losses":29,"wins":4},"gpt-5.4-mini":{"draws":4,"losses":14,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":22,"wins":9},"gpt-5.5":{"draws":8,"losses":24,"wins":2},"gpt-5.6-luna":{"draws":6,"losses":23,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":33,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":22,"wins":2},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":10,"losses":22,"wins":4},"gpt-6-sol":{"draws":7,"losses":27,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"gpt-6.1-terra":{"draws":1,"losses":35,"wins":0},"gpt-6.1-terra-pro":{"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":9,"wins":7},"inception/mercury-3":{"draws":3,"losses":12,"wins":7},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":9},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":22,"wins":15},"meta/muse-glimmer-30b":{"draws":12,"losses":11,"wins":9},"meta/muse-spark-1.2":{"draws":8,"losses":22,"wins":4},"meta/muse-spark-1.3":{"draws":5,"losses":30,"wins":1},"meta/muse-spark-open":{"draws":7,"losses":29,"wins":0},"meta/muse-wonder":{"draws":5,"losses":30,"wins":1},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":7},"minimax/minimax-m3.1-flash":{"draws":8,"losses":20,"wins":4},"mistralai/mistral-large-4-0":{"draws":8,"losses":14,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":7,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":22,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":35,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":9,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":12,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":12,"wins":2},"o3":{"draws":8,"losses":46,"wins":6},"openai/gpt-oss-120b":{"draws":8,"losses":16,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":12,"wins":12},"qwen/qwen3.7-max":{"draws":5,"losses":13,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":11,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":25,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":18,"wins":2},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":9,"losses":27,"wins":0},"qwen/qwen3.8-max-0902":{"draws":12,"losses":24,"wins":0},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":26,"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":5,"losses":18,"wins":5},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":7,"wins":7},"tencent/hy4-preview":{"draws":10,"losses":23,"wins":3},"thinkingmachines/inkling":{"draws":13,"losses":22,"wins":13},"thinkingmachines/inkling-small":{"draws":10,"losses":11,"wins":15},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":7,"losses":28,"wins":1},"x-ai/grok-4.6":{"draws":9,"losses":24,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":16,"losses":23,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":10,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":20,"wins":0},"z-ai/glm-5.2":{"draws":13,"losses":46,"wins":13},"z-ai/glm-5.3":{"draws":2,"losses":32,"wins":0},"z-ai/glm-5.3-flash":{"draws":5,"losses":25,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":22,"wins":4}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":8,"wins":28},"claude-fable-5":{"draws":9,"losses":27,"wins":12},"claude-fable-5-1":{"draws":6,"losses":48,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":17,"wins":19},"claude-opus-4-5":{"draws":19,"losses":18,"wins":41},"claude-opus-4-8":{"draws":9,"losses":15,"wins":20},"claude-opus-5":{"draws":10,"losses":63,"wins":9},"claude-opus-5-5":{"draws":5,"losses":45,"wins":2},"claude-sonnet-5":{"draws":9,"losses":12,"wins":27},"claude-sonnet-5-5":{"draws":7,"losses":20,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":17,"losses":14,"wins":41},"deepseek/deepseek-v4-pro":{"draws":10,"losses":10,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":8,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":19,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":25,"wins":13},"elorian/glimpse":{"draws":6,"losses":9,"wins":11},"fireworks/ember-1":{"draws":9,"losses":15,"wins":24},"gemini-3.1-pro-preview":{"draws":6,"losses":12,"wins":30},"gemini-4-argon":{"draws":5,"losses":43,"wins":0},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":27},"google/gemini-3.5-flash":{"draws":6,"losses":14,"wins":24},"google/gemini-3.5-flash-lite":{"draws":15,"losses":6,"wins":63},"google/gemini-3.6-flash":{"draws":16,"losses":37,"wins":39},"google/gemini-3.8-flash":{"draws":7,"losses":26,"wins":15},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":16},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":10,"wins":26},"gpt-5.4":{"draws":8,"losses":25,"wins":13},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":16},"gpt-5.4-nano":{"draws":7,"losses":8,"wins":33},"gpt-5.5":{"draws":12,"losses":19,"wins":13},"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":10,"losses":13,"wins":23},"gpt-6-astra":{"draws":0,"losses":45,"wins":3},"gpt-6-luna":{"draws":10,"losses":16,"wins":22},"gpt-6-sol":{"draws":4,"losses":33,"wins":11},"gpt-6.1-sol":{"draws":2,"losses":41,"wins":5},"gpt-6.1-terra":{"draws":3,"losses":38,"wins":7},"gpt-6.1-terra-pro":{"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":1,"wins":21},"inception/mercury-3":{"draws":8,"losses":15,"wins":9},"inclusionai/ling-3.0-flash":{"draws":9,"losses":2,"wins":23},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":9,"losses":10,"wins":33},"meta/muse-glimmer-30b":{"draws":10,"losses":3,"wins":29},"meta/muse-spark-1.2":{"draws":9,"losses":17,"wins":20},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":16},"meta/muse-spark-open":{"draws":12,"losses":15,"wins":21},"meta/muse-wonder":{"draws":10,"losses":29,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":14},"minimax/minimax-m3.1-flash":{"draws":10,"losses":8,"wins":24},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":38,"wins":5},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":6,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":6,"wins":11},"o3":{"draws":6,"losses":17,"wins":43},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":26},"poolside/laguna-s-2.1":{"draws":9,"losses":3,"wins":34},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":14},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":23},"qwen/qwen3.8-27b":{"draws":6,"losses":7,"wins":21},"qwen/qwen3.8-flash":{"draws":6,"losses":9,"wins":17},"qwen/qwen3.8-max":{"draws":11,"losses":15,"wins":22},"qwen/qwen3.8-max-0902":{"draws":11,"losses":19,"wins":18},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":15,"wins":18},"stealth/ox-alpha":{"draws":23,"losses":58,"wins":77},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":23},"stepfun/step-5-preview":{"draws":1,"losses":4,"wins":11},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":7,"losses":20,"wins":19},"thinkingmachines/inkling":{"draws":15,"losses":7,"wins":42},"thinkingmachines/inkling-small":{"draws":12,"losses":8,"wins":28},"unbiased/pareto-26.10":{"draws":3,"losses":12,"wins":1},"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":9,"losses":16,"wins":23},"x-ai/grok-4.6":{"draws":12,"losses":25,"wins":11},"x-ai/grok-4.7":{"draws":5,"losses":31,"wins":6},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":18,"losses":15,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":9},"z-ai/glm-5.2":{"draws":21,"losses":22,"wins":53},"z-ai/glm-5.3":{"draws":10,"losses":20,"wins":16},"z-ai/glm-5.3-flash":{"draws":7,"losses":24,"wins":17},"z-ai/glm-5.3-flashx":{"draws":10,"losses":18,"wins":20}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":34,"wins":20},"claude-fable-5":{"draws":13,"losses":66,"wins":5},"claude-fable-5-1":{"draws":6,"losses":87,"wins":1},"claude-haiku-5-5":{"draws":20,"losses":48,"wins":12},"claude-opus-4-5":{"draws":45,"losses":77,"wins":14},"claude-opus-4-8":{"draws":22,"losses":51,"wins":3},"claude-opus-5":{"draws":20,"losses":114,"wins":10},"claude-opus-5-5":{"draws":6,"losses":86,"wins":0},"claude-sonnet-5":{"draws":21,"losses":50,"wins":13},"claude-sonnet-5-5":{"draws":15,"losses":58,"wins":11},"cohere/north-mini-code":{"draws":9,"losses":16,"wins":7},"deepseek/deepseek-v4-flash":{"draws":32,"losses":60,"wins":32},"deepseek/deepseek-v4-pro":{"draws":18,"losses":38,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":46,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":49,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":60,"wins":9},"elorian/glimpse":{"draws":12,"losses":28,"wins":6},"fireworks/ember-1":{"draws":31,"losses":44,"wins":9},"gemini-3.1-pro-preview":{"draws":29,"losses":41,"wins":14},"gemini-4-argon":{"draws":7,"losses":77,"wins":0},"google/gemini-3.1-flash-lite":{"draws":15,"losses":17,"wins":24},"google/gemini-3.5-flash":{"draws":21,"losses":64,"wins":21},"google/gemini-3.5-flash-lite":{"draws":34,"losses":51,"wins":37},"google/gemini-3.6-flash":{"draws":42,"losses":97,"wins":23},"google/gemini-3.8-flash":{"draws":16,"losses":63,"wins":5},"google/gemma-4-31b-it":{"draws":20,"losses":14,"wins":14},"gpt-4.1":{"draws":7,"losses":18,"wins":3},"gpt-4.1-nano":{"draws":6,"losses":3,"wins":1},"gpt-5":{"draws":19,"losses":34,"wins":21},"gpt-5.4":{"draws":22,"losses":50,"wins":10},"gpt-5.4-mini":{"draws":19,"losses":27,"wins":10},"gpt-5.4-nano":{"draws":20,"losses":35,"wins":29},"gpt-5.5":{"draws":29,"losses":42,"wins":7},"gpt-5.6-luna":{"draws":25,"losses":43,"wins":16},"gpt-5.6-sol":{"draws":12,"losses":69,"wins":3},"gpt-5.6-terra":{"draws":22,"losses":52,"wins":6},"gpt-6-astra":{"draws":5,"losses":79,"wins":0},"gpt-6-luna":{"draws":24,"losses":40,"wins":20},"gpt-6-sol":{"draws":14,"losses":61,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":78,"wins":1},"gpt-6.1-terra":{"draws":6,"losses":77,"wins":1},"gpt-6.1-terra-pro":{"draws":5,"losses":73,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":25,"wins":16},"inception/mercury-3":{"draws":17,"losses":28,"wins":9},"inclusionai/ling-3.0-flash":{"draws":21,"losses":20,"wins":19},"inclusionai/ling-3.1-flash":{"draws":6,"losses":14,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":47,"wins":24},"meta/muse-glimmer-30b":{"draws":25,"losses":24,"wins":25},"meta/muse-spark-1.2":{"draws":18,"losses":50,"wins":12},"meta/muse-spark-1.3":{"draws":13,"losses":63,"wins":8},"meta/muse-spark-open":{"draws":14,"losses":63,"wins":7},"meta/muse-wonder":{"draws":15,"losses":63,"wins":6},"minimax/minimax-m3":{"draws":9,"losses":16,"wins":19},"minimax/minimax-m3.1-flash":{"draws":19,"losses":36,"wins":19},"mistralai/mistral-large-4-0":{"draws":18,"losses":27,"wins":7},"mistralai/mistral-medium-3-5":{"draws":19,"losses":16,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":31,"losses":41,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":68,"wins":5},"nex-agi/nex-n2-pro":{"draws":9,"losses":19,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":6,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":29,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":24,"wins":4},"o3":{"draws":17,"losses":86,"wins":15},"openai/gpt-oss-120b":{"draws":21,"losses":32,"wins":19},"poolside/laguna-s-2.1":{"draws":22,"losses":44,"wins":16},"qwen/qwen3.7-max":{"draws":11,"losses":26,"wins":11},"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":20,"losses":31,"wins":5},"qwen/qwen3.8-max":{"draws":24,"losses":49,"wins":11},"qwen/qwen3.8-max-0902":{"draws":19,"losses":58,"wins":7},"recursive/flint-v1.0":{"draws":6,"losses":5,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":22,"losses":48,"wins":6},"stealth/ox-alpha":{"draws":61,"losses":182,"wins":39},"stealth/space-bunny-alpha":{"draws":17,"losses":38,"wins":11},"stepfun/step-3.7-flash":{"draws":15,"losses":30,"wins":15},"stepfun/step-5-preview":{"draws":4,"losses":12,"wins":8},"tencent/hy3-preview":{"draws":15,"losses":24,"wins":7},"tencent/hy4-preview":{"draws":24,"losses":43,"wins":15},"thinkingmachines/inkling":{"draws":26,"losses":50,"wins":38},"thinkingmachines/inkling-small":{"draws":20,"losses":28,"wins":36},"unbiased/pareto-26.10":{"draws":1,"losses":27,"wins":0},"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":55,"wins":8},"x-ai/grok-4.6":{"draws":21,"losses":56,"wins":7},"x-ai/grok-4.7":{"draws":7,"losses":58,"wins":7},"x-ai/grok-build-0.1":{"draws":11,"losses":13,"wins":4},"xiaomi/mimo-v2.5":{"draws":36,"losses":61,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":14,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":43,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":44,"wins":6},"z-ai/glm-5.2":{"draws":54,"losses":80,"wins":34},"z-ai/glm-5.3":{"draws":16,"losses":63,"wins":1},"z-ai/glm-5.3-flash":{"draws":19,"losses":51,"wins":14},"z-ai/glm-5.3-flashx":{"draws":17,"losses":55,"wins":12}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":12,"wins":49},"claude-fable-5":{"draws":12,"losses":43,"wins":29},"claude-fable-5-1":{"draws":4,"losses":82,"wins":10},"claude-haiku-5-5":{"draws":13,"losses":31,"wins":36},"claude-opus-4-5":{"draws":33,"losses":30,"wins":73},"claude-opus-4-8":{"draws":16,"losses":26,"wins":34},"claude-opus-5":{"draws":14,"losses":88,"wins":38},"claude-opus-5-5":{"draws":5,"losses":70,"wins":13},"claude-sonnet-5":{"draws":20,"losses":24,"wins":40},"claude-sonnet-5-5":{"draws":13,"losses":33,"wins":38},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":26},"deepseek/deepseek-v4-flash":{"draws":24,"losses":18,"wins":82},"deepseek/deepseek-v4-pro":{"draws":18,"losses":27,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":19,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":25,"wins":40},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":35,"wins":36},"elorian/glimpse":{"draws":9,"losses":14,"wins":23},"fireworks/ember-1":{"draws":17,"losses":34,"wins":33},"gemini-3.1-pro-preview":{"draws":15,"losses":23,"wins":46},"gemini-4-argon":{"draws":5,"losses":61,"wins":18},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":46},"google/gemini-3.5-flash":{"draws":21,"losses":32,"wins":53},"google/gemini-3.5-flash-lite":{"draws":36,"losses":25,"wins":89},"google/gemini-3.6-flash":{"draws":30,"losses":44,"wins":62},"google/gemini-3.8-flash":{"draws":15,"losses":39,"wins":30},"google/gemma-4-31b-it":{"draws":13,"losses":7,"wins":28},"gpt-4.1":{"draws":7,"losses":3,"wins":18},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":6},"gpt-5":{"draws":13,"losses":15,"wins":46},"gpt-5.4":{"draws":14,"losses":30,"wins":38},"gpt-5.4-mini":{"draws":17,"losses":8,"wins":31},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":58},"gpt-5.5":{"draws":17,"losses":31,"wins":30},"gpt-5.6-luna":{"draws":24,"losses":11,"wins":49},"gpt-5.6-sol":{"draws":10,"losses":48,"wins":26},"gpt-5.6-terra":{"draws":19,"losses":14,"wins":47},"gpt-6-astra":{"draws":6,"losses":71,"wins":7},"gpt-6-luna":{"draws":19,"losses":25,"wins":40},"gpt-6-sol":{"draws":8,"losses":51,"wins":25},"gpt-6.1-sol":{"draws":4,"losses":69,"wins":11},"gpt-6.1-terra":{"draws":5,"losses":67,"wins":12},"gpt-6.1-terra-pro":{"draws":5,"losses":67,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":4,"wins":37},"inception/mercury-3":{"draws":14,"losses":11,"wins":27},"inclusionai/ling-3.0-flash":{"draws":16,"losses":2,"wins":40},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":20,"losses":9,"wins":63},"meta/muse-glimmer-30b":{"draws":18,"losses":12,"wins":44},"meta/muse-spark-1.2":{"draws":15,"losses":31,"wins":34},"meta/muse-spark-1.3":{"draws":6,"losses":40,"wins":38},"meta/muse-spark-open":{"draws":19,"losses":30,"wins":35},"meta/muse-wonder":{"draws":14,"losses":42,"wins":28},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":31},"minimax/minimax-m3.1-flash":{"draws":18,"losses":14,"wins":46},"mistralai/mistral-large-4-0":{"draws":10,"losses":19,"wins":23},"mistralai/mistral-medium-3-5":{"draws":12,"losses":6,"wins":30},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":21,"losses":24,"wins":35},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":60,"wins":18},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":31},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":9,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":5,"wins":22},"o3":{"draws":14,"losses":26,"wins":80},"openai/gpt-oss-120b":{"draws":19,"losses":10,"wins":43},"poolside/laguna-s-2.1":{"draws":16,"losses":13,"wins":49},"qwen/qwen3.7-max":{"draws":7,"losses":11,"wins":30},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":24,"wins":40},"qwen/qwen3.8-27b":{"draws":11,"losses":18,"wins":33},"qwen/qwen3.8-flash":{"draws":13,"losses":15,"wins":28},"qwen/qwen3.8-max":{"draws":17,"losses":28,"wins":39},"qwen/qwen3.8-max-0902":{"draws":15,"losses":32,"wins":37},"recursive/flint-v1.0":{"draws":8,"losses":0,"wins":16},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":23,"wins":35},"stealth/ox-alpha":{"draws":50,"losses":106,"wins":128},"stealth/space-bunny-alpha":{"draws":18,"losses":9,"wins":41},"stepfun/step-3.7-flash":{"draws":10,"losses":8,"wins":44},"stepfun/step-5-preview":{"draws":3,"losses":7,"wins":16},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":24},"tencent/hy4-preview":{"draws":19,"losses":25,"wins":38},"thinkingmachines/inkling":{"draws":29,"losses":15,"wins":72},"thinkingmachines/inkling-small":{"draws":19,"losses":12,"wins":53},"unbiased/pareto-26.10":{"draws":2,"losses":24,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":25,"wins":3},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":21},"x-ai/grok-4.5":{"draws":19,"losses":29,"wins":36},"x-ai/grok-4.6":{"draws":20,"losses":35,"wins":29},"x-ai/grok-4.7":{"draws":4,"losses":46,"wins":22},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":19},"xiaomi/mimo-v2.5":{"draws":35,"losses":10,"wins":83},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":17,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":19,"wins":25},"z-ai/glm-5.2":{"draws":36,"losses":46,"wins":86},"z-ai/glm-5.3":{"draws":14,"losses":44,"wins":22},"z-ai/glm-5.3-flash":{"draws":8,"losses":44,"wins":32},"z-ai/glm-5.3-flashx":{"draws":15,"losses":29,"wins":40}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":8,"wins":27},"claude-fable-5":{"draws":6,"losses":17,"wins":25},"claude-fable-5-1":{"draws":2,"losses":48,"wins":4},"claude-haiku-5-5":{"draws":11,"losses":13,"wins":22},"claude-opus-4-5":{"draws":28,"losses":12,"wins":38},"claude-opus-4-8":{"draws":13,"losses":11,"wins":20},"claude-opus-5":{"draws":11,"losses":51,"wins":20},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":15,"losses":10,"wins":23},"claude-sonnet-5-5":{"draws":10,"losses":22,"wins":16},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":17,"losses":6,"wins":49},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":9,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":12,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":23,"wins":14},"elorian/glimpse":{"draws":5,"losses":11,"wins":10},"fireworks/ember-1":{"draws":13,"losses":12,"wins":23},"gemini-3.1-pro-preview":{"draws":13,"losses":8,"wins":27},"gemini-4-argon":{"draws":12,"losses":33,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":10,"losses":14,"wins":36},"google/gemini-3.5-flash-lite":{"draws":20,"losses":4,"wins":60},"google/gemini-3.6-flash":{"draws":23,"losses":26,"wins":43},"google/gemini-3.8-flash":{"draws":8,"losses":10,"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":9,"losses":13,"wins":20},"gpt-5.4":{"draws":10,"losses":16,"wins":20},"gpt-5.4-mini":{"draws":9,"losses":4,"wins":19},"gpt-5.4-nano":{"draws":9,"losses":8,"wins":31},"gpt-5.5":{"draws":21,"losses":13,"wins":10},"gpt-5.6-luna":{"draws":12,"losses":7,"wins":29},"gpt-5.6-sol":{"draws":9,"losses":25,"wins":14},"gpt-5.6-terra":{"draws":11,"losses":13,"wins":22},"gpt-6-astra":{"draws":4,"losses":41,"wins":3},"gpt-6-luna":{"draws":14,"losses":14,"wins":20},"gpt-6-sol":{"draws":8,"losses":30,"wins":10},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"gpt-6.1-terra":{"draws":5,"losses":33,"wins":10},"gpt-6.1-terra-pro":{"draws":6,"losses":33,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":0,"wins":20},"inception/mercury-3":{"draws":9,"losses":9,"wins":14},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":26},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":4,"wins":35},"meta/muse-glimmer-30b":{"draws":13,"losses":3,"wins":26},"meta/muse-spark-1.2":{"draws":9,"losses":25,"wins":12},"meta/muse-spark-1.3":{"draws":15,"losses":14,"wins":19},"meta/muse-spark-open":{"draws":11,"losses":19,"wins":18},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":19},"minimax/minimax-m3.1-flash":{"draws":7,"losses":8,"wins":27},"mistralai/mistral-large-4-0":{"draws":11,"losses":6,"wins":13},"mistralai/mistral-medium-3-5":{"draws":9,"losses":0,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":11,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":32,"wins":11},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":0,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":7,"wins":13},"o3":{"draws":8,"losses":20,"wins":38},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":11,"losses":6,"wins":29},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":14},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":15,"wins":20},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":22},"qwen/qwen3.8-flash":{"draws":6,"losses":9,"wins":17},"qwen/qwen3.8-max":{"draws":12,"losses":15,"wins":21},"qwen/qwen3.8-max-0902":{"draws":18,"losses":11,"wins":19},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":12,"wins":22},"stealth/ox-alpha":{"draws":34,"losses":44,"wins":80},"stealth/space-bunny-alpha":{"draws":7,"losses":8,"wins":23},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":25},"stepfun/step-5-preview":{"draws":1,"losses":6,"wins":5},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":12},"tencent/hy4-preview":{"draws":10,"losses":14,"wins":22},"thinkingmachines/inkling":{"draws":21,"losses":5,"wins":38},"thinkingmachines/inkling-small":{"draws":13,"losses":4,"wins":31},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":3},"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":10,"losses":22,"wins":16},"x-ai/grok-4.6":{"draws":21,"losses":16,"wins":11},"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":23,"losses":3,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":3,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":25,"losses":16,"wins":55},"z-ai/glm-5.3":{"draws":8,"losses":22,"wins":16},"z-ai/glm-5.3-flash":{"draws":5,"losses":16,"wins":27},"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":12,"losses":29,"wins":7},"claude-fable-5-1":{"draws":0,"losses":54,"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":12,"losses":63,"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":17,"losses":22,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":19,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":32,"wins":6},"elorian/glimpse":{"draws":6,"losses":13,"wins":7},"fireworks/ember-1":{"draws":19,"losses":21,"wins":8},"gemini-3.1-pro-preview":{"draws":16,"losses":21,"wins":11},"gemini-4-argon":{"draws":3,"losses":44,"wins":1},"google/gemini-3.1-flash-lite":{"draws":12,"losses":5,"wins":15},"google/gemini-3.5-flash":{"draws":16,"losses":28,"wins":16},"google/gemini-3.5-flash-lite":{"draws":29,"losses":31,"wins":24},"google/gemini-3.6-flash":{"draws":27,"losses":51,"wins":14},"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},"gpt-6.1-terra":{"draws":6,"losses":42,"wins":0},"gpt-6.1-terra-pro":{"draws":3,"losses":44,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":9,"wins":9},"inception/mercury-3":{"draws":13,"losses":13,"wins":6},"inclusionai/ling-3.0-flash":{"draws":18,"losses":7,"wins":9},"inclusionai/ling-3.1-flash":{"draws":5,"losses":4,"wins":1},"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":13,"losses":18,"wins":15},"meta/muse-spark-1.3":{"draws":12,"losses":30,"wins":6},"meta/muse-spark-open":{"draws":14,"losses":30,"wins":4},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":11,"losses":7,"wins":8},"minimax/minimax-m3.1-flash":{"draws":10,"losses":17,"wins":15},"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":0},"moonshotai/kimi-k3":{"draws":15,"losses":19,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":40,"wins":2},"nex-agi/nex-n2-pro":{"draws":10,"losses":3,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":10,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":12,"wins":3},"o3":{"draws":14,"losses":35,"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},"recursive/flint-v1.0":{"draws":3,"losses":5,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":21,"wins":10},"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":3,"losses":5,"wins":2},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":6},"tencent/hy4-preview":{"draws":16,"losses":21,"wins":9},"thinkingmachines/inkling":{"draws":24,"losses":18,"wins":22},"thinkingmachines/inkling-small":{"draws":19,"losses":13,"wins":16},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":8,"losses":31,"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":33,"losses":19,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":7,"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":8,"losses":16,"wins":16},"claude-fable-5":{"draws":5,"losses":29,"wins":8},"claude-fable-5-1":{"draws":1,"losses":47,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":22,"wins":6},"claude-opus-4-5":{"draws":13,"losses":32,"wins":23},"claude-opus-4-8":{"draws":7,"losses":22,"wins":9},"claude-opus-5":{"draws":9,"losses":56,"wins":5},"claude-opus-5-5":{"draws":3,"losses":42,"wins":1},"claude-sonnet-5":{"draws":12,"losses":15,"wins":15},"claude-sonnet-5-5":{"draws":6,"losses":27,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":13,"losses":18,"wins":31},"deepseek/deepseek-v4-pro":{"draws":9,"losses":16,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":20,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":25,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":24,"wins":8},"elorian/glimpse":{"draws":6,"losses":10,"wins":8},"fireworks/ember-1":{"draws":8,"losses":22,"wins":12},"gemini-3.1-pro-preview":{"draws":11,"losses":17,"wins":14},"gemini-4-argon":{"draws":3,"losses":33,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":11,"losses":25,"wins":18},"google/gemini-3.5-flash-lite":{"draws":14,"losses":25,"wins":37},"google/gemini-3.6-flash":{"draws":10,"losses":39,"wins":33},"google/gemini-3.8-flash":{"draws":5,"losses":29,"wins":8},"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":6,"losses":12,"wins":6},"gpt-5.4":{"draws":7,"losses":25,"wins":10},"gpt-5.4-mini":{"draws":6,"losses":10,"wins":12},"gpt-5.4-nano":{"draws":2,"losses":21,"wins":19},"gpt-5.5":{"draws":9,"losses":18,"wins":13},"gpt-5.6-luna":{"draws":11,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":3,"losses":33,"wins":6},"gpt-5.6-terra":{"draws":9,"losses":18,"wins":13},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":11,"losses":19,"wins":12},"gpt-6-sol":{"draws":2,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"gpt-6.1-terra":{"draws":1,"losses":39,"wins":2},"gpt-6.1-terra-pro":{"draws":2,"losses":36,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":15},"inception/mercury-3":{"draws":1,"losses":20,"wins":5},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":7,"wins":29},"meta/muse-glimmer-30b":{"draws":9,"losses":12,"wins":17},"meta/muse-spark-1.2":{"draws":8,"losses":21,"wins":11},"meta/muse-spark-1.3":{"draws":6,"losses":27,"wins":9},"meta/muse-spark-open":{"draws":6,"losses":28,"wins":8},"meta/muse-wonder":{"draws":7,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":2,"losses":8,"wins":12},"minimax/minimax-m3.1-flash":{"draws":10,"losses":11,"wins":17},"mistralai/mistral-large-4-0":{"draws":8,"losses":15,"wins":3},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":17},"moonshotai/kimi-k3":{"draws":5,"losses":18,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":33,"wins":6},"nex-agi/nex-n2-pro":{"draws":3,"losses":9,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":12,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":9},"o3":{"draws":8,"losses":23,"wins":33},"openai/gpt-oss-120b":{"draws":8,"losses":9,"wins":19},"poolside/laguna-s-2.1":{"draws":4,"losses":12,"wins":24},"qwen/qwen3.7-max":{"draws":3,"losses":9,"wins":12},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":21,"wins":10},"qwen/qwen3.8-27b":{"draws":5,"losses":16,"wins":9},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":9},"qwen/qwen3.8-max":{"draws":3,"losses":31,"wins":8},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":8},"recursive/flint-v1.0":{"draws":1,"losses":5,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":19,"wins":14},"stealth/ox-alpha":{"draws":29,"losses":63,"wins":50},"stealth/space-bunny-alpha":{"draws":5,"losses":16,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":19},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":6},"tencent/hy4-preview":{"draws":9,"losses":20,"wins":13},"thinkingmachines/inkling":{"draws":11,"losses":14,"wins":33},"thinkingmachines/inkling-small":{"draws":12,"losses":7,"wins":23},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":9,"losses":27,"wins":6},"x-ai/grok-4.7":{"draws":2,"losses":27,"wins":7},"x-ai/grok-build-0.1":{"draws":1,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":18,"losses":16,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":19,"wins":6},"z-ai/glm-5.2":{"draws":21,"losses":27,"wins":36},"z-ai/glm-5.3":{"draws":6,"losses":26,"wins":8},"z-ai/glm-5.3-flash":{"draws":4,"losses":26,"wins":12},"z-ai/glm-5.3-flashx":{"draws":7,"losses":27,"wins":8}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":10,"wins":25},"claude-fable-5":{"draws":10,"losses":25,"wins":13},"claude-fable-5-1":{"draws":4,"losses":45,"wins":5},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":15},"claude-opus-4-5":{"draws":25,"losses":14,"wins":39},"claude-opus-4-8":{"draws":13,"losses":15,"wins":16},"claude-opus-5":{"draws":7,"losses":62,"wins":13},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":17,"losses":10,"wins":21},"claude-sonnet-5-5":{"draws":13,"losses":24,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":7,"wins":8},"deepseek/deepseek-v4-flash":{"draws":21,"losses":13,"wins":38},"deepseek/deepseek-v4-pro":{"draws":9,"losses":12,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":14,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":23,"wins":15},"elorian/glimpse":{"draws":7,"losses":11,"wins":8},"fireworks/ember-1":{"draws":13,"losses":15,"wins":20},"gemini-3.1-pro-preview":{"draws":14,"losses":14,"wins":20},"gemini-4-argon":{"draws":7,"losses":34,"wins":7},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":22},"google/gemini-3.5-flash":{"draws":7,"losses":23,"wins":30},"google/gemini-3.5-flash-lite":{"draws":21,"losses":17,"wins":46},"google/gemini-3.6-flash":{"draws":19,"losses":41,"wins":32},"google/gemini-3.8-flash":{"draws":11,"losses":20,"wins":17},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":12},"gpt-4.1":{"draws":4,"losses":6,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":16,"wins":19},"gpt-5.4":{"draws":8,"losses":10,"wins":12},"gpt-5.4-mini":{"draws":9,"losses":2,"wins":21},"gpt-5.4-nano":{"draws":7,"losses":12,"wins":29},"gpt-5.5":{"draws":9,"losses":18,"wins":17},"gpt-5.6-luna":{"draws":19,"losses":7,"wins":22},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":14},"gpt-5.6-terra":{"draws":14,"losses":12,"wins":20},"gpt-6-astra":{"draws":3,"losses":37,"wins":8},"gpt-6-luna":{"draws":13,"losses":14,"wins":21},"gpt-6-sol":{"draws":4,"losses":38,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":6},"gpt-6.1-terra":{"draws":2,"losses":38,"wins":8},"gpt-6.1-terra-pro":{"draws":6,"losses":36,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":15},"inception/mercury-3":{"draws":8,"losses":9,"wins":15},"inclusionai/ling-3.0-flash":{"draws":10,"losses":9,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":12,"losses":10,"wins":30},"meta/muse-glimmer-30b":{"draws":14,"losses":5,"wins":23},"meta/muse-spark-1.2":{"draws":10,"losses":16,"wins":20},"meta/muse-spark-1.3":{"draws":15,"losses":18,"wins":15},"meta/muse-spark-open":{"draws":10,"losses":24,"wins":14},"meta/muse-wonder":{"draws":14,"losses":21,"wins":13},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":16},"minimax/minimax-m3.1-flash":{"draws":13,"losses":6,"wins":23},"mistralai/mistral-large-4-0":{"draws":12,"losses":5,"wins":13},"mistralai/mistral-medium-3-5":{"draws":9,"losses":6,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":13,"wins":24},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":35,"wins":8},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":8,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":10},"o3":{"draws":8,"losses":13,"wins":45},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":19},"poolside/laguna-s-2.1":{"draws":11,"losses":9,"wins":26},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":15},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":22,"wins":18},"qwen/qwen3.8-27b":{"draws":6,"losses":6,"wins":22},"qwen/qwen3.8-flash":{"draws":7,"losses":8,"wins":17},"qwen/qwen3.8-max":{"draws":11,"losses":19,"wins":18},"qwen/qwen3.8-max-0902":{"draws":14,"losses":16,"wins":18},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":14,"wins":18},"stealth/ox-alpha":{"draws":43,"losses":54,"wins":61},"stealth/space-bunny-alpha":{"draws":11,"losses":9,"wins":18},"stepfun/step-3.7-flash":{"draws":7,"losses":7,"wins":20},"stepfun/step-5-preview":{"draws":1,"losses":6,"wins":5},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":10,"losses":17,"wins":19},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":36},"thinkingmachines/inkling-small":{"draws":15,"losses":5,"wins":28},"unbiased/pareto-26.10":{"draws":3,"losses":11,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"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":17,"losses":17,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"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":5,"losses":5,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":8,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":14,"wins":14},"z-ai/glm-5.2":{"draws":30,"losses":20,"wins":46},"z-ai/glm-5.3":{"draws":11,"losses":24,"wins":11},"z-ai/glm-5.3-flash":{"draws":7,"losses":22,"wins":19},"z-ai/glm-5.3-flashx":{"draws":8,"losses":21,"wins":19}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":11,"wins":21},"claude-fable-5":{"draws":9,"losses":29,"wins":10},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":23,"wins":10},"claude-opus-4-5":{"draws":20,"losses":33,"wins":25},"claude-opus-4-8":{"draws":10,"losses":13,"wins":21},"claude-opus-5":{"draws":10,"losses":63,"wins":9},"claude-opus-5-5":{"draws":2,"losses":47,"wins":3},"claude-sonnet-5":{"draws":17,"losses":11,"wins":20},"claude-sonnet-5-5":{"draws":7,"losses":29,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":21,"losses":14,"wins":37},"deepseek/deepseek-v4-pro":{"draws":13,"losses":12,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":16,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":32,"wins":7},"elorian/glimpse":{"draws":7,"losses":10,"wins":9},"fireworks/ember-1":{"draws":13,"losses":24,"wins":11},"gemini-3.1-pro-preview":{"draws":13,"losses":16,"wins":19},"gemini-4-argon":{"draws":6,"losses":42,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":23},"google/gemini-3.5-flash":{"draws":15,"losses":18,"wins":27},"google/gemini-3.5-flash-lite":{"draws":22,"losses":15,"wins":47},"google/gemini-3.6-flash":{"draws":20,"losses":45,"wins":27},"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":2,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":11,"wins":24},"gpt-5.4":{"draws":9,"losses":30,"wins":7},"gpt-5.4-mini":{"draws":5,"losses":2,"wins":9},"gpt-5.4-nano":{"draws":7,"losses":19,"wins":22},"gpt-5.5":{"draws":20,"losses":15,"wins":9},"gpt-5.6-luna":{"draws":16,"losses":15,"wins":17},"gpt-5.6-sol":{"draws":7,"losses":30,"wins":11},"gpt-5.6-terra":{"draws":17,"losses":14,"wins":15},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":21,"losses":16,"wins":11},"gpt-6-sol":{"draws":7,"losses":33,"wins":8},"gpt-6.1-sol":{"draws":1,"losses":42,"wins":5},"gpt-6.1-terra":{"draws":5,"losses":38,"wins":5},"gpt-6.1-terra-pro":{"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":6,"wins":16},"inception/mercury-3":{"draws":8,"losses":18,"wins":6},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":22},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":12,"losses":9,"wins":31},"meta/muse-glimmer-30b":{"draws":17,"losses":0,"wins":25},"meta/muse-spark-1.2":{"draws":11,"losses":20,"wins":15},"meta/muse-spark-1.3":{"draws":9,"losses":29,"wins":10},"meta/muse-spark-open":{"draws":11,"losses":25,"wins":12},"meta/muse-wonder":{"draws":10,"losses":30,"wins":8},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":14},"minimax/minimax-m3.1-flash":{"draws":13,"losses":14,"wins":15},"mistralai/mistral-large-4-0":{"draws":13,"losses":9,"wins":8},"mistralai/mistral-medium-3-5":{"draws":9,"losses":1,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":15,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":39,"wins":4},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":6,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":10,"wins":6},"o3":{"draws":7,"losses":31,"wins":28},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":26},"poolside/laguna-s-2.1":{"draws":11,"losses":6,"wins":29},"qwen/qwen3.7-max":{"draws":5,"losses":13,"wins":10},"qwen/qwen3.7-plus":{"draws":6,"losses":7,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":24,"wins":11},"qwen/qwen3.8-27b":{"draws":6,"losses":17,"wins":11},"qwen/qwen3.8-flash":{"draws":6,"losses":14,"wins":12},"qwen/qwen3.8-max":{"draws":11,"losses":23,"wins":14},"qwen/qwen3.8-max-0902":{"draws":14,"losses":20,"wins":14},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":19,"wins":15},"stealth/ox-alpha":{"draws":32,"losses":79,"wins":47},"stealth/space-bunny-alpha":{"draws":11,"losses":11,"wins":16},"stepfun/step-3.7-flash":{"draws":7,"losses":9,"wins":18},"stepfun/step-5-preview":{"draws":1,"losses":8,"wins":5},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":12},"tencent/hy4-preview":{"draws":12,"losses":21,"wins":13},"thinkingmachines/inkling":{"draws":21,"losses":10,"wins":33},"thinkingmachines/inkling-small":{"draws":16,"losses":8,"wins":24},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":11,"losses":24,"wins":13},"x-ai/grok-4.6":{"draws":12,"losses":26,"wins":10},"x-ai/grok-4.7":{"draws":6,"losses":31,"wins":5},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":10},"xiaomi/mimo-v2.5":{"draws":19,"losses":14,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":2,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":8},"z-ai/glm-5.2":{"draws":29,"losses":33,"wins":34},"z-ai/glm-5.3":{"draws":5,"losses":34,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":26,"wins":11}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":28,"wins":26},"claude-fable-5":{"draws":6,"losses":56,"wins":10},"claude-fable-5-1":{"draws":2,"losses":75,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":38,"wins":24},"claude-opus-4-5":{"draws":28,"losses":51,"wins":41},"claude-opus-4-8":{"draws":11,"losses":42,"wins":19},"claude-opus-5":{"draws":11,"losses":93,"wins":12},"claude-opus-5-5":{"draws":1,"losses":78,"wins":1},"claude-sonnet-5":{"draws":10,"losses":37,"wins":25},"claude-sonnet-5-5":{"draws":8,"losses":52,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":20},"deepseek/deepseek-v4-flash":{"draws":20,"losses":37,"wins":55},"deepseek/deepseek-v4-pro":{"draws":6,"losses":36,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":31,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":36,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":46,"wins":16},"elorian/glimpse":{"draws":5,"losses":18,"wins":15},"fireworks/ember-1":{"draws":13,"losses":36,"wins":23},"gemini-3.1-pro-preview":{"draws":13,"losses":34,"wins":25},"gemini-4-argon":{"draws":2,"losses":66,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":9,"wins":39},"google/gemini-3.5-flash":{"draws":11,"losses":49,"wins":34},"google/gemini-3.5-flash-lite":{"draws":16,"losses":57,"wins":55},"google/gemini-3.6-flash":{"draws":20,"losses":82,"wins":36},"google/gemini-3.8-flash":{"draws":8,"losses":48,"wins":16},"google/gemma-4-31b-it":{"draws":11,"losses":7,"wins":26},"gpt-4.1":{"draws":3,"losses":11,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":7,"losses":30,"wins":27},"gpt-5.4":{"draws":7,"losses":44,"wins":19},"gpt-5.4-mini":{"draws":8,"losses":12,"wins":28},"gpt-5.4-nano":{"draws":4,"losses":26,"wins":30},"gpt-5.5":{"draws":12,"losses":35,"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":8,"losses":36,"wins":24},"gpt-6-astra":{"draws":0,"losses":70,"wins":2},"gpt-6-luna":{"draws":12,"losses":31,"wins":29},"gpt-6-sol":{"draws":12,"losses":56,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":67,"wins":3},"gpt-6.1-terra":{"draws":1,"losses":71,"wins":0},"gpt-6.1-terra-pro":{"draws":2,"losses":68,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":14,"losses":5,"wins":33},"inception/mercury-3":{"draws":11,"losses":21,"wins":16},"inclusionai/ling-3.0-flash":{"draws":11,"losses":18,"wins":23},"inclusionai/ling-3.1-flash":{"draws":2,"losses":4,"wins":4},"meituan/longcat-2.0":{"draws":8,"losses":22,"wins":52},"meta/muse-glimmer-30b":{"draws":11,"losses":21,"wins":30},"meta/muse-spark-1.2":{"draws":11,"losses":32,"wins":25},"meta/muse-spark-1.3":{"draws":10,"losses":42,"wins":20},"meta/muse-spark-open":{"draws":13,"losses":42,"wins":17},"meta/muse-wonder":{"draws":9,"losses":53,"wins":10},"minimax/minimax-m3":{"draws":7,"losses":15,"wins":20},"minimax/minimax-m3.1-flash":{"draws":8,"losses":27,"wins":27},"mistralai/mistral-large-4-0":{"draws":8,"losses":23,"wins":13},"mistralai/mistral-medium-3-5":{"draws":7,"losses":6,"wins":27},"moonshotai/kimi-k3":{"draws":15,"losses":32,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":63,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":11,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":8,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":23,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":14,"wins":15},"o3":{"draws":7,"losses":46,"wins":65},"openai/gpt-oss-120b":{"draws":11,"losses":23,"wins":28},"poolside/laguna-s-2.1":{"draws":6,"losses":24,"wins":38},"qwen/qwen3.7-max":{"draws":6,"losses":19,"wins":21},"qwen/qwen3.7-plus":{"draws":7,"losses":16,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":40,"wins":15},"qwen/qwen3.8-27b":{"draws":5,"losses":25,"wins":22},"qwen/qwen3.8-flash":{"draws":7,"losses":23,"wins":18},"qwen/qwen3.8-max":{"draws":16,"losses":37,"wins":19},"qwen/qwen3.8-max-0902":{"draws":14,"losses":38,"wins":20},"recursive/flint-v1.0":{"draws":3,"losses":10,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":30,"wins":24},"stealth/ox-alpha":{"draws":28,"losses":103,"wins":71},"stealth/space-bunny-alpha":{"draws":13,"losses":20,"wins":25},"stepfun/step-3.7-flash":{"draws":7,"losses":16,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":8,"losses":16,"wins":16},"tencent/hy4-preview":{"draws":8,"losses":41,"wins":21},"thinkingmachines/inkling":{"draws":16,"losses":30,"wins":48},"thinkingmachines/inkling-small":{"draws":18,"losses":18,"wins":36},"unbiased/pareto-26.10":{"draws":2,"losses":20,"wins":2},"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":38,"wins":20},"x-ai/grok-4.6":{"draws":8,"losses":51,"wins":13},"x-ai/grok-4.7":{"draws":6,"losses":54,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":15},"xiaomi/mimo-v2.5":{"draws":24,"losses":35,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":11,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":26,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":31,"wins":10},"z-ai/glm-5.2":{"draws":24,"losses":60,"wins":60},"z-ai/glm-5.3":{"draws":7,"losses":47,"wins":14},"z-ai/glm-5.3-flash":{"draws":9,"losses":39,"wins":24},"z-ai/glm-5.3-flashx":{"draws":10,"losses":41,"wins":21}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":9,"wins":18},"claude-fable-5":{"draws":11,"losses":22,"wins":15},"claude-fable-5-1":{"draws":2,"losses":49,"wins":3},"claude-haiku-5-5":{"draws":20,"losses":19,"wins":7},"claude-opus-4-5":{"draws":34,"losses":17,"wins":27},"claude-opus-4-8":{"draws":12,"losses":13,"wins":19},"claude-opus-5":{"draws":12,"losses":54,"wins":16},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":18,"losses":9,"wins":21},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":15},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":23,"losses":11,"wins":38},"deepseek/deepseek-v4-pro":{"draws":9,"losses":12,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":16,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":19,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":20,"wins":13},"elorian/glimpse":{"draws":6,"losses":11,"wins":9},"fireworks/ember-1":{"draws":17,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":11,"losses":14,"wins":23},"gemini-4-argon":{"draws":2,"losses":41,"wins":5},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":24},"google/gemini-3.5-flash":{"draws":17,"losses":19,"wins":24},"google/gemini-3.5-flash-lite":{"draws":30,"losses":17,"wins":37},"google/gemini-3.6-flash":{"draws":21,"losses":37,"wins":34},"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":3,"losses":4,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":12,"losses":10,"wins":20},"gpt-5.4":{"draws":12,"losses":18,"wins":16},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":11},"gpt-5.4-nano":{"draws":10,"losses":18,"wins":20},"gpt-5.5":{"draws":9,"losses":9,"wins":10},"gpt-5.6-luna":{"draws":19,"losses":7,"wins":22},"gpt-5.6-sol":{"draws":10,"losses":22,"wins":16},"gpt-5.6-terra":{"draws":14,"losses":13,"wins":19},"gpt-6-astra":{"draws":2,"losses":42,"wins":4},"gpt-6-luna":{"draws":20,"losses":10,"wins":18},"gpt-6-sol":{"draws":6,"losses":30,"wins":12},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":6},"gpt-6.1-terra":{"draws":4,"losses":37,"wins":7},"gpt-6.1-terra-pro":{"draws":4,"losses":38,"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},"inception/mercury-3":{"draws":10,"losses":8,"wins":14},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":16},"inclusionai/ling-3.1-flash":{"draws":3,"losses":3,"wins":2},"meituan/longcat-2.0":{"draws":16,"losses":11,"wins":25},"meta/muse-glimmer-30b":{"draws":17,"losses":7,"wins":18},"meta/muse-spark-1.2":{"draws":10,"losses":17,"wins":19},"meta/muse-spark-1.3":{"draws":13,"losses":17,"wins":18},"meta/muse-spark-open":{"draws":13,"losses":20,"wins":15},"meta/muse-wonder":{"draws":11,"losses":26,"wins":11},"minimax/minimax-m3":{"draws":8,"losses":2,"wins":16},"minimax/minimax-m3.1-flash":{"draws":11,"losses":11,"wins":20},"mistralai/mistral-large-4-0":{"draws":11,"losses":7,"wins":12},"mistralai/mistral-medium-3-5":{"draws":8,"losses":5,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":16,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":35,"wins":7},"nex-agi/nex-n2-pro":{"draws":3,"losses":4,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":4,"wins":9},"o3":{"draws":13,"losses":20,"wins":33},"openai/gpt-oss-120b":{"draws":18,"losses":5,"wins":19},"poolside/laguna-s-2.1":{"draws":15,"losses":13,"wins":18},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":16},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-27b":{"draws":12,"losses":10,"wins":12},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":13},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":17},"qwen/qwen3.8-max-0902":{"draws":19,"losses":14,"wins":15},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":8,"wins":24},"stealth/ox-alpha":{"draws":39,"losses":70,"wins":49},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":11,"losses":2,"wins":13},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":15},"thinkingmachines/inkling":{"draws":20,"losses":15,"wins":29},"thinkingmachines/inkling-small":{"draws":17,"losses":9,"wins":22},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":3},"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":23,"wins":17},"x-ai/grok-4.6":{"draws":13,"losses":21,"wins":14},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":14},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":29,"losses":13,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":7,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":14,"wins":11},"z-ai/glm-5.2":{"draws":35,"losses":19,"wins":42},"z-ai/glm-5.3":{"draws":13,"losses":26,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":18,"wins":21},"z-ai/glm-5.3-flashx":{"draws":12,"losses":20,"wins":16}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":14,"wins":17},"claude-fable-5":{"draws":11,"losses":34,"wins":3},"claude-fable-5-1":{"draws":5,"losses":49,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":28,"losses":31,"wins":19},"claude-opus-4-8":{"draws":10,"losses":25,"wins":9},"claude-opus-5":{"draws":9,"losses":62,"wins":11},"claude-opus-5-5":{"draws":6,"losses":46,"wins":0},"claude-sonnet-5":{"draws":15,"losses":20,"wins":13},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":21,"losses":20,"wins":31},"deepseek/deepseek-v4-pro":{"draws":15,"losses":19,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":23,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":31,"wins":6},"elorian/glimpse":{"draws":8,"losses":13,"wins":5},"fireworks/ember-1":{"draws":15,"losses":19,"wins":14},"gemini-3.1-pro-preview":{"draws":14,"losses":15,"wins":19},"gemini-4-argon":{"draws":5,"losses":41,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":16,"losses":28,"wins":16},"google/gemini-3.5-flash-lite":{"draws":20,"losses":20,"wins":44},"google/gemini-3.6-flash":{"draws":26,"losses":45,"wins":21},"google/gemini-3.8-flash":{"draws":12,"losses":31,"wins":5},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":13},"gpt-4.1":{"draws":3,"losses":8,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":19,"wins":12},"gpt-5.4":{"draws":14,"losses":25,"wins":7},"gpt-5.4-mini":{"draws":13,"losses":3,"wins":16},"gpt-5.4-nano":{"draws":13,"losses":13,"wins":22},"gpt-5.5":{"draws":16,"losses":19,"wins":9},"gpt-5.6-luna":{"draws":10,"losses":8,"wins":14},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":10,"losses":23,"wins":13},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":16,"losses":18,"wins":14},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":44,"wins":1},"gpt-6.1-terra":{"draws":7,"losses":39,"wins":2},"gpt-6.1-terra-pro":{"draws":6,"losses":40,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":3,"wins":16},"inception/mercury-3":{"draws":10,"losses":14,"wins":8},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":5,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":10,"losses":13,"wins":29},"meta/muse-glimmer-30b":{"draws":13,"losses":6,"wins":23},"meta/muse-spark-1.2":{"draws":13,"losses":22,"wins":11},"meta/muse-spark-1.3":{"draws":10,"losses":26,"wins":12},"meta/muse-spark-open":{"draws":11,"losses":26,"wins":11},"meta/muse-wonder":{"draws":9,"losses":33,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":2,"wins":16},"minimax/minimax-m3.1-flash":{"draws":9,"losses":18,"wins":15},"mistralai/mistral-large-4-0":{"draws":13,"losses":15,"wins":2},"mistralai/mistral-medium-3-5":{"draws":9,"losses":1,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":23,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":41,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":11,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":9,"wins":6},"o3":{"draws":13,"losses":23,"wins":30},"openai/gpt-oss-120b":{"draws":13,"losses":8,"wins":21},"poolside/laguna-s-2.1":{"draws":16,"losses":10,"wins":20},"qwen/qwen3.7-max":{"draws":8,"losses":11,"wins":9},"qwen/qwen3.7-plus":{"draws":9,"losses":4,"wins":11},"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":17,"losses":23,"wins":8},"qwen/qwen3.8-max-0902":{"draws":15,"losses":21,"wins":12},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":21,"wins":9},"stealth/ox-alpha":{"draws":48,"losses":75,"wins":35},"stealth/space-bunny-alpha":{"draws":8,"losses":16,"wins":14},"stepfun/step-3.7-flash":{"draws":7,"losses":9,"wins":18},"stepfun/step-5-preview":{"draws":0,"losses":7,"wins":3},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":12},"tencent/hy4-preview":{"draws":11,"losses":25,"wins":10},"thinkingmachines/inkling":{"draws":17,"losses":14,"wins":33},"thinkingmachines/inkling-small":{"draws":17,"losses":8,"wins":23},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":26,"wins":9},"x-ai/grok-4.6":{"draws":13,"losses":31,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":28,"losses":10,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":10,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":16,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":21,"wins":6},"z-ai/glm-5.2":{"draws":28,"losses":35,"wins":33},"z-ai/glm-5.3":{"draws":7,"losses":32,"wins":7},"z-ai/glm-5.3-flash":{"draws":10,"losses":28,"wins":10},"z-ai/glm-5.3-flashx":{"draws":12,"losses":22,"wins":14}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":32},"claude-fable-5":{"draws":7,"losses":20,"wins":21},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":9,"losses":15,"wins":22},"claude-opus-4-5":{"draws":17,"losses":11,"wins":50},"claude-opus-4-8":{"draws":5,"losses":13,"wins":26},"claude-opus-5":{"draws":15,"losses":49,"wins":18},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":6,"losses":7,"wins":35},"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":12,"losses":6,"wins":54},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":9,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":18,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":16,"wins":25},"elorian/glimpse":{"draws":2,"losses":7,"wins":17},"fireworks/ember-1":{"draws":6,"losses":11,"wins":31},"gemini-3.1-pro-preview":{"draws":4,"losses":17,"wins":27},"gemini-4-argon":{"draws":6,"losses":30,"wins":12},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":29},"google/gemini-3.5-flash":{"draws":3,"losses":15,"wins":42},"google/gemini-3.5-flash-lite":{"draws":10,"losses":10,"wins":64},"google/gemini-3.6-flash":{"draws":8,"losses":28,"wins":56},"google/gemini-3.8-flash":{"draws":5,"losses":17,"wins":26},"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":9,"losses":14,"wins":23},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":25},"gpt-5.4-nano":{"draws":3,"losses":8,"wins":37},"gpt-5.5":{"draws":8,"losses":13,"wins":23},"gpt-5.6-luna":{"draws":4,"losses":9,"wins":35},"gpt-5.6-sol":{"draws":4,"losses":21,"wins":7},"gpt-5.6-terra":{"draws":10,"losses":6,"wins":30},"gpt-6-astra":{"draws":6,"losses":40,"wins":2},"gpt-6-luna":{"draws":8,"losses":10,"wins":30},"gpt-6-sol":{"draws":4,"losses":30,"wins":14},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":7},"gpt-6.1-terra":{"draws":10,"losses":31,"wins":7},"gpt-6.1-terra-pro":{"draws":7,"losses":33,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inception/mercury-3":{"draws":5,"losses":7,"wins":20},"inclusionai/ling-3.0-flash":{"draws":3,"losses":3,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":7,"losses":6,"wins":39},"meta/muse-glimmer-30b":{"draws":4,"losses":3,"wins":35},"meta/muse-spark-1.2":{"draws":6,"losses":14,"wins":26},"meta/muse-spark-1.3":{"draws":9,"losses":16,"wins":23},"meta/muse-spark-open":{"draws":10,"losses":17,"wins":21},"meta/muse-wonder":{"draws":10,"losses":22,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":22},"minimax/minimax-m3.1-flash":{"draws":5,"losses":9,"wins":28},"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":0,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":10,"wins":24},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":30,"wins":10},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":4,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":5,"wins":15},"o3":{"draws":4,"losses":11,"wins":51},"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":6,"losses":11,"wins":31},"qwen/qwen3.8-27b":{"draws":4,"losses":6,"wins":24},"qwen/qwen3.8-flash":{"draws":4,"losses":7,"wins":21},"qwen/qwen3.8-max":{"draws":11,"losses":13,"wins":24},"qwen/qwen3.8-max-0902":{"draws":6,"losses":11,"wins":31},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":6,"wins":35},"stealth/ox-alpha":{"draws":21,"losses":35,"wins":102},"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":3,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":2,"wins":17},"tencent/hy4-preview":{"draws":6,"losses":15,"wins":25},"thinkingmachines/inkling":{"draws":7,"losses":8,"wins":49},"thinkingmachines/inkling-small":{"draws":7,"losses":8,"wins":33},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":6,"losses":15,"wins":27},"x-ai/grok-4.6":{"draws":9,"losses":22,"wins":17},"x-ai/grok-4.7":{"draws":5,"losses":26,"wins":11},"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":6,"losses":5,"wins":17},"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":9,"losses":15,"wins":22},"z-ai/glm-5.3-flash":{"draws":11,"losses":16,"wins":21},"z-ai/glm-5.3-flashx":{"draws":8,"losses":15,"wins":25}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":11,"wins":22},"claude-fable-5":{"draws":9,"losses":31,"wins":8},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":23,"losses":25,"wins":30},"claude-opus-4-8":{"draws":8,"losses":21,"wins":15},"claude-opus-5":{"draws":8,"losses":69,"wins":5},"claude-opus-5-5":{"draws":2,"losses":49,"wins":1},"claude-sonnet-5":{"draws":13,"losses":16,"wins":19},"claude-sonnet-5-5":{"draws":8,"losses":29,"wins":11},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":20,"losses":14,"wins":38},"deepseek/deepseek-v4-pro":{"draws":16,"losses":13,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":14,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":16,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":24,"wins":13},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":11,"losses":22,"wins":15},"gemini-3.1-pro-preview":{"draws":14,"losses":14,"wins":20},"gemini-4-argon":{"draws":7,"losses":38,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":23},"google/gemini-3.5-flash":{"draws":11,"losses":19,"wins":30},"google/gemini-3.5-flash-lite":{"draws":19,"losses":17,"wins":48},"google/gemini-3.6-flash":{"draws":19,"losses":47,"wins":26},"google/gemini-3.8-flash":{"draws":14,"losses":18,"wins":16},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":6,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":10,"wins":24},"gpt-5.4":{"draws":10,"losses":23,"wins":13},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":9,"losses":15,"wins":24},"gpt-5.5":{"draws":13,"losses":19,"wins":12},"gpt-5.6-luna":{"draws":12,"losses":16,"wins":20},"gpt-5.6-sol":{"draws":9,"losses":30,"wins":9},"gpt-5.6-terra":{"draws":10,"losses":11,"wins":9},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":9,"losses":23,"wins":16},"gpt-6-sol":{"draws":6,"losses":37,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":42,"wins":5},"gpt-6.1-terra":{"draws":6,"losses":39,"wins":3},"gpt-6.1-terra-pro":{"draws":4,"losses":39,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":20},"inception/mercury-3":{"draws":9,"losses":11,"wins":12},"inclusionai/ling-3.0-flash":{"draws":12,"losses":1,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":10,"losses":13,"wins":29},"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":7,"losses":27,"wins":14},"meta/muse-spark-open":{"draws":12,"losses":20,"wins":16},"meta/muse-wonder":{"draws":12,"losses":26,"wins":10},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":17},"minimax/minimax-m3.1-flash":{"draws":14,"losses":14,"wins":14},"mistralai/mistral-large-4-0":{"draws":10,"losses":11,"wins":9},"mistralai/mistral-medium-3-5":{"draws":5,"losses":5,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":8,"losses":21,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":39,"wins":5},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":5,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":9,"wins":8},"o3":{"draws":10,"losses":24,"wins":32},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":22},"poolside/laguna-s-2.1":{"draws":14,"losses":4,"wins":28},"qwen/qwen3.7-max":{"draws":7,"losses":9,"wins":12},"qwen/qwen3.7-plus":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":21,"wins":11},"qwen/qwen3.8-27b":{"draws":9,"losses":9,"wins":16},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":9},"qwen/qwen3.8-max":{"draws":16,"losses":15,"wins":17},"qwen/qwen3.8-max-0902":{"draws":16,"losses":17,"wins":15},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":15,"wins":16},"stealth/ox-alpha":{"draws":40,"losses":67,"wins":51},"stealth/space-bunny-alpha":{"draws":9,"losses":11,"wins":18},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":3,"wins":7},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":12},"tencent/hy4-preview":{"draws":11,"losses":20,"wins":15},"thinkingmachines/inkling":{"draws":20,"losses":12,"wins":32},"thinkingmachines/inkling-small":{"draws":12,"losses":11,"wins":25},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":12,"losses":21,"wins":15},"x-ai/grok-4.6":{"draws":15,"losses":23,"wins":10},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":20,"losses":6,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":3,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":14,"wins":9},"z-ai/glm-5.2":{"draws":33,"losses":25,"wins":38},"z-ai/glm-5.3":{"draws":9,"losses":32,"wins":5},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":11,"losses":19,"wins":18}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":42},"claude-fable-5":{"draws":4,"losses":5,"wins":39},"claude-fable-5-1":{"draws":5,"losses":20,"wins":29},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":41},"claude-opus-4-5":{"draws":7,"losses":2,"wins":69},"claude-opus-4-8":{"draws":1,"losses":3,"wins":40},"claude-opus-5":{"draws":8,"losses":23,"wins":51},"claude-opus-5-5":{"draws":4,"losses":25,"wins":23},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"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":3,"wins":65},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":3,"wins":42},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":2,"wins":40},"elorian/glimpse":{"draws":1,"losses":1,"wins":24},"fireworks/ember-1":{"draws":1,"losses":3,"wins":44},"gemini-3.1-pro-preview":{"draws":3,"losses":1,"wins":44},"gemini-4-argon":{"draws":3,"losses":14,"wins":31},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":2,"losses":5,"wins":53},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":80},"google/gemini-3.6-flash":{"draws":4,"losses":7,"wins":81},"google/gemini-3.8-flash":{"draws":4,"losses":1,"wins":43},"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":1,"losses":1,"wins":46},"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":8,"wins":36},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":42},"gpt-6-astra":{"draws":3,"losses":20,"wins":9},"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":20,"wins":21},"gpt-6.1-terra":{"draws":7,"losses":13,"wins":28},"gpt-6.1-terra-pro":{"draws":9,"losses":15,"wins":24},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inception/mercury-3":{"draws":3,"losses":1,"wins":28},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":33},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":10},"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":5,"wins":36},"meta/muse-spark-open":{"draws":1,"losses":1,"wins":46},"meta/muse-wonder":{"draws":4,"losses":5,"wins":39},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"minimax/minimax-m3.1-flash":{"draws":1,"losses":0,"wins":41},"mistralai/mistral-large-4-0":{"draws":3,"losses":0,"wins":27},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":27},"moonshotai/kimi-k3":{"draws":6,"losses":4,"wins":36},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":12,"wins":32},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":22},"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":1,"losses":0,"wins":27},"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},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":0,"wins":41},"stealth/ox-alpha":{"draws":10,"losses":9,"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":0,"wins":8},"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":{"draws":2,"losses":9,"wins":5},"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":4,"losses":7,"wins":37},"x-ai/grok-4.6":{"draws":5,"losses":6,"wins":37},"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":0,"losses":0,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":0,"wins":27},"z-ai/glm-5.2":{"draws":5,"losses":3,"wins":88},"z-ai/glm-5.3":{"draws":3,"losses":4,"wins":39},"z-ai/glm-5.3-flash":{"draws":2,"losses":2,"wins":44},"z-ai/glm-5.3-flashx":{"draws":4,"losses":3,"wins":41}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":14,"wins":13},"claude-fable-5":{"draws":8,"losses":30,"wins":10},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":23,"wins":9},"claude-opus-4-5":{"draws":27,"losses":34,"wins":17},"claude-opus-4-8":{"draws":7,"losses":26,"wins":11},"claude-opus-5":{"draws":18,"losses":59,"wins":5},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":12,"losses":24,"wins":12},"claude-sonnet-5-5":{"draws":14,"losses":21,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":26,"losses":19,"wins":27},"deepseek/deepseek-v4-pro":{"draws":13,"losses":11,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":21,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":23,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":28,"wins":11},"elorian/glimpse":{"draws":7,"losses":10,"wins":9},"fireworks/ember-1":{"draws":15,"losses":21,"wins":12},"gemini-3.1-pro-preview":{"draws":11,"losses":21,"wins":16},"gemini-4-argon":{"draws":2,"losses":45,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":17},"google/gemini-3.5-flash":{"draws":15,"losses":26,"wins":19},"google/gemini-3.5-flash-lite":{"draws":24,"losses":27,"wins":33},"google/gemini-3.6-flash":{"draws":25,"losses":51,"wins":16},"google/gemini-3.8-flash":{"draws":17,"losses":25,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":10},"gpt-4.1":{"draws":5,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":2,"wins":1},"gpt-5":{"draws":17,"losses":14,"wins":11},"gpt-5.4":{"draws":13,"losses":24,"wins":9},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":12,"losses":16,"wins":20},"gpt-5.5":{"draws":19,"losses":19,"wins":6},"gpt-5.6-luna":{"draws":18,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":7,"losses":36,"wins":5},"gpt-5.6-terra":{"draws":12,"losses":14,"wins":20},"gpt-6-astra":{"draws":4,"losses":43,"wins":1},"gpt-6-luna":{"draws":9,"losses":13,"wins":10},"gpt-6-sol":{"draws":8,"losses":36,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":44,"wins":0},"gpt-6.1-terra":{"draws":7,"losses":41,"wins":0},"gpt-6.1-terra-pro":{"draws":3,"losses":41,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":15,"losses":6,"wins":13},"inception/mercury-3":{"draws":10,"losses":11,"wins":11},"inclusionai/ling-3.0-flash":{"draws":11,"losses":5,"wins":18},"inclusionai/ling-3.1-flash":{"draws":4,"losses":4,"wins":8},"meituan/longcat-2.0":{"draws":10,"losses":14,"wins":28},"meta/muse-glimmer-30b":{"draws":14,"losses":10,"wins":18},"meta/muse-spark-1.2":{"draws":14,"losses":23,"wins":9},"meta/muse-spark-1.3":{"draws":6,"losses":31,"wins":11},"meta/muse-spark-open":{"draws":14,"losses":23,"wins":11},"meta/muse-wonder":{"draws":12,"losses":26,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":9,"wins":11},"minimax/minimax-m3.1-flash":{"draws":9,"losses":17,"wins":16},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":1},"moonshotai/kimi-k3":{"draws":18,"losses":17,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":38,"wins":3},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":11,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":8},"o3":{"draws":14,"losses":22,"wins":30},"openai/gpt-oss-120b":{"draws":11,"losses":14,"wins":17},"poolside/laguna-s-2.1":{"draws":15,"losses":15,"wins":16},"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":9,"losses":17,"wins":8},"qwen/qwen3.8-flash":{"draws":12,"losses":11,"wins":9},"qwen/qwen3.8-max":{"draws":13,"losses":21,"wins":14},"qwen/qwen3.8-max-0902":{"draws":13,"losses":22,"wins":13},"recursive/flint-v1.0":{"draws":3,"losses":4,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":16,"wins":16},"stealth/ox-alpha":{"draws":35,"losses":78,"wins":45},"stealth/space-bunny-alpha":{"draws":11,"losses":12,"wins":15},"stepfun/step-3.7-flash":{"draws":9,"losses":11,"wins":14},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":4},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":10},"tencent/hy4-preview":{"draws":18,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":27,"losses":10,"wins":27},"thinkingmachines/inkling-small":{"draws":14,"losses":11,"wins":23},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":13,"losses":32,"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":25,"losses":14,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":7,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":16,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":17,"wins":8},"z-ai/glm-5.2":{"draws":42,"losses":24,"wins":30},"z-ai/glm-5.3":{"draws":9,"losses":31,"wins":6},"z-ai/glm-5.3-flash":{"draws":15,"losses":27,"wins":6},"z-ai/glm-5.3-flashx":{"draws":7,"losses":27,"wins":14}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":2,"wins":34},"claude-fable-5":{"draws":7,"losses":11,"wins":30},"claude-fable-5-1":{"draws":6,"losses":35,"wins":13},"claude-haiku-5-5":{"draws":11,"losses":7,"wins":28},"claude-opus-4-5":{"draws":17,"losses":5,"wins":56},"claude-opus-4-8":{"draws":8,"losses":9,"wins":27},"claude-opus-5":{"draws":12,"losses":35,"wins":35},"claude-opus-5-5":{"draws":6,"losses":34,"wins":12},"claude-sonnet-5":{"draws":10,"losses":7,"wins":31},"claude-sonnet-5-5":{"draws":4,"losses":17,"wins":27},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"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":11,"losses":6,"wins":31},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":11,"wins":33},"elorian/glimpse":{"draws":5,"losses":4,"wins":17},"fireworks/ember-1":{"draws":7,"losses":6,"wins":35},"gemini-3.1-pro-preview":{"draws":2,"losses":8,"wins":38},"gemini-4-argon":{"draws":5,"losses":22,"wins":21},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":9,"losses":4,"wins":47},"google/gemini-3.5-flash-lite":{"draws":19,"losses":5,"wins":60},"google/gemini-3.6-flash":{"draws":13,"losses":16,"wins":63},"google/gemini-3.8-flash":{"draws":9,"losses":8,"wins":31},"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":7,"losses":3,"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":6,"losses":10,"wins":28},"gpt-5.6-luna":{"draws":11,"losses":3,"wins":34},"gpt-5.6-sol":{"draws":5,"losses":15,"wins":28},"gpt-5.6-terra":{"draws":9,"losses":5,"wins":32},"gpt-6-astra":{"draws":8,"losses":28,"wins":12},"gpt-6-luna":{"draws":7,"losses":8,"wins":33},"gpt-6-sol":{"draws":5,"losses":14,"wins":13},"gpt-6.1-sol":{"draws":8,"losses":29,"wins":11},"gpt-6.1-terra":{"draws":5,"losses":25,"wins":18},"gpt-6.1-terra-pro":{"draws":6,"losses":31,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":5,"losses":0,"wins":29},"inception/mercury-3":{"draws":4,"losses":4,"wins":24},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":26},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":6},"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":5,"losses":9,"wins":32},"meta/muse-spark-1.3":{"draws":10,"losses":8,"wins":30},"meta/muse-spark-open":{"draws":3,"losses":7,"wins":38},"meta/muse-wonder":{"draws":4,"losses":16,"wins":28},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"minimax/minimax-m3.1-flash":{"draws":6,"losses":0,"wins":36},"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":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":7,"wins":32},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":29,"wins":15},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":2,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":18},"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":8,"losses":4,"wins":22},"qwen/qwen3.8-flash":{"draws":3,"losses":5,"wins":24},"qwen/qwen3.8-max":{"draws":5,"losses":7,"wins":36},"qwen/qwen3.8-max-0902":{"draws":5,"losses":9,"wins":34},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":4,"wins":34},"stealth/ox-alpha":{"draws":24,"losses":19,"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":3,"losses":4,"wins":7},"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":{"draws":0,"losses":16,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":6,"losses":7,"wins":35},"x-ai/grok-4.6":{"draws":8,"losses":8,"wins":32},"x-ai/grok-4.7":{"draws":4,"losses":22,"wins":16},"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":3,"losses":3,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":7,"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":13,"wins":26},"z-ai/glm-5.3-flash":{"draws":8,"losses":8,"wins":32},"z-ai/glm-5.3-flashx":{"draws":6,"losses":11,"wins":31}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":5,"wins":38},"claude-fable-5":{"draws":2,"losses":9,"wins":37},"claude-fable-5-1":{"draws":2,"losses":23,"wins":29},"claude-haiku-5-5":{"draws":4,"losses":4,"wins":38},"claude-opus-4-5":{"draws":2,"losses":4,"wins":72},"claude-opus-4-8":{"draws":1,"losses":6,"wins":37},"claude-opus-5":{"draws":13,"losses":26,"wins":43},"claude-opus-5-5":{"draws":4,"losses":25,"wins":23},"claude-sonnet-5":{"draws":1,"losses":2,"wins":45},"claude-sonnet-5-5":{"draws":1,"losses":10,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":65},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":5,"wins":39},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":10,"wins":33},"elorian/glimpse":{"draws":1,"losses":4,"wins":21},"fireworks/ember-1":{"draws":0,"losses":8,"wins":40},"gemini-3.1-pro-preview":{"draws":1,"losses":5,"wins":42},"gemini-4-argon":{"draws":7,"losses":16,"wins":25},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":2,"losses":5,"wins":53},"google/gemini-3.5-flash-lite":{"draws":6,"losses":1,"wins":77},"google/gemini-3.6-flash":{"draws":6,"losses":3,"wins":83},"google/gemini-3.8-flash":{"draws":3,"losses":6,"wins":39},"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":1,"losses":4,"wins":41},"gpt-5.4-mini":{"draws":1,"losses":2,"wins":29},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":46},"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":6,"wins":39},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":41},"gpt-6-astra":{"draws":7,"losses":24,"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":1,"losses":14,"wins":17},"gpt-6.1-terra":{"draws":8,"losses":14,"wins":26},"gpt-6.1-terra-pro":{"draws":8,"losses":21,"wins":19},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":32},"inception/mercury-3":{"draws":0,"losses":1,"wins":31},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":33},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":7},"meituan/longcat-2.0":{"draws":1,"losses":5,"wins":46},"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-spark-open":{"draws":0,"losses":5,"wins":43},"meta/muse-wonder":{"draws":6,"losses":11,"wins":31},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"minimax/minimax-m3.1-flash":{"draws":1,"losses":0,"wins":41},"mistralai/mistral-large-4-0":{"draws":3,"losses":4,"wins":23},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k3":{"draws":3,"losses":4,"wins":39},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":16,"wins":29},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":22},"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":2,"losses":1,"wins":25},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":7,"wins":39},"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":4,"losses":2,"wins":42},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":45},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":4,"wins":39},"stealth/ox-alpha":{"draws":12,"losses":9,"wins":137},"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":6},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":1,"losses":2,"wins":43},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":61},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":46},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":6},"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":4,"wins":41},"x-ai/grok-4.7":{"draws":1,"losses":13,"wins":28},"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":2,"losses":0,"wins":16},"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":7,"losses":7,"wins":32},"z-ai/glm-5.3-flash":{"draws":4,"losses":5,"wins":39},"z-ai/glm-5.3-flashx":{"draws":3,"losses":5,"wins":40}},"gpt-6.1-terra":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":5,"wins":29},"claude-fable-5":{"draws":7,"losses":13,"wins":28},"claude-fable-5-1":{"draws":4,"losses":30,"wins":20},"claude-haiku-5-5":{"draws":8,"losses":7,"wins":31},"claude-opus-4-5":{"draws":18,"losses":4,"wins":56},"claude-opus-4-8":{"draws":3,"losses":6,"wins":35},"claude-opus-5":{"draws":12,"losses":33,"wins":37},"claude-opus-5-5":{"draws":4,"losses":32,"wins":16},"claude-sonnet-5":{"draws":7,"losses":5,"wins":36},"claude-sonnet-5-5":{"draws":8,"losses":14,"wins":26},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":11,"losses":0,"wins":61},"deepseek/deepseek-v4-pro":{"draws":8,"losses":4,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":3,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":8,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":9,"wins":34},"elorian/glimpse":{"draws":3,"losses":5,"wins":18},"fireworks/ember-1":{"draws":6,"losses":6,"wins":36},"gemini-3.1-pro-preview":{"draws":4,"losses":6,"wins":38},"gemini-4-argon":{"draws":9,"losses":21,"wins":18},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":8,"losses":10,"wins":42},"google/gemini-3.5-flash-lite":{"draws":12,"losses":2,"wins":70},"google/gemini-3.6-flash":{"draws":13,"losses":6,"wins":73},"google/gemini-3.8-flash":{"draws":6,"losses":10,"wins":32},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":26},"gpt-4.1":{"draws":1,"losses":1,"wins":14},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":2,"wins":34},"gpt-5.4":{"draws":2,"losses":6,"wins":38},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":24},"gpt-5.4-nano":{"draws":3,"losses":0,"wins":45},"gpt-5.5":{"draws":7,"losses":8,"wins":29},"gpt-5.6-luna":{"draws":10,"losses":4,"wins":34},"gpt-5.6-sol":{"draws":8,"losses":11,"wins":29},"gpt-5.6-terra":{"draws":6,"losses":5,"wins":35},"gpt-6-astra":{"draws":8,"losses":29,"wins":11},"gpt-6-luna":{"draws":10,"losses":4,"wins":34},"gpt-6-sol":{"draws":7,"losses":20,"wins":21},"gpt-6.1-sol":{"draws":6,"losses":26,"wins":16},"gpt-6.1-terra":{"draws":8,"losses":15,"wins":9},"gpt-6.1-terra-pro":{"draws":7,"losses":21,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":1,"wins":30},"inception/mercury-3":{"draws":5,"losses":4,"wins":23},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":31},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":42},"meta/muse-glimmer-30b":{"draws":6,"losses":1,"wins":35},"meta/muse-spark-1.2":{"draws":3,"losses":4,"wins":39},"meta/muse-spark-1.3":{"draws":7,"losses":3,"wins":38},"meta/muse-spark-open":{"draws":4,"losses":7,"wins":35},"meta/muse-wonder":{"draws":8,"losses":13,"wins":27},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"minimax/minimax-m3.1-flash":{"draws":7,"losses":1,"wins":34},"mistralai/mistral-large-4-0":{"draws":6,"losses":2,"wins":22},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":8,"wins":32},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":16,"wins":23},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":18},"o3":{"draws":6,"losses":1,"wins":59},"openai/gpt-oss-120b":{"draws":7,"losses":0,"wins":35},"poolside/laguna-s-2.1":{"draws":7,"losses":1,"wins":38},"qwen/qwen3.7-max":{"draws":5,"losses":0,"wins":23},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":6,"wins":33},"qwen/qwen3.8-27b":{"draws":7,"losses":2,"wins":25},"qwen/qwen3.8-flash":{"draws":6,"losses":5,"wins":21},"qwen/qwen3.8-max":{"draws":9,"losses":4,"wins":35},"qwen/qwen3.8-max-0902":{"draws":5,"losses":4,"wins":39},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":1,"wins":37},"stealth/ox-alpha":{"draws":31,"losses":20,"wins":107},"stealth/space-bunny-alpha":{"draws":5,"losses":2,"wins":31},"stepfun/step-3.7-flash":{"draws":6,"losses":1,"wins":27},"stepfun/step-5-preview":{"draws":3,"losses":2,"wins":9},"tencent/hy3-preview":{"draws":7,"losses":1,"wins":18},"tencent/hy4-preview":{"draws":6,"losses":4,"wins":36},"thinkingmachines/inkling":{"draws":10,"losses":4,"wins":50},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":43},"unbiased/pareto-26.10":{"draws":3,"losses":11,"wins":2},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":8,"losses":9,"wins":31},"x-ai/grok-4.6":{"draws":8,"losses":2,"wins":38},"x-ai/grok-4.7":{"draws":4,"losses":18,"wins":20},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":12,"losses":3,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":2,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":12,"wins":16},"z-ai/glm-5.2":{"draws":10,"losses":7,"wins":79},"z-ai/glm-5.3":{"draws":10,"losses":10,"wins":26},"z-ai/glm-5.3-flash":{"draws":11,"losses":4,"wins":33},"z-ai/glm-5.3-flashx":{"draws":5,"losses":7,"wins":36}},"gpt-6.1-terra-pro":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":3,"wins":35},"claude-fable-5":{"draws":3,"losses":13,"wins":32},"claude-fable-5-1":{"draws":9,"losses":24,"wins":21},"claude-haiku-5-5":{"draws":5,"losses":5,"wins":36},"claude-opus-4-5":{"draws":7,"losses":6,"wins":65},"claude-opus-4-8":{"draws":6,"losses":6,"wins":32},"claude-opus-5":{"draws":9,"losses":37,"wins":36},"claude-opus-5-5":{"draws":4,"losses":33,"wins":15},"claude-sonnet-5":{"draws":6,"losses":4,"wins":38},"claude-sonnet-5-5":{"draws":6,"losses":14,"wins":28},"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":5,"losses":6,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":6,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":7,"wins":33},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":10,"wins":32},"elorian/glimpse":{"draws":5,"losses":3,"wins":18},"fireworks/ember-1":{"draws":7,"losses":5,"wins":36},"gemini-3.1-pro-preview":{"draws":4,"losses":8,"wins":36},"gemini-4-argon":{"draws":11,"losses":18,"wins":19},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":52},"google/gemini-3.5-flash-lite":{"draws":5,"losses":5,"wins":74},"google/gemini-3.6-flash":{"draws":7,"losses":14,"wins":71},"google/gemini-3.8-flash":{"draws":7,"losses":6,"wins":35},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":26},"gpt-4.1":{"draws":0,"losses":2,"wins":14},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":3,"losses":3,"wins":36},"gpt-5.4":{"draws":5,"losses":9,"wins":32},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":26},"gpt-5.4-nano":{"draws":1,"losses":4,"wins":43},"gpt-5.5":{"draws":6,"losses":6,"wins":32},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":40},"gpt-5.6-sol":{"draws":7,"losses":11,"wins":30},"gpt-5.6-terra":{"draws":6,"losses":7,"wins":33},"gpt-6-astra":{"draws":8,"losses":29,"wins":11},"gpt-6-luna":{"draws":5,"losses":3,"wins":40},"gpt-6-sol":{"draws":6,"losses":10,"wins":32},"gpt-6.1-sol":{"draws":5,"losses":30,"wins":13},"gpt-6.1-terra":{"draws":9,"losses":22,"wins":17},"gpt-6.1-terra-pro":{"draws":3,"losses":20,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":28},"inception/mercury-3":{"draws":7,"losses":1,"wins":26},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":5,"wins":42},"meta/muse-glimmer-30b":{"draws":4,"losses":2,"wins":36},"meta/muse-spark-1.2":{"draws":5,"losses":4,"wins":37},"meta/muse-spark-1.3":{"draws":5,"losses":6,"wins":37},"meta/muse-spark-open":{"draws":2,"losses":8,"wins":36},"meta/muse-wonder":{"draws":7,"losses":10,"wins":31},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":22},"minimax/minimax-m3.1-flash":{"draws":8,"losses":1,"wins":33},"mistralai/mistral-large-4-0":{"draws":3,"losses":5,"wins":22},"mistralai/mistral-medium-3-5":{"draws":5,"losses":0,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":6,"wins":35},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":19,"wins":23},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":21},"o3":{"draws":0,"losses":8,"wins":58},"openai/gpt-oss-120b":{"draws":2,"losses":3,"wins":37},"poolside/laguna-s-2.1":{"draws":5,"losses":8,"wins":33},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":20},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":7,"wins":38},"qwen/qwen3.8-27b":{"draws":5,"losses":4,"wins":25},"qwen/qwen3.8-flash":{"draws":3,"losses":3,"wins":26},"qwen/qwen3.8-max":{"draws":3,"losses":7,"wins":38},"qwen/qwen3.8-max-0902":{"draws":9,"losses":8,"wins":31},"recursive/flint-v1.0":{"draws":0,"losses":2,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":4,"wins":39},"stealth/ox-alpha":{"draws":21,"losses":16,"wins":121},"stealth/space-bunny-alpha":{"draws":4,"losses":3,"wins":31},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":4,"wins":21},"tencent/hy4-preview":{"draws":6,"losses":8,"wins":32},"thinkingmachines/inkling":{"draws":13,"losses":1,"wins":50},"thinkingmachines/inkling-small":{"draws":4,"losses":3,"wins":41},"unbiased/pareto-26.10":{"draws":2,"losses":10,"wins":4},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":35},"x-ai/grok-4.6":{"draws":12,"losses":4,"wins":32},"x-ai/grok-4.7":{"draws":5,"losses":13,"wins":24},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":8,"losses":3,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":3,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":4,"wins":24},"z-ai/glm-5.2":{"draws":13,"losses":9,"wins":74},"z-ai/glm-5.3":{"draws":7,"losses":7,"wins":32},"z-ai/glm-5.3-flash":{"draws":6,"losses":8,"wins":34},"z-ai/glm-5.3-flashx":{"draws":2,"losses":7,"wins":39}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":3,"losses":3,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":1,"wins":0},"elorian/glimpse":{"draws":3,"losses":1,"wins":0},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"gemini-4-argon":{"draws":1,"losses":5,"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},"gpt-6.1-terra":{"draws":1,"losses":4,"wins":1},"gpt-6.1-terra-pro":{"draws":1,"losses":5,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":1,"wins":0},"inception/mercury-3":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"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-spark-open":{"draws":4,"losses":2,"wins":0},"meta/muse-wonder":{"draws":4,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3.1-flash":{"draws":5,"losses":0,"wins":1},"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":1,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":0},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":5,"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},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"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},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":0},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":3,"wins":0},"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},"stepfun/step-5-preview":{"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":7,"losses":1,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10":{"draws":1,"losses":1,"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":11,"losses":13,"wins":8},"claude-fable-5":{"draws":8,"losses":28,"wins":0},"claude-fable-5-1":{"draws":3,"losses":37,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":25,"wins":1},"claude-opus-4-5":{"draws":19,"losses":40,"wins":1},"claude-opus-4-8":{"draws":9,"losses":26,"wins":1},"claude-opus-5":{"draws":6,"losses":49,"wins":3},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":11,"losses":22,"wins":3},"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":17,"losses":28,"wins":9},"deepseek/deepseek-v4-pro":{"draws":11,"losses":20,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":16,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":21,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":26,"wins":2},"elorian/glimpse":{"draws":4,"losses":13,"wins":1},"fireworks/ember-1":{"draws":12,"losses":24,"wins":0},"gemini-3.1-pro-preview":{"draws":14,"losses":18,"wins":4},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":11,"wins":11},"google/gemini-3.5-flash":{"draws":14,"losses":25,"wins":7},"google/gemini-3.5-flash-lite":{"draws":18,"losses":33,"wins":13},"google/gemini-3.6-flash":{"draws":20,"losses":44,"wins":4},"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":4,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":18,"wins":2},"gpt-5.4":{"draws":12,"losses":19,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":10,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":25,"wins":4},"gpt-5.5":{"draws":12,"losses":18,"wins":2},"gpt-5.6-luna":{"draws":12,"losses":17,"wins":7},"gpt-5.6-sol":{"draws":5,"losses":31,"wins":0},"gpt-5.6-terra":{"draws":11,"losses":21,"wins":2},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":12,"losses":21,"wins":3},"gpt-6-sol":{"draws":5,"losses":30,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"gpt-6.1-terra":{"draws":4,"losses":32,"wins":0},"gpt-6.1-terra-pro":{"draws":5,"losses":31,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":4,"wins":6},"inception/mercury-3":{"draws":8,"losses":14,"wins":2},"inclusionai/ling-3.0-flash":{"draws":14,"losses":6,"wins":4},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":9,"losses":18,"wins":15},"meta/muse-glimmer-30b":{"draws":10,"losses":13,"wins":7},"meta/muse-spark-1.2":{"draws":11,"losses":20,"wins":3},"meta/muse-spark-1.3":{"draws":8,"losses":26,"wins":2},"meta/muse-spark-open":{"draws":11,"losses":23,"wins":2},"meta/muse-wonder":{"draws":10,"losses":25,"wins":1},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":3},"minimax/minimax-m3.1-flash":{"draws":9,"losses":19,"wins":2},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":1},"mistralai/mistral-medium-3-5":{"draws":10,"losses":9,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":18,"wins":0},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":32,"wins":0},"nex-agi/nex-n2-pro":{"draws":5,"losses":9,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":12,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":10,"wins":2},"o3":{"draws":12,"losses":37,"wins":3},"openai/gpt-oss-120b":{"draws":9,"losses":16,"wins":7},"poolside/laguna-s-2.1":{"draws":14,"losses":11,"wins":7},"qwen/qwen3.7-max":{"draws":6,"losses":10,"wins":6},"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":11,"losses":24,"wins":1},"qwen/qwen3.8-max-0902":{"draws":12,"losses":20,"wins":4},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":21,"wins":2},"stealth/ox-alpha":{"draws":29,"losses":70,"wins":3},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":5},"stepfun/step-3.7-flash":{"draws":6,"losses":16,"wins":2},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":8,"losses":20,"wins":6},"thinkingmachines/inkling":{"draws":14,"losses":21,"wins":9},"thinkingmachines/inkling-small":{"draws":13,"losses":14,"wins":9},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":5,"losses":29,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":22,"losses":29,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":18,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":0},"z-ai/glm-5.2":{"draws":21,"losses":44,"wins":7},"z-ai/glm-5.3":{"draws":10,"losses":24,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":26,"wins":3},"z-ai/glm-5.3-flashx":{"draws":7,"losses":27,"wins":2}},"inception/mercury-3":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":5,"wins":8},"claude-fable-5":{"draws":4,"losses":10,"wins":6},"claude-fable-5-1":{"draws":0,"losses":19,"wins":1},"claude-haiku-5-5":{"draws":3,"losses":7,"wins":8},"claude-opus-4-5":{"draws":9,"losses":9,"wins":12},"claude-opus-4-8":{"draws":4,"losses":8,"wins":6},"claude-opus-5":{"draws":5,"losses":24,"wins":3},"claude-opus-5-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":5,"losses":5,"wins":8},"claude-sonnet-5-5":{"draws":3,"losses":11,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":22},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":4,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":8,"wins":5},"elorian/glimpse":{"draws":2,"losses":3,"wins":5},"fireworks/ember-1":{"draws":5,"losses":5,"wins":8},"gemini-3.1-pro-preview":{"draws":6,"losses":4,"wins":10},"gemini-4-argon":{"draws":1,"losses":11,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":9},"google/gemini-3.5-flash":{"draws":6,"losses":3,"wins":13},"google/gemini-3.5-flash-lite":{"draws":8,"losses":3,"wins":17},"google/gemini-3.6-flash":{"draws":4,"losses":11,"wins":17},"google/gemini-3.8-flash":{"draws":3,"losses":6,"wins":9},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":7},"gpt-4.1":{"draws":0,"losses":1,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":3,"wins":10},"gpt-5.4":{"draws":2,"losses":5,"wins":9},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":5,"wins":10},"gpt-5.5":{"draws":3,"losses":7,"wins":6},"gpt-5.6-luna":{"draws":6,"losses":1,"wins":11},"gpt-5.6-sol":{"draws":3,"losses":10,"wins":5},"gpt-5.6-terra":{"draws":5,"losses":2,"wins":13},"gpt-6-astra":{"draws":2,"losses":16,"wins":0},"gpt-6-luna":{"draws":5,"losses":5,"wins":8},"gpt-6-sol":{"draws":3,"losses":12,"wins":3},"gpt-6.1-sol":{"draws":0,"losses":18,"wins":0},"gpt-6.1-terra":{"draws":1,"losses":16,"wins":1},"gpt-6.1-terra-pro":{"draws":1,"losses":19,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":8},"inception/mercury-3":{"draws":3,"losses":1,"wins":6},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":10},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":14},"meta/muse-glimmer-30b":{"draws":4,"losses":1,"wins":11},"meta/muse-spark-1.2":{"draws":6,"losses":6,"wins":8},"meta/muse-spark-1.3":{"draws":4,"losses":7,"wins":7},"meta/muse-spark-open":{"draws":3,"losses":9,"wins":6},"meta/muse-wonder":{"draws":6,"losses":8,"wins":4},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":9},"minimax/minimax-m3.1-flash":{"draws":2,"losses":1,"wins":9},"mistralai/mistral-large-4-0":{"draws":3,"losses":4,"wins":5},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":5,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":12,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":5},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":8},"o3":{"draws":1,"losses":9,"wins":18},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":11},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":12},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":8},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":6,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":2,"wins":4},"qwen/qwen3.8-flash":{"draws":3,"losses":2,"wins":7},"qwen/qwen3.8-max":{"draws":4,"losses":9,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":2,"wins":11},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":4,"wins":10},"stealth/ox-alpha":{"draws":11,"losses":16,"wins":25},"stealth/space-bunny-alpha":{"draws":4,"losses":0,"wins":10},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":8},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":6},"tencent/hy4-preview":{"draws":1,"losses":7,"wins":8},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":16},"thinkingmachines/inkling-small":{"draws":6,"losses":3,"wins":9},"unbiased/pareto-26.10":{"draws":0,"losses":5,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":7,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":6,"losses":8,"wins":4},"x-ai/grok-4.6":{"draws":4,"losses":12,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":13,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":7,"losses":3,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":6,"wins":5},"z-ai/glm-5.2":{"draws":12,"losses":3,"wins":21},"z-ai/glm-5.3":{"draws":5,"losses":7,"wins":6},"z-ai/glm-5.3-flash":{"draws":4,"losses":5,"wins":11},"z-ai/glm-5.3-flashx":{"draws":3,"losses":2,"wins":13}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":12,"wins":6},"claude-fable-5":{"draws":5,"losses":30,"wins":1},"claude-fable-5-1":{"draws":3,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":27,"wins":1},"claude-opus-4-5":{"draws":24,"losses":25,"wins":11},"claude-opus-4-8":{"draws":10,"losses":26,"wins":0},"claude-opus-5":{"draws":9,"losses":44,"wins":1},"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":11,"losses":21,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":28,"wins":1},"elorian/glimpse":{"draws":7,"losses":9,"wins":4},"fireworks/ember-1":{"draws":13,"losses":19,"wins":4},"gemini-3.1-pro-preview":{"draws":11,"losses":20,"wins":5},"gemini-4-argon":{"draws":1,"losses":33,"wins":2},"google/gemini-3.1-flash-lite":{"draws":5,"losses":8,"wins":15},"google/gemini-3.5-flash":{"draws":10,"losses":29,"wins":7},"google/gemini-3.5-flash-lite":{"draws":17,"losses":30,"wins":15},"google/gemini-3.6-flash":{"draws":23,"losses":40,"wins":7},"google/gemini-3.8-flash":{"draws":8,"losses":27,"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":8,"losses":20,"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":10,"losses":22,"wins":4},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":8,"losses":22,"wins":6},"gpt-6-sol":{"draws":5,"losses":29,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"gpt-6.1-terra":{"draws":1,"losses":35,"wins":0},"gpt-6.1-terra-pro":{"draws":4,"losses":32,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":12},"inception/mercury-3":{"draws":10,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":4,"losses":7,"wins":5},"inclusionai/ling-3.1-flash":{"draws":3,"losses":2,"wins":3},"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":12,"losses":15,"wins":7},"meta/muse-spark-1.3":{"draws":1,"losses":30,"wins":5},"meta/muse-spark-open":{"draws":7,"losses":26,"wins":3},"meta/muse-wonder":{"draws":7,"losses":29,"wins":0},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":7},"minimax/minimax-m3.1-flash":{"draws":10,"losses":18,"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-k3":{"draws":8,"losses":20,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":31,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":5},"o3":{"draws":5,"losses":36,"wins":11},"openai/gpt-oss-120b":{"draws":8,"losses":16,"wins":6},"poolside/laguna-s-2.1":{"draws":7,"losses":15,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":15,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":17,"wins":3},"qwen/qwen3.8-27b":{"draws":4,"losses":19,"wins":5},"qwen/qwen3.8-flash":{"draws":7,"losses":13,"wins":4},"qwen/qwen3.8-max":{"draws":13,"losses":15,"wins":8},"qwen/qwen3.8-max-0902":{"draws":10,"losses":20,"wins":6},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":9,"wins":12},"stealth/ox-alpha":{"draws":22,"losses":64,"wins":16},"stealth/space-bunny-alpha":{"draws":10,"losses":15,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":16,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":9,"wins":1},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":4},"tencent/hy4-preview":{"draws":8,"losses":22,"wins":4},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":10},"thinkingmachines/inkling-small":{"draws":13,"losses":14,"wins":9},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"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":9,"wins":3},"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":10,"losses":23,"wins":3},"z-ai/glm-5.3-flashx":{"draws":8,"losses":26,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":28,"wins":22},"claude-fable-5":{"draws":6,"losses":55,"wins":11},"claude-fable-5-1":{"draws":3,"losses":75,"wins":4},"claude-haiku-5-5":{"draws":14,"losses":45,"wins":11},"claude-opus-4-5":{"draws":25,"losses":69,"wins":24},"claude-opus-4-8":{"draws":14,"losses":41,"wins":13},"claude-opus-5":{"draws":9,"losses":95,"wins":12},"claude-opus-5-5":{"draws":6,"losses":70,"wins":4},"claude-sonnet-5":{"draws":15,"losses":42,"wins":15},"claude-sonnet-5-5":{"draws":8,"losses":47,"wins":17},"cohere/north-mini-code":{"draws":6,"losses":8,"wins":20},"deepseek/deepseek-v4-flash":{"draws":28,"losses":42,"wins":36},"deepseek/deepseek-v4-pro":{"draws":13,"losses":40,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":33,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":46,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":48,"wins":13},"elorian/glimpse":{"draws":11,"losses":17,"wins":10},"fireworks/ember-1":{"draws":13,"losses":38,"wins":21},"gemini-3.1-pro-preview":{"draws":13,"losses":31,"wins":28},"gemini-4-argon":{"draws":5,"losses":61,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":15,"wins":33},"google/gemini-3.5-flash":{"draws":17,"losses":54,"wins":21},"google/gemini-3.5-flash-lite":{"draws":31,"losses":38,"wins":61},"google/gemini-3.6-flash":{"draws":27,"losses":84,"wins":27},"google/gemini-3.8-flash":{"draws":14,"losses":46,"wins":12},"google/gemma-4-31b-it":{"draws":13,"losses":15,"wins":18},"gpt-4.1":{"draws":6,"losses":11,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":15,"losses":32,"wins":15},"gpt-5.4":{"draws":13,"losses":42,"wins":15},"gpt-5.4-mini":{"draws":12,"losses":18,"wins":18},"gpt-5.4-nano":{"draws":11,"losses":39,"wins":22},"gpt-5.5":{"draws":11,"losses":41,"wins":14},"gpt-5.6-luna":{"draws":16,"losses":30,"wins":26},"gpt-5.6-sol":{"draws":10,"losses":54,"wins":8},"gpt-5.6-terra":{"draws":18,"losses":32,"wins":18},"gpt-6-astra":{"draws":2,"losses":67,"wins":3},"gpt-6-luna":{"draws":13,"losses":41,"wins":18},"gpt-6-sol":{"draws":4,"losses":63,"wins":5},"gpt-6.1-sol":{"draws":5,"losses":62,"wins":5},"gpt-6.1-terra":{"draws":6,"losses":62,"wins":4},"gpt-6.1-terra-pro":{"draws":4,"losses":66,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":12,"wins":26},"inception/mercury-3":{"draws":10,"losses":22,"wins":14},"inclusionai/ling-3.0-flash":{"draws":22,"losses":7,"wins":19},"inclusionai/ling-3.1-flash":{"draws":4,"losses":4,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":18,"wins":30},"meta/muse-glimmer-30b":{"draws":17,"losses":17,"wins":28},"meta/muse-spark-1.2":{"draws":13,"losses":39,"wins":16},"meta/muse-spark-1.3":{"draws":12,"losses":46,"wins":14},"meta/muse-spark-open":{"draws":14,"losses":49,"wins":9},"meta/muse-wonder":{"draws":11,"losses":51,"wins":10},"minimax/minimax-m3":{"draws":7,"losses":10,"wins":21},"minimax/minimax-m3.1-flash":{"draws":17,"losses":30,"wins":15},"mistralai/mistral-large-4-0":{"draws":16,"losses":19,"wins":9},"mistralai/mistral-medium-3-5":{"draws":14,"losses":8,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":40,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":63,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":15,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":7,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":14,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":13,"wins":11},"o3":{"draws":13,"losses":58,"wins":35},"openai/gpt-oss-120b":{"draws":15,"losses":13,"wins":36},"poolside/laguna-s-2.1":{"draws":16,"losses":19,"wins":31},"qwen/qwen3.7-max":{"draws":8,"losses":26,"wins":8},"qwen/qwen3.7-plus":{"draws":8,"losses":13,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":42,"wins":13},"qwen/qwen3.8-27b":{"draws":8,"losses":32,"wins":8},"qwen/qwen3.8-flash":{"draws":12,"losses":24,"wins":12},"qwen/qwen3.8-max":{"draws":18,"losses":46,"wins":8},"qwen/qwen3.8-max-0902":{"draws":9,"losses":52,"wins":11},"recursive/flint-v1.0":{"draws":6,"losses":4,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":16,"losses":36,"wins":16},"stealth/ox-alpha":{"draws":48,"losses":142,"wins":38},"stealth/space-bunny-alpha":{"draws":15,"losses":24,"wins":21},"stepfun/step-3.7-flash":{"draws":10,"losses":27,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":14,"wins":6},"tencent/hy3-preview":{"draws":13,"losses":12,"wins":13},"tencent/hy4-preview":{"draws":20,"losses":39,"wins":11},"thinkingmachines/inkling":{"draws":24,"losses":35,"wins":33},"thinkingmachines/inkling-small":{"draws":16,"losses":20,"wins":36},"unbiased/pareto-26.10":{"draws":1,"losses":23,"wins":0},"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":12,"losses":45,"wins":15},"x-ai/grok-4.7":{"draws":3,"losses":57,"wins":2},"x-ai/grok-build-0.1":{"draws":8,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":34,"losses":36,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":10,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":24,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":37,"wins":6},"z-ai/glm-5.2":{"draws":34,"losses":73,"wins":37},"z-ai/glm-5.3":{"draws":11,"losses":53,"wins":8},"z-ai/glm-5.3-flash":{"draws":11,"losses":46,"wins":15},"z-ai/glm-5.3-flashx":{"draws":13,"losses":49,"wins":10}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":18,"wins":13},"claude-fable-5":{"draws":8,"losses":38,"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":25,"losses":43,"wins":10},"claude-opus-4-8":{"draws":9,"losses":29,"wins":6},"claude-opus-5":{"draws":3,"losses":71,"wins":8},"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":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":28,"losses":32,"wins":12},"deepseek/deepseek-v4-pro":{"draws":12,"losses":23,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":28,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":31,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":33,"wins":5},"elorian/glimpse":{"draws":7,"losses":13,"wins":6},"fireworks/ember-1":{"draws":13,"losses":29,"wins":6},"gemini-3.1-pro-preview":{"draws":20,"losses":23,"wins":5},"gemini-4-argon":{"draws":5,"losses":42,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":11,"wins":11},"google/gemini-3.5-flash":{"draws":16,"losses":35,"wins":9},"google/gemini-3.5-flash-lite":{"draws":32,"losses":34,"wins":18},"google/gemini-3.6-flash":{"draws":24,"losses":59,"wins":9},"google/gemini-3.8-flash":{"draws":9,"losses":34,"wins":5},"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":10,"losses":22,"wins":10},"gpt-5.4":{"draws":8,"losses":30,"wins":8},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":8,"losses":23,"wins":17},"gpt-5.5":{"draws":10,"losses":24,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":24,"wins":9},"gpt-5.6-sol":{"draws":8,"losses":38,"wins":2},"gpt-5.6-terra":{"draws":12,"losses":27,"wins":7},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":14,"losses":27,"wins":7},"gpt-6-sol":{"draws":10,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"gpt-6.1-terra":{"draws":4,"losses":44,"wins":0},"gpt-6.1-terra-pro":{"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":10,"wins":9},"inception/mercury-3":{"draws":9,"losses":17,"wins":6},"inclusionai/ling-3.0-flash":{"draws":20,"losses":6,"wins":8},"inclusionai/ling-3.1-flash":{"draws":1,"losses":5,"wins":6},"meituan/longcat-2.0":{"draws":16,"losses":19,"wins":17},"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-spark-open":{"draws":13,"losses":33,"wins":2},"meta/muse-wonder":{"draws":8,"losses":34,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":11,"wins":8},"minimax/minimax-m3.1-flash":{"draws":10,"losses":24,"wins":8},"mistralai/mistral-large-4-0":{"draws":9,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":11,"losses":6,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":29,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":40,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":8,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":17,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":11,"wins":3},"o3":{"draws":14,"losses":45,"wins":7},"openai/gpt-oss-120b":{"draws":17,"losses":17,"wins":8},"poolside/laguna-s-2.1":{"draws":15,"losses":17,"wins":14},"qwen/qwen3.7-max":{"draws":8,"losses":15,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":8,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":34,"wins":2},"qwen/qwen3.8-27b":{"draws":11,"losses":19,"wins":4},"qwen/qwen3.8-flash":{"draws":8,"losses":15,"wins":9},"qwen/qwen3.8-max":{"draws":11,"losses":29,"wins":8},"qwen/qwen3.8-max-0902":{"draws":17,"losses":28,"wins":3},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":27,"wins":4},"stealth/ox-alpha":{"draws":34,"losses":108,"wins":16},"stealth/space-bunny-alpha":{"draws":13,"losses":17,"wins":8},"stepfun/step-3.7-flash":{"draws":8,"losses":16,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":8,"wins":4},"tencent/hy3-preview":{"draws":9,"losses":9,"wins":8},"tencent/hy4-preview":{"draws":8,"losses":33,"wins":5},"thinkingmachines/inkling":{"draws":21,"losses":24,"wins":19},"thinkingmachines/inkling-small":{"draws":15,"losses":14,"wins":19},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":13,"losses":30,"wins":5},"x-ai/grok-4.7":{"draws":1,"losses":38,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":5},"xiaomi/mimo-v2.5":{"draws":27,"losses":27,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":12,"wins":8},"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":33,"losses":45,"wins":18},"z-ai/glm-5.3":{"draws":8,"losses":35,"wins":3},"z-ai/glm-5.3-flash":{"draws":11,"losses":30,"wins":7},"z-ai/glm-5.3-flashx":{"draws":15,"losses":29,"wins":4}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":9,"wins":21},"claude-fable-5":{"draws":6,"losses":25,"wins":11},"claude-fable-5-1":{"draws":2,"losses":39,"wins":7},"claude-haiku-5-5":{"draws":8,"losses":16,"wins":16},"claude-opus-4-5":{"draws":20,"losses":10,"wins":38},"claude-opus-4-8":{"draws":10,"losses":10,"wins":18},"claude-opus-5":{"draws":11,"losses":53,"wins":16},"claude-opus-5-5":{"draws":5,"losses":37,"wins":4},"claude-sonnet-5":{"draws":11,"losses":10,"wins":21},"claude-sonnet-5-5":{"draws":14,"losses":16,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":16,"losses":4,"wins":42},"deepseek/deepseek-v4-pro":{"draws":6,"losses":15,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":8,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":11,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":19,"wins":16},"elorian/glimpse":{"draws":5,"losses":7,"wins":12},"fireworks/ember-1":{"draws":11,"losses":14,"wins":17},"gemini-3.1-pro-preview":{"draws":10,"losses":12,"wins":20},"gemini-4-argon":{"draws":4,"losses":32,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":19},"google/gemini-3.5-flash":{"draws":10,"losses":11,"wins":31},"google/gemini-3.5-flash-lite":{"draws":21,"losses":8,"wins":43},"google/gemini-3.6-flash":{"draws":13,"losses":24,"wins":43},"google/gemini-3.8-flash":{"draws":6,"losses":13,"wins":23},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":12},"gpt-4.1":{"draws":4,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":10,"losses":8,"wins":20},"gpt-5.4":{"draws":8,"losses":16,"wins":16},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":16},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":24},"gpt-5.5":{"draws":7,"losses":16,"wins":17},"gpt-5.6-luna":{"draws":14,"losses":5,"wins":23},"gpt-5.6-sol":{"draws":4,"losses":24,"wins":14},"gpt-5.6-terra":{"draws":13,"losses":9,"wins":18},"gpt-6-astra":{"draws":4,"losses":37,"wins":1},"gpt-6-luna":{"draws":12,"losses":7,"wins":23},"gpt-6-sol":{"draws":4,"losses":28,"wins":10},"gpt-6.1-sol":{"draws":6,"losses":29,"wins":7},"gpt-6.1-terra":{"draws":5,"losses":32,"wins":5},"gpt-6.1-terra-pro":{"draws":3,"losses":33,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":14},"inception/mercury-3":{"draws":9,"losses":5,"wins":14},"inclusionai/ling-3.0-flash":{"draws":9,"losses":4,"wins":15},"inclusionai/ling-3.1-flash":{"draws":4,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":6,"wins":29},"meta/muse-glimmer-30b":{"draws":11,"losses":2,"wins":27},"meta/muse-spark-1.2":{"draws":8,"losses":8,"wins":12},"meta/muse-spark-1.3":{"draws":9,"losses":12,"wins":21},"meta/muse-spark-open":{"draws":12,"losses":14,"wins":16},"meta/muse-wonder":{"draws":8,"losses":18,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":19},"minimax/minimax-m3.1-flash":{"draws":8,"losses":8,"wins":20},"mistralai/mistral-large-4-0":{"draws":7,"losses":5,"wins":16},"mistralai/mistral-medium-3-5":{"draws":6,"losses":5,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":14,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":32,"wins":7},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":4,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":3,"wins":11},"o3":{"draws":9,"losses":14,"wins":31},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":26},"poolside/laguna-s-2.1":{"draws":11,"losses":7,"wins":24},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":13,"wins":17},"qwen/qwen3.8-27b":{"draws":6,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":14},"qwen/qwen3.8-max":{"draws":11,"losses":14,"wins":17},"qwen/qwen3.8-max-0902":{"draws":13,"losses":13,"wins":16},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":11,"wins":20},"stealth/ox-alpha":{"draws":38,"losses":59,"wins":45},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":19},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":9,"losses":16,"wins":15},"thinkingmachines/inkling":{"draws":14,"losses":6,"wins":38},"thinkingmachines/inkling-small":{"draws":13,"losses":4,"wins":25},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":10,"losses":19,"wins":13},"x-ai/grok-4.6":{"draws":9,"losses":22,"wins":11},"x-ai/grok-4.7":{"draws":1,"losses":23,"wins":14},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":13,"losses":5,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":20,"wins":7},"z-ai/glm-5.2":{"draws":15,"losses":17,"wins":52},"z-ai/glm-5.3":{"draws":7,"losses":21,"wins":12},"z-ai/glm-5.3-flash":{"draws":8,"losses":14,"wins":20},"z-ai/glm-5.3-flashx":{"draws":9,"losses":16,"wins":17}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":7,"wins":30},"claude-fable-5":{"draws":7,"losses":21,"wins":20},"claude-fable-5-1":{"draws":3,"losses":43,"wins":8},"claude-haiku-5-5":{"draws":5,"losses":18,"wins":23},"claude-opus-4-5":{"draws":12,"losses":13,"wins":53},"claude-opus-4-8":{"draws":5,"losses":17,"wins":22},"claude-opus-5":{"draws":8,"losses":50,"wins":24},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":11,"losses":8,"wins":29},"claude-sonnet-5-5":{"draws":6,"losses":18,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":11,"losses":4,"wins":57},"deepseek/deepseek-v4-pro":{"draws":4,"losses":7,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":9,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":17,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":16,"wins":27},"elorian/glimpse":{"draws":7,"losses":6,"wins":13},"fireworks/ember-1":{"draws":10,"losses":15,"wins":23},"gemini-3.1-pro-preview":{"draws":5,"losses":10,"wins":33},"gemini-4-argon":{"draws":8,"losses":33,"wins":7},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":8,"losses":8,"wins":44},"google/gemini-3.5-flash-lite":{"draws":13,"losses":9,"wins":62},"google/gemini-3.6-flash":{"draws":18,"losses":24,"wins":50},"google/gemini-3.8-flash":{"draws":10,"losses":14,"wins":24},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":19},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"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":4,"losses":8,"wins":36},"gpt-5.5":{"draws":9,"losses":16,"wins":19},"gpt-5.6-luna":{"draws":10,"losses":5,"wins":33},"gpt-5.6-sol":{"draws":9,"losses":19,"wins":20},"gpt-5.6-terra":{"draws":12,"losses":8,"wins":26},"gpt-6-astra":{"draws":6,"losses":37,"wins":5},"gpt-6-luna":{"draws":5,"losses":10,"wins":33},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":35,"wins":8},"gpt-6.1-terra":{"draws":6,"losses":39,"wins":3},"gpt-6.1-terra-pro":{"draws":7,"losses":34,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":3,"wins":23},"inception/mercury-3":{"draws":5,"losses":7,"wins":20},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":30},"inclusionai/ling-3.1-flash":{"draws":2,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":43},"meta/muse-glimmer-30b":{"draws":9,"losses":1,"wins":32},"meta/muse-spark-1.2":{"draws":10,"losses":16,"wins":20},"meta/muse-spark-1.3":{"draws":7,"losses":11,"wins":14},"meta/muse-spark-open":{"draws":8,"losses":12,"wins":28},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"minimax/minimax-m3.1-flash":{"draws":8,"losses":8,"wins":26},"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":1,"losses":1,"wins":6},"moonshotai/kimi-k3":{"draws":7,"losses":9,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":41,"wins":4},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":4,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":5,"wins":15},"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":1,"losses":7,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":18,"wins":22},"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},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":7,"wins":30},"stealth/ox-alpha":{"draws":29,"losses":47,"wins":82},"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":2,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":19},"tencent/hy4-preview":{"draws":7,"losses":12,"wins":27},"thinkingmachines/inkling":{"draws":8,"losses":4,"wins":52},"thinkingmachines/inkling-small":{"draws":8,"losses":4,"wins":36},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":18,"wins":20},"x-ai/grok-4.7":{"draws":2,"losses":28,"wins":12},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":13,"losses":1,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":18,"losses":15,"wins":63},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":17},"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-spark-open":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":10,"wins":22},"claude-fable-5":{"draws":11,"losses":26,"wins":11},"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":29,"losses":23,"wins":26},"claude-opus-4-8":{"draws":13,"losses":16,"wins":15},"claude-opus-5":{"draws":10,"losses":64,"wins":8},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":17,"losses":9,"wins":22},"claude-sonnet-5-5":{"draws":11,"losses":23,"wins":14},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":18,"losses":10,"wins":44},"deepseek/deepseek-v4-pro":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":11,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":19,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":25,"wins":13},"elorian/glimpse":{"draws":7,"losses":10,"wins":9},"fireworks/ember-1":{"draws":14,"losses":21,"wins":13},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":20},"gemini-4-argon":{"draws":6,"losses":37,"wins":5},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":11,"losses":14,"wins":35},"google/gemini-3.5-flash-lite":{"draws":20,"losses":11,"wins":53},"google/gemini-3.6-flash":{"draws":24,"losses":34,"wins":34},"google/gemini-3.8-flash":{"draws":11,"losses":22,"wins":15},"google/gemma-4-31b-it":{"draws":11,"losses":2,"wins":15},"gpt-4.1":{"draws":3,"losses":5,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":7,"wins":23},"gpt-5.4":{"draws":13,"losses":15,"wins":18},"gpt-5.4-mini":{"draws":10,"losses":3,"wins":19},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":32},"gpt-5.5":{"draws":10,"losses":19,"wins":15},"gpt-5.6-luna":{"draws":15,"losses":13,"wins":20},"gpt-5.6-sol":{"draws":9,"losses":29,"wins":10},"gpt-5.6-terra":{"draws":13,"losses":13,"wins":20},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":16,"losses":14,"wins":18},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":43,"wins":2},"gpt-6.1-terra":{"draws":7,"losses":39,"wins":2},"gpt-6.1-terra-pro":{"draws":4,"losses":40,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inception/mercury-3":{"draws":8,"losses":6,"wins":18},"inclusionai/ling-3.0-flash":{"draws":7,"losses":3,"wins":24},"inclusionai/ling-3.1-flash":{"draws":3,"losses":2,"wins":3},"meituan/longcat-2.0":{"draws":12,"losses":4,"wins":36},"meta/muse-glimmer-30b":{"draws":11,"losses":7,"wins":24},"meta/muse-spark-1.2":{"draws":12,"losses":16,"wins":18},"meta/muse-spark-1.3":{"draws":11,"losses":22,"wins":15},"meta/muse-spark-open":{"draws":6,"losses":16,"wins":8},"meta/muse-wonder":{"draws":8,"losses":26,"wins":14},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":17},"minimax/minimax-m3.1-flash":{"draws":8,"losses":10,"wins":24},"mistralai/mistral-large-4-0":{"draws":8,"losses":7,"wins":15},"mistralai/mistral-medium-3-5":{"draws":7,"losses":6,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":14,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":38,"wins":4},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":4,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":7,"wins":10},"o3":{"draws":10,"losses":15,"wins":41},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":26},"poolside/laguna-s-2.1":{"draws":11,"losses":11,"wins":24},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":16},"qwen/qwen3.7-plus":{"draws":9,"losses":1,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":19,"wins":17},"qwen/qwen3.8-27b":{"draws":10,"losses":12,"wins":12},"qwen/qwen3.8-flash":{"draws":6,"losses":12,"wins":14},"qwen/qwen3.8-max":{"draws":13,"losses":15,"wins":20},"qwen/qwen3.8-max-0902":{"draws":12,"losses":18,"wins":18},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":12,"wins":19},"stealth/ox-alpha":{"draws":40,"losses":61,"wins":57},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"wins":18},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":6},"tencent/hy3-preview":{"draws":6,"losses":8,"wins":12},"tencent/hy4-preview":{"draws":10,"losses":16,"wins":20},"thinkingmachines/inkling":{"draws":15,"losses":8,"wins":41},"thinkingmachines/inkling-small":{"draws":14,"losses":5,"wins":29},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":14,"losses":24,"wins":10},"x-ai/grok-4.6":{"draws":11,"losses":23,"wins":14},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":8},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":28,"losses":2,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":3,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":10,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":13,"wins":10},"z-ai/glm-5.2":{"draws":33,"losses":17,"wins":46},"z-ai/glm-5.3":{"draws":11,"losses":25,"wins":10},"z-ai/glm-5.3-flash":{"draws":12,"losses":19,"wins":17},"z-ai/glm-5.3-flashx":{"draws":12,"losses":20,"wins":16}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":5,"wins":28},"claude-fable-5":{"draws":10,"losses":16,"wins":22},"claude-fable-5-1":{"draws":3,"losses":44,"wins":7},"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":9,"losses":51,"wins":22},"claude-opus-5-5":{"draws":5,"losses":38,"wins":9},"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":8,"losses":12,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":23,"wins":19},"elorian/glimpse":{"draws":6,"losses":7,"wins":13},"fireworks/ember-1":{"draws":8,"losses":15,"wins":25},"gemini-3.1-pro-preview":{"draws":6,"losses":6,"wins":36},"gemini-4-argon":{"draws":7,"losses":34,"wins":7},"google/gemini-3.1-flash-lite":{"draws":3,"losses":3,"wins":26},"google/gemini-3.5-flash":{"draws":9,"losses":11,"wins":40},"google/gemini-3.5-flash-lite":{"draws":15,"losses":11,"wins":58},"google/gemini-3.6-flash":{"draws":15,"losses":27,"wins":50},"google/gemini-3.8-flash":{"draws":10,"losses":11,"wins":27},"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":6,"losses":9,"wins":33},"gpt-5.5":{"draws":10,"losses":15,"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},"gpt-6.1-terra":{"draws":12,"losses":31,"wins":5},"gpt-6.1-terra-pro":{"draws":2,"losses":37,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":24},"inception/mercury-3":{"draws":5,"losses":10,"wins":17},"inclusionai/ling-3.0-flash":{"draws":7,"losses":2,"wins":25},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"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":10,"losses":16,"wins":20},"meta/muse-spark-1.3":{"draws":9,"losses":15,"wins":24},"meta/muse-spark-open":{"draws":8,"losses":17,"wins":23},"meta/muse-wonder":{"draws":5,"losses":13,"wins":14},"minimax/minimax-m3":{"draws":3,"losses":5,"wins":18},"minimax/minimax-m3.1-flash":{"draws":9,"losses":9,"wins":24},"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":1,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":5,"losses":13,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":30,"wins":13},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":9,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":5,"wins":14},"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":6,"wins":35},"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},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":11,"wins":26},"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":2,"losses":2,"wins":8},"tencent/hy3-preview":{"draws":2,"losses":8,"wins":16},"tencent/hy4-preview":{"draws":5,"losses":19,"wins":22},"thinkingmachines/inkling":{"draws":10,"losses":12,"wins":42},"thinkingmachines/inkling-small":{"draws":11,"losses":6,"wins":31},"unbiased/pareto-26.10":{"draws":2,"losses":11,"wins":3},"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":3,"losses":5,"wins":14},"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":16,"wins":57},"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":12,"losses":20,"wins":6},"claude-fable-5":{"draws":9,"losses":32,"wins":1},"claude-fable-5-1":{"draws":2,"losses":44,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":31,"wins":5},"claude-opus-4-5":{"draws":20,"losses":47,"wins":3},"claude-opus-4-8":{"draws":11,"losses":28,"wins":3},"claude-opus-5":{"draws":9,"losses":58,"wins":3},"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":33,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":7},"deepseek/deepseek-v4-flash":{"draws":16,"losses":30,"wins":18},"deepseek/deepseek-v4-pro":{"draws":7,"losses":28,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":27,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":25,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":32,"wins":2},"elorian/glimpse":{"draws":6,"losses":12,"wins":4},"fireworks/ember-1":{"draws":9,"losses":30,"wins":3},"gemini-3.1-pro-preview":{"draws":9,"losses":25,"wins":8},"gemini-4-argon":{"draws":1,"losses":40,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":16,"wins":7},"google/gemini-3.5-flash":{"draws":13,"losses":32,"wins":9},"google/gemini-3.5-flash-lite":{"draws":18,"losses":38,"wins":18},"google/gemini-3.6-flash":{"draws":16,"losses":52,"wins":12},"google/gemini-3.8-flash":{"draws":10,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":12,"losses":7,"wins":7},"gpt-4.1":{"draws":4,"losses":9,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":6,"losses":24,"wins":6},"gpt-5.4":{"draws":10,"losses":27,"wins":3},"gpt-5.4-mini":{"draws":7,"losses":12,"wins":9},"gpt-5.4-nano":{"draws":8,"losses":28,"wins":10},"gpt-5.5":{"draws":12,"losses":22,"wins":4},"gpt-5.6-luna":{"draws":13,"losses":20,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":34,"wins":2},"gpt-5.6-terra":{"draws":10,"losses":27,"wins":3},"gpt-6-astra":{"draws":1,"losses":41,"wins":0},"gpt-6-luna":{"draws":13,"losses":23,"wins":6},"gpt-6-sol":{"draws":7,"losses":33,"wins":2},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":0},"gpt-6.1-terra":{"draws":3,"losses":39,"wins":0},"gpt-6.1-terra-pro":{"draws":0,"losses":42,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":10,"wins":8},"inception/mercury-3":{"draws":7,"losses":21,"wins":0},"inclusionai/ling-3.0-flash":{"draws":11,"losses":12,"wins":7},"inclusionai/ling-3.1-flash":{"draws":3,"losses":6,"wins":1},"meituan/longcat-2.0":{"draws":6,"losses":28,"wins":12},"meta/muse-glimmer-30b":{"draws":10,"losses":18,"wins":8},"meta/muse-spark-1.2":{"draws":8,"losses":28,"wins":4},"meta/muse-spark-1.3":{"draws":6,"losses":34,"wins":2},"meta/muse-spark-open":{"draws":11,"losses":29,"wins":2},"meta/muse-wonder":{"draws":8,"losses":30,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":2},"minimax/minimax-m3.1-flash":{"draws":10,"losses":23,"wins":3},"mistralai/mistral-large-4-0":{"draws":8,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":9,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":26,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":38,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":10,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":23,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":11,"wins":3},"o3":{"draws":7,"losses":43,"wins":12},"openai/gpt-oss-120b":{"draws":10,"losses":17,"wins":9},"poolside/laguna-s-2.1":{"draws":8,"losses":21,"wins":9},"qwen/qwen3.7-max":{"draws":7,"losses":14,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":13,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":29,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":21,"wins":3},"qwen/qwen3.8-flash":{"draws":6,"losses":15,"wins":7},"qwen/qwen3.8-max":{"draws":9,"losses":27,"wins":6},"qwen/qwen3.8-max-0902":{"draws":10,"losses":26,"wins":6},"recursive/flint-v1.0":{"draws":4,"losses":7,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":26,"wins":5},"stealth/ox-alpha":{"draws":18,"losses":88,"wins":12},"stealth/space-bunny-alpha":{"draws":8,"losses":22,"wins":4},"stepfun/step-3.7-flash":{"draws":7,"losses":11,"wins":12},"stepfun/step-5-preview":{"draws":2,"losses":10,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":12,"wins":2},"tencent/hy4-preview":{"draws":9,"losses":29,"wins":2},"thinkingmachines/inkling":{"draws":12,"losses":32,"wins":10},"thinkingmachines/inkling-small":{"draws":13,"losses":14,"wins":15},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":9,"losses":31,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":32,"wins":5},"x-ai/grok-build-0.1":{"draws":3,"losses":8,"wins":3},"xiaomi/mimo-v2.5":{"draws":20,"losses":35,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":11,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":21,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":23,"wins":1},"z-ai/glm-5.2":{"draws":22,"losses":51,"wins":11},"z-ai/glm-5.3":{"draws":10,"losses":29,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":29,"wins":6},"z-ai/glm-5.3-flashx":{"draws":9,"losses":31,"wins":2}},"minimax/minimax-m3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":15,"wins":18},"claude-fable-5":{"draws":3,"losses":30,"wins":9},"claude-fable-5-1":{"draws":3,"losses":44,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":20,"wins":14},"claude-opus-4-5":{"draws":11,"losses":29,"wins":28},"claude-opus-4-8":{"draws":5,"losses":20,"wins":13},"claude-opus-5":{"draws":2,"losses":60,"wins":8},"claude-opus-5-5":{"draws":2,"losses":42,"wins":2},"claude-sonnet-5":{"draws":6,"losses":20,"wins":16},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":6,"losses":24,"wins":32},"deepseek/deepseek-v4-pro":{"draws":9,"losses":16,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":15,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":17,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":27,"wins":8},"elorian/glimpse":{"draws":3,"losses":15,"wins":6},"fireworks/ember-1":{"draws":10,"losses":16,"wins":16},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":17},"gemini-4-argon":{"draws":4,"losses":34,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":5,"losses":25,"wins":24},"google/gemini-3.5-flash-lite":{"draws":12,"losses":24,"wins":40},"google/gemini-3.6-flash":{"draws":15,"losses":36,"wins":31},"google/gemini-3.8-flash":{"draws":7,"losses":21,"wins":14},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":15},"gpt-4.1":{"draws":0,"losses":6,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":19,"wins":14},"gpt-5.4":{"draws":5,"losses":28,"wins":9},"gpt-5.4-mini":{"draws":6,"losses":3,"wins":19},"gpt-5.4-nano":{"draws":2,"losses":16,"wins":24},"gpt-5.5":{"draws":11,"losses":19,"wins":10},"gpt-5.6-luna":{"draws":6,"losses":13,"wins":23},"gpt-5.6-sol":{"draws":4,"losses":28,"wins":10},"gpt-5.6-terra":{"draws":9,"losses":18,"wins":13},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":8,"losses":16,"wins":18},"gpt-6-sol":{"draws":3,"losses":35,"wins":4},"gpt-6.1-sol":{"draws":6,"losses":35,"wins":1},"gpt-6.1-terra":{"draws":9,"losses":32,"wins":1},"gpt-6.1-terra-pro":{"draws":6,"losses":35,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":4,"wins":19},"inception/mercury-3":{"draws":5,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":5,"losses":5,"wins":20},"inclusionai/ling-3.1-flash":{"draws":2,"losses":3,"wins":5},"meituan/longcat-2.0":{"draws":9,"losses":12,"wins":27},"meta/muse-glimmer-30b":{"draws":5,"losses":7,"wins":26},"meta/muse-spark-1.2":{"draws":5,"losses":17,"wins":18},"meta/muse-spark-1.3":{"draws":5,"losses":22,"wins":15},"meta/muse-spark-open":{"draws":5,"losses":22,"wins":15},"meta/muse-wonder":{"draws":4,"losses":30,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":17},"minimax/minimax-m3.1-flash":{"draws":1,"losses":8,"wins":15},"mistralai/mistral-large-4-0":{"draws":1,"losses":14,"wins":11},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":17,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":31,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":13,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":9},"o3":{"draws":5,"losses":26,"wins":33},"openai/gpt-oss-120b":{"draws":5,"losses":7,"wins":24},"poolside/laguna-s-2.1":{"draws":4,"losses":13,"wins":23},"qwen/qwen3.7-max":{"draws":1,"losses":9,"wins":14},"qwen/qwen3.7-plus":{"draws":1,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":20,"wins":12},"qwen/qwen3.8-27b":{"draws":4,"losses":9,"wins":17},"qwen/qwen3.8-flash":{"draws":6,"losses":11,"wins":11},"qwen/qwen3.8-max":{"draws":7,"losses":21,"wins":14},"qwen/qwen3.8-max-0902":{"draws":5,"losses":24,"wins":13},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":16,"wins":14},"stealth/ox-alpha":{"draws":20,"losses":74,"wins":48},"stealth/space-bunny-alpha":{"draws":5,"losses":14,"wins":15},"stepfun/step-3.7-flash":{"draws":1,"losses":5,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":12,"wins":9},"tencent/hy4-preview":{"draws":6,"losses":20,"wins":16},"thinkingmachines/inkling":{"draws":10,"losses":14,"wins":34},"thinkingmachines/inkling-small":{"draws":10,"losses":8,"wins":24},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":1},"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":7,"losses":22,"wins":13},"x-ai/grok-4.6":{"draws":11,"losses":19,"wins":12},"x-ai/grok-4.7":{"draws":2,"losses":23,"wins":11},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":8,"losses":20,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":14,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":16,"wins":9},"z-ai/glm-5.2":{"draws":14,"losses":31,"wins":39},"z-ai/glm-5.3":{"draws":4,"losses":26,"wins":10},"z-ai/glm-5.3-flash":{"draws":2,"losses":17,"wins":23},"z-ai/glm-5.3-flashx":{"draws":5,"losses":22,"wins":15}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":3,"wins":8},"claude-fable-5":{"draws":5,"losses":6,"wins":3},"claude-fable-5-1":{"draws":0,"losses":6,"wins":2},"claude-haiku-5-5":{"draws":3,"losses":9,"wins":4},"claude-opus-4-5":{"draws":4,"losses":3,"wins":5},"claude-opus-4-8":{"draws":4,"losses":2,"wins":2},"claude-opus-5":{"draws":2,"losses":5,"wins":3},"claude-opus-5-5":{"draws":0,"losses":8,"wins":2},"claude-sonnet-5":{"draws":1,"losses":1,"wins":2},"claude-sonnet-5-5":{"draws":2,"losses":4,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":4},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":3,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":4,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":4,"wins":4},"elorian/glimpse":{"draws":4,"losses":7,"wins":3},"fireworks/ember-1":{"draws":7,"losses":0,"wins":5},"gemini-3.1-pro-preview":{"draws":3,"losses":1,"wins":6},"gemini-4-argon":{"draws":0,"losses":10,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":2},"google/gemini-3.5-flash-lite":{"draws":7,"losses":2,"wins":9},"google/gemini-3.6-flash":{"draws":7,"losses":2,"wins":11},"google/gemini-3.8-flash":{"draws":1,"losses":4,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":9},"gpt-4.1":{"draws":5,"losses":0,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":7,"losses":3,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":5},"gpt-5.4-nano":{"draws":1,"losses":3,"wins":4},"gpt-5.5":{"draws":2,"losses":3,"wins":3},"gpt-5.6-luna":{"draws":6,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":7,"losses":2,"wins":5},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":7,"losses":8,"wins":7},"gpt-6-sol":{"draws":0,"losses":6,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":3,"wins":4},"gpt-6.1-terra":{"draws":1,"losses":11,"wins":4},"gpt-6.1-terra-pro":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":8},"inception/mercury-3":{"draws":0,"losses":2,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":2},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":0,"wins":2},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":4},"meta/muse-spark-1.2":{"draws":7,"losses":2,"wins":1},"meta/muse-spark-1.3":{"draws":2,"losses":7,"wins":5},"meta/muse-spark-open":{"draws":5,"losses":4,"wins":5},"meta/muse-wonder":{"draws":4,"losses":10,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":4},"minimax/minimax-m3.1-flash":{"draws":1,"losses":2,"wins":5},"mistralai/mistral-large-4-0":{"draws":2,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":1,"wins":2},"o3":{"draws":3,"losses":3,"wins":4},"poolside/laguna-s-2.1":{"draws":5,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":0,"wins":3},"qwen/qwen3.8-27b":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":3,"losses":2,"wins":5},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":6},"qwen/qwen3.8-max-0902":{"draws":6,"losses":0,"wins":4},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":1,"wins":6},"stealth/ox-alpha":{"draws":7,"losses":8,"wins":9},"stealth/space-bunny-alpha":{"draws":2,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":6},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":6,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":5,"losses":1,"wins":6},"thinkingmachines/inkling-small":{"draws":3,"losses":2,"wins":9},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":8,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":8,"losses":2,"wins":0},"x-ai/grok-4.6":{"draws":4,"losses":3,"wins":7},"x-ai/grok-4.7":{"draws":1,"losses":1,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":10,"losses":0,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":2,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":0,"wins":4},"z-ai/glm-5.3":{"draws":3,"losses":5,"wins":4},"z-ai/glm-5.3-flash":{"draws":1,"losses":0,"wins":7},"z-ai/glm-5.3-flashx":{"draws":2,"losses":4,"wins":6}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":12,"wins":21},"claude-fable-5":{"draws":13,"losses":32,"wins":3},"claude-fable-5-1":{"draws":5,"losses":48,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":23,"wins":11},"claude-opus-4-5":{"draws":27,"losses":27,"wins":24},"claude-opus-4-8":{"draws":14,"losses":17,"wins":13},"claude-opus-5":{"draws":14,"losses":60,"wins":8},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":14,"losses":16,"wins":18},"claude-sonnet-5-5":{"draws":11,"losses":23,"wins":14},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":18,"losses":12,"wins":42},"deepseek/deepseek-v4-pro":{"draws":10,"losses":13,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":19,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":15,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":31,"wins":9},"elorian/glimpse":{"draws":7,"losses":13,"wins":6},"fireworks/ember-1":{"draws":14,"losses":20,"wins":14},"gemini-3.1-pro-preview":{"draws":12,"losses":13,"wins":23},"gemini-4-argon":{"draws":3,"losses":44,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":4,"wins":20},"google/gemini-3.5-flash":{"draws":14,"losses":22,"wins":24},"google/gemini-3.5-flash-lite":{"draws":25,"losses":16,"wins":43},"google/gemini-3.6-flash":{"draws":25,"losses":40,"wins":27},"google/gemini-3.8-flash":{"draws":12,"losses":29,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":13},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":17,"wins":16},"gpt-5.4":{"draws":11,"losses":28,"wins":7},"gpt-5.4-mini":{"draws":9,"losses":6,"wins":17},"gpt-5.4-nano":{"draws":8,"losses":14,"wins":26},"gpt-5.5":{"draws":15,"losses":18,"wins":11},"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":16,"losses":15,"wins":15},"gpt-6-astra":{"draws":2,"losses":42,"wins":4},"gpt-6-luna":{"draws":16,"losses":16,"wins":16},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":3,"losses":40,"wins":5},"gpt-6.1-terra":{"draws":5,"losses":35,"wins":8},"gpt-6.1-terra-pro":{"draws":7,"losses":37,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":16,"losses":2,"wins":16},"inception/mercury-3":{"draws":12,"losses":16,"wins":4},"inclusionai/ling-3.0-flash":{"draws":5,"losses":4,"wins":25},"inclusionai/ling-3.1-flash":{"draws":5,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":13,"losses":8,"wins":31},"meta/muse-glimmer-30b":{"draws":9,"losses":7,"wins":26},"meta/muse-spark-1.2":{"draws":11,"losses":20,"wins":15},"meta/muse-spark-1.3":{"draws":11,"losses":25,"wins":12},"meta/muse-spark-open":{"draws":11,"losses":23,"wins":14},"meta/muse-wonder":{"draws":11,"losses":30,"wins":7},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":18},"minimax/minimax-m3.1-flash":{"draws":12,"losses":16,"wins":14},"mistralai/mistral-large-4-0":{"draws":13,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":11,"losses":2,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":12,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":38,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":4,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":9},"o3":{"draws":9,"losses":26,"wins":31},"openai/gpt-oss-120b":{"draws":12,"losses":5,"wins":25},"poolside/laguna-s-2.1":{"draws":9,"losses":7,"wins":30},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":22,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":7,"wins":17},"qwen/qwen3.8-flash":{"draws":8,"losses":9,"wins":15},"qwen/qwen3.8-max":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-max-0902":{"draws":15,"losses":22,"wins":11},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":19,"wins":13},"stealth/ox-alpha":{"draws":33,"losses":69,"wins":56},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":4,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":12,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":12,"losses":20,"wins":14},"thinkingmachines/inkling":{"draws":18,"losses":14,"wins":32},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":32},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":10,"losses":26,"wins":12},"x-ai/grok-4.6":{"draws":17,"losses":23,"wins":8},"x-ai/grok-4.7":{"draws":5,"losses":31,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":26,"losses":8,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":15,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":9},"z-ai/glm-5.2":{"draws":27,"losses":32,"wins":37},"z-ai/glm-5.3":{"draws":11,"losses":23,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":25,"wins":16},"z-ai/glm-5.3-flashx":{"draws":9,"losses":27,"wins":12}},"moonshotai/kimi-k3.1-pro":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":7,"wins":27},"claude-fable-5":{"draws":5,"losses":14,"wins":29},"claude-fable-5-1":{"draws":5,"losses":36,"wins":13},"claude-haiku-5-5":{"draws":6,"losses":10,"wins":30},"claude-opus-4-5":{"draws":14,"losses":10,"wins":54},"claude-opus-4-8":{"draws":5,"losses":7,"wins":32},"claude-opus-5":{"draws":10,"losses":47,"wins":25},"claude-opus-5-5":{"draws":2,"losses":37,"wins":13},"claude-sonnet-5":{"draws":6,"losses":7,"wins":35},"claude-sonnet-5-5":{"draws":5,"losses":16,"wins":27},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":8,"losses":6,"wins":58},"deepseek/deepseek-v4-pro":{"draws":4,"losses":8,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":9,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":13,"wins":30},"elorian/glimpse":{"draws":1,"losses":7,"wins":18},"fireworks/ember-1":{"draws":6,"losses":8,"wins":34},"gemini-3.1-pro-preview":{"draws":4,"losses":9,"wins":35},"gemini-4-argon":{"draws":4,"losses":29,"wins":15},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":6,"losses":8,"wins":46},"google/gemini-3.5-flash-lite":{"draws":10,"losses":9,"wins":65},"google/gemini-3.6-flash":{"draws":12,"losses":23,"wins":57},"google/gemini-3.8-flash":{"draws":4,"losses":13,"wins":31},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":22},"gpt-4.1":{"draws":1,"losses":2,"wins":13},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":3},"gpt-5":{"draws":6,"losses":7,"wins":29},"gpt-5.4":{"draws":6,"losses":12,"wins":28},"gpt-5.4-mini":{"draws":3,"losses":5,"wins":24},"gpt-5.4-nano":{"draws":5,"losses":3,"wins":40},"gpt-5.5":{"draws":4,"losses":12,"wins":28},"gpt-5.6-luna":{"draws":4,"losses":5,"wins":39},"gpt-5.6-sol":{"draws":5,"losses":15,"wins":28},"gpt-5.6-terra":{"draws":3,"losses":7,"wins":36},"gpt-6-astra":{"draws":2,"losses":36,"wins":10},"gpt-6-luna":{"draws":5,"losses":7,"wins":36},"gpt-6-sol":{"draws":4,"losses":17,"wins":27},"gpt-6.1-sol":{"draws":2,"losses":31,"wins":15},"gpt-6.1-terra":{"draws":9,"losses":20,"wins":19},"gpt-6.1-terra-pro":{"draws":6,"losses":28,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":7,"losses":3,"wins":24},"inception/mercury-3":{"draws":5,"losses":4,"wins":23},"inclusionai/ling-3.0-flash":{"draws":6,"losses":4,"wins":24},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":8},"meituan/longcat-2.0":{"draws":2,"losses":7,"wins":43},"meta/muse-glimmer-30b":{"draws":8,"losses":5,"wins":29},"meta/muse-spark-1.2":{"draws":6,"losses":9,"wins":31},"meta/muse-spark-1.3":{"draws":4,"losses":6,"wins":38},"meta/muse-spark-open":{"draws":4,"losses":9,"wins":33},"meta/muse-wonder":{"draws":5,"losses":19,"wins":24},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":23},"minimax/minimax-m3.1-flash":{"draws":4,"losses":5,"wins":33},"mistralai/mistral-large-4-0":{"draws":3,"losses":7,"wins":20},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":9,"wins":32},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":20,"wins":9},"nex-agi/nex-n2-pro":{"draws":1,"losses":4,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":4,"wins":16},"o3":{"draws":5,"losses":6,"wins":55},"openai/gpt-oss-120b":{"draws":5,"losses":5,"wins":32},"poolside/laguna-s-2.1":{"draws":6,"losses":9,"wins":31},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":22},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":7,"wins":35},"qwen/qwen3.8-27b":{"draws":5,"losses":4,"wins":25},"qwen/qwen3.8-flash":{"draws":1,"losses":4,"wins":27},"qwen/qwen3.8-max":{"draws":5,"losses":10,"wins":33},"qwen/qwen3.8-max-0902":{"draws":7,"losses":8,"wins":33},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":9,"wins":28},"stealth/ox-alpha":{"draws":22,"losses":41,"wins":95},"stealth/space-bunny-alpha":{"draws":5,"losses":5,"wins":28},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":30},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":9},"tencent/hy3-preview":{"draws":7,"losses":2,"wins":17},"tencent/hy4-preview":{"draws":3,"losses":8,"wins":35},"thinkingmachines/inkling":{"draws":9,"losses":8,"wins":47},"thinkingmachines/inkling-small":{"draws":5,"losses":4,"wins":39},"unbiased/pareto-26.10":{"draws":2,"losses":9,"wins":5},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":4},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":9,"losses":10,"wins":29},"x-ai/grok-4.6":{"draws":6,"losses":12,"wins":30},"x-ai/grok-4.7":{"draws":2,"losses":16,"wins":24},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":9,"losses":2,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":6,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":10,"wins":15},"z-ai/glm-5.2":{"draws":13,"losses":16,"wins":67},"z-ai/glm-5.3":{"draws":5,"losses":15,"wins":26},"z-ai/glm-5.3-flash":{"draws":5,"losses":11,"wins":32},"z-ai/glm-5.3-flashx":{"draws":5,"losses":9,"wins":34}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":20,"wins":5},"claude-fable-5":{"draws":4,"losses":26,"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":3,"losses":42,"wins":3},"claude-opus-4-8":{"draws":3,"losses":23,"wins":0},"claude-opus-5":{"draws":0,"losses":46,"wins":0},"claude-opus-5-5":{"draws":3,"losses":31,"wins":0},"claude-sonnet-5":{"draws":5,"losses":21,"wins":4},"claude-sonnet-5-5":{"draws":2,"losses":26,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":9,"wins":6},"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":1,"losses":21,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":26,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":24,"wins":4},"elorian/glimpse":{"draws":0,"losses":11,"wins":5},"fireworks/ember-1":{"draws":2,"losses":26,"wins":2},"gemini-3.1-pro-preview":{"draws":3,"losses":22,"wins":5},"gemini-4-argon":{"draws":0,"losses":29,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":9,"wins":13},"google/gemini-3.5-flash":{"draws":3,"losses":32,"wins":3},"google/gemini-3.5-flash-lite":{"draws":4,"losses":37,"wins":13},"google/gemini-3.6-flash":{"draws":2,"losses":52,"wins":4},"google/gemini-3.8-flash":{"draws":0,"losses":30,"wins":0},"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":1,"losses":1,"wins":2},"gpt-5":{"draws":1,"losses":21,"wins":6},"gpt-5.4":{"draws":4,"losses":21,"wins":5},"gpt-5.4-mini":{"draws":3,"losses":10,"wins":7},"gpt-5.4-nano":{"draws":1,"losses":19,"wins":12},"gpt-5.5":{"draws":0,"losses":26,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":21,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":29,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":24,"wins":3},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":2,"losses":23,"wins":5},"gpt-6-sol":{"draws":0,"losses":30,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":30,"wins":0},"gpt-6.1-terra":{"draws":2,"losses":28,"wins":0},"gpt-6.1-terra-pro":{"draws":1,"losses":29,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":10,"wins":8},"inception/mercury-3":{"draws":0,"losses":19,"wins":1},"inclusionai/ling-3.0-flash":{"draws":1,"losses":10,"wins":9},"inclusionai/ling-3.1-flash":{"draws":0,"losses":4,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":27,"wins":10},"meta/muse-glimmer-30b":{"draws":4,"losses":17,"wins":5},"meta/muse-spark-1.2":{"draws":1,"losses":26,"wins":1},"meta/muse-spark-1.3":{"draws":0,"losses":30,"wins":0},"meta/muse-spark-open":{"draws":3,"losses":26,"wins":1},"meta/muse-wonder":{"draws":1,"losses":26,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":9,"wins":5},"minimax/minimax-m3.1-flash":{"draws":3,"losses":19,"wins":4},"mistralai/mistral-large-4-0":{"draws":1,"losses":14,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":14,"wins":4},"moonshotai/kimi-k3":{"draws":1,"losses":24,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":28,"wins":2},"nex-agi/nex-n2-pro":{"draws":1,"losses":7,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":7,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":22,"wins":3},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":9,"wins":3},"o3":{"draws":1,"losses":45,"wins":4},"openai/gpt-oss-120b":{"draws":4,"losses":14,"wins":10},"poolside/laguna-s-2.1":{"draws":6,"losses":21,"wins":5},"qwen/qwen3.7-max":{"draws":3,"losses":13,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":11,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":24,"wins":3},"qwen/qwen3.8-27b":{"draws":2,"losses":14,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":17,"wins":1},"qwen/qwen3.8-max":{"draws":4,"losses":22,"wins":4},"qwen/qwen3.8-max-0902":{"draws":4,"losses":24,"wins":2},"recursive/flint-v1.0":{"draws":0,"losses":5,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":22,"wins":3},"stealth/ox-alpha":{"draws":13,"losses":86,"wins":9},"stealth/space-bunny-alpha":{"draws":1,"losses":19,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":13,"wins":9},"stepfun/step-5-preview":{"draws":0,"losses":7,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":8,"wins":5},"tencent/hy4-preview":{"draws":0,"losses":27,"wins":3},"thinkingmachines/inkling":{"draws":6,"losses":25,"wins":9},"thinkingmachines/inkling-small":{"draws":3,"losses":20,"wins":7},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":1,"losses":25,"wins":4},"x-ai/grok-4.6":{"draws":3,"losses":26,"wins":1},"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":3,"losses":12,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":17,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":19,"wins":1},"z-ai/glm-5.2":{"draws":11,"losses":43,"wins":6},"z-ai/glm-5.3":{"draws":2,"losses":28,"wins":0},"z-ai/glm-5.3-flash":{"draws":2,"losses":27,"wins":1},"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":2,"losses":4,"wins":8},"claude-fable-5":{"draws":4,"losses":5,"wins":1},"claude-fable-5-1":{"draws":1,"losses":8,"wins":1},"claude-haiku-5-5":{"draws":2,"losses":3,"wins":1},"claude-opus-4-5":{"draws":8,"losses":14,"wins":12},"claude-opus-4-8":{"draws":5,"losses":4,"wins":3},"claude-opus-5":{"draws":4,"losses":15,"wins":5},"claude-opus-5-5":{"draws":2,"losses":12,"wins":2},"claude-sonnet-5":{"draws":4,"losses":7,"wins":1},"claude-sonnet-5-5":{"draws":5,"losses":8,"wins":3},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":2,"losses":9,"wins":7},"deepseek/deepseek-v4-pro":{"draws":3,"losses":2,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":3,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":6,"wins":4},"elorian/glimpse":{"draws":1,"losses":4,"wins":3},"fireworks/ember-1":{"draws":2,"losses":14,"wins":4},"gemini-3.1-pro-preview":{"draws":3,"losses":12,"wins":7},"gemini-4-argon":{"draws":0,"losses":14,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":5},"google/gemini-3.5-flash-lite":{"draws":3,"losses":4,"wins":5},"google/gemini-3.6-flash":{"draws":5,"losses":2,"wins":11},"google/gemini-3.8-flash":{"draws":2,"losses":8,"wins":6},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":8},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":5,"wins":9},"gpt-5.4":{"draws":2,"losses":2,"wins":8},"gpt-5.4-mini":{"draws":0,"losses":4,"wins":8},"gpt-5.4-nano":{"draws":0,"losses":1,"wins":11},"gpt-5.5":{"draws":9,"losses":6,"wins":11},"gpt-5.6-luna":{"draws":6,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":1,"losses":4,"wins":1},"gpt-5.6-terra":{"draws":3,"losses":3,"wins":8},"gpt-6-astra":{"draws":2,"losses":10,"wins":0},"gpt-6-luna":{"draws":3,"losses":5,"wins":2},"gpt-6-sol":{"draws":4,"losses":3,"wins":3},"gpt-6.1-sol":{"draws":0,"losses":4,"wins":2},"gpt-6.1-terra":{"draws":0,"losses":13,"wins":1},"gpt-6.1-terra-pro":{"draws":3,"losses":11,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":2,"wins":6},"inception/mercury-3":{"draws":2,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":5},"inclusionai/ling-3.1-flash":{"draws":5,"losses":3,"wins":6},"meituan/longcat-2.0":{"draws":0,"losses":6,"wins":4},"meta/muse-glimmer-30b":{"draws":2,"losses":3,"wins":7},"meta/muse-spark-1.2":{"draws":0,"losses":9,"wins":3},"meta/muse-spark-1.3":{"draws":2,"losses":6,"wins":6},"meta/muse-spark-open":{"draws":3,"losses":4,"wins":9},"meta/muse-wonder":{"draws":0,"losses":13,"wins":7},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":7},"minimax/minimax-m3.1-flash":{"draws":0,"losses":2,"wins":6},"mistralai/mistral-large-4-0":{"draws":2,"losses":3,"wins":9},"mistralai/mistral-medium-3-5":{"draws":4,"losses":1,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":3,"wins":4},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":4},"o3":{"draws":2,"losses":2,"wins":12},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":8},"poolside/laguna-s-2.1":{"draws":2,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.8-flash":{"draws":2,"losses":3,"wins":7},"qwen/qwen3.8-max":{"draws":1,"losses":6,"wins":5},"qwen/qwen3.8-max-0902":{"draws":2,"losses":10,"wins":6},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":2,"wins":4},"stealth/ox-alpha":{"draws":9,"losses":16,"wins":11},"stealth/space-bunny-alpha":{"draws":2,"losses":4,"wins":8},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":6},"stepfun/step-5-preview":{"draws":3,"losses":2,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":5},"tencent/hy4-preview":{"draws":5,"losses":6,"wins":5},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":10},"thinkingmachines/inkling-small":{"draws":4,"losses":2,"wins":6},"unbiased/pareto-26.10":{"draws":0,"losses":4,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.6":{"draws":4,"losses":5,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":8,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":4,"losses":3,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":7,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":9,"losses":3,"wins":14},"z-ai/glm-5.3":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.3-flash":{"draws":3,"losses":7,"wins":2},"z-ai/glm-5.3-flashx":{"draws":1,"losses":9,"wins":2}},"nvidia/nemotron-3.5-super-vl":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":7,"wins":21},"claude-fable-5":{"draws":9,"losses":35,"wins":4},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":8,"losses":22,"wins":16},"claude-opus-4-5":{"draws":27,"losses":21,"wins":30},"claude-opus-4-8":{"draws":10,"losses":23,"wins":11},"claude-opus-5":{"draws":14,"losses":56,"wins":12},"claude-opus-5-5":{"draws":3,"losses":45,"wins":4},"claude-sonnet-5":{"draws":12,"losses":20,"wins":16},"claude-sonnet-5-5":{"draws":12,"losses":26,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":18,"losses":16,"wins":38},"deepseek/deepseek-v4-pro":{"draws":12,"losses":15,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":15,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":22,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":27,"wins":11},"elorian/glimpse":{"draws":7,"losses":12,"wins":7},"fireworks/ember-1":{"draws":14,"losses":19,"wins":15},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":22},"gemini-4-argon":{"draws":4,"losses":39,"wins":5},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":12,"losses":23,"wins":25},"google/gemini-3.5-flash-lite":{"draws":24,"losses":11,"wins":49},"google/gemini-3.6-flash":{"draws":23,"losses":42,"wins":27},"google/gemini-3.8-flash":{"draws":8,"losses":26,"wins":14},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":4,"losses":3,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":12,"wins":21},"gpt-5.4":{"draws":10,"losses":26,"wins":10},"gpt-5.4-mini":{"draws":10,"losses":3,"wins":19},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":25},"gpt-5.5":{"draws":17,"losses":18,"wins":9},"gpt-5.6-luna":{"draws":16,"losses":11,"wins":21},"gpt-5.6-sol":{"draws":8,"losses":28,"wins":12},"gpt-5.6-terra":{"draws":19,"losses":12,"wins":15},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":13,"losses":22,"wins":13},"gpt-6-sol":{"draws":5,"losses":36,"wins":7},"gpt-6.1-sol":{"draws":3,"losses":43,"wins":2},"gpt-6.1-terra":{"draws":8,"losses":37,"wins":3},"gpt-6.1-terra-pro":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inception/mercury-3":{"draws":11,"losses":14,"wins":9},"inclusionai/ling-3.0-flash":{"draws":12,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":3,"losses":3,"wins":4},"meituan/longcat-2.0":{"draws":16,"losses":5,"wins":31},"meta/muse-glimmer-30b":{"draws":13,"losses":3,"wins":26},"meta/muse-spark-1.2":{"draws":13,"losses":20,"wins":13},"meta/muse-spark-1.3":{"draws":6,"losses":24,"wins":18},"meta/muse-spark-open":{"draws":10,"losses":25,"wins":11},"meta/muse-wonder":{"draws":9,"losses":31,"wins":8},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":13},"minimax/minimax-m3.1-flash":{"draws":10,"losses":15,"wins":17},"mistralai/mistral-large-4-0":{"draws":11,"losses":11,"wins":8},"mistralai/mistral-medium-3-5":{"draws":11,"losses":1,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":13,"losses":20,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":40,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":11,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":1,"wins":4},"o3":{"draws":7,"losses":13,"wins":46},"openai/gpt-oss-120b":{"draws":11,"losses":5,"wins":26},"poolside/laguna-s-2.1":{"draws":12,"losses":7,"wins":27},"qwen/qwen3.7-max":{"draws":6,"losses":10,"wins":12},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":21,"wins":14},"qwen/qwen3.8-27b":{"draws":8,"losses":14,"wins":12},"qwen/qwen3.8-flash":{"draws":11,"losses":13,"wins":8},"qwen/qwen3.8-max":{"draws":14,"losses":18,"wins":16},"qwen/qwen3.8-max-0902":{"draws":13,"losses":23,"wins":12},"recursive/flint-v1.0":{"draws":4,"losses":1,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":16,"wins":15},"stealth/ox-alpha":{"draws":41,"losses":70,"wins":47},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":19},"stepfun/step-3.7-flash":{"draws":7,"losses":5,"wins":22},"stepfun/step-5-preview":{"draws":3,"losses":8,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":4,"wins":13},"tencent/hy4-preview":{"draws":12,"losses":23,"wins":11},"thinkingmachines/inkling":{"draws":17,"losses":12,"wins":35},"thinkingmachines/inkling-small":{"draws":14,"losses":4,"wins":30},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":3,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":14,"losses":24,"wins":10},"x-ai/grok-4.6":{"draws":11,"losses":28,"wins":9},"x-ai/grok-4.7":{"draws":3,"losses":28,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":21,"losses":13,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":2,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":17,"wins":12},"z-ai/glm-5.2":{"draws":31,"losses":26,"wins":39},"z-ai/glm-5.3":{"draws":7,"losses":35,"wins":4},"z-ai/glm-5.3-flash":{"draws":8,"losses":24,"wins":16},"z-ai/glm-5.3-flashx":{"draws":11,"losses":25,"wins":12}},"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":11,"losses":30,"wins":19},"claude-opus-4-8":{"draws":6,"losses":19,"wins":11},"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":15,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":26,"wins":6},"elorian/glimpse":{"draws":4,"losses":11,"wins":5},"fireworks/ember-1":{"draws":13,"losses":16,"wins":7},"gemini-3.1-pro-preview":{"draws":7,"losses":12,"wins":17},"gemini-4-argon":{"draws":1,"losses":32,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":23},"google/gemini-3.5-flash":{"draws":8,"losses":23,"wins":17},"google/gemini-3.5-flash-lite":{"draws":14,"losses":15,"wins":37},"google/gemini-3.6-flash":{"draws":13,"losses":32,"wins":25},"google/gemini-3.8-flash":{"draws":2,"losses":24,"wins":10},"google/gemma-4-31b-it":{"draws":6,"losses":2,"wins":14},"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":20,"wins":10},"gpt-5.4-mini":{"draws":3,"losses":10,"wins":11},"gpt-5.4-nano":{"draws":3,"losses":16,"wins":21},"gpt-5.5":{"draws":8,"losses":19,"wins":7},"gpt-5.6-luna":{"draws":5,"losses":12,"wins":19},"gpt-5.6-sol":{"draws":2,"losses":28,"wins":6},"gpt-5.6-terra":{"draws":5,"losses":22,"wins":7},"gpt-6-astra":{"draws":1,"losses":34,"wins":1},"gpt-6-luna":{"draws":6,"losses":16,"wins":14},"gpt-6-sol":{"draws":5,"losses":28,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"gpt-6.1-terra":{"draws":1,"losses":35,"wins":0},"gpt-6.1-terra-pro":{"draws":0,"losses":33,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":1,"wins":19},"inception/mercury-3":{"draws":4,"losses":12,"wins":6},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":4,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":13,"wins":23},"meta/muse-glimmer-30b":{"draws":6,"losses":4,"wins":22},"meta/muse-spark-1.2":{"draws":5,"losses":19,"wins":10},"meta/muse-spark-1.3":{"draws":3,"losses":25,"wins":8},"meta/muse-spark-open":{"draws":6,"losses":26,"wins":4},"meta/muse-wonder":{"draws":2,"losses":29,"wins":5},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":16},"minimax/minimax-m3.1-flash":{"draws":6,"losses":15,"wins":11},"mistralai/mistral-large-4-0":{"draws":9,"losses":8,"wins":5},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":13},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":32,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":9,"wins":5},"o3":{"draws":5,"losses":23,"wins":20},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":25},"poolside/laguna-s-2.1":{"draws":2,"losses":10,"wins":20},"qwen/qwen3.7-max":{"draws":5,"losses":6,"wins":11},"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":7,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":11,"losses":18,"wins":7},"recursive/flint-v1.0":{"draws":1,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":11,"losses":62,"wins":29},"stealth/space-bunny-alpha":{"draws":6,"losses":8,"wins":16},"stepfun/step-3.7-flash":{"draws":6,"losses":8,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":6,"losses":20,"wins":10},"thinkingmachines/inkling":{"draws":9,"losses":9,"wins":30},"thinkingmachines/inkling-small":{"draws":8,"losses":3,"wins":25},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":1,"wins":8},"x-ai/grok-4.5":{"draws":6,"losses":21,"wins":9},"x-ai/grok-4.6":{"draws":7,"losses":22,"wins":7},"x-ai/grok-4.7":{"draws":4,"losses":22,"wins":6},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":16,"losses":10,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":17,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":17,"wins":4},"z-ai/glm-5.2":{"draws":14,"losses":27,"wins":31},"z-ai/glm-5.3":{"draws":4,"losses":27,"wins":3},"z-ai/glm-5.3-flash":{"draws":6,"losses":18,"wins":12},"z-ai/glm-5.3-flashx":{"draws":2,"losses":24,"wins":10}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":15,"wins":14},"claude-fable-5":{"draws":10,"losses":37,"wins":1},"claude-fable-5-1":{"draws":0,"losses":54,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":32,"wins":3},"claude-opus-4-5":{"draws":25,"losses":44,"wins":9},"claude-opus-4-8":{"draws":12,"losses":30,"wins":2},"claude-opus-5":{"draws":11,"losses":66,"wins":5},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":12,"losses":30,"wins":6},"claude-sonnet-5-5":{"draws":11,"losses":32,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":9,"wins":4},"deepseek/deepseek-v4-flash":{"draws":22,"losses":28,"wins":22},"deepseek/deepseek-v4-pro":{"draws":11,"losses":24,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":21,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":33,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":35,"wins":4},"elorian/glimpse":{"draws":4,"losses":15,"wins":7},"fireworks/ember-1":{"draws":17,"losses":25,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":23,"wins":13},"gemini-4-argon":{"draws":0,"losses":47,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":10,"wins":13},"google/gemini-3.5-flash":{"draws":14,"losses":36,"wins":10},"google/gemini-3.5-flash-lite":{"draws":24,"losses":32,"wins":28},"google/gemini-3.6-flash":{"draws":23,"losses":55,"wins":14},"google/gemini-3.8-flash":{"draws":10,"losses":36,"wins":2},"google/gemma-4-31b-it":{"draws":12,"losses":4,"wins":12},"gpt-4.1":{"draws":5,"losses":8,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":24,"wins":7},"gpt-5.4":{"draws":14,"losses":30,"wins":2},"gpt-5.4-mini":{"draws":13,"losses":14,"wins":5},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":18},"gpt-5.5":{"draws":17,"losses":24,"wins":3},"gpt-5.6-luna":{"draws":16,"losses":24,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":41,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":29,"wins":3},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":15,"losses":24,"wins":9},"gpt-6-sol":{"draws":6,"losses":39,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"gpt-6.1-terra":{"draws":6,"losses":42,"wins":0},"gpt-6.1-terra-pro":{"draws":2,"losses":45,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":10,"wins":11},"inception/mercury-3":{"draws":11,"losses":14,"wins":7},"inclusionai/ling-3.0-flash":{"draws":17,"losses":4,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":11,"losses":28,"wins":13},"meta/muse-glimmer-30b":{"draws":13,"losses":14,"wins":15},"meta/muse-spark-1.2":{"draws":14,"losses":28,"wins":4},"meta/muse-spark-1.3":{"draws":11,"losses":33,"wins":4},"meta/muse-spark-open":{"draws":13,"losses":32,"wins":3},"meta/muse-wonder":{"draws":10,"losses":36,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":11,"wins":7},"minimax/minimax-m3.1-flash":{"draws":10,"losses":22,"wins":10},"mistralai/mistral-large-4-0":{"draws":10,"losses":18,"wins":2},"mistralai/mistral-medium-3-5":{"draws":11,"losses":8,"wins":9},"moonshotai/kimi-k3":{"draws":14,"losses":26,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":42,"wins":1},"nex-agi/nex-n2-pro":{"draws":6,"losses":12,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":18,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":14,"wins":2},"o3":{"draws":9,"losses":51,"wins":6},"openai/gpt-oss-120b":{"draws":7,"losses":14,"wins":5},"poolside/laguna-s-2.1":{"draws":15,"losses":21,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":15,"wins":7},"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":11,"losses":16,"wins":5},"qwen/qwen3.8-max":{"draws":18,"losses":28,"wins":2},"qwen/qwen3.8-max-0902":{"draws":12,"losses":34,"wins":2},"recursive/flint-v1.0":{"draws":3,"losses":4,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":26,"wins":5},"stealth/ox-alpha":{"draws":38,"losses":104,"wins":16},"stealth/space-bunny-alpha":{"draws":11,"losses":20,"wins":7},"stepfun/step-3.7-flash":{"draws":11,"losses":15,"wins":8},"stepfun/step-5-preview":{"draws":0,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":13,"wins":5},"tencent/hy4-preview":{"draws":15,"losses":23,"wins":8},"thinkingmachines/inkling":{"draws":18,"losses":24,"wins":22},"thinkingmachines/inkling-small":{"draws":15,"losses":16,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":16,"losses":30,"wins":2},"x-ai/grok-4.7":{"draws":5,"losses":36,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":8,"wins":2},"xiaomi/mimo-v2.5":{"draws":22,"losses":31,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":25,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":24,"wins":2},"z-ai/glm-5.2":{"draws":31,"losses":47,"wins":18},"z-ai/glm-5.3":{"draws":9,"losses":36,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":36,"wins":5},"z-ai/glm-5.3-flashx":{"draws":7,"losses":34,"wins":7}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":25,"wins":14},"claude-fable-5":{"draws":14,"losses":45,"wins":7},"claude-fable-5-1":{"draws":5,"losses":65,"wins":2},"claude-haiku-5-5":{"draws":18,"losses":31,"wins":13},"claude-opus-4-5":{"draws":40,"losses":55,"wins":11},"claude-opus-4-8":{"draws":23,"losses":30,"wins":5},"claude-opus-5":{"draws":16,"losses":100,"wins":6},"claude-opus-5-5":{"draws":5,"losses":69,"wins":0},"claude-sonnet-5":{"draws":23,"losses":36,"wins":7},"claude-sonnet-5-5":{"draws":16,"losses":39,"wins":11},"cohere/north-mini-code":{"draws":8,"losses":11,"wins":5},"deepseek/deepseek-v4-flash":{"draws":40,"losses":33,"wins":25},"deepseek/deepseek-v4-pro":{"draws":19,"losses":21,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":29,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":28,"losses":27,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":43,"wins":7},"elorian/glimpse":{"draws":11,"losses":18,"wins":5},"fireworks/ember-1":{"draws":27,"losses":28,"wins":11},"gemini-3.1-pro-preview":{"draws":23,"losses":29,"wins":14},"gemini-4-argon":{"draws":6,"losses":58,"wins":2},"google/gemini-3.1-flash-lite":{"draws":15,"losses":10,"wins":13},"google/gemini-3.5-flash":{"draws":21,"losses":47,"wins":12},"google/gemini-3.5-flash-lite":{"draws":41,"losses":34,"wins":39},"google/gemini-3.6-flash":{"draws":36,"losses":72,"wins":16},"google/gemini-3.8-flash":{"draws":12,"losses":49,"wins":5},"google/gemma-4-31b-it":{"draws":20,"losses":10,"wins":8},"gpt-4.1":{"draws":9,"losses":7,"wins":6},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":2},"gpt-5":{"draws":18,"losses":28,"wins":12},"gpt-5.4":{"draws":16,"losses":37,"wins":9},"gpt-5.4-mini":{"draws":15,"losses":18,"wins":11},"gpt-5.4-nano":{"draws":17,"losses":27,"wins":22},"gpt-5.5":{"draws":22,"losses":26,"wins":12},"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":23,"losses":35,"wins":4},"gpt-6-astra":{"draws":5,"losses":61,"wins":0},"gpt-6-luna":{"draws":25,"losses":32,"wins":9},"gpt-6-sol":{"draws":12,"losses":51,"wins":3},"gpt-6.1-sol":{"draws":5,"losses":61,"wins":0},"gpt-6.1-terra":{"draws":9,"losses":57,"wins":0},"gpt-6.1-terra-pro":{"draws":7,"losses":55,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":24,"losses":12,"wins":10},"inception/mercury-3":{"draws":19,"losses":22,"wins":5},"inclusionai/ling-3.0-flash":{"draws":20,"losses":13,"wins":11},"inclusionai/ling-3.1-flash":{"draws":8,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":25,"wins":22},"meta/muse-glimmer-30b":{"draws":24,"losses":14,"wins":20},"meta/muse-spark-1.2":{"draws":19,"losses":42,"wins":3},"meta/muse-spark-1.3":{"draws":19,"losses":40,"wins":7},"meta/muse-spark-open":{"draws":21,"losses":39,"wins":6},"meta/muse-wonder":{"draws":12,"losses":47,"wins":7},"minimax/minimax-m3":{"draws":13,"losses":11,"wins":12},"minimax/minimax-m3.1-flash":{"draws":16,"losses":23,"wins":15},"mistralai/mistral-large-4-0":{"draws":19,"losses":19,"wins":4},"mistralai/mistral-medium-3-5":{"draws":18,"losses":8,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":23,"losses":37,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":52,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":14,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":21,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":14,"wins":4},"o3":{"draws":16,"losses":45,"wins":21},"openai/gpt-oss-120b":{"draws":29,"losses":22,"wins":9},"poolside/laguna-s-2.1":{"draws":14,"losses":22,"wins":14},"qwen/qwen3.7-max":{"draws":15,"losses":13,"wins":10},"qwen/qwen3.7-plus":{"draws":11,"losses":7,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":40,"wins":5},"qwen/qwen3.8-27b":{"draws":16,"losses":22,"wins":6},"qwen/qwen3.8-flash":{"draws":14,"losses":21,"wins":9},"qwen/qwen3.8-max":{"draws":21,"losses":36,"wins":9},"qwen/qwen3.8-max-0902":{"draws":22,"losses":38,"wins":6},"recursive/flint-v1.0":{"draws":5,"losses":2,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":20,"losses":34,"wins":8},"stealth/ox-alpha":{"draws":65,"losses":138,"wins":27},"stealth/space-bunny-alpha":{"draws":20,"losses":20,"wins":10},"stepfun/step-3.7-flash":{"draws":16,"losses":14,"wins":12},"stepfun/step-5-preview":{"draws":2,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":17,"losses":13,"wins":8},"tencent/hy4-preview":{"draws":17,"losses":33,"wins":12},"thinkingmachines/inkling":{"draws":34,"losses":26,"wins":28},"thinkingmachines/inkling-small":{"draws":25,"losses":12,"wins":29},"unbiased/pareto-26.10":{"draws":1,"losses":21,"wins":0},"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":21,"losses":39,"wins":6},"x-ai/grok-4.6":{"draws":15,"losses":44,"wins":7},"x-ai/grok-4.7":{"draws":8,"losses":46,"wins":4},"x-ai/grok-build-0.1":{"draws":10,"losses":8,"wins":4},"xiaomi/mimo-v2.5":{"draws":39,"losses":27,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":8,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":29,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":31,"wins":5},"z-ai/glm-5.2":{"draws":51,"losses":50,"wins":31},"z-ai/glm-5.3":{"draws":19,"losses":40,"wins":5},"z-ai/glm-5.3-flash":{"draws":15,"losses":37,"wins":14},"z-ai/glm-5.3-flashx":{"draws":23,"losses":32,"wins":11}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":6,"wins":19},"claude-fable-5":{"draws":6,"losses":28,"wins":8},"claude-fable-5-1":{"draws":2,"losses":43,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":15,"wins":12},"claude-opus-4-5":{"draws":18,"losses":30,"wins":22},"claude-opus-4-8":{"draws":12,"losses":17,"wins":13},"claude-opus-5":{"draws":8,"losses":53,"wins":9},"claude-opus-5-5":{"draws":1,"losses":45,"wins":0},"claude-sonnet-5":{"draws":10,"losses":19,"wins":13},"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":25,"losses":13,"wins":26},"deepseek/deepseek-v4-pro":{"draws":10,"losses":18,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":12,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":12,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":29,"wins":5},"elorian/glimpse":{"draws":3,"losses":11,"wins":8},"fireworks/ember-1":{"draws":8,"losses":19,"wins":15},"gemini-3.1-pro-preview":{"draws":11,"losses":14,"wins":17},"gemini-4-argon":{"draws":4,"losses":33,"wins":5},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":15,"losses":17,"wins":22},"google/gemini-3.5-flash-lite":{"draws":21,"losses":19,"wins":34},"google/gemini-3.6-flash":{"draws":20,"losses":34,"wins":26},"google/gemini-3.8-flash":{"draws":10,"losses":21,"wins":11},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":10},"gpt-4.1":{"draws":6,"losses":3,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":14,"wins":10},"gpt-5.4":{"draws":7,"losses":23,"wins":10},"gpt-5.4-mini":{"draws":6,"losses":8,"wins":14},"gpt-5.4-nano":{"draws":10,"losses":14,"wins":22},"gpt-5.5":{"draws":13,"losses":18,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":14,"wins":16},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":8},"gpt-5.6-terra":{"draws":9,"losses":19,"wins":12},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":10,"losses":20,"wins":12},"gpt-6-sol":{"draws":7,"losses":30,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":39,"wins":1},"gpt-6.1-terra":{"draws":4,"losses":37,"wins":1},"gpt-6.1-terra-pro":{"draws":3,"losses":36,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":5,"wins":14},"inception/mercury-3":{"draws":9,"losses":10,"wins":9},"inclusionai/ling-3.0-flash":{"draws":12,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"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":9,"losses":22,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":21,"wins":13},"meta/muse-spark-open":{"draws":8,"losses":22,"wins":12},"meta/muse-wonder":{"draws":6,"losses":33,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":11},"minimax/minimax-m3.1-flash":{"draws":8,"losses":11,"wins":17},"mistralai/mistral-large-4-0":{"draws":9,"losses":14,"wins":3},"mistralai/mistral-medium-3-5":{"draws":8,"losses":1,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":19,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":38,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":5,"wins":10},"o3":{"draws":11,"losses":23,"wins":28},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":18},"poolside/laguna-s-2.1":{"draws":10,"losses":8,"wins":20},"qwen/qwen3.7-max":{"draws":1,"losses":5,"wins":6},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":17,"wins":10},"qwen/qwen3.8-27b":{"draws":8,"losses":14,"wins":8},"qwen/qwen3.8-flash":{"draws":8,"losses":12,"wins":8},"qwen/qwen3.8-max":{"draws":8,"losses":17,"wins":17},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":8},"recursive/flint-v1.0":{"draws":3,"losses":4,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":19,"wins":10},"stealth/ox-alpha":{"draws":29,"losses":56,"wins":33},"stealth/space-bunny-alpha":{"draws":7,"losses":9,"wins":18},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":4,"losses":23,"wins":13},"thinkingmachines/inkling":{"draws":15,"losses":6,"wins":33},"thinkingmachines/inkling-small":{"draws":14,"losses":7,"wins":21},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":24,"wins":11},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":24,"losses":14,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":5},"z-ai/glm-5.2":{"draws":18,"losses":34,"wins":32},"z-ai/glm-5.3":{"draws":9,"losses":21,"wins":10},"z-ai/glm-5.3-flash":{"draws":13,"losses":17,"wins":12},"z-ai/glm-5.3-flashx":{"draws":11,"losses":19,"wins":12}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":12,"wins":14},"claude-fable-5":{"draws":3,"losses":28,"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":13,"losses":26,"wins":21},"claude-opus-4-8":{"draws":8,"losses":20,"wins":8},"claude-opus-5":{"draws":9,"losses":48,"wins":1},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":9,"losses":15,"wins":12},"claude-sonnet-5-5":{"draws":7,"losses":20,"wins":9},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":14,"losses":18,"wins":26},"deepseek/deepseek-v4-pro":{"draws":4,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":10,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":18,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":24,"wins":6},"elorian/glimpse":{"draws":2,"losses":13,"wins":3},"fireworks/ember-1":{"draws":8,"losses":17,"wins":11},"gemini-3.1-pro-preview":{"draws":11,"losses":13,"wins":12},"gemini-4-argon":{"draws":2,"losses":33,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":6,"losses":26,"wins":14},"google/gemini-3.5-flash-lite":{"draws":12,"losses":20,"wins":30},"google/gemini-3.6-flash":{"draws":12,"losses":36,"wins":20},"google/gemini-3.8-flash":{"draws":6,"losses":26,"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":6,"losses":18,"wins":8},"gpt-5.4":{"draws":4,"losses":23,"wins":7},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":7,"losses":11,"wins":26},"gpt-5.5":{"draws":11,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":12,"wins":12},"gpt-5.6-sol":{"draws":6,"losses":25,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":12,"wins":8},"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":3,"losses":29,"wins":4},"gpt-6.1-terra":{"draws":7,"losses":29,"wins":0},"gpt-6.1-terra-pro":{"draws":6,"losses":27,"wins":3},"inception/mercury-2.5-preview":{"draws":10,"losses":1,"wins":15},"inception/mercury-3":{"draws":7,"losses":12,"wins":7},"inclusionai/ling-3.0-flash":{"draws":7,"losses":4,"wins":15},"inclusionai/ling-3.1-flash":{"draws":0,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":7,"losses":10,"wins":23},"meta/muse-glimmer-30b":{"draws":8,"losses":12,"wins":10},"meta/muse-spark-1.2":{"draws":6,"losses":23,"wins":5},"meta/muse-spark-1.3":{"draws":8,"losses":19,"wins":9},"meta/muse-spark-open":{"draws":9,"losses":20,"wins":7},"meta/muse-wonder":{"draws":10,"losses":25,"wins":1},"minimax/minimax-m3":{"draws":3,"losses":6,"wins":13},"minimax/minimax-m3.1-flash":{"draws":3,"losses":15,"wins":12},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":1},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":13,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":29,"wins":2},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":8,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":6,"wins":8},"o3":{"draws":4,"losses":30,"wins":24},"openai/gpt-oss-120b":{"draws":12,"losses":3,"wins":17},"poolside/laguna-s-2.1":{"draws":8,"losses":18,"wins":10},"qwen/qwen3.7-max":{"draws":3,"losses":11,"wins":10},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":18,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":10,"wins":12},"qwen/qwen3.8-flash":{"draws":4,"losses":7,"wins":13},"qwen/qwen3.8-max":{"draws":9,"losses":13,"wins":14},"qwen/qwen3.8-max-0902":{"draws":13,"losses":16,"wins":7},"recursive/flint-v1.0":{"draws":3,"losses":3,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":13,"wins":11},"stealth/ox-alpha":{"draws":15,"losses":65,"wins":20},"stealth/space-bunny-alpha":{"draws":8,"losses":12,"wins":8},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":17},"stepfun/step-5-preview":{"draws":1,"losses":4,"wins":3},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":8},"tencent/hy4-preview":{"draws":3,"losses":21,"wins":10},"thinkingmachines/inkling":{"draws":9,"losses":6,"wins":31},"thinkingmachines/inkling-small":{"draws":9,"losses":8,"wins":19},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"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":11,"losses":21,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":26,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":16,"losses":9,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":16,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":18,"wins":4},"z-ai/glm-5.2":{"draws":14,"losses":32,"wins":26},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":5},"z-ai/glm-5.3-flash":{"draws":7,"losses":18,"wins":11},"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":16,"losses":14,"wins":14},"claude-fable-5":{"draws":11,"losses":33,"wins":4},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":23,"wins":8},"claude-opus-4-5":{"draws":31,"losses":30,"wins":17},"claude-opus-4-8":{"draws":16,"losses":20,"wins":8},"claude-opus-5":{"draws":13,"losses":59,"wins":10},"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":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":28,"losses":15,"wins":29},"deepseek/deepseek-v4-pro":{"draws":11,"losses":19,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":23,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":22,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":29,"wins":10},"elorian/glimpse":{"draws":8,"losses":10,"wins":8},"fireworks/ember-1":{"draws":22,"losses":22,"wins":4},"gemini-3.1-pro-preview":{"draws":13,"losses":18,"wins":17},"gemini-4-argon":{"draws":2,"losses":43,"wins":3},"google/gemini-3.1-flash-lite":{"draws":12,"losses":4,"wins":16},"google/gemini-3.5-flash":{"draws":18,"losses":26,"wins":16},"google/gemini-3.5-flash-lite":{"draws":31,"losses":19,"wins":34},"google/gemini-3.6-flash":{"draws":23,"losses":48,"wins":21},"google/gemini-3.8-flash":{"draws":8,"losses":31,"wins":9},"google/gemma-4-31b-it":{"draws":14,"losses":6,"wins":8},"gpt-4.1":{"draws":7,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":16,"losses":16,"wins":10},"gpt-5.4":{"draws":10,"losses":27,"wins":9},"gpt-5.4-mini":{"draws":11,"losses":7,"wins":14},"gpt-5.4-nano":{"draws":14,"losses":15,"wins":19},"gpt-5.5":{"draws":16,"losses":19,"wins":9},"gpt-5.6-luna":{"draws":25,"losses":10,"wins":13},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":6},"gpt-5.6-terra":{"draws":18,"losses":15,"wins":13},"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":4,"losses":39,"wins":5},"gpt-6.1-terra":{"draws":3,"losses":42,"wins":3},"gpt-6.1-terra-pro":{"draws":4,"losses":40,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":15},"inception/mercury-3":{"draws":11,"losses":17,"wins":4},"inclusionai/ling-3.0-flash":{"draws":16,"losses":2,"wins":16},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":15,"losses":13,"wins":24},"meta/muse-glimmer-30b":{"draws":21,"losses":2,"wins":19},"meta/muse-spark-1.2":{"draws":14,"losses":23,"wins":9},"meta/muse-spark-1.3":{"draws":14,"losses":29,"wins":5},"meta/muse-spark-open":{"draws":12,"losses":26,"wins":10},"meta/muse-wonder":{"draws":9,"losses":33,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"minimax/minimax-m3.1-flash":{"draws":16,"losses":12,"wins":14},"mistralai/mistral-large-4-0":{"draws":14,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":23,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":37,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":8,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":8,"wins":6},"o3":{"draws":12,"losses":29,"wins":25},"openai/gpt-oss-120b":{"draws":20,"losses":4,"wins":18},"poolside/laguna-s-2.1":{"draws":13,"losses":6,"wins":27},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":16,"wins":6},"qwen/qwen3.8-27b":{"draws":13,"losses":13,"wins":8},"qwen/qwen3.8-flash":{"draws":11,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":18,"losses":17,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":26,"wins":4},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":18,"wins":14},"stealth/ox-alpha":{"draws":50,"losses":73,"wins":35},"stealth/space-bunny-alpha":{"draws":17,"losses":12,"wins":9},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":7},"tencent/hy3-preview":{"draws":13,"losses":4,"wins":9},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":15},"thinkingmachines/inkling":{"draws":20,"losses":11,"wins":33},"thinkingmachines/inkling-small":{"draws":16,"losses":7,"wins":25},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":30,"wins":7},"x-ai/grok-4.6":{"draws":13,"losses":27,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":8},"x-ai/grok-build-0.1":{"draws":9,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":34,"losses":16,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":17,"wins":6},"z-ai/glm-5.2":{"draws":40,"losses":31,"wins":25},"z-ai/glm-5.3":{"draws":7,"losses":33,"wins":6},"z-ai/glm-5.3-flash":{"draws":7,"losses":36,"wins":5},"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":4,"losses":44,"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":13,"losses":12,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":19,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":23,"wins":13},"elorian/glimpse":{"draws":7,"losses":8,"wins":7},"fireworks/ember-1":{"draws":14,"losses":13,"wins":15},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"wins":17},"gemini-4-argon":{"draws":3,"losses":36,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":19},"google/gemini-3.5-flash":{"draws":13,"losses":25,"wins":14},"google/gemini-3.5-flash-lite":{"draws":19,"losses":19,"wins":36},"google/gemini-3.6-flash":{"draws":24,"losses":38,"wins":20},"google/gemini-3.8-flash":{"draws":7,"losses":28,"wins":7},"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":7,"losses":7,"wins":14},"gpt-5.4-nano":{"draws":10,"losses":10,"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":32,"wins":4},"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},"gpt-6.1-terra":{"draws":10,"losses":32,"wins":0},"gpt-6.1-terra-pro":{"draws":3,"losses":34,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":4,"wins":13},"inception/mercury-3":{"draws":11,"losses":7,"wins":8},"inclusionai/ling-3.0-flash":{"draws":8,"losses":5,"wins":15},"inclusionai/ling-3.1-flash":{"draws":5,"losses":0,"wins":5},"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":8,"losses":26,"wins":8},"meta/muse-spark-open":{"draws":15,"losses":16,"wins":9},"meta/muse-wonder":{"draws":10,"losses":27,"wins":5},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":13},"minimax/minimax-m3.1-flash":{"draws":13,"losses":11,"wins":16},"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":4,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":14,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":35,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":4,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":4,"wins":7},"o3":{"draws":7,"losses":20,"wins":29},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":16},"poolside/laguna-s-2.1":{"draws":15,"losses":9,"wins":14},"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},"recursive/flint-v1.0":{"draws":3,"losses":3,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":14,"wins":11},"stealth/ox-alpha":{"draws":40,"losses":60,"wins":42},"stealth/space-bunny-alpha":{"draws":12,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":8,"losses":10,"wins":12},"stepfun/step-5-preview":{"draws":3,"losses":8,"wins":3},"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":{"draws":1,"losses":13,"wins":0},"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":23,"losses":10,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":9},"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":33,"losses":28,"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":12,"losses":5,"wins":27},"claude-fable-5":{"draws":10,"losses":18,"wins":20},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":15,"losses":15,"wins":16},"claude-opus-4-5":{"draws":22,"losses":13,"wins":43},"claude-opus-4-8":{"draws":15,"losses":11,"wins":18},"claude-opus-5":{"draws":13,"losses":59,"wins":10},"claude-opus-5-5":{"draws":7,"losses":43,"wins":2},"claude-sonnet-5":{"draws":11,"losses":10,"wins":27},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":24},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":12},"deepseek/deepseek-v4-flash":{"draws":17,"losses":6,"wins":49},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":6,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":16,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":19,"wins":16},"elorian/glimpse":{"draws":6,"losses":7,"wins":13},"fireworks/ember-1":{"draws":13,"losses":10,"wins":25},"gemini-3.1-pro-preview":{"draws":13,"losses":11,"wins":24},"gemini-4-argon":{"draws":10,"losses":27,"wins":11},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":15,"losses":12,"wins":33},"google/gemini-3.5-flash-lite":{"draws":22,"losses":3,"wins":59},"google/gemini-3.6-flash":{"draws":19,"losses":28,"wins":45},"google/gemini-3.8-flash":{"draws":9,"losses":11,"wins":28},"google/gemma-4-31b-it":{"draws":14,"losses":1,"wins":13},"gpt-4.1":{"draws":3,"losses":2,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":9,"losses":4,"wins":29},"gpt-5.4":{"draws":10,"losses":17,"wins":19},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":20},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":32},"gpt-5.5":{"draws":13,"losses":16,"wins":15},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":28},"gpt-5.6-sol":{"draws":11,"losses":24,"wins":13},"gpt-5.6-terra":{"draws":14,"losses":10,"wins":22},"gpt-6-astra":{"draws":6,"losses":39,"wins":3},"gpt-6-luna":{"draws":12,"losses":11,"wins":25},"gpt-6-sol":{"draws":6,"losses":28,"wins":14},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":7},"gpt-6.1-terra":{"draws":5,"losses":33,"wins":10},"gpt-6.1-terra-pro":{"draws":4,"losses":35,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":0,"wins":21},"inception/mercury-3":{"draws":11,"losses":4,"wins":17},"inclusionai/ling-3.0-flash":{"draws":11,"losses":1,"wins":22},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":35},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":23},"meta/muse-spark-1.2":{"draws":10,"losses":14,"wins":22},"meta/muse-spark-1.3":{"draws":11,"losses":15,"wins":22},"meta/muse-spark-open":{"draws":12,"losses":10,"wins":26},"meta/muse-wonder":{"draws":13,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"minimax/minimax-m3.1-flash":{"draws":11,"losses":9,"wins":22},"mistralai/mistral-large-4-0":{"draws":11,"losses":3,"wins":16},"mistralai/mistral-medium-3-5":{"draws":8,"losses":1,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":8,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":33,"wins":12},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":0,"wins":15},"o3":{"draws":6,"losses":13,"wins":47},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":25},"poolside/laguna-s-2.1":{"draws":11,"losses":2,"wins":33},"qwen/qwen3.7-max":{"draws":5,"losses":2,"wins":21},"qwen/qwen3.7-plus":{"draws":5,"losses":5,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":12,"wins":27},"qwen/qwen3.8-27b":{"draws":9,"losses":6,"wins":19},"qwen/qwen3.8-flash":{"draws":7,"losses":0,"wins":9},"qwen/qwen3.8-max":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-max-0902":{"draws":14,"losses":11,"wins":23},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":9,"wins":26},"stealth/ox-alpha":{"draws":40,"losses":41,"wins":77},"stealth/space-bunny-alpha":{"draws":13,"losses":4,"wins":21},"stepfun/step-3.7-flash":{"draws":7,"losses":0,"wins":27},"stepfun/step-5-preview":{"draws":3,"losses":3,"wins":6},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":16},"tencent/hy4-preview":{"draws":13,"losses":11,"wins":22},"thinkingmachines/inkling":{"draws":18,"losses":7,"wins":39},"thinkingmachines/inkling-small":{"draws":16,"losses":6,"wins":26},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":5},"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":17,"losses":17,"wins":14},"x-ai/grok-4.7":{"draws":6,"losses":26,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":21,"losses":5,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":1,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":4,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":13,"wins":11},"z-ai/glm-5.2":{"draws":29,"losses":12,"wins":55},"z-ai/glm-5.3":{"draws":10,"losses":23,"wins":13},"z-ai/glm-5.3-flash":{"draws":6,"losses":14,"wins":28},"z-ai/glm-5.3-flashx":{"draws":10,"losses":16,"wins":22}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":10,"wins":20},"claude-fable-5":{"draws":5,"losses":31,"wins":12},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":7,"losses":27,"wins":12},"claude-opus-4-5":{"draws":24,"losses":17,"wins":37},"claude-opus-4-8":{"draws":10,"losses":22,"wins":12},"claude-opus-5":{"draws":15,"losses":59,"wins":8},"claude-opus-5-5":{"draws":5,"losses":42,"wins":5},"claude-sonnet-5":{"draws":15,"losses":12,"wins":21},"claude-sonnet-5-5":{"draws":9,"losses":27,"wins":12},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":19,"losses":12,"wins":41},"deepseek/deepseek-v4-pro":{"draws":14,"losses":13,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":17,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":29,"wins":7},"elorian/glimpse":{"draws":7,"losses":10,"wins":9},"fireworks/ember-1":{"draws":16,"losses":20,"wins":12},"gemini-3.1-pro-preview":{"draws":12,"losses":17,"wins":19},"gemini-4-argon":{"draws":0,"losses":46,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":14,"losses":22,"wins":24},"google/gemini-3.5-flash-lite":{"draws":23,"losses":18,"wins":43},"google/gemini-3.6-flash":{"draws":25,"losses":46,"wins":21},"google/gemini-3.8-flash":{"draws":11,"losses":20,"wins":17},"google/gemma-4-31b-it":{"draws":10,"losses":1,"wins":17},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":8,"wins":22},"gpt-5.4":{"draws":10,"losses":20,"wins":16},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":16},"gpt-5.4-nano":{"draws":10,"losses":12,"wins":26},"gpt-5.5":{"draws":15,"losses":18,"wins":11},"gpt-5.6-luna":{"draws":16,"losses":9,"wins":23},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":13},"gpt-5.6-terra":{"draws":17,"losses":16,"wins":13},"gpt-6-astra":{"draws":6,"losses":40,"wins":2},"gpt-6-luna":{"draws":14,"losses":13,"wins":21},"gpt-6-sol":{"draws":6,"losses":35,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":41,"wins":1},"gpt-6.1-terra":{"draws":5,"losses":40,"wins":3},"gpt-6.1-terra-pro":{"draws":6,"losses":38,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":3,"wins":17},"inception/mercury-3":{"draws":13,"losses":7,"wins":12},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":14},"inclusionai/ling-3.1-flash":{"draws":3,"losses":3,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":15,"wins":27},"meta/muse-glimmer-30b":{"draws":13,"losses":8,"wins":21},"meta/muse-spark-1.2":{"draws":13,"losses":12,"wins":21},"meta/muse-spark-1.3":{"draws":10,"losses":29,"wins":9},"meta/muse-spark-open":{"draws":15,"losses":20,"wins":13},"meta/muse-wonder":{"draws":11,"losses":29,"wins":8},"minimax/minimax-m3":{"draws":7,"losses":1,"wins":18},"minimax/minimax-m3.1-flash":{"draws":10,"losses":15,"wins":17},"mistralai/mistral-large-4-0":{"draws":10,"losses":10,"wins":10},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":15,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":41,"wins":4},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":9},"o3":{"draws":10,"losses":20,"wins":36},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":13,"losses":11,"wins":22},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":12},"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":10,"losses":15,"wins":9},"qwen/qwen3.8-flash":{"draws":12,"losses":12,"wins":8},"qwen/qwen3.8-max":{"draws":8,"losses":8,"wins":16},"qwen/qwen3.8-max-0902":{"draws":16,"losses":19,"wins":13},"recursive/flint-v1.0":{"draws":5,"losses":1,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":10,"wins":25},"stealth/ox-alpha":{"draws":33,"losses":64,"wins":61},"stealth/space-bunny-alpha":{"draws":14,"losses":10,"wins":14},"stepfun/step-3.7-flash":{"draws":7,"losses":5,"wins":22},"stepfun/step-5-preview":{"draws":1,"losses":4,"wins":5},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":11,"losses":20,"wins":15},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":36},"thinkingmachines/inkling-small":{"draws":11,"losses":15,"wins":22},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":5,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":24,"losses":14,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":7,"wins":13},"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":28,"losses":26,"wins":42},"z-ai/glm-5.3":{"draws":12,"losses":24,"wins":10},"z-ai/glm-5.3-flash":{"draws":10,"losses":22,"wins":16},"z-ai/glm-5.3-flashx":{"draws":10,"losses":23,"wins":15}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":13,"wins":23},"claude-fable-5":{"draws":8,"losses":35,"wins":5},"claude-fable-5-1":{"draws":4,"losses":48,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":20,"wins":11},"claude-opus-4-5":{"draws":22,"losses":41,"wins":15},"claude-opus-4-8":{"draws":11,"losses":24,"wins":9},"claude-opus-5":{"draws":15,"losses":58,"wins":9},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":10,"losses":17,"wins":21},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":18},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":19,"losses":19,"wins":34},"deepseek/deepseek-v4-pro":{"draws":12,"losses":18,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":21,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":28,"wins":9},"elorian/glimpse":{"draws":6,"losses":12,"wins":8},"fireworks/ember-1":{"draws":10,"losses":23,"wins":15},"gemini-3.1-pro-preview":{"draws":9,"losses":20,"wins":19},"gemini-4-argon":{"draws":2,"losses":42,"wins":4},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":15,"losses":25,"wins":20},"google/gemini-3.5-flash-lite":{"draws":26,"losses":24,"wins":34},"google/gemini-3.6-flash":{"draws":17,"losses":49,"wins":26},"google/gemini-3.8-flash":{"draws":13,"losses":28,"wins":7},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":12},"gpt-4.1":{"draws":3,"losses":7,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":17,"wins":16},"gpt-5.4":{"draws":7,"losses":26,"wins":13},"gpt-5.4-mini":{"draws":14,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":13,"losses":19,"wins":16},"gpt-5.5":{"draws":9,"losses":22,"wins":13},"gpt-5.6-luna":{"draws":14,"losses":15,"wins":19},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":16,"losses":14,"wins":16},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":12,"losses":25,"wins":11},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":42,"wins":2},"gpt-6.1-terra":{"draws":3,"losses":43,"wins":2},"gpt-6.1-terra-pro":{"draws":4,"losses":40,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":3,"wins":17},"inception/mercury-3":{"draws":9,"losses":16,"wins":9},"inclusionai/ling-3.0-flash":{"draws":11,"losses":5,"wins":18},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":16,"wins":31},"meta/muse-glimmer-30b":{"draws":13,"losses":8,"wins":21},"meta/muse-spark-1.2":{"draws":14,"losses":24,"wins":8},"meta/muse-spark-1.3":{"draws":13,"losses":25,"wins":10},"meta/muse-spark-open":{"draws":15,"losses":27,"wins":6},"meta/muse-wonder":{"draws":7,"losses":30,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":12},"minimax/minimax-m3.1-flash":{"draws":11,"losses":15,"wins":16},"mistralai/mistral-large-4-0":{"draws":12,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":43,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":10,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":10,"wins":4},"o3":{"draws":11,"losses":29,"wins":26},"openai/gpt-oss-120b":{"draws":10,"losses":9,"wins":23},"poolside/laguna-s-2.1":{"draws":16,"losses":14,"wins":16},"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":11,"losses":16,"wins":5},"qwen/qwen3.8-max":{"draws":13,"losses":20,"wins":15},"qwen/qwen3.8-max-0902":{"draws":8,"losses":19,"wins":5},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":18,"wins":13},"stealth/ox-alpha":{"draws":33,"losses":80,"wins":45},"stealth/space-bunny-alpha":{"draws":13,"losses":11,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":9,"wins":16},"stepfun/step-5-preview":{"draws":1,"losses":7,"wins":6},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":9,"losses":25,"wins":12},"thinkingmachines/inkling":{"draws":22,"losses":15,"wins":27},"thinkingmachines/inkling-small":{"draws":12,"losses":11,"wins":25},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":11,"losses":26,"wins":11},"x-ai/grok-4.7":{"draws":9,"losses":26,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":25,"losses":19,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":17,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":22,"wins":6},"z-ai/glm-5.2":{"draws":32,"losses":30,"wins":34},"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":11,"losses":25,"wins":12}},"recursive/flint-v1.0":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":21,"wins":9},"claude-fable-5":{"draws":3,"losses":39,"wins":0},"claude-fable-5-1":{"draws":2,"losses":44,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":25,"wins":8},"claude-opus-4-5":{"draws":18,"losses":47,"wins":5},"claude-opus-4-8":{"draws":11,"losses":29,"wins":2},"claude-opus-5":{"draws":7,"losses":62,"wins":1},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":12,"losses":27,"wins":3},"claude-sonnet-5-5":{"draws":7,"losses":31,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":7},"deepseek/deepseek-v4-flash":{"draws":12,"losses":36,"wins":16},"deepseek/deepseek-v4-pro":{"draws":8,"losses":21,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":22,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":27,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":35,"wins":1},"elorian/glimpse":{"draws":5,"losses":13,"wins":4},"fireworks/ember-1":{"draws":10,"losses":27,"wins":5},"gemini-3.1-pro-preview":{"draws":11,"losses":27,"wins":4},"gemini-4-argon":{"draws":3,"losses":39,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":12,"wins":12},"google/gemini-3.5-flash":{"draws":10,"losses":36,"wins":8},"google/gemini-3.5-flash-lite":{"draws":20,"losses":42,"wins":12},"google/gemini-3.6-flash":{"draws":26,"losses":45,"wins":9},"google/gemini-3.8-flash":{"draws":7,"losses":33,"wins":2},"google/gemma-4-31b-it":{"draws":7,"losses":12,"wins":7},"gpt-4.1":{"draws":4,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":5,"losses":21,"wins":10},"gpt-5.4":{"draws":6,"losses":30,"wins":4},"gpt-5.4-mini":{"draws":8,"losses":12,"wins":8},"gpt-5.4-nano":{"draws":10,"losses":19,"wins":17},"gpt-5.5":{"draws":11,"losses":25,"wins":2},"gpt-5.6-luna":{"draws":9,"losses":23,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":38,"wins":1},"gpt-5.6-terra":{"draws":10,"losses":28,"wins":2},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":11,"losses":26,"wins":5},"gpt-6-sol":{"draws":5,"losses":35,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"gpt-6.1-terra":{"draws":1,"losses":41,"wins":0},"gpt-6.1-terra-pro":{"draws":2,"losses":37,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":8,"wins":12},"inception/mercury-3":{"draws":8,"losses":14,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":8,"wins":14},"inclusionai/ling-3.1-flash":{"draws":4,"losses":8,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":22,"wins":13},"meta/muse-glimmer-30b":{"draws":11,"losses":17,"wins":8},"meta/muse-spark-1.2":{"draws":7,"losses":30,"wins":3},"meta/muse-spark-1.3":{"draws":4,"losses":34,"wins":4},"meta/muse-spark-open":{"draws":6,"losses":33,"wins":3},"meta/muse-wonder":{"draws":6,"losses":36,"wins":0},"minimax/minimax-m3":{"draws":7,"losses":9,"wins":8},"minimax/minimax-m3.1-flash":{"draws":10,"losses":19,"wins":7},"mistralai/mistral-large-4-0":{"draws":6,"losses":17,"wins":3},"mistralai/mistral-medium-3-5":{"draws":8,"losses":8,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":27,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":35,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":8,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":14,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":13,"wins":1},"o3":{"draws":4,"losses":52,"wins":6},"openai/gpt-oss-120b":{"draws":8,"losses":19,"wins":9},"poolside/laguna-s-2.1":{"draws":7,"losses":24,"wins":7},"qwen/qwen3.7-max":{"draws":5,"losses":13,"wins":8},"qwen/qwen3.7-plus":{"draws":7,"losses":9,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":28,"wins":2},"qwen/qwen3.8-27b":{"draws":5,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":17,"wins":3},"qwen/qwen3.8-max":{"draws":10,"losses":26,"wins":6},"qwen/qwen3.8-max-0902":{"draws":9,"losses":27,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":29,"wins":1},"stealth/ox-alpha":{"draws":23,"losses":85,"wins":10},"stealth/space-bunny-alpha":{"draws":9,"losses":15,"wins":10},"stepfun/step-3.7-flash":{"draws":3,"losses":16,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":11,"wins":5},"tencent/hy4-preview":{"draws":9,"losses":27,"wins":4},"thinkingmachines/inkling":{"draws":16,"losses":24,"wins":14},"thinkingmachines/inkling-small":{"draws":12,"losses":14,"wins":16},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":12,"losses":30,"wins":0},"x-ai/grok-4.6":{"draws":7,"losses":30,"wins":5},"x-ai/grok-4.7":{"draws":2,"losses":35,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":11,"wins":0},"xiaomi/mimo-v2.5":{"draws":20,"losses":31,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":20,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":20,"wins":2},"z-ai/glm-5.2":{"draws":17,"losses":49,"wins":18},"z-ai/glm-5.3":{"draws":7,"losses":31,"wins":2},"z-ai/glm-5.3-flash":{"draws":9,"losses":24,"wins":9},"z-ai/glm-5.3-flashx":{"draws":10,"losses":29,"wins":3}},"reflection/beam-1.0-501b-a23b":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":17},"claude-fable-5":{"draws":8,"losses":29,"wins":5},"claude-fable-5-1":{"draws":1,"losses":47,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":24,"wins":9},"claude-opus-4-5":{"draws":21,"losses":30,"wins":17},"claude-opus-4-8":{"draws":6,"losses":25,"wins":7},"claude-opus-5":{"draws":8,"losses":59,"wins":3},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":10,"losses":21,"wins":11},"claude-sonnet-5-5":{"draws":10,"losses":22,"wins":10},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":14},"deepseek/deepseek-v4-flash":{"draws":15,"losses":15,"wins":32},"deepseek/deepseek-v4-pro":{"draws":8,"losses":20,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":17,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":22,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":28,"wins":6},"elorian/glimpse":{"draws":7,"losses":11,"wins":4},"fireworks/ember-1":{"draws":12,"losses":18,"wins":12},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"wins":17},"gemini-4-argon":{"draws":3,"losses":36,"wins":3},"google/gemini-3.1-flash-lite":{"draws":3,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":14,"losses":19,"wins":19},"google/gemini-3.5-flash-lite":{"draws":22,"losses":14,"wins":38},"google/gemini-3.6-flash":{"draws":17,"losses":42,"wins":21},"google/gemini-3.8-flash":{"draws":9,"losses":27,"wins":6},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":19},"gpt-4.1":{"draws":4,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":13,"wins":14},"gpt-5.4":{"draws":12,"losses":19,"wins":9},"gpt-5.4-mini":{"draws":9,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":7,"losses":16,"wins":17},"gpt-5.5":{"draws":7,"losses":21,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":12,"wins":15},"gpt-5.6-sol":{"draws":8,"losses":30,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":11,"wins":15},"gpt-6-astra":{"draws":2,"losses":39,"wins":1},"gpt-6-luna":{"draws":7,"losses":24,"wins":11},"gpt-6-sol":{"draws":5,"losses":35,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":39,"wins":1},"gpt-6.1-terra":{"draws":3,"losses":38,"wins":1},"gpt-6.1-terra-pro":{"draws":2,"losses":40,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":1,"wins":18},"inception/mercury-3":{"draws":5,"losses":17,"wins":6},"inclusionai/ling-3.0-flash":{"draws":7,"losses":6,"wins":15},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":31},"meta/muse-glimmer-30b":{"draws":14,"losses":6,"wins":16},"meta/muse-spark-1.2":{"draws":10,"losses":23,"wins":7},"meta/muse-spark-1.3":{"draws":9,"losses":25,"wins":8},"meta/muse-spark-open":{"draws":7,"losses":31,"wins":2},"meta/muse-wonder":{"draws":6,"losses":31,"wins":5},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":12},"minimax/minimax-m3.1-flash":{"draws":9,"losses":16,"wins":11},"mistralai/mistral-large-4-0":{"draws":10,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":5,"losses":5,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":21,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":35,"wins":5},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":8,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":6},"o3":{"draws":6,"losses":21,"wins":29},"openai/gpt-oss-120b":{"draws":13,"losses":3,"wins":22},"poolside/laguna-s-2.1":{"draws":7,"losses":13,"wins":20},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":7,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":25,"wins":8},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.8-flash":{"draws":6,"losses":15,"wins":7},"qwen/qwen3.8-max":{"draws":6,"losses":33,"wins":3},"qwen/qwen3.8-max-0902":{"draws":8,"losses":26,"wins":8},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":10,"wins":9},"stealth/ox-alpha":{"draws":30,"losses":77,"wins":35},"stealth/space-bunny-alpha":{"draws":9,"losses":12,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":15,"wins":6},"stepfun/step-5-preview":{"draws":3,"losses":8,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":12},"tencent/hy4-preview":{"draws":13,"losses":19,"wins":8},"thinkingmachines/inkling":{"draws":14,"losses":14,"wins":26},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":18},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":13,"losses":21,"wins":8},"x-ai/grok-4.6":{"draws":12,"losses":23,"wins":7},"x-ai/grok-4.7":{"draws":2,"losses":34,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":19,"losses":12,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":17,"wins":8},"z-ai/glm-5.2":{"draws":32,"losses":31,"wins":21},"z-ai/glm-5.3":{"draws":4,"losses":35,"wins":3},"z-ai/glm-5.3-flash":{"draws":5,"losses":25,"wins":12},"z-ai/glm-5.3-flashx":{"draws":8,"losses":26,"wins":8}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":33,"wins":81},"claude-fable-5":{"draws":27,"losses":92,"wins":37},"claude-fable-5-1":{"draws":7,"losses":167,"wins":8},"claude-haiku-5-5":{"draws":32,"losses":59,"wins":51},"claude-opus-4-5":{"draws":67,"losses":77,"wins":102},"claude-opus-4-8":{"draws":28,"losses":51,"wins":49},"claude-opus-5":{"draws":49,"losses":188,"wins":43},"claude-opus-5-5":{"draws":20,"losses":142,"wins":6},"claude-sonnet-5":{"draws":36,"losses":43,"wins":77},"claude-sonnet-5-5":{"draws":32,"losses":76,"wins":48},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":47},"deepseek/deepseek-v4-flash":{"draws":51,"losses":49,"wins":128},"deepseek/deepseek-v4-pro":{"draws":32,"losses":45,"wins":69},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":50,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":64,"wins":57},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":83,"wins":47},"elorian/glimpse":{"draws":20,"losses":30,"wins":38},"fireworks/ember-1":{"draws":34,"losses":64,"wins":58},"gemini-3.1-pro-preview":{"draws":36,"losses":48,"wins":72},"gemini-4-argon":{"draws":16,"losses":125,"wins":15},"google/gemini-3.1-flash-lite":{"draws":19,"losses":13,"wins":54},"google/gemini-3.5-flash":{"draws":33,"losses":66,"wins":89},"google/gemini-3.5-flash-lite":{"draws":58,"losses":58,"wins":154},"google/gemini-3.6-flash":{"draws":72,"losses":125,"wins":103},"google/gemini-3.8-flash":{"draws":34,"losses":73,"wins":49},"google/gemma-4-31b-it":{"draws":18,"losses":17,"wins":51},"gpt-4.1":{"draws":10,"losses":9,"wins":33},"gpt-4.1-nano":{"draws":13,"losses":1,"wins":10},"gpt-5":{"draws":28,"losses":45,"wins":67},"gpt-5.4":{"draws":36,"losses":59,"wins":55},"gpt-5.4-mini":{"draws":28,"losses":17,"wins":59},"gpt-5.4-nano":{"draws":26,"losses":35,"wins":75},"gpt-5.5":{"draws":36,"losses":56,"wins":54},"gpt-5.6-luna":{"draws":49,"losses":31,"wins":76},"gpt-5.6-sol":{"draws":23,"losses":103,"wins":30},"gpt-5.6-terra":{"draws":37,"losses":39,"wins":74},"gpt-6-astra":{"draws":9,"losses":141,"wins":6},"gpt-6-luna":{"draws":36,"losses":58,"wins":62},"gpt-6-sol":{"draws":23,"losses":115,"wins":18},"gpt-6.1-sol":{"draws":14,"losses":133,"wins":9},"gpt-6.1-terra":{"draws":25,"losses":118,"wins":13},"gpt-6.1-terra-pro":{"draws":18,"losses":130,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":32,"losses":11,"wins":59},"inception/mercury-3":{"draws":29,"losses":34,"wins":43},"inclusionai/ling-3.0-flash":{"draws":26,"losses":9,"wins":71},"inclusionai/ling-3.1-flash":{"draws":8,"losses":8,"wins":10},"meituan/longcat-2.0":{"draws":29,"losses":26,"wins":113},"meta/muse-glimmer-30b":{"draws":27,"losses":21,"wins":94},"meta/muse-spark-1.2":{"draws":36,"losses":55,"wins":61},"meta/muse-spark-1.3":{"draws":37,"losses":69,"wins":50},"meta/muse-spark-open":{"draws":37,"losses":76,"wins":43},"meta/muse-wonder":{"draws":38,"losses":75,"wins":43},"minimax/minimax-m3":{"draws":17,"losses":16,"wins":47},"minimax/minimax-m3.1-flash":{"draws":27,"losses":42,"wins":69},"mistralai/mistral-large-4-0":{"draws":32,"losses":25,"wins":43},"mistralai/mistral-medium-3-5":{"draws":17,"losses":20,"wins":57},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":39,"losses":63,"wins":50},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":116,"wins":21},"nex-agi/nex-n2-pro":{"draws":15,"losses":14,"wins":55},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":9,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":13,"wins":65},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":19,"wins":32},"o3":{"draws":24,"losses":71,"wins":97},"openai/gpt-oss-120b":{"draws":28,"losses":25,"wins":89},"poolside/laguna-s-2.1":{"draws":31,"losses":30,"wins":99},"qwen/qwen3.7-max":{"draws":22,"losses":22,"wins":40},"qwen/qwen3.7-plus":{"draws":14,"losses":10,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":42,"losses":64,"wins":50},"qwen/qwen3.8-27b":{"draws":22,"losses":40,"wins":44},"qwen/qwen3.8-flash":{"draws":27,"losses":36,"wins":41},"qwen/qwen3.8-max":{"draws":45,"losses":53,"wins":58},"qwen/qwen3.8-max-0902":{"draws":27,"losses":71,"wins":58},"recursive/flint-v1.0":{"draws":8,"losses":4,"wins":26},"reflection/beam-1.0-501b-a23b":{"draws":28,"losses":50,"wins":70},"stealth/ox-alpha":{"draws":93,"losses":249,"wins":208},"stealth/space-bunny-alpha":{"draws":31,"losses":30,"wins":61},"stepfun/step-3.7-flash":{"draws":14,"losses":23,"wins":69},"stepfun/step-5-preview":{"draws":6,"losses":16,"wins":16},"tencent/hy3-preview":{"draws":23,"losses":12,"wins":45},"tencent/hy4-preview":{"draws":30,"losses":67,"wins":53},"thinkingmachines/inkling":{"draws":52,"losses":46,"wins":118},"thinkingmachines/inkling-small":{"draws":38,"losses":37,"wins":81},"unbiased/pareto-26.10":{"draws":5,"losses":45,"wins":2},"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":36,"losses":72,"wins":48},"x-ai/grok-4.6":{"draws":40,"losses":64,"wins":52},"x-ai/grok-4.7":{"draws":16,"losses":98,"wins":18},"x-ai/grok-build-0.1":{"draws":11,"losses":6,"wins":35},"xiaomi/mimo-v2.5":{"draws":54,"losses":32,"wins":122},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":22,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":35,"wins":44},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":51,"wins":37},"z-ai/glm-5.2":{"draws":77,"losses":82,"wins":153},"z-ai/glm-5.3":{"draws":30,"losses":88,"wins":34},"z-ai/glm-5.3-flash":{"draws":27,"losses":77,"wins":52},"z-ai/glm-5.3-flashx":{"draws":25,"losses":78,"wins":53}},"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":0,"losses":48,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":20,"wins":8},"claude-opus-4-5":{"draws":21,"losses":23,"wins":24},"claude-opus-4-8":{"draws":10,"losses":23,"wins":5},"claude-opus-5":{"draws":9,"losses":56,"wins":5},"claude-opus-5-5":{"draws":1,"losses":40,"wins":1},"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":19,"wins":26},"deepseek/deepseek-v4-pro":{"draws":10,"losses":18,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":18,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":24,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":26,"wins":6},"elorian/glimpse":{"draws":5,"losses":10,"wins":7},"fireworks/ember-1":{"draws":14,"losses":20,"wins":8},"gemini-3.1-pro-preview":{"draws":12,"losses":19,"wins":11},"gemini-4-argon":{"draws":5,"losses":37,"wins":0},"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":17,"losses":28,"wins":29},"google/gemini-3.6-flash":{"draws":22,"losses":44,"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":12,"losses":22,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":6,"losses":18,"wins":16},"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":21,"wins":4},"gpt-6-sol":{"draws":9,"losses":30,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":2},"gpt-6.1-terra":{"draws":4,"losses":38,"wins":0},"gpt-6.1-terra-pro":{"draws":7,"losses":33,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":4,"wins":16},"inception/mercury-3":{"draws":9,"losses":10,"wins":7},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":14},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":2},"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":12,"losses":20,"wins":8},"meta/muse-spark-1.3":{"draws":6,"losses":32,"wins":4},"meta/muse-spark-open":{"draws":12,"losses":19,"wins":11},"meta/muse-wonder":{"draws":14,"losses":21,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":12},"minimax/minimax-m3.1-flash":{"draws":9,"losses":14,"wins":17},"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":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":13,"losses":19,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":36,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":8,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":14,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":8,"wins":3},"o3":{"draws":6,"losses":26,"wins":24},"openai/gpt-oss-120b":{"draws":11,"losses":12,"wins":13},"poolside/laguna-s-2.1":{"draws":9,"losses":14,"wins":15},"qwen/qwen3.7-max":{"draws":5,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":15,"wins":8},"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":15,"losses":15,"wins":12},"qwen/qwen3.8-max-0902":{"draws":12,"losses":22,"wins":8},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":19,"wins":6},"stealth/ox-alpha":{"draws":31,"losses":76,"wins":35},"stealth/space-bunny-alpha":{"draws":7,"losses":11,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":9,"wins":16},"stepfun/step-5-preview":{"draws":3,"losses":3,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":8},"tencent/hy4-preview":{"draws":10,"losses":22,"wins":8},"thinkingmachines/inkling":{"draws":19,"losses":19,"wins":20},"thinkingmachines/inkling-small":{"draws":12,"losses":13,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":19,"wins":11},"x-ai/grok-4.6":{"draws":14,"losses":23,"wins":5},"x-ai/grok-4.7":{"draws":5,"losses":26,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":23,"losses":17,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"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":32,"losses":28,"wins":24},"z-ai/glm-5.3":{"draws":10,"losses":28,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":26,"wins":9},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":30,"wins":5},"elorian/glimpse":{"draws":0,"losses":16,"wins":4},"fireworks/ember-1":{"draws":5,"losses":22,"wins":9},"gemini-3.1-pro-preview":{"draws":4,"losses":19,"wins":13},"gemini-4-argon":{"draws":0,"losses":34,"wins":2},"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":24,"wins":27},"google/gemini-3.6-flash":{"draws":10,"losses":44,"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":7,"losses":8,"wins":9},"gpt-5.4-nano":{"draws":6,"losses":21,"wins":13},"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},"gpt-6.1-terra":{"draws":3,"losses":33,"wins":0},"gpt-6.1-terra-pro":{"draws":2,"losses":34,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":7,"wins":11},"inception/mercury-3":{"draws":4,"losses":12,"wins":8},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":3,"wins":1},"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-spark-open":{"draws":1,"losses":29,"wins":6},"meta/muse-wonder":{"draws":1,"losses":32,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":8},"minimax/minimax-m3.1-flash":{"draws":1,"losses":18,"wins":13},"mistralai/mistral-large-4-0":{"draws":6,"losses":12,"wins":4},"mistralai/mistral-medium-3-5":{"draws":5,"losses":6,"wins":9},"moonshotai/kimi-k3":{"draws":9,"losses":20,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":35,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":11,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":11,"wins":4},"o3":{"draws":10,"losses":32,"wins":18},"openai/gpt-oss-120b":{"draws":10,"losses":9,"wins":13},"poolside/laguna-s-2.1":{"draws":13,"losses":13,"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},"recursive/flint-v1.0":{"draws":0,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":16,"wins":14},"stealth/ox-alpha":{"draws":17,"losses":87,"wins":20},"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":0,"losses":7,"wins":1},"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":{"draws":0,"losses":12,"wins":0},"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":4,"losses":6,"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}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":6,"wins":25},"claude-fable-5":{"draws":3,"losses":30,"wins":9},"claude-fable-5-1":{"draws":1,"losses":43,"wins":4},"claude-haiku-5-5":{"draws":5,"losses":13,"wins":22},"claude-opus-4-5":{"draws":13,"losses":15,"wins":40},"claude-opus-4-8":{"draws":7,"losses":14,"wins":17},"claude-opus-5":{"draws":2,"losses":55,"wins":13},"claude-opus-5-5":{"draws":3,"losses":35,"wins":8},"claude-sonnet-5":{"draws":11,"losses":13,"wins":18},"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":12,"wins":39},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":23,"wins":12},"elorian/glimpse":{"draws":6,"losses":10,"wins":8},"fireworks/ember-1":{"draws":8,"losses":16,"wins":18},"gemini-3.1-pro-preview":{"draws":7,"losses":10,"wins":25},"gemini-4-argon":{"draws":9,"losses":23,"wins":10},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":7,"losses":16,"wins":31},"google/gemini-3.5-flash-lite":{"draws":15,"losses":13,"wins":48},"google/gemini-3.6-flash":{"draws":8,"losses":40,"wins":34},"google/gemini-3.8-flash":{"draws":9,"losses":14,"wins":19},"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":7,"wins":33},"gpt-5.5":{"draws":9,"losses":14,"wins":17},"gpt-5.6-luna":{"draws":7,"losses":11,"wins":24},"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":37,"wins":3},"gpt-6-luna":{"draws":8,"losses":10,"wins":24},"gpt-6-sol":{"draws":2,"losses":32,"wins":8},"gpt-6.1-sol":{"draws":0,"losses":38,"wins":4},"gpt-6.1-terra":{"draws":4,"losses":31,"wins":7},"gpt-6.1-terra-pro":{"draws":2,"losses":35,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":3,"wins":18},"inception/mercury-3":{"draws":5,"losses":5,"wins":16},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":6},"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":7,"losses":13,"wins":20},"meta/muse-spark-1.3":{"draws":3,"losses":17,"wins":22},"meta/muse-spark-open":{"draws":9,"losses":21,"wins":12},"meta/muse-wonder":{"draws":6,"losses":20,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":17},"minimax/minimax-m3.1-flash":{"draws":8,"losses":10,"wins":20},"mistralai/mistral-large-4-0":{"draws":2,"losses":12,"wins":12},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":18,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":30,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":3,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":3,"wins":12},"o3":{"draws":5,"losses":14,"wins":45},"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":0,"losses":7,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":18},"qwen/qwen3.8-27b":{"draws":6,"losses":9,"wins":15},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.8-max":{"draws":6,"losses":19,"wins":17},"qwen/qwen3.8-max-0902":{"draws":6,"losses":17,"wins":19},"recursive/flint-v1.0":{"draws":1,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":7,"wins":22},"stealth/ox-alpha":{"draws":31,"losses":55,"wins":56},"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":8,"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":6,"wins":39},"thinkingmachines/inkling-small":{"draws":10,"losses":3,"wins":29},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":18,"wins":14},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":9,"losses":8,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":15},"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":21,"wins":45},"z-ai/glm-5.3":{"draws":4,"losses":28,"wins":8},"z-ai/glm-5.3-flash":{"draws":2,"losses":21,"wins":19},"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":9,"losses":20,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":25,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":26,"wins":1},"elorian/glimpse":{"draws":5,"losses":10,"wins":5},"fireworks/ember-1":{"draws":8,"losses":27,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":21,"wins":7},"gemini-4-argon":{"draws":4,"losses":29,"wins":3},"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":17,"losses":31,"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},"gpt-6.1-terra":{"draws":5,"losses":31,"wins":0},"gpt-6.1-terra-pro":{"draws":4,"losses":32,"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},"inception/mercury-3":{"draws":7,"losses":12,"wins":1},"inclusionai/ling-3.0-flash":{"draws":9,"losses":5,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":5,"wins":1},"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":8,"losses":22,"wins":4},"meta/muse-spark-1.3":{"draws":4,"losses":31,"wins":1},"meta/muse-spark-open":{"draws":8,"losses":27,"wins":1},"meta/muse-wonder":{"draws":8,"losses":27,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":8},"minimax/minimax-m3.1-flash":{"draws":12,"losses":20,"wins":4},"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":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":22,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":30,"wins":1},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":14,"wins":5},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":10,"wins":1},"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},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":19,"wins":3},"stealth/ox-alpha":{"draws":34,"losses":78,"wins":14},"stealth/space-bunny-alpha":{"draws":10,"losses":15,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":17,"wins":4},"stepfun/step-5-preview":{"draws":0,"losses":8,"wins":0},"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":{"draws":0,"losses":12,"wins":0},"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":9,"losses":26,"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":2,"losses":9,"wins":3},"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":12,"losses":20,"wins":12},"claude-fable-5":{"draws":10,"losses":34,"wins":4},"claude-fable-5-1":{"draws":5,"losses":49,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":33,"wins":3},"claude-opus-4-5":{"draws":21,"losses":50,"wins":7},"claude-opus-4-8":{"draws":12,"losses":28,"wins":4},"claude-opus-5":{"draws":15,"losses":61,"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":10,"losses":32,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":29,"losses":29,"wins":14},"deepseek/deepseek-v4-pro":{"draws":9,"losses":29,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":25,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":24,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":33,"wins":7},"elorian/glimpse":{"draws":5,"losses":17,"wins":4},"fireworks/ember-1":{"draws":14,"losses":28,"wins":6},"gemini-3.1-pro-preview":{"draws":13,"losses":29,"wins":6},"gemini-4-argon":{"draws":4,"losses":41,"wins":3},"google/gemini-3.1-flash-lite":{"draws":9,"losses":11,"wins":12},"google/gemini-3.5-flash":{"draws":11,"losses":36,"wins":13},"google/gemini-3.5-flash-lite":{"draws":26,"losses":42,"wins":16},"google/gemini-3.6-flash":{"draws":22,"losses":57,"wins":13},"google/gemini-3.8-flash":{"draws":11,"losses":29,"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":11,"losses":23,"wins":8},"gpt-5.4":{"draws":14,"losses":27,"wins":5},"gpt-5.4-mini":{"draws":12,"losses":11,"wins":9},"gpt-5.4-nano":{"draws":10,"losses":29,"wins":9},"gpt-5.5":{"draws":12,"losses":22,"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":12,"losses":25,"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},"gpt-6.1-terra":{"draws":5,"losses":43,"wins":0},"gpt-6.1-terra-pro":{"draws":4,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":10,"wins":10},"inception/mercury-3":{"draws":8,"losses":20,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":10,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":3,"wins":1},"meituan/longcat-2.0":{"draws":12,"losses":24,"wins":16},"meta/muse-glimmer-30b":{"draws":14,"losses":20,"wins":8},"meta/muse-spark-1.2":{"draws":12,"losses":26,"wins":8},"meta/muse-spark-1.3":{"draws":8,"losses":35,"wins":5},"meta/muse-spark-open":{"draws":10,"losses":33,"wins":5},"meta/muse-wonder":{"draws":10,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":16,"wins":4},"minimax/minimax-m3.1-flash":{"draws":9,"losses":21,"wins":12},"mistralai/mistral-large-4-0":{"draws":10,"losses":15,"wins":5},"mistralai/mistral-medium-3-5":{"draws":10,"losses":9,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":27,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":43,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":8,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":20,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":12,"wins":3},"o3":{"draws":10,"losses":45,"wins":11},"openai/gpt-oss-120b":{"draws":14,"losses":20,"wins":8},"poolside/laguna-s-2.1":{"draws":10,"losses":30,"wins":6},"qwen/qwen3.7-max":{"draws":8,"losses":13,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":10,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":32,"wins":5},"qwen/qwen3.8-27b":{"draws":8,"losses":22,"wins":4},"qwen/qwen3.8-flash":{"draws":8,"losses":18,"wins":6},"qwen/qwen3.8-max":{"draws":12,"losses":28,"wins":8},"qwen/qwen3.8-max-0902":{"draws":14,"losses":28,"wins":6},"recursive/flint-v1.0":{"draws":4,"losses":6,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":22,"wins":8},"stealth/ox-alpha":{"draws":41,"losses":94,"wins":23},"stealth/space-bunny-alpha":{"draws":12,"losses":17,"wins":9},"stepfun/step-3.7-flash":{"draws":10,"losses":15,"wins":9},"stepfun/step-5-preview":{"draws":3,"losses":9,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":13,"wins":3},"tencent/hy4-preview":{"draws":10,"losses":31,"wins":5},"thinkingmachines/inkling":{"draws":20,"losses":32,"wins":12},"thinkingmachines/inkling-small":{"draws":10,"losses":14,"wins":8},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":11,"losses":32,"wins":5},"x-ai/grok-4.7":{"draws":3,"losses":39,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":8,"wins":5},"xiaomi/mimo-v2.5":{"draws":27,"losses":28,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":16,"wins":7},"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":28,"losses":51,"wins":17},"z-ai/glm-5.3":{"draws":7,"losses":34,"wins":5},"z-ai/glm-5.3-flash":{"draws":8,"losses":34,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":32,"wins":6}},"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":1,"losses":11,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":10,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":12,"wins":0},"elorian/glimpse":{"draws":0,"losses":4,"wins":2},"fireworks/ember-1":{"draws":0,"losses":11,"wins":1},"gemini-3.1-pro-preview":{"draws":2,"losses":7,"wins":3},"gemini-4-argon":{"draws":0,"losses":12,"wins":0},"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},"gpt-6.1-terra":{"draws":0,"losses":12,"wins":0},"gpt-6.1-terra-pro":{"draws":0,"losses":12,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":4,"wins":4},"inception/mercury-3":{"draws":0,"losses":8,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":4},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"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-spark-open":{"draws":0,"losses":12,"wins":0},"meta/muse-wonder":{"draws":0,"losses":12,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":2},"minimax/minimax-m3.1-flash":{"draws":0,"losses":10,"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":2,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":8,"wins":2},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":12,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":4,"wins":0},"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},"recursive/flint-v1.0":{"draws":0,"losses":2,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":7,"wins":1},"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":{"draws":0,"losses":4,"wins":0},"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":5,"wins":3},"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":9,"losses":24,"wins":15},"claude-fable-5-1":{"draws":5,"losses":46,"wins":3},"claude-haiku-5-5":{"draws":9,"losses":17,"wins":20},"claude-opus-4-5":{"draws":19,"losses":18,"wins":41},"claude-opus-4-8":{"draws":8,"losses":15,"wins":21},"claude-opus-5":{"draws":13,"losses":52,"wins":17},"claude-opus-5-5":{"draws":5,"losses":40,"wins":7},"claude-sonnet-5":{"draws":12,"losses":10,"wins":26},"claude-sonnet-5-5":{"draws":9,"losses":22,"wins":17},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":16},"deepseek/deepseek-v4-flash":{"draws":11,"losses":9,"wins":52},"deepseek/deepseek-v4-pro":{"draws":9,"losses":10,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":14,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":13,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":20,"wins":17},"elorian/glimpse":{"draws":5,"losses":9,"wins":12},"fireworks/ember-1":{"draws":11,"losses":15,"wins":22},"gemini-3.1-pro-preview":{"draws":9,"losses":13,"wins":26},"gemini-4-argon":{"draws":4,"losses":38,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":10,"losses":20,"wins":30},"google/gemini-3.5-flash-lite":{"draws":17,"losses":13,"wins":54},"google/gemini-3.6-flash":{"draws":23,"losses":30,"wins":39},"google/gemini-3.8-flash":{"draws":8,"losses":16,"wins":24},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":19},"gpt-4.1":{"draws":5,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":7,"wins":27},"gpt-5.4":{"draws":13,"losses":17,"wins":16},"gpt-5.4-mini":{"draws":10,"losses":4,"wins":18},"gpt-5.4-nano":{"draws":10,"losses":11,"wins":27},"gpt-5.5":{"draws":13,"losses":9,"wins":22},"gpt-5.6-luna":{"draws":14,"losses":9,"wins":25},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":13},"gpt-5.6-terra":{"draws":14,"losses":9,"wins":23},"gpt-6-astra":{"draws":5,"losses":38,"wins":5},"gpt-6-luna":{"draws":10,"losses":15,"wins":23},"gpt-6-sol":{"draws":7,"losses":33,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":40,"wins":5},"gpt-6.1-terra":{"draws":9,"losses":33,"wins":6},"gpt-6.1-terra-pro":{"draws":6,"losses":34,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":21},"inception/mercury-3":{"draws":10,"losses":6,"wins":16},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"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":10,"losses":10,"wins":26},"meta/muse-spark-1.3":{"draws":10,"losses":16,"wins":22},"meta/muse-spark-open":{"draws":9,"losses":16,"wins":23},"meta/muse-wonder":{"draws":9,"losses":25,"wins":14},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":23},"minimax/minimax-m3.1-flash":{"draws":11,"losses":8,"wins":23},"mistralai/mistral-large-4-0":{"draws":6,"losses":9,"wins":15},"mistralai/mistral-medium-3-5":{"draws":5,"losses":0,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":13,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":30,"wins":9},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":3,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":12},"o3":{"draws":7,"losses":17,"wins":42},"openai/gpt-oss-120b":{"draws":12,"losses":3,"wins":27},"poolside/laguna-s-2.1":{"draws":10,"losses":6,"wins":30},"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":15,"wins":23},"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":14,"wins":26},"qwen/qwen3.8-max-0902":{"draws":10,"losses":15,"wins":23},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":5,"wins":26},"stealth/ox-alpha":{"draws":30,"losses":45,"wins":83},"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":2,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":18},"tencent/hy4-preview":{"draws":10,"losses":14,"wins":22},"thinkingmachines/inkling":{"draws":20,"losses":5,"wins":39},"thinkingmachines/inkling-small":{"draws":16,"losses":5,"wins":27},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":8,"losses":7,"wins":17},"x-ai/grok-4.6":{"draws":16,"losses":16,"wins":16},"x-ai/grok-4.7":{"draws":6,"losses":24,"wins":12},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":20,"losses":5,"wins":49},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":12,"wins":15},"z-ai/glm-5.2":{"draws":24,"losses":15,"wins":57},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":27},"z-ai/glm-5.3-flashx":{"draws":8,"losses":18,"wins":22}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":3,"wins":36},"claude-fable-5":{"draws":7,"losses":17,"wins":24},"claude-fable-5-1":{"draws":4,"losses":42,"wins":8},"claude-haiku-5-5":{"draws":7,"losses":10,"wins":29},"claude-opus-4-5":{"draws":15,"losses":15,"wins":48},"claude-opus-4-8":{"draws":10,"losses":11,"wins":23},"claude-opus-5":{"draws":11,"losses":50,"wins":21},"claude-opus-5-5":{"draws":7,"losses":37,"wins":8},"claude-sonnet-5":{"draws":10,"losses":8,"wins":30},"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":5,"wins":56},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":4,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":13,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":12,"wins":22},"elorian/glimpse":{"draws":7,"losses":6,"wins":13},"fireworks/ember-1":{"draws":8,"losses":7,"wins":33},"gemini-3.1-pro-preview":{"draws":11,"losses":7,"wins":30},"gemini-4-argon":{"draws":5,"losses":34,"wins":9},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":28},"google/gemini-3.5-flash":{"draws":12,"losses":8,"wins":40},"google/gemini-3.5-flash-lite":{"draws":12,"losses":6,"wins":66},"google/gemini-3.6-flash":{"draws":18,"losses":20,"wins":54},"google/gemini-3.8-flash":{"draws":11,"losses":16,"wins":21},"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":9,"losses":4,"wins":29},"gpt-5.4":{"draws":10,"losses":11,"wins":25},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":23},"gpt-5.4-nano":{"draws":4,"losses":2,"wins":42},"gpt-5.5":{"draws":8,"losses":15,"wins":21},"gpt-5.6-luna":{"draws":8,"losses":4,"wins":36},"gpt-5.6-sol":{"draws":10,"losses":13,"wins":25},"gpt-5.6-terra":{"draws":13,"losses":6,"wins":27},"gpt-6-astra":{"draws":2,"losses":42,"wins":4},"gpt-6-luna":{"draws":7,"losses":2,"wins":39},"gpt-6-sol":{"draws":8,"losses":28,"wins":12},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"gpt-6.1-terra":{"draws":7,"losses":38,"wins":3},"gpt-6.1-terra-pro":{"draws":9,"losses":35,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":26},"inception/mercury-3":{"draws":8,"losses":6,"wins":18},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":27},"inclusionai/ling-3.1-flash":{"draws":2,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":38},"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":9,"losses":13,"wins":26},"meta/muse-spark-open":{"draws":11,"losses":7,"wins":30},"meta/muse-wonder":{"draws":9,"losses":17,"wins":22},"minimax/minimax-m3":{"draws":7,"losses":0,"wins":19},"minimax/minimax-m3.1-flash":{"draws":12,"losses":5,"wins":25},"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":3,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":25},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":33,"wins":10},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":0,"wins":17},"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":10,"wins":28},"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":10,"wins":26},"qwen/qwen3.8-max-0902":{"draws":11,"losses":9,"wins":28},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":7,"wins":27},"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":4,"losses":1,"wins":5},"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":2,"wins":37},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"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":5,"losses":19,"wins":18},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":20,"losses":2,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":8,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":10,"wins":15},"z-ai/glm-5.2":{"draws":20,"losses":9,"wins":67},"z-ai/glm-5.3":{"draws":8,"losses":21,"wins":17},"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":29,"wins":17},"claude-haiku-5-5":{"draws":0,"losses":2,"wins":38},"claude-opus-4-5":{"draws":2,"losses":3,"wins":63},"claude-opus-4-8":{"draws":2,"losses":5,"wins":31},"claude-opus-5":{"draws":11,"losses":24,"wins":45},"claude-opus-5-5":{"draws":5,"losses":29,"wins":12},"claude-sonnet-5":{"draws":3,"losses":5,"wins":34},"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":2,"losses":4,"wins":56},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":3,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":10,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":6,"wins":30},"elorian/glimpse":{"draws":1,"losses":0,"wins":23},"fireworks/ember-1":{"draws":1,"losses":6,"wins":35},"gemini-3.1-pro-preview":{"draws":3,"losses":5,"wins":34},"gemini-4-argon":{"draws":3,"losses":22,"wins":17},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":43},"google/gemini-3.5-flash-lite":{"draws":5,"losses":8,"wins":59},"google/gemini-3.6-flash":{"draws":2,"losses":9,"wins":69},"google/gemini-3.8-flash":{"draws":0,"losses":5,"wins":37},"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":3,"losses":0,"wins":37},"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":7,"losses":25,"wins":10},"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":26,"wins":14},"gpt-6.1-terra":{"draws":6,"losses":19,"wins":17},"gpt-6.1-terra-pro":{"draws":4,"losses":20,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":1,"wins":25},"inception/mercury-3":{"draws":2,"losses":2,"wins":24},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":25},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":41},"meta/muse-glimmer-30b":{"draws":0,"losses":1,"wins":39},"meta/muse-spark-1.2":{"draws":0,"losses":5,"wins":37},"meta/muse-spark-1.3":{"draws":2,"losses":7,"wins":33},"meta/muse-spark-open":{"draws":2,"losses":4,"wins":36},"meta/muse-wonder":{"draws":1,"losses":10,"wins":31},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":23},"minimax/minimax-m3.1-flash":{"draws":1,"losses":1,"wins":34},"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":1,"wins":1},"moonshotai/kimi-k3":{"draws":1,"losses":7,"wins":34},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":17,"wins":20},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":3,"wins":17},"o3":{"draws":3,"losses":2,"wins":49},"openai/gpt-oss-120b":{"draws":0,"losses":3,"wins":35},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"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":5,"wins":34},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":3,"wins":33},"stealth/ox-alpha":{"draws":12,"losses":15,"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":2,"wins":10},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":22},"tencent/hy4-preview":{"draws":1,"losses":9,"wins":30},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":51},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":41},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":4},"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":6,"wins":17},"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":1,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":20},"z-ai/glm-5.2":{"draws":3,"losses":6,"wins":75},"z-ai/glm-5.3":{"draws":3,"losses":9,"wins":28},"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":12,"losses":21,"wins":11},"claude-fable-5":{"draws":8,"losses":34,"wins":6},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":30,"wins":4},"claude-opus-4-5":{"draws":24,"losses":41,"wins":13},"claude-opus-4-8":{"draws":9,"losses":28,"wins":7},"claude-opus-5":{"draws":15,"losses":64,"wins":3},"claude-opus-5-5":{"draws":1,"losses":51,"wins":0},"claude-sonnet-5":{"draws":17,"losses":27,"wins":4},"claude-sonnet-5-5":{"draws":9,"losses":33,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":20,"losses":32,"wins":20},"deepseek/deepseek-v4-pro":{"draws":15,"losses":18,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":26,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":26,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":35,"wins":7},"elorian/glimpse":{"draws":6,"losses":14,"wins":6},"fireworks/ember-1":{"draws":16,"losses":24,"wins":8},"gemini-3.1-pro-preview":{"draws":12,"losses":22,"wins":14},"gemini-4-argon":{"draws":3,"losses":44,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":13,"losses":38,"wins":9},"google/gemini-3.5-flash-lite":{"draws":26,"losses":29,"wins":29},"google/gemini-3.6-flash":{"draws":25,"losses":59,"wins":8},"google/gemini-3.8-flash":{"draws":12,"losses":32,"wins":4},"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":11,"losses":22,"wins":9},"gpt-5.4":{"draws":9,"losses":29,"wins":8},"gpt-5.4-mini":{"draws":9,"losses":14,"wins":9},"gpt-5.4-nano":{"draws":7,"losses":26,"wins":15},"gpt-5.5":{"draws":19,"losses":17,"wins":8},"gpt-5.6-luna":{"draws":15,"losses":22,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":26,"wins":6},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"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},"gpt-6.1-terra":{"draws":5,"losses":41,"wins":2},"gpt-6.1-terra-pro":{"draws":5,"losses":43,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":8,"wins":10},"inception/mercury-3":{"draws":11,"losses":17,"wins":4},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":19},"inclusionai/ling-3.1-flash":{"draws":5,"losses":3,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":19,"wins":19},"meta/muse-glimmer-30b":{"draws":14,"losses":12,"wins":16},"meta/muse-spark-1.2":{"draws":9,"losses":29,"wins":8},"meta/muse-spark-1.3":{"draws":12,"losses":28,"wins":8},"meta/muse-spark-open":{"draws":12,"losses":29,"wins":7},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":6,"losses":9,"wins":11},"minimax/minimax-m3.1-flash":{"draws":13,"losses":18,"wins":11},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":25,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":37,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":11,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":14,"wins":5},"o3":{"draws":11,"losses":38,"wins":17},"openai/gpt-oss-120b":{"draws":13,"losses":12,"wins":17},"poolside/laguna-s-2.1":{"draws":14,"losses":14,"wins":18},"qwen/qwen3.7-max":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.7-plus":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":12,"losses":21,"wins":1},"qwen/qwen3.8-flash":{"draws":13,"losses":13,"wins":6},"qwen/qwen3.8-max":{"draws":15,"losses":26,"wins":7},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":21,"wins":11},"stealth/ox-alpha":{"draws":33,"losses":105,"wins":20},"stealth/space-bunny-alpha":{"draws":9,"losses":19,"wins":10},"stepfun/step-3.7-flash":{"draws":8,"losses":15,"wins":11},"stepfun/step-5-preview":{"draws":3,"losses":9,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":13,"wins":6},"tencent/hy4-preview":{"draws":12,"losses":26,"wins":8},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":28},"thinkingmachines/inkling-small":{"draws":14,"losses":16,"wins":18},"unbiased/pareto-26.10":{"draws":0,"losses":15,"wins":1},"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":28,"losses":20,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":9,"wins":8},"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":36,"losses":38,"wins":22},"z-ai/glm-5.3":{"draws":10,"losses":36,"wins":0},"z-ai/glm-5.3-flash":{"draws":9,"losses":31,"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":29,"losses":36,"wins":15},"claude-fable-5":{"draws":16,"losses":69,"wins":5},"claude-fable-5-1":{"draws":5,"losses":92,"wins":3},"claude-haiku-5-5":{"draws":29,"losses":51,"wins":10},"claude-opus-4-5":{"draws":57,"losses":72,"wins":21},"claude-opus-4-8":{"draws":31,"losses":49,"wins":10},"claude-opus-5":{"draws":23,"losses":124,"wins":15},"claude-opus-5-5":{"draws":5,"losses":89,"wins":4},"claude-sonnet-5":{"draws":33,"losses":41,"wins":16},"claude-sonnet-5-5":{"draws":23,"losses":55,"wins":12},"cohere/north-mini-code":{"draws":7,"losses":15,"wins":10},"deepseek/deepseek-v4-flash":{"draws":52,"losses":40,"wins":42},"deepseek/deepseek-v4-pro":{"draws":28,"losses":40,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":42,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":30,"losses":49,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":61,"wins":5},"elorian/glimpse":{"draws":16,"losses":22,"wins":10},"fireworks/ember-1":{"draws":32,"losses":49,"wins":9},"gemini-3.1-pro-preview":{"draws":33,"losses":35,"wins":22},"gemini-4-argon":{"draws":6,"losses":83,"wins":1},"google/gemini-3.1-flash-lite":{"draws":20,"losses":14,"wins":30},"google/gemini-3.5-flash":{"draws":34,"losses":60,"wins":20},"google/gemini-3.5-flash-lite":{"draws":52,"losses":45,"wins":59},"google/gemini-3.6-flash":{"draws":54,"losses":100,"wins":16},"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":12,"losses":12,"wins":6},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":22,"losses":35,"wins":19},"gpt-5.4":{"draws":26,"losses":48,"wins":10},"gpt-5.4-mini":{"draws":22,"losses":25,"wins":13},"gpt-5.4-nano":{"draws":24,"losses":38,"wins":30},"gpt-5.5":{"draws":30,"losses":46,"wins":6},"gpt-5.6-luna":{"draws":32,"losses":37,"wins":21},"gpt-5.6-sol":{"draws":17,"losses":72,"wins":1},"gpt-5.6-terra":{"draws":31,"losses":49,"wins":6},"gpt-6-astra":{"draws":5,"losses":84,"wins":1},"gpt-6-luna":{"draws":34,"losses":43,"wins":13},"gpt-6-sol":{"draws":16,"losses":69,"wins":5},"gpt-6.1-sol":{"draws":8,"losses":80,"wins":2},"gpt-6.1-terra":{"draws":6,"losses":83,"wins":1},"gpt-6.1-terra-pro":{"draws":8,"losses":82,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":33,"losses":13,"wins":24},"inception/mercury-3":{"draws":23,"losses":27,"wins":10},"inclusionai/ling-3.0-flash":{"draws":29,"losses":13,"wins":20},"inclusionai/ling-3.1-flash":{"draws":3,"losses":4,"wins":3},"meituan/longcat-2.0":{"draws":26,"losses":33,"wins":35},"meta/muse-glimmer-30b":{"draws":27,"losses":25,"wins":28},"meta/muse-spark-1.2":{"draws":26,"losses":53,"wins":9},"meta/muse-spark-1.3":{"draws":21,"losses":59,"wins":10},"meta/muse-spark-open":{"draws":31,"losses":54,"wins":5},"meta/muse-wonder":{"draws":26,"losses":60,"wins":4},"minimax/minimax-m3":{"draws":20,"losses":16,"wins":16},"minimax/minimax-m3.1-flash":{"draws":24,"losses":32,"wins":20},"mistralai/mistral-large-4-0":{"draws":24,"losses":27,"wins":7},"mistralai/mistral-medium-3-5":{"draws":24,"losses":10,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":32,"losses":43,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":78,"wins":1},"nex-agi/nex-n2-pro":{"draws":9,"losses":16,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":7,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":24,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":18,"wins":10},"o3":{"draws":22,"losses":79,"wins":17},"openai/gpt-oss-120b":{"draws":27,"losses":27,"wins":24},"poolside/laguna-s-2.1":{"draws":21,"losses":30,"wins":29},"qwen/qwen3.7-max":{"draws":17,"losses":26,"wins":11},"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":23,"losses":23,"wins":14},"qwen/qwen3.8-max":{"draws":34,"losses":47,"wins":9},"qwen/qwen3.8-max-0902":{"draws":31,"losses":46,"wins":13},"recursive/flint-v1.0":{"draws":12,"losses":6,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":31,"losses":42,"wins":11},"stealth/ox-alpha":{"draws":68,"losses":149,"wins":37},"stealth/space-bunny-alpha":{"draws":30,"losses":31,"wins":13},"stepfun/step-3.7-flash":{"draws":15,"losses":22,"wins":21},"stepfun/step-5-preview":{"draws":3,"losses":11,"wins":4},"tencent/hy3-preview":{"draws":24,"losses":16,"wins":14},"tencent/hy4-preview":{"draws":22,"losses":48,"wins":14},"thinkingmachines/inkling":{"draws":40,"losses":33,"wins":43},"thinkingmachines/inkling-small":{"draws":34,"losses":27,"wins":29},"unbiased/pareto-26.10":{"draws":3,"losses":27,"wins":0},"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":27,"losses":59,"wins":4},"x-ai/grok-4.6":{"draws":24,"losses":59,"wins":7},"x-ai/grok-4.7":{"draws":10,"losses":66,"wins":6},"x-ai/grok-build-0.1":{"draws":12,"losses":10,"wins":8},"xiaomi/mimo-v2.5":{"draws":54,"losses":38,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":12,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":37,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":38,"wins":4},"z-ai/glm-5.2":{"draws":65,"losses":79,"wins":36},"z-ai/glm-5.3":{"draws":21,"losses":65,"wins":0},"z-ai/glm-5.3-flash":{"draws":25,"losses":54,"wins":11},"z-ai/glm-5.3-flashx":{"draws":29,"losses":55,"wins":6}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":15,"wins":9},"claude-fable-5":{"draws":6,"losses":27,"wins":5},"claude-fable-5-1":{"draws":2,"losses":34,"wins":0},"claude-haiku-5-5":{"draws":4,"losses":18,"wins":2},"claude-opus-4-5":{"draws":13,"losses":31,"wins":12},"claude-opus-4-8":{"draws":2,"losses":16,"wins":6},"claude-opus-5":{"draws":10,"losses":49,"wins":5},"claude-opus-5-5":{"draws":3,"losses":15,"wins":0},"claude-sonnet-5":{"draws":6,"losses":6,"wins":14},"claude-sonnet-5-5":{"draws":6,"losses":11,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":8,"wins":4},"deepseek/deepseek-v4-flash":{"draws":12,"losses":17,"wins":15},"deepseek/deepseek-v4-pro":{"draws":5,"losses":19,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":20,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":13,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":8,"wins":1},"elorian/glimpse":{"draws":6,"losses":9,"wins":3},"fireworks/ember-1":{"draws":12,"losses":9,"wins":5},"gemini-3.1-pro-preview":{"draws":6,"losses":13,"wins":7},"gemini-4-argon":{"draws":4,"losses":20,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":9,"wins":7},"google/gemini-3.5-flash":{"draws":11,"losses":23,"wins":14},"google/gemini-3.5-flash-lite":{"draws":10,"losses":27,"wins":17},"google/gemini-3.6-flash":{"draws":8,"losses":33,"wins":15},"google/gemini-3.8-flash":{"draws":5,"losses":28,"wins":7},"google/gemma-4-31b-it":{"draws":3,"losses":6,"wins":7},"gpt-4.1":{"draws":2,"losses":6,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":5,"losses":18,"wins":9},"gpt-5.4":{"draws":7,"losses":20,"wins":7},"gpt-5.4-mini":{"draws":7,"losses":7,"wins":6},"gpt-5.4-nano":{"draws":7,"losses":18,"wins":13},"gpt-5.5":{"draws":8,"losses":14,"wins":6},"gpt-5.6-luna":{"draws":8,"losses":15,"wins":13},"gpt-5.6-sol":{"draws":6,"losses":26,"wins":4},"gpt-5.6-terra":{"draws":10,"losses":15,"wins":5},"gpt-6-astra":{"draws":5,"losses":29,"wins":0},"gpt-6-luna":{"draws":7,"losses":14,"wins":7},"gpt-6-sol":{"draws":6,"losses":20,"wins":2},"gpt-6.1-sol":{"draws":5,"losses":21,"wins":0},"gpt-6.1-terra":{"draws":2,"losses":15,"wins":1},"gpt-6.1-terra-pro":{"draws":2,"losses":12,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":9,"wins":8},"inception/mercury-3":{"draws":6,"losses":7,"wins":3},"inclusionai/ling-3.0-flash":{"draws":3,"losses":8,"wins":7},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":11,"wins":21},"meta/muse-glimmer-30b":{"draws":6,"losses":11,"wins":11},"meta/muse-spark-1.2":{"draws":2,"losses":14,"wins":6},"meta/muse-spark-1.3":{"draws":8,"losses":14,"wins":4},"meta/muse-spark-open":{"draws":7,"losses":14,"wins":1},"meta/muse-wonder":{"draws":7,"losses":14,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":8},"minimax/minimax-m3.1-flash":{"draws":11,"losses":10,"wins":5},"mistralai/mistral-large-4-0":{"draws":1,"losses":8,"wins":3},"mistralai/mistral-medium-3-5":{"draws":4,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":15,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":24,"wins":1},"nex-agi/nex-n2-pro":{"draws":5,"losses":8,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":13,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":1},"o3":{"draws":2,"losses":30,"wins":10},"openai/gpt-oss-120b":{"draws":6,"losses":11,"wins":13},"poolside/laguna-s-2.1":{"draws":7,"losses":18,"wins":11},"qwen/qwen3.7-max":{"draws":4,"losses":12,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":24,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":4},"qwen/qwen3.8-flash":{"draws":7,"losses":10,"wins":3},"qwen/qwen3.8-max":{"draws":7,"losses":16,"wins":7},"qwen/qwen3.8-max-0902":{"draws":5,"losses":12,"wins":1},"recursive/flint-v1.0":{"draws":2,"losses":3,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":9,"wins":4},"stealth/ox-alpha":{"draws":16,"losses":64,"wins":26},"stealth/space-bunny-alpha":{"draws":4,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":7},"stepfun/step-5-preview":{"draws":1,"losses":11,"wins":6},"tencent/hy3-preview":{"draws":6,"losses":7,"wins":7},"tencent/hy4-preview":{"draws":5,"losses":14,"wins":9},"thinkingmachines/inkling":{"draws":6,"losses":18,"wins":10},"thinkingmachines/inkling-small":{"draws":12,"losses":13,"wins":19},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"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":3,"losses":21,"wins":8},"x-ai/grok-4.6":{"draws":9,"losses":21,"wins":6},"x-ai/grok-4.7":{"draws":1,"losses":12,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":17,"losses":22,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":4,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":11,"wins":2},"z-ai/glm-5.2":{"draws":10,"losses":34,"wins":22},"z-ai/glm-5.3":{"draws":4,"losses":18,"wins":4},"z-ai/glm-5.3-flash":{"draws":5,"losses":22,"wins":9},"z-ai/glm-5.3-flashx":{"draws":7,"losses":18,"wins":5}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":9,"wins":34},"claude-fable-5":{"draws":5,"losses":26,"wins":17},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":19,"wins":17},"claude-opus-4-5":{"draws":9,"losses":18,"wins":51},"claude-opus-4-8":{"draws":5,"losses":11,"wins":28},"claude-opus-5":{"draws":7,"losses":64,"wins":11},"claude-opus-5-5":{"draws":3,"losses":47,"wins":2},"claude-sonnet-5":{"draws":4,"losses":12,"wins":32},"claude-sonnet-5-5":{"draws":2,"losses":24,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":5,"losses":12,"wins":55},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":22,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":21,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":26,"wins":16},"elorian/glimpse":{"draws":2,"losses":9,"wins":15},"fireworks/ember-1":{"draws":2,"losses":19,"wins":27},"gemini-3.1-pro-preview":{"draws":5,"losses":13,"wins":30},"gemini-4-argon":{"draws":1,"losses":41,"wins":6},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":27},"google/gemini-3.5-flash":{"draws":4,"losses":19,"wins":37},"google/gemini-3.5-flash-lite":{"draws":9,"losses":8,"wins":67},"google/gemini-3.6-flash":{"draws":8,"losses":34,"wins":50},"google/gemini-3.8-flash":{"draws":6,"losses":20,"wins":22},"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":1,"losses":0,"wins":5},"gpt-5":{"draws":2,"losses":10,"wins":30},"gpt-5.4":{"draws":9,"losses":19,"wins":18},"gpt-5.4-mini":{"draws":2,"losses":6,"wins":24},"gpt-5.4-nano":{"draws":7,"losses":11,"wins":30},"gpt-5.5":{"draws":4,"losses":21,"wins":19},"gpt-5.6-luna":{"draws":5,"losses":15,"wins":28},"gpt-5.6-sol":{"draws":2,"losses":31,"wins":15},"gpt-5.6-terra":{"draws":5,"losses":14,"wins":27},"gpt-6-astra":{"draws":2,"losses":43,"wins":3},"gpt-6-luna":{"draws":6,"losses":13,"wins":29},"gpt-6-sol":{"draws":6,"losses":31,"wins":11},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"gpt-6.1-terra":{"draws":8,"losses":37,"wins":3},"gpt-6.1-terra-pro":{"draws":5,"losses":40,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":3,"losses":4,"wins":27},"inception/mercury-3":{"draws":3,"losses":12,"wins":17},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":25},"inclusionai/ling-3.1-flash":{"draws":4,"losses":3,"wins":5},"meituan/longcat-2.0":{"draws":5,"losses":12,"wins":35},"meta/muse-glimmer-30b":{"draws":5,"losses":7,"wins":30},"meta/muse-spark-1.2":{"draws":4,"losses":20,"wins":22},"meta/muse-spark-1.3":{"draws":6,"losses":20,"wins":22},"meta/muse-spark-open":{"draws":4,"losses":24,"wins":18},"meta/muse-wonder":{"draws":1,"losses":31,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":19},"minimax/minimax-m3.1-flash":{"draws":1,"losses":9,"wins":32},"mistralai/mistral-large-4-0":{"draws":9,"losses":7,"wins":14},"mistralai/mistral-medium-3-5":{"draws":3,"losses":5,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":14,"wins":25},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":34,"wins":7},"nex-agi/nex-n2-pro":{"draws":3,"losses":4,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":7,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":6,"wins":13},"o3":{"draws":5,"losses":15,"wins":46},"openai/gpt-oss-120b":{"draws":5,"losses":4,"wins":33},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":34},"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":6,"losses":17,"wins":25},"qwen/qwen3.8-27b":{"draws":3,"losses":11,"wins":20},"qwen/qwen3.8-flash":{"draws":7,"losses":13,"wins":12},"qwen/qwen3.8-max":{"draws":5,"losses":20,"wins":23},"qwen/qwen3.8-max-0902":{"draws":5,"losses":16,"wins":27},"recursive/flint-v1.0":{"draws":0,"losses":3,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":17,"wins":25},"stealth/ox-alpha":{"draws":18,"losses":64,"wins":76},"stealth/space-bunny-alpha":{"draws":4,"losses":7,"wins":27},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":30},"stepfun/step-5-preview":{"draws":1,"losses":7,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":7,"wins":18},"tencent/hy4-preview":{"draws":7,"losses":19,"wins":20},"thinkingmachines/inkling":{"draws":13,"losses":9,"wins":42},"thinkingmachines/inkling-small":{"draws":9,"losses":1,"wins":38},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":6,"losses":19,"wins":23},"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":6,"losses":14,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":5,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":13},"z-ai/glm-5.2":{"draws":8,"losses":23,"wins":65},"z-ai/glm-5.3":{"draws":5,"losses":28,"wins":13},"z-ai/glm-5.3-flash":{"draws":5,"losses":18,"wins":25},"z-ai/glm-5.3-flashx":{"draws":2,"losses":21,"wins":25}},"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":7,"losses":39,"wins":8},"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":15,"losses":40,"wins":27},"claude-opus-5-5":{"draws":5,"losses":38,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":15,"wins":27},"elorian/glimpse":{"draws":4,"losses":9,"wins":13},"fireworks/ember-1":{"draws":7,"losses":11,"wins":30},"gemini-3.1-pro-preview":{"draws":2,"losses":9,"wins":37},"gemini-4-argon":{"draws":5,"losses":25,"wins":18},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":30},"google/gemini-3.5-flash":{"draws":7,"losses":11,"wins":42},"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":7,"wins":34},"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":1,"losses":7,"wins":40},"gpt-5.5":{"draws":9,"losses":9,"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},"gpt-6.1-terra":{"draws":7,"losses":24,"wins":17},"gpt-6.1-terra-pro":{"draws":9,"losses":32,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":30},"inception/mercury-3":{"draws":6,"losses":5,"wins":21},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":7,"wins":44},"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-spark-open":{"draws":3,"losses":15,"wins":30},"meta/muse-wonder":{"draws":9,"losses":15,"wins":24},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":22},"minimax/minimax-m3.1-flash":{"draws":3,"losses":8,"wins":31},"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":1,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":31},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":19,"wins":19},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":6,"wins":16},"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},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":7,"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":5,"wins":9},"tencent/hy3-preview":{"draws":1,"losses":7,"wins":18},"tencent/hy4-preview":{"draws":5,"losses":11,"wins":30},"thinkingmachines/inkling":{"draws":3,"losses":4,"wins":57},"thinkingmachines/inkling-small":{"draws":0,"losses":5,"wins":43},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":5,"losses":13,"wins":30},"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":2,"losses":3,"wins":17},"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":25,"losses":18,"wins":45},"claude-fable-5":{"draws":23,"losses":58,"wins":15},"claude-fable-5-1":{"draws":6,"losses":100,"wins":2},"claude-haiku-5-5":{"draws":23,"losses":39,"wins":30},"claude-opus-4-5":{"draws":51,"losses":48,"wins":57},"claude-opus-4-8":{"draws":24,"losses":40,"wins":24},"claude-opus-5":{"draws":24,"losses":131,"wins":9},"claude-opus-5-5":{"draws":5,"losses":94,"wins":5},"claude-sonnet-5":{"draws":25,"losses":35,"wins":36},"claude-sonnet-5-5":{"draws":19,"losses":53,"wins":24},"cohere/north-mini-code":{"draws":10,"losses":8,"wins":18},"deepseek/deepseek-v4-flash":{"draws":50,"losses":33,"wins":61},"deepseek/deepseek-v4-pro":{"draws":27,"losses":30,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":36,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":37,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":22,"losses":54,"wins":20},"elorian/glimpse":{"draws":13,"losses":23,"wins":16},"fireworks/ember-1":{"draws":28,"losses":41,"wins":27},"gemini-3.1-pro-preview":{"draws":25,"losses":34,"wins":37},"gemini-4-argon":{"draws":9,"losses":83,"wins":4},"google/gemini-3.1-flash-lite":{"draws":19,"losses":5,"wins":40},"google/gemini-3.5-flash":{"draws":30,"losses":40,"wins":50},"google/gemini-3.5-flash-lite":{"draws":54,"losses":39,"wins":75},"google/gemini-3.6-flash":{"draws":39,"losses":82,"wins":63},"google/gemini-3.8-flash":{"draws":21,"losses":50,"wins":25},"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":27,"losses":29,"wins":28},"gpt-5.4":{"draws":27,"losses":39,"wins":26},"gpt-5.4-mini":{"draws":25,"losses":10,"wins":29},"gpt-5.4-nano":{"draws":22,"losses":28,"wins":46},"gpt-5.5":{"draws":34,"losses":40,"wins":14},"gpt-5.6-luna":{"draws":39,"losses":20,"wins":37},"gpt-5.6-sol":{"draws":12,"losses":60,"wins":24},"gpt-5.6-terra":{"draws":34,"losses":31,"wins":27},"gpt-6-astra":{"draws":9,"losses":82,"wins":5},"gpt-6-luna":{"draws":31,"losses":35,"wins":30},"gpt-6-sol":{"draws":12,"losses":72,"wins":12},"gpt-6.1-sol":{"draws":14,"losses":78,"wins":4},"gpt-6.1-terra":{"draws":12,"losses":78,"wins":6},"gpt-6.1-terra-pro":{"draws":11,"losses":78,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":4,"wins":34},"inception/mercury-3":{"draws":22,"losses":24,"wins":18},"inclusionai/ling-3.0-flash":{"draws":29,"losses":13,"wins":26},"inclusionai/ling-3.1-flash":{"draws":3,"losses":7,"wins":4},"meituan/longcat-2.0":{"draws":30,"losses":23,"wins":51},"meta/muse-glimmer-30b":{"draws":32,"losses":18,"wins":34},"meta/muse-spark-1.2":{"draws":24,"losses":46,"wins":22},"meta/muse-spark-1.3":{"draws":25,"losses":45,"wins":26},"meta/muse-spark-open":{"draws":26,"losses":46,"wins":24},"meta/muse-wonder":{"draws":25,"losses":52,"wins":19},"minimax/minimax-m3":{"draws":10,"losses":13,"wins":29},"minimax/minimax-m3.1-flash":{"draws":24,"losses":26,"wins":34},"mistralai/mistral-large-4-0":{"draws":29,"losses":19,"wins":12},"mistralai/mistral-medium-3-5":{"draws":20,"losses":7,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":33,"losses":30,"wins":29},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":73,"wins":12},"nex-agi/nex-n2-pro":{"draws":14,"losses":6,"wins":28},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":7,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":20,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":13,"wins":16},"o3":{"draws":21,"losses":53,"wins":58},"openai/gpt-oss-120b":{"draws":39,"losses":10,"wins":35},"poolside/laguna-s-2.1":{"draws":32,"losses":24,"wins":36},"qwen/qwen3.7-max":{"draws":16,"losses":14,"wins":26},"qwen/qwen3.7-plus":{"draws":12,"losses":11,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":43,"wins":26},"qwen/qwen3.8-27b":{"draws":20,"losses":20,"wins":28},"qwen/qwen3.8-flash":{"draws":15,"losses":27,"wins":22},"qwen/qwen3.8-max":{"draws":24,"losses":41,"wins":31},"qwen/qwen3.8-max-0902":{"draws":30,"losses":44,"wins":22},"recursive/flint-v1.0":{"draws":5,"losses":6,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":29,"losses":35,"wins":24},"stealth/ox-alpha":{"draws":78,"losses":145,"wins":93},"stealth/space-bunny-alpha":{"draws":28,"losses":23,"wins":25},"stepfun/step-3.7-flash":{"draws":17,"losses":7,"wins":44},"stepfun/step-5-preview":{"draws":3,"losses":9,"wins":6},"tencent/hy3-preview":{"draws":17,"losses":15,"wins":20},"tencent/hy4-preview":{"draws":17,"losses":47,"wins":28},"thinkingmachines/inkling":{"draws":38,"losses":30,"wins":60},"thinkingmachines/inkling-small":{"draws":30,"losses":12,"wins":54},"unbiased/pareto-26.10":{"draws":1,"losses":30,"wins":1},"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":25,"losses":52,"wins":19},"x-ai/grok-4.7":{"draws":9,"losses":60,"wins":15},"x-ai/grok-build-0.1":{"draws":14,"losses":4,"wins":14},"xiaomi/mimo-v2.5":{"draws":54,"losses":18,"wins":76},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":14,"wins":32},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":25,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":32,"wins":15},"z-ai/glm-5.2":{"draws":54,"losses":46,"wins":60},"z-ai/glm-5.3":{"draws":18,"losses":58,"wins":16},"z-ai/glm-5.3-flash":{"draws":21,"losses":44,"wins":31},"z-ai/glm-5.3-flashx":{"draws":29,"losses":42,"wins":25}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":31},"claude-fable-5":{"draws":8,"losses":18,"wins":22},"claude-fable-5-1":{"draws":5,"losses":42,"wins":7},"claude-haiku-5-5":{"draws":8,"losses":10,"wins":28},"claude-opus-4-5":{"draws":15,"losses":5,"wins":58},"claude-opus-4-8":{"draws":6,"losses":11,"wins":27},"claude-opus-5":{"draws":13,"losses":51,"wins":18},"claude-opus-5-5":{"draws":5,"losses":35,"wins":12},"claude-sonnet-5":{"draws":6,"losses":6,"wins":36},"claude-sonnet-5-5":{"draws":5,"losses":15,"wins":28},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":13,"losses":3,"wins":56},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":8,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":5,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":14,"wins":29},"elorian/glimpse":{"draws":4,"losses":5,"wins":17},"fireworks/ember-1":{"draws":5,"losses":11,"wins":32},"gemini-3.1-pro-preview":{"draws":7,"losses":9,"wins":32},"gemini-4-argon":{"draws":5,"losses":32,"wins":11},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"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":18,"losses":18,"wins":56},"google/gemini-3.8-flash":{"draws":9,"losses":11,"wins":28},"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":3,"losses":8,"wins":31},"gpt-5.4":{"draws":5,"losses":12,"wins":29},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":24},"gpt-5.4-nano":{"draws":4,"losses":7,"wins":37},"gpt-5.5":{"draws":10,"losses":10,"wins":24},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":40},"gpt-5.6-sol":{"draws":8,"losses":23,"wins":17},"gpt-5.6-terra":{"draws":11,"losses":4,"wins":31},"gpt-6-astra":{"draws":6,"losses":41,"wins":1},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":5,"losses":26,"wins":17},"gpt-6.1-sol":{"draws":10,"losses":31,"wins":7},"gpt-6.1-terra":{"draws":8,"losses":32,"wins":8},"gpt-6.1-terra-pro":{"draws":3,"losses":34,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":25},"inception/mercury-3":{"draws":7,"losses":7,"wins":18},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.1-flash":{"draws":2,"losses":3,"wins":5},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":42},"meta/muse-glimmer-30b":{"draws":6,"losses":2,"wins":34},"meta/muse-spark-1.2":{"draws":5,"losses":13,"wins":28},"meta/muse-spark-1.3":{"draws":7,"losses":14,"wins":27},"meta/muse-spark-open":{"draws":7,"losses":12,"wins":29},"meta/muse-wonder":{"draws":4,"losses":23,"wins":21},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"minimax/minimax-m3.1-flash":{"draws":4,"losses":11,"wins":27},"mistralai/mistral-large-4-0":{"draws":3,"losses":6,"wins":21},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":17,"wins":24},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":28,"wins":17},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":2,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":19},"o3":{"draws":5,"losses":8,"wins":53},"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":3,"losses":3,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":12,"wins":30},"qwen/qwen3.8-27b":{"draws":8,"losses":6,"wins":20},"qwen/qwen3.8-flash":{"draws":5,"losses":4,"wins":23},"qwen/qwen3.8-max":{"draws":9,"losses":8,"wins":31},"qwen/qwen3.8-max-0902":{"draws":7,"losses":7,"wins":34},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":4,"wins":34},"stealth/ox-alpha":{"draws":22,"losses":38,"wins":98},"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":1,"losses":3,"wins":10},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":19},"tencent/hy4-preview":{"draws":3,"losses":12,"wins":31},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":47},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":43},"unbiased/pareto-26.10":{"draws":2,"losses":13,"wins":1},"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":5,"losses":15,"wins":28},"x-ai/grok-4.6":{"draws":9,"losses":15,"wins":24},"x-ai/grok-4.7":{"draws":5,"losses":26,"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":4,"losses":0,"wins":20},"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":16,"losses":14,"wins":66},"z-ai/glm-5.3":{"draws":10,"losses":7,"wins":13},"z-ai/glm-5.3-flash":{"draws":11,"losses":9,"wins":28},"z-ai/glm-5.3-flashx":{"draws":6,"losses":10,"wins":32}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":7,"wins":27},"claude-fable-5":{"draws":8,"losses":23,"wins":17},"claude-fable-5-1":{"draws":5,"losses":45,"wins":4},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":19,"losses":13,"wins":46},"claude-opus-4-8":{"draws":8,"losses":12,"wins":24},"claude-opus-5":{"draws":9,"losses":54,"wins":19},"claude-opus-5-5":{"draws":3,"losses":43,"wins":6},"claude-sonnet-5":{"draws":9,"losses":7,"wins":32},"claude-sonnet-5-5":{"draws":4,"losses":25,"wins":19},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":16,"losses":8,"wins":48},"deepseek/deepseek-v4-pro":{"draws":9,"losses":14,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":11,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":20,"wins":19},"elorian/glimpse":{"draws":5,"losses":11,"wins":10},"fireworks/ember-1":{"draws":7,"losses":13,"wins":28},"gemini-3.1-pro-preview":{"draws":9,"losses":11,"wins":28},"gemini-4-argon":{"draws":6,"losses":35,"wins":7},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":7,"losses":11,"wins":42},"google/gemini-3.5-flash-lite":{"draws":13,"losses":7,"wins":64},"google/gemini-3.6-flash":{"draws":12,"losses":25,"wins":55},"google/gemini-3.8-flash":{"draws":8,"losses":23,"wins":17},"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":6,"losses":11,"wins":25},"gpt-5.4":{"draws":8,"losses":20,"wins":18},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":24},"gpt-5.4-nano":{"draws":6,"losses":10,"wins":32},"gpt-5.5":{"draws":10,"losses":14,"wins":20},"gpt-5.6-luna":{"draws":12,"losses":7,"wins":29},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":20},"gpt-5.6-terra":{"draws":11,"losses":11,"wins":24},"gpt-6-astra":{"draws":6,"losses":37,"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":4,"losses":38,"wins":6},"gpt-6.1-terra":{"draws":9,"losses":34,"wins":5},"gpt-6.1-terra-pro":{"draws":2,"losses":39,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":0,"wins":24},"inception/mercury-3":{"draws":4,"losses":10,"wins":18},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":7,"losses":8,"wins":37},"meta/muse-glimmer-30b":{"draws":8,"losses":4,"wins":30},"meta/muse-spark-1.2":{"draws":6,"losses":18,"wins":22},"meta/muse-spark-1.3":{"draws":12,"losses":14,"wins":22},"meta/muse-spark-open":{"draws":11,"losses":13,"wins":24},"meta/muse-wonder":{"draws":8,"losses":23,"wins":17},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":17},"minimax/minimax-m3.1-flash":{"draws":6,"losses":12,"wins":24},"mistralai/mistral-large-4-0":{"draws":8,"losses":7,"wins":15},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":15,"wins":24},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":31,"wins":13},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":9,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":11},"o3":{"draws":8,"losses":18,"wins":40},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":29},"qwen/qwen3.7-max":{"draws":9,"losses":4,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":23},"qwen/qwen3.8-27b":{"draws":6,"losses":8,"wins":20},"qwen/qwen3.8-flash":{"draws":6,"losses":11,"wins":15},"qwen/qwen3.8-max":{"draws":7,"losses":16,"wins":25},"qwen/qwen3.8-max-0902":{"draws":16,"losses":14,"wins":18},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":9,"wins":28},"stealth/ox-alpha":{"draws":23,"losses":53,"wins":82},"stealth/space-bunny-alpha":{"draws":7,"losses":3,"wins":28},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":28},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":8},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":16},"tencent/hy4-preview":{"draws":3,"losses":18,"wins":25},"thinkingmachines/inkling":{"draws":11,"losses":5,"wins":48},"thinkingmachines/inkling-small":{"draws":9,"losses":4,"wins":35},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":2},"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":9,"losses":17,"wins":22},"x-ai/grok-4.7":{"draws":7,"losses":22,"wins":13},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":16,"losses":5,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":15},"z-ai/glm-5.2":{"draws":16,"losses":15,"wins":65},"z-ai/glm-5.3":{"draws":9,"losses":22,"wins":15},"z-ai/glm-5.3-flash":{"draws":3,"losses":7,"wins":22},"z-ai/glm-5.3-flashx":{"draws":10,"losses":16,"wins":22}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":11,"wins":27},"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-fable-5-1":{"draws":5,"losses":43,"wins":6},"claude-haiku-5-5":{"draws":7,"losses":26,"wins":13},"claude-opus-4-5":{"draws":21,"losses":18,"wins":39},"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":9,"losses":15,"wins":24},"claude-sonnet-5-5":{"draws":4,"losses":25,"wins":19},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":14},"deepseek/deepseek-v4-flash":{"draws":17,"losses":15,"wins":40},"deepseek/deepseek-v4-pro":{"draws":9,"losses":20,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":16,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":22,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":27,"wins":12},"elorian/glimpse":{"draws":7,"losses":11,"wins":8},"fireworks/ember-1":{"draws":10,"losses":21,"wins":17},"gemini-3.1-pro-preview":{"draws":8,"losses":16,"wins":24},"gemini-4-argon":{"draws":4,"losses":38,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":21},"google/gemini-3.5-flash":{"draws":12,"losses":23,"wins":25},"google/gemini-3.5-flash-lite":{"draws":14,"losses":25,"wins":45},"google/gemini-3.6-flash":{"draws":18,"losses":40,"wins":34},"google/gemini-3.8-flash":{"draws":10,"losses":25,"wins":13},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":12},"gpt-4.1":{"draws":3,"losses":5,"wins":8},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":18,"wins":17},"gpt-5.4":{"draws":9,"losses":24,"wins":13},"gpt-5.4-mini":{"draws":5,"losses":4,"wins":23},"gpt-5.4-nano":{"draws":12,"losses":13,"wins":23},"gpt-5.5":{"draws":8,"losses":21,"wins":15},"gpt-5.6-luna":{"draws":11,"losses":14,"wins":23},"gpt-5.6-sol":{"draws":9,"losses":30,"wins":9},"gpt-5.6-terra":{"draws":14,"losses":14,"wins":18},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":10,"losses":19,"wins":19},"gpt-6-sol":{"draws":4,"losses":33,"wins":11},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":6},"gpt-6.1-terra":{"draws":2,"losses":41,"wins":5},"gpt-6.1-terra-pro":{"draws":4,"losses":39,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":3,"wins":23},"inception/mercury-3":{"draws":7,"losses":11,"wins":14},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":36},"meta/muse-glimmer-30b":{"draws":9,"losses":11,"wins":22},"meta/muse-spark-1.2":{"draws":14,"losses":20,"wins":12},"meta/muse-spark-1.3":{"draws":9,"losses":24,"wins":15},"meta/muse-spark-open":{"draws":11,"losses":23,"wins":14},"meta/muse-wonder":{"draws":11,"losses":25,"wins":12},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":15},"minimax/minimax-m3.1-flash":{"draws":8,"losses":13,"wins":21},"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":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":16,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":36,"wins":6},"nex-agi/nex-n2-pro":{"draws":1,"losses":4,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":13},"o3":{"draws":4,"losses":31,"wins":31},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":26},"poolside/laguna-s-2.1":{"draws":7,"losses":15,"wins":24},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":15},"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":8,"losses":7,"wins":17},"qwen/qwen3.8-max":{"draws":9,"losses":21,"wins":18},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":16},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":17,"wins":19},"stealth/ox-alpha":{"draws":30,"losses":65,"wins":63},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"wins":18},"stepfun/step-3.7-flash":{"draws":5,"losses":8,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":18},"tencent/hy4-preview":{"draws":12,"losses":22,"wins":12},"thinkingmachines/inkling":{"draws":15,"losses":8,"wins":41},"thinkingmachines/inkling-small":{"draws":9,"losses":12,"wins":27},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":2},"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":22,"wins":18},"x-ai/grok-4.6":{"draws":11,"losses":24,"wins":13},"x-ai/grok-4.7":{"draws":6,"losses":27,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":10},"xiaomi/mimo-v2.5":{"draws":20,"losses":10,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":17,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":15,"wins":10},"z-ai/glm-5.2":{"draws":24,"losses":27,"wins":45},"z-ai/glm-5.3":{"draws":6,"losses":29,"wins":11},"z-ai/glm-5.3-flash":{"draws":9,"losses":19,"wins":20},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":8}}},"none":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":5},"claude-fable-5":{"draws":3,"losses":36,"wins":3},"claude-fable-5-1":{"draws":1,"losses":45,"wins":2},"claude-haiku-5-5":{"draws":8,"losses":29,"wins":3},"claude-opus-4-5":{"draws":17,"losses":40,"wins":11},"claude-opus-4-8":{"draws":7,"losses":30,"wins":1},"claude-opus-5":{"draws":7,"losses":62,"wins":1},"claude-opus-5-5":{"draws":0,"losses":46,"wins":0},"claude-sonnet-5":{"draws":7,"losses":31,"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":14,"losses":32,"wins":16},"deepseek/deepseek-v4-pro":{"draws":10,"losses":26,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":22,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":28,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":33,"wins":5},"elorian/glimpse":{"draws":4,"losses":14,"wins":6},"fireworks/ember-1":{"draws":9,"losses":27,"wins":6},"gemini-3.1-pro-preview":{"draws":6,"losses":27,"wins":9},"gemini-4-argon":{"draws":0,"losses":42,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":10,"wins":14},"google/gemini-3.5-flash":{"draws":9,"losses":34,"wins":11},"google/gemini-3.5-flash-lite":{"draws":15,"losses":39,"wins":22},"google/gemini-3.6-flash":{"draws":14,"losses":56,"wins":12},"google/gemini-3.8-flash":{"draws":6,"losses":32,"wins":4},"google/gemma-4-31b-it":{"draws":9,"losses":8,"wins":7},"gpt-4.1":{"draws":3,"losses":8,"wins":3},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":2},"gpt-5":{"draws":9,"losses":18,"wins":11},"gpt-5.4":{"draws":10,"losses":25,"wins":7},"gpt-5.4-mini":{"draws":6,"losses":14,"wins":8},"gpt-5.4-nano":{"draws":5,"losses":20,"wins":17},"gpt-5.5":{"draws":11,"losses":26,"wins":3},"gpt-5.6-luna":{"draws":6,"losses":24,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":37,"wins":1},"gpt-5.6-terra":{"draws":6,"losses":30,"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},"gpt-6.1-terra":{"draws":3,"losses":39,"wins":0},"gpt-6.1-terra-pro":{"draws":3,"losses":39,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":9,"wins":12},"inception/mercury-3":{"draws":3,"losses":21,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":7,"wins":10},"inclusionai/ling-3.1-flash":{"draws":3,"losses":5,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":21,"wins":15},"meta/muse-glimmer-30b":{"draws":10,"losses":19,"wins":9},"meta/muse-spark-1.2":{"draws":8,"losses":27,"wins":5},"meta/muse-spark-1.3":{"draws":3,"losses":35,"wins":4},"meta/muse-spark-open":{"draws":8,"losses":30,"wins":4},"meta/muse-wonder":{"draws":5,"losses":35,"wins":2},"minimax/minimax-m3":{"draws":3,"losses":9,"wins":10},"minimax/minimax-m3.1-flash":{"draws":7,"losses":19,"wins":12},"mistralai/mistral-large-4-0":{"draws":8,"losses":14,"wins":4},"mistralai/mistral-medium-3-5":{"draws":9,"losses":8,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":21,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":35,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":10,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":19,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":11,"wins":3},"o3":{"draws":15,"losses":38,"wins":11},"openai/gpt-oss-120b":{"draws":5,"losses":19,"wins":12},"poolside/laguna-s-2.1":{"draws":12,"losses":19,"wins":9},"qwen/qwen3.7-max":{"draws":4,"losses":14,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":12,"wins":5},"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":9,"losses":15,"wins":4},"qwen/qwen3.8-max":{"draws":13,"losses":24,"wins":5},"qwen/qwen3.8-max-0902":{"draws":8,"losses":29,"wins":5},"recursive/flint-v1.0":{"draws":2,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":23,"wins":8},"stealth/ox-alpha":{"draws":23,"losses":100,"wins":19},"stealth/space-bunny-alpha":{"draws":8,"losses":21,"wins":5},"stepfun/step-3.7-flash":{"draws":10,"losses":14,"wins":8},"stepfun/step-5-preview":{"draws":0,"losses":7,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":12,"wins":8},"tencent/hy4-preview":{"draws":9,"losses":29,"wins":4},"thinkingmachines/inkling":{"draws":14,"losses":24,"wins":20},"thinkingmachines/inkling-small":{"draws":12,"losses":12,"wins":18},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":8,"losses":29,"wins":5},"x-ai/grok-4.7":{"draws":2,"losses":33,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":5,"wins":6},"xiaomi/mimo-v2.5":{"draws":15,"losses":29,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":20,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":22,"wins":2},"z-ai/glm-5.2":{"draws":29,"losses":41,"wins":14},"z-ai/glm-5.3":{"draws":7,"losses":32,"wins":1},"z-ai/glm-5.3-flash":{"draws":10,"losses":26,"wins":6},"z-ai/glm-5.3-flashx":{"draws":3,"losses":32,"wins":7}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":31},"claude-fable-5":{"draws":5,"losses":20,"wins":7},"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":16,"wins":43},"claude-opus-4-8":{"draws":11,"losses":17,"wins":16},"claude-opus-5":{"draws":13,"losses":54,"wins":15},"claude-opus-5-5":{"draws":1,"losses":46,"wins":5},"claude-sonnet-5":{"draws":12,"losses":12,"wins":24},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":16,"losses":7,"wins":49},"deepseek/deepseek-v4-pro":{"draws":15,"losses":10,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":9,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":20,"wins":18},"elorian/glimpse":{"draws":5,"losses":12,"wins":9},"fireworks/ember-1":{"draws":14,"losses":10,"wins":24},"gemini-3.1-pro-preview":{"draws":11,"losses":15,"wins":22},"gemini-4-argon":{"draws":1,"losses":41,"wins":6},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":26},"google/gemini-3.5-flash":{"draws":14,"losses":16,"wins":30},"google/gemini-3.5-flash-lite":{"draws":21,"losses":12,"wins":51},"google/gemini-3.6-flash":{"draws":21,"losses":31,"wins":40},"google/gemini-3.8-flash":{"draws":8,"losses":22,"wins":18},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":15},"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":13,"wins":19},"gpt-5.4-mini":{"draws":9,"losses":3,"wins":20},"gpt-5.4-nano":{"draws":10,"losses":4,"wins":34},"gpt-5.5":{"draws":16,"losses":10,"wins":18},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":28},"gpt-5.6-sol":{"draws":7,"losses":26,"wins":15},"gpt-5.6-terra":{"draws":14,"losses":8,"wins":24},"gpt-6-astra":{"draws":4,"losses":38,"wins":6},"gpt-6-luna":{"draws":11,"losses":10,"wins":27},"gpt-6-sol":{"draws":7,"losses":30,"wins":11},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":7},"gpt-6.1-terra":{"draws":3,"losses":34,"wins":11},"gpt-6.1-terra-pro":{"draws":5,"losses":36,"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},"inception/mercury-3":{"draws":13,"losses":4,"wins":17},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":8,"losses":9,"wins":35},"meta/muse-glimmer-30b":{"draws":12,"losses":1,"wins":29},"meta/muse-spark-1.2":{"draws":11,"losses":13,"wins":22},"meta/muse-spark-1.3":{"draws":10,"losses":18,"wins":20},"meta/muse-spark-open":{"draws":14,"losses":11,"wins":23},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":8,"losses":0,"wins":18},"minimax/minimax-m3.1-flash":{"draws":11,"losses":10,"wins":21},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":10,"wins":22},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":40,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":1,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":4,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":0,"wins":14},"o3":{"draws":7,"losses":11,"wins":48},"openai/gpt-oss-120b":{"draws":13,"losses":3,"wins":26},"poolside/laguna-s-2.1":{"draws":14,"losses":7,"wins":25},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":19},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":14,"wins":19},"qwen/qwen3.8-27b":{"draws":11,"losses":8,"wins":15},"qwen/qwen3.8-flash":{"draws":8,"losses":9,"wins":15},"qwen/qwen3.8-max":{"draws":12,"losses":13,"wins":23},"qwen/qwen3.8-max-0902":{"draws":12,"losses":12,"wins":24},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":10,"wins":24},"stealth/ox-alpha":{"draws":34,"losses":53,"wins":71},"stealth/space-bunny-alpha":{"draws":12,"losses":7,"wins":19},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":12,"losses":4,"wins":10},"tencent/hy4-preview":{"draws":7,"losses":16,"wins":23},"thinkingmachines/inkling":{"draws":18,"losses":4,"wins":42},"thinkingmachines/inkling-small":{"draws":13,"losses":5,"wins":30},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":11,"losses":21,"wins":16},"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":16,"losses":4,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":9,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":19,"wins":12},"z-ai/glm-5.2":{"draws":29,"losses":19,"wins":48},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":18},"z-ai/glm-5.3-flashx":{"draws":9,"losses":18,"wins":21}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":38},"claude-fable-5":{"draws":7,"losses":5,"wins":36},"claude-fable-5-1":{"draws":2,"losses":28,"wins":8},"claude-haiku-5-5":{"draws":3,"losses":6,"wins":37},"claude-opus-4-5":{"draws":7,"losses":2,"wins":69},"claude-opus-4-8":{"draws":3,"losses":5,"wins":36},"claude-opus-5":{"draws":12,"losses":25,"wins":45},"claude-opus-5-5":{"draws":5,"losses":25,"wins":22},"claude-sonnet-5":{"draws":4,"losses":2,"wins":42},"claude-sonnet-5-5":{"draws":4,"losses":14,"wins":30},"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":2,"losses":1,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":3,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":7,"wins":38},"elorian/glimpse":{"draws":4,"losses":4,"wins":18},"fireworks/ember-1":{"draws":3,"losses":1,"wins":44},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":42},"gemini-4-argon":{"draws":7,"losses":19,"wins":22},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":28},"google/gemini-3.5-flash":{"draws":6,"losses":3,"wins":51},"google/gemini-3.5-flash-lite":{"draws":7,"losses":0,"wins":77},"google/gemini-3.6-flash":{"draws":7,"losses":3,"wins":82},"google/gemini-3.8-flash":{"draws":5,"losses":4,"wins":39},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":25},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":0,"wins":41},"gpt-5.4":{"draws":5,"losses":7,"wins":34},"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":5,"wins":36},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":41},"gpt-5.6-sol":{"draws":5,"losses":7,"wins":36},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":42},"gpt-6-astra":{"draws":4,"losses":29,"wins":15},"gpt-6-luna":{"draws":6,"losses":1,"wins":41},"gpt-6-sol":{"draws":6,"losses":15,"wins":27},"gpt-6.1-sol":{"draws":2,"losses":27,"wins":19},"gpt-6.1-terra":{"draws":5,"losses":24,"wins":19},"gpt-6.1-terra-pro":{"draws":9,"losses":22,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":30},"inception/mercury-3":{"draws":2,"losses":1,"wins":29},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":8},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":49},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":40},"meta/muse-spark-1.2":{"draws":4,"losses":1,"wins":41},"meta/muse-spark-1.3":{"draws":5,"losses":6,"wins":37},"meta/muse-spark-open":{"draws":2,"losses":4,"wins":42},"meta/muse-wonder":{"draws":6,"losses":11,"wins":31},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"minimax/minimax-m3.1-flash":{"draws":2,"losses":1,"wins":39},"mistralai/mistral-large-4-0":{"draws":3,"losses":2,"wins":25},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":3,"losses":5,"wins":38},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":19,"wins":26},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":1,"wins":18},"o3":{"draws":1,"losses":3,"wins":62},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":40},"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":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":2,"wins":42},"qwen/qwen3.8-27b":{"draws":5,"losses":1,"wins":28},"qwen/qwen3.8-flash":{"draws":4,"losses":1,"wins":27},"qwen/qwen3.8-max":{"draws":5,"losses":1,"wins":42},"qwen/qwen3.8-max-0902":{"draws":4,"losses":5,"wins":39},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":0,"wins":38},"stealth/ox-alpha":{"draws":11,"losses":8,"wins":139},"stealth/space-bunny-alpha":{"draws":2,"losses":0,"wins":36},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":22},"tencent/hy4-preview":{"draws":5,"losses":6,"wins":35},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":62},"thinkingmachines/inkling-small":{"draws":7,"losses":0,"wins":41},"unbiased/pareto-26.10":{"draws":1,"losses":12,"wins":3},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":6},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":8,"losses":3,"wins":37},"x-ai/grok-4.6":{"draws":3,"losses":8,"wins":37},"x-ai/grok-4.7":{"draws":2,"losses":16,"wins":24},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":2,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":23},"z-ai/glm-5.2":{"draws":9,"losses":1,"wins":86},"z-ai/glm-5.3":{"draws":3,"losses":11,"wins":32},"z-ai/glm-5.3-flash":{"draws":4,"losses":2,"wins":42},"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":10,"losses":35,"wins":3},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":17,"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":11,"losses":65,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":31,"wins":9},"elorian/glimpse":{"draws":6,"losses":14,"wins":6},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":15,"losses":23,"wins":10},"gemini-4-argon":{"draws":2,"losses":43,"wins":3},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":19,"losses":26,"wins":15},"google/gemini-3.5-flash-lite":{"draws":30,"losses":22,"wins":32},"google/gemini-3.6-flash":{"draws":29,"losses":49,"wins":14},"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":23,"wins":5},"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":34,"wins":7},"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},"gpt-6.1-terra":{"draws":8,"losses":38,"wins":2},"gpt-6.1-terra-pro":{"draws":5,"losses":42,"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},"inception/mercury-3":{"draws":9,"losses":17,"wins":6},"inclusionai/ling-3.0-flash":{"draws":15,"losses":3,"wins":16},"inclusionai/ling-3.1-flash":{"draws":0,"losses":1,"wins":3},"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":12,"losses":22,"wins":12},"meta/muse-spark-1.3":{"draws":11,"losses":28,"wins":9},"meta/muse-spark-open":{"draws":14,"losses":28,"wins":6},"meta/muse-wonder":{"draws":11,"losses":36,"wins":1},"minimax/minimax-m3":{"draws":5,"losses":9,"wins":12},"minimax/minimax-m3.1-flash":{"draws":14,"losses":16,"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":1,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":19,"losses":19,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":40,"wins":2},"nex-agi/nex-n2-pro":{"draws":9,"losses":5,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":11,"wins":5},"o3":{"draws":16,"losses":35,"wins":15},"openai/gpt-oss-120b":{"draws":17,"losses":7,"wins":18},"poolside/laguna-s-2.1":{"draws":20,"losses":18,"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},"recursive/flint-v1.0":{"draws":4,"losses":6,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":16,"losses":19,"wins":9},"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":3,"losses":5,"wins":2},"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":{"draws":1,"losses":15,"wins":0},"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":25,"wins":7},"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":8,"losses":4,"wins":12},"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":13,"losses":17,"wins":14},"claude-fable-5":{"draws":9,"losses":27,"wins":12},"claude-fable-5-1":{"draws":2,"losses":49,"wins":3},"claude-haiku-5-5":{"draws":15,"losses":19,"wins":12},"claude-opus-4-5":{"draws":21,"losses":20,"wins":21},"claude-opus-4-8":{"draws":11,"losses":24,"wins":9},"claude-opus-5":{"draws":15,"losses":59,"wins":8},"claude-opus-5-5":{"draws":6,"losses":42,"wins":4},"claude-sonnet-5":{"draws":16,"losses":23,"wins":9},"claude-sonnet-5-5":{"draws":9,"losses":26,"wins":13},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":16},"deepseek/deepseek-v4-flash":{"draws":22,"losses":19,"wins":31},"deepseek/deepseek-v4-pro":{"draws":14,"losses":20,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":17,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":22,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":31,"wins":7},"elorian/glimpse":{"draws":7,"losses":12,"wins":7},"fireworks/ember-1":{"draws":18,"losses":21,"wins":9},"gemini-3.1-pro-preview":{"draws":13,"losses":18,"wins":17},"gemini-4-argon":{"draws":3,"losses":43,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":14,"losses":26,"wins":20},"google/gemini-3.5-flash-lite":{"draws":29,"losses":18,"wins":37},"google/gemini-3.6-flash":{"draws":26,"losses":42,"wins":24},"google/gemini-3.8-flash":{"draws":15,"losses":22,"wins":11},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":13},"gpt-4.1":{"draws":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":14,"wins":14},"gpt-5.4":{"draws":11,"losses":21,"wins":14},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":11},"gpt-5.4-nano":{"draws":12,"losses":13,"wins":23},"gpt-5.5":{"draws":22,"losses":16,"wins":6},"gpt-5.6-luna":{"draws":19,"losses":10,"wins":19},"gpt-5.6-sol":{"draws":9,"losses":33,"wins":6},"gpt-5.6-terra":{"draws":20,"losses":15,"wins":11},"gpt-6-astra":{"draws":2,"losses":42,"wins":4},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":5,"losses":39,"wins":4},"gpt-6.1-terra":{"draws":8,"losses":36,"wins":4},"gpt-6.1-terra-pro":{"draws":5,"losses":40,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":18},"inception/mercury-3":{"draws":9,"losses":13,"wins":10},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":17,"losses":6,"wins":29},"meta/muse-glimmer-30b":{"draws":16,"losses":7,"wins":19},"meta/muse-spark-1.2":{"draws":12,"losses":17,"wins":17},"meta/muse-spark-1.3":{"draws":12,"losses":29,"wins":7},"meta/muse-spark-open":{"draws":17,"losses":18,"wins":13},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":17},"minimax/minimax-m3.1-flash":{"draws":13,"losses":12,"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":0,"wins":0},"moonshotai/kimi-k3":{"draws":18,"losses":15,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":34,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":7,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":7,"wins":6},"o3":{"draws":8,"losses":17,"wins":41},"openai/gpt-oss-120b":{"draws":15,"losses":13,"wins":14},"poolside/laguna-s-2.1":{"draws":18,"losses":7,"wins":21},"qwen/qwen3.7-max":{"draws":5,"losses":10,"wins":13},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":20,"wins":12},"qwen/qwen3.8-27b":{"draws":13,"losses":12,"wins":9},"qwen/qwen3.8-flash":{"draws":12,"losses":11,"wins":9},"qwen/qwen3.8-max":{"draws":13,"losses":20,"wins":15},"qwen/qwen3.8-max-0902":{"draws":10,"losses":17,"wins":21},"recursive/flint-v1.0":{"draws":6,"losses":0,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":13,"wins":17},"stealth/ox-alpha":{"draws":43,"losses":76,"wins":39},"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":4,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":14},"tencent/hy4-preview":{"draws":13,"losses":20,"wins":13},"thinkingmachines/inkling":{"draws":25,"losses":9,"wins":30},"thinkingmachines/inkling-small":{"draws":16,"losses":6,"wins":26},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":13,"losses":20,"wins":15},"x-ai/grok-4.6":{"draws":10,"losses":24,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":23,"losses":12,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":10,"wins":10},"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":10,"losses":8,"wins":20},"claude-fable-5":{"draws":5,"losses":31,"wins":6},"claude-fable-5-1":{"draws":2,"losses":42,"wins":2},"claude-haiku-5-5":{"draws":8,"losses":19,"wins":15},"claude-opus-4-5":{"draws":21,"losses":21,"wins":28},"claude-opus-4-8":{"draws":7,"losses":16,"wins":5},"claude-opus-5":{"draws":10,"losses":51,"wins":9},"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":23,"wins":12},"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":8,"losses":18,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":21,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":24,"wins":8},"elorian/glimpse":{"draws":5,"losses":11,"wins":6},"fireworks/ember-1":{"draws":15,"losses":15,"wins":12},"gemini-3.1-pro-preview":{"draws":12,"losses":11,"wins":19},"gemini-4-argon":{"draws":1,"losses":38,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":22},"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":41,"wins":21},"google/gemini-3.8-flash":{"draws":8,"losses":25,"wins":9},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":14},"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":6,"losses":30,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":15,"wins":13},"gpt-6-astra":{"draws":2,"losses":37,"wins":3},"gpt-6-luna":{"draws":9,"losses":17,"wins":16},"gpt-6-sol":{"draws":5,"losses":27,"wins":10},"gpt-6.1-sol":{"draws":1,"losses":36,"wins":5},"gpt-6.1-terra":{"draws":5,"losses":35,"wins":2},"gpt-6.1-terra-pro":{"draws":6,"losses":33,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":5,"wins":16},"inception/mercury-3":{"draws":9,"losses":6,"wins":13},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":20},"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":10,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":10,"losses":19,"wins":11},"meta/muse-spark-1.3":{"draws":8,"losses":22,"wins":12},"meta/muse-spark-open":{"draws":11,"losses":22,"wins":9},"meta/muse-wonder":{"draws":8,"losses":22,"wins":12},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":17},"minimax/minimax-m3.1-flash":{"draws":8,"losses":12,"wins":16},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":9},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":17,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":36,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":10},"o3":{"draws":7,"losses":28,"wins":27},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":19},"poolside/laguna-s-2.1":{"draws":12,"losses":7,"wins":19},"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":12,"losses":18,"wins":12},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":11},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":14},"qwen/qwen3.8-max":{"draws":10,"losses":17,"wins":15},"qwen/qwen3.8-max-0902":{"draws":9,"losses":18,"wins":15},"recursive/flint-v1.0":{"draws":6,"losses":0,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":12,"wins":17},"stealth/ox-alpha":{"draws":18,"losses":64,"wins":36},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":15},"stepfun/step-3.7-flash":{"draws":4,"losses":8,"wins":18},"stepfun/step-5-preview":{"draws":1,"losses":7,"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":8,"wins":33},"thinkingmachines/inkling-small":{"draws":12,"losses":6,"wins":24},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":1},"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":11,"losses":24,"wins":7},"x-ai/grok-4.6":{"draws":10,"losses":22,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":20,"losses":13,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":10},"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":27,"wins":5},"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":12,"losses":10,"wins":56},"claude-fable-5":{"draws":16,"losses":28,"wins":40},"claude-fable-5-1":{"draws":8,"losses":67,"wins":19},"claude-haiku-5-5":{"draws":19,"losses":14,"wins":47},"claude-opus-4-5":{"draws":34,"losses":19,"wins":83},"claude-opus-4-8":{"draws":17,"losses":12,"wins":47},"claude-opus-5":{"draws":21,"losses":69,"wins":36},"claude-opus-5-5":{"draws":11,"losses":66,"wins":15},"claude-sonnet-5":{"draws":17,"losses":18,"wins":49},"claude-sonnet-5-5":{"draws":16,"losses":33,"wins":35},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":26},"deepseek/deepseek-v4-flash":{"draws":24,"losses":12,"wins":88},"deepseek/deepseek-v4-pro":{"draws":13,"losses":16,"wins":49},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":11,"wins":56},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":13,"wins":53},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":21,"wins":45},"elorian/glimpse":{"draws":8,"losses":11,"wins":27},"fireworks/ember-1":{"draws":15,"losses":16,"wins":53},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":56},"gemini-4-argon":{"draws":13,"losses":45,"wins":26},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":45},"google/gemini-3.5-flash":{"draws":14,"losses":23,"wins":67},"google/gemini-3.5-flash-lite":{"draws":27,"losses":18,"wins":101},"google/gemini-3.6-flash":{"draws":32,"losses":42,"wins":86},"google/gemini-3.8-flash":{"draws":15,"losses":23,"wins":46},"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":17,"losses":13,"wins":50},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":34},"gpt-5.4-nano":{"draws":11,"losses":6,"wins":65},"gpt-5.5":{"draws":14,"losses":18,"wins":46},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":60},"gpt-5.6-sol":{"draws":7,"losses":27,"wins":50},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":60},"gpt-6-astra":{"draws":10,"losses":58,"wins":16},"gpt-6-luna":{"draws":20,"losses":11,"wins":53},"gpt-6-sol":{"draws":14,"losses":38,"wins":32},"gpt-6.1-sol":{"draws":12,"losses":52,"wins":20},"gpt-6.1-terra":{"draws":9,"losses":51,"wins":24},"gpt-6.1-terra-pro":{"draws":10,"losses":48,"wins":26},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":42},"inception/mercury-3":{"draws":10,"losses":10,"wins":36},"inclusionai/ling-3.0-flash":{"draws":17,"losses":2,"wins":39},"inclusionai/ling-3.1-flash":{"draws":5,"losses":0,"wins":9},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":68},"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":16,"losses":23,"wins":45},"meta/muse-spark-open":{"draws":13,"losses":21,"wins":50},"meta/muse-wonder":{"draws":14,"losses":28,"wins":42},"minimax/minimax-m3":{"draws":11,"losses":0,"wins":35},"minimax/minimax-m3.1-flash":{"draws":13,"losses":9,"wins":50},"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":1,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":18,"losses":23,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":52,"wins":24},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":35},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":4,"wins":47},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":3,"wins":25},"o3":{"draws":15,"losses":7,"wins":86},"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":6,"losses":6,"wins":36},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":24,"wins":49},"qwen/qwen3.8-27b":{"draws":15,"losses":4,"wins":39},"qwen/qwen3.8-flash":{"draws":13,"losses":9,"wins":34},"qwen/qwen3.8-max":{"draws":21,"losses":21,"wins":42},"qwen/qwen3.8-max-0902":{"draws":17,"losses":20,"wins":47},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":20},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":15,"wins":50},"stealth/ox-alpha":{"draws":67,"losses":69,"wins":146},"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":1,"losses":3,"wins":12},"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":{"draws":3,"losses":19,"wins":6},"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":15,"losses":22,"wins":47},"x-ai/grok-4.6":{"draws":16,"losses":22,"wins":46},"x-ai/grok-4.7":{"draws":8,"losses":39,"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":6,"losses":3,"wins":35},"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":42,"losses":13,"wins":113},"z-ai/glm-5.3":{"draws":14,"losses":34,"wins":32},"z-ai/glm-5.3-flash":{"draws":18,"losses":20,"wins":46},"z-ai/glm-5.3-flashx":{"draws":17,"losses":23,"wins":44}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":38},"claude-fable-5":{"draws":8,"losses":16,"wins":30},"claude-fable-5-1":{"draws":3,"losses":41,"wins":16},"claude-haiku-5-5":{"draws":12,"losses":6,"wins":34},"claude-opus-4-5":{"draws":15,"losses":13,"wins":60},"claude-opus-4-8":{"draws":7,"losses":16,"wins":27},"claude-opus-5":{"draws":17,"losses":50,"wins":27},"claude-opus-5-5":{"draws":2,"losses":31,"wins":11},"claude-sonnet-5":{"draws":10,"losses":9,"wins":35},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":29},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":20},"deepseek/deepseek-v4-flash":{"draws":11,"losses":6,"wins":65},"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":9,"losses":9,"wins":36},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":14,"wins":33},"elorian/glimpse":{"draws":6,"losses":5,"wins":19},"fireworks/ember-1":{"draws":8,"losses":10,"wins":36},"gemini-3.1-pro-preview":{"draws":8,"losses":6,"wins":40},"gemini-4-argon":{"draws":6,"losses":26,"wins":22},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":10,"losses":8,"wins":50},"google/gemini-3.5-flash-lite":{"draws":16,"losses":1,"wins":77},"google/gemini-3.6-flash":{"draws":17,"losses":11,"wins":74},"google/gemini-3.8-flash":{"draws":9,"losses":16,"wins":29},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":27},"gpt-4.1":{"draws":3,"losses":1,"wins":14},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":2,"wins":38},"gpt-5.4":{"draws":8,"losses":4,"wins":40},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":31},"gpt-5.4-nano":{"draws":6,"losses":1,"wins":49},"gpt-5.5":{"draws":11,"losses":11,"wins":28},"gpt-5.6-luna":{"draws":14,"losses":1,"wins":39},"gpt-5.6-sol":{"draws":9,"losses":13,"wins":32},"gpt-5.6-terra":{"draws":8,"losses":2,"wins":42},"gpt-6-astra":{"draws":7,"losses":35,"wins":12},"gpt-6-luna":{"draws":12,"losses":2,"wins":40},"gpt-6-sol":{"draws":7,"losses":24,"wins":23},"gpt-6.1-sol":{"draws":8,"losses":35,"wins":11},"gpt-6.1-terra":{"draws":4,"losses":34,"wins":16},"gpt-6.1-terra-pro":{"draws":7,"losses":33,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":30},"inception/mercury-3":{"draws":2,"losses":1,"wins":35},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":9,"losses":5,"wins":46},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":41},"meta/muse-spark-1.2":{"draws":11,"losses":5,"wins":36},"meta/muse-spark-1.3":{"draws":8,"losses":11,"wins":35},"meta/muse-spark-open":{"draws":10,"losses":12,"wins":32},"meta/muse-wonder":{"draws":5,"losses":21,"wins":28},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":27},"minimax/minimax-m3.1-flash":{"draws":5,"losses":1,"wins":38},"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":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":42},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":29,"wins":23},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":1,"wins":21},"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":3,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":12,"wins":32},"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":12,"losses":11,"wins":31},"qwen/qwen3.8-max-0902":{"draws":9,"losses":5,"wins":40},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":3,"wins":36},"stealth/ox-alpha":{"draws":38,"losses":25,"wins":111},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":36},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":4,"losses":2,"wins":8},"tencent/hy3-preview":{"draws":6,"losses":0,"wins":24},"tencent/hy4-preview":{"draws":9,"losses":10,"wins":33},"thinkingmachines/inkling":{"draws":15,"losses":0,"wins":55},"thinkingmachines/inkling-small":{"draws":8,"losses":0,"wins":46},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":6},"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":14,"wins":28},"x-ai/grok-4.6":{"draws":12,"losses":11,"wins":31},"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":12,"losses":4,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":2,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":16,"losses":10,"wins":82},"z-ai/glm-5.3":{"draws":6,"losses":18,"wins":28},"z-ai/glm-5.3-flash":{"draws":6,"losses":7,"wins":41},"z-ai/glm-5.3-flashx":{"draws":11,"losses":5,"wins":38}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":14,"wins":17},"claude-fable-5":{"draws":8,"losses":33,"wins":7},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":21,"wins":10},"claude-opus-4-5":{"draws":26,"losses":31,"wins":21},"claude-opus-4-8":{"draws":12,"losses":23,"wins":9},"claude-opus-5":{"draws":13,"losses":60,"wins":9},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":7,"losses":16,"wins":9},"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":19,"losses":19,"wins":34},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":15,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":21,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":30,"wins":8},"elorian/glimpse":{"draws":5,"losses":10,"wins":11},"fireworks/ember-1":{"draws":15,"losses":23,"wins":10},"gemini-3.1-pro-preview":{"draws":12,"losses":21,"wins":15},"gemini-4-argon":{"draws":2,"losses":46,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":19},"google/gemini-3.5-flash":{"draws":14,"losses":31,"wins":15},"google/gemini-3.5-flash-lite":{"draws":19,"losses":23,"wins":42},"google/gemini-3.6-flash":{"draws":24,"losses":42,"wins":26},"google/gemini-3.8-flash":{"draws":8,"losses":29,"wins":11},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":19,"wins":12},"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":15,"losses":21,"wins":8},"gpt-5.6-luna":{"draws":12,"losses":12,"wins":24},"gpt-5.6-sol":{"draws":7,"losses":37,"wins":4},"gpt-5.6-terra":{"draws":15,"losses":21,"wins":10},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":13,"losses":19,"wins":16},"gpt-6-sol":{"draws":7,"losses":36,"wins":5},"gpt-6.1-sol":{"draws":0,"losses":46,"wins":2},"gpt-6.1-terra":{"draws":8,"losses":40,"wins":0},"gpt-6.1-terra-pro":{"draws":5,"losses":39,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":18},"inception/mercury-3":{"draws":10,"losses":13,"wins":9},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":5,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":15,"wins":26},"meta/muse-glimmer-30b":{"draws":14,"losses":8,"wins":20},"meta/muse-spark-1.2":{"draws":11,"losses":25,"wins":10},"meta/muse-spark-1.3":{"draws":12,"losses":28,"wins":8},"meta/muse-spark-open":{"draws":15,"losses":26,"wins":7},"meta/muse-wonder":{"draws":10,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":11},"minimax/minimax-m3.1-flash":{"draws":10,"losses":12,"wins":20},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":18},"moonshotai/kimi-k3":{"draws":14,"losses":18,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":38,"wins":4},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":6,"wins":11},"o3":{"draws":10,"losses":28,"wins":28},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":22},"poolside/laguna-s-2.1":{"draws":14,"losses":14,"wins":18},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":15},"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":7,"losses":13,"wins":12},"qwen/qwen3.8-max":{"draws":17,"losses":25,"wins":6},"qwen/qwen3.8-max-0902":{"draws":11,"losses":27,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":19,"wins":10},"stealth/ox-alpha":{"draws":34,"losses":84,"wins":40},"stealth/space-bunny-alpha":{"draws":9,"losses":16,"wins":13},"stepfun/step-3.7-flash":{"draws":9,"losses":10,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":11},"tencent/hy4-preview":{"draws":13,"losses":22,"wins":11},"thinkingmachines/inkling":{"draws":20,"losses":8,"wins":36},"thinkingmachines/inkling-small":{"draws":13,"losses":10,"wins":25},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":28,"wins":9},"x-ai/grok-4.6":{"draws":14,"losses":27,"wins":7},"x-ai/grok-4.7":{"draws":4,"losses":32,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":25,"losses":19,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":9,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":20,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":19,"wins":10},"z-ai/glm-5.2":{"draws":24,"losses":35,"wins":37},"z-ai/glm-5.3":{"draws":8,"losses":32,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":28,"wins":12},"z-ai/glm-5.3-flashx":{"draws":9,"losses":31,"wins":8}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":17,"wins":19},"claude-fable-5":{"draws":9,"losses":30,"wins":9},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":21,"wins":15},"claude-opus-4-5":{"draws":17,"losses":35,"wins":26},"claude-opus-4-8":{"draws":12,"losses":23,"wins":9},"claude-opus-5":{"draws":11,"losses":64,"wins":7},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":11,"losses":20,"wins":17},"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":21,"losses":20,"wins":31},"deepseek/deepseek-v4-pro":{"draws":15,"losses":19,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":20,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":24,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":33,"wins":7},"elorian/glimpse":{"draws":6,"losses":11,"wins":9},"fireworks/ember-1":{"draws":11,"losses":22,"wins":15},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":17},"gemini-4-argon":{"draws":2,"losses":43,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":10,"wins":15},"google/gemini-3.5-flash":{"draws":15,"losses":25,"wins":20},"google/gemini-3.5-flash-lite":{"draws":20,"losses":21,"wins":43},"google/gemini-3.6-flash":{"draws":23,"losses":51,"wins":18},"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":11,"losses":24,"wins":11},"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":12,"losses":17,"wins":17},"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},"gpt-6.1-terra":{"draws":8,"losses":40,"wins":0},"gpt-6.1-terra-pro":{"draws":3,"losses":45,"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},"inception/mercury-3":{"draws":8,"losses":11,"wins":13},"inclusionai/ling-3.0-flash":{"draws":11,"losses":4,"wins":19},"inclusionai/ling-3.1-flash":{"draws":1,"losses":3,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":18,"wins":26},"meta/muse-glimmer-30b":{"draws":11,"losses":12,"wins":19},"meta/muse-spark-1.2":{"draws":10,"losses":28,"wins":8},"meta/muse-spark-1.3":{"draws":9,"losses":31,"wins":8},"meta/muse-spark-open":{"draws":10,"losses":28,"wins":8},"meta/muse-wonder":{"draws":5,"losses":32,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":12},"minimax/minimax-m3.1-flash":{"draws":10,"losses":16,"wins":16},"mistralai/mistral-large-4-0":{"draws":11,"losses":15,"wins":4},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":27,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":44,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":7,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":9,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":7,"wins":10},"o3":{"draws":8,"losses":30,"wins":28},"openai/gpt-oss-120b":{"draws":10,"losses":10,"wins":22},"poolside/laguna-s-2.1":{"draws":10,"losses":12,"wins":24},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":6,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":29,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":15,"wins":13},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":11},"qwen/qwen3.8-max":{"draws":9,"losses":25,"wins":14},"qwen/qwen3.8-max-0902":{"draws":10,"losses":29,"wins":9},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":21,"wins":11},"stealth/ox-alpha":{"draws":36,"losses":90,"wins":32},"stealth/space-bunny-alpha":{"draws":8,"losses":15,"wins":15},"stepfun/step-3.7-flash":{"draws":2,"losses":19,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":8,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":15},"tencent/hy4-preview":{"draws":8,"losses":29,"wins":9},"thinkingmachines/inkling":{"draws":16,"losses":23,"wins":25},"thinkingmachines/inkling-small":{"draws":13,"losses":16,"wins":19},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":7,"losses":32,"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":20,"losses":18,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":18,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":9},"z-ai/glm-5.2":{"draws":20,"losses":42,"wins":34},"z-ai/glm-5.3":{"draws":6,"losses":33,"wins":7},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":18,"wins":0},"elorian/glimpse":{"draws":0,"losses":9,"wins":1},"fireworks/ember-1":{"draws":3,"losses":13,"wins":2},"gemini-3.1-pro-preview":{"draws":4,"losses":10,"wins":4},"gemini-4-argon":{"draws":0,"losses":18,"wins":0},"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},"gpt-6.1-terra":{"draws":0,"losses":18,"wins":0},"gpt-6.1-terra-pro":{"draws":0,"losses":18,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":6,"wins":2},"inception/mercury-3":{"draws":0,"losses":10,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":4,"wins":0},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"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-spark-open":{"draws":0,"losses":18,"wins":0},"meta/muse-wonder":{"draws":0,"losses":18,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":8,"wins":2},"minimax/minimax-m3.1-flash":{"draws":0,"losses":12,"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-k3":{"draws":4,"losses":14,"wins":0},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":18,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":7,"wins":3},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":8,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":9,"wins":1},"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},"recursive/flint-v1.0":{"draws":0,"losses":3,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":18,"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":0,"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":{"draws":0,"losses":6,"wins":0},"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":2,"losses":5,"wins":3},"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":8,"losses":13,"wins":17},"claude-fable-5":{"draws":7,"losses":35,"wins":0},"claude-fable-5-1":{"draws":0,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":24,"wins":4},"claude-opus-4-5":{"draws":19,"losses":37,"wins":12},"claude-opus-4-8":{"draws":6,"losses":26,"wins":6},"claude-opus-5":{"draws":7,"losses":61,"wins":2},"claude-opus-5-5":{"draws":4,"losses":42,"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":3,"losses":3,"wins":10},"deepseek/deepseek-v4-flash":{"draws":14,"losses":17,"wins":21},"deepseek/deepseek-v4-pro":{"draws":8,"losses":18,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":17,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":25,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":32,"wins":4},"elorian/glimpse":{"draws":4,"losses":12,"wins":6},"fireworks/ember-1":{"draws":14,"losses":16,"wins":12},"gemini-3.1-pro-preview":{"draws":10,"losses":18,"wins":14},"gemini-4-argon":{"draws":0,"losses":42,"wins":0},"google/gemini-3.1-flash-lite":{"draws":3,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":7,"losses":27,"wins":18},"google/gemini-3.5-flash-lite":{"draws":11,"losses":25,"wins":36},"google/gemini-3.6-flash":{"draws":14,"losses":57,"wins":9},"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":4,"losses":26,"wins":8},"gpt-5.4":{"draws":7,"losses":28,"wins":5},"gpt-5.4-mini":{"draws":10,"losses":8,"wins":10},"gpt-5.4-nano":{"draws":11,"losses":17,"wins":18},"gpt-5.5":{"draws":7,"losses":24,"wins":7},"gpt-5.6-luna":{"draws":9,"losses":17,"wins":16},"gpt-5.6-sol":{"draws":5,"losses":31,"wins":6},"gpt-5.6-terra":{"draws":8,"losses":26,"wins":6},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":9,"losses":21,"wins":12},"gpt-6-sol":{"draws":5,"losses":35,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":0},"gpt-6.1-terra":{"draws":5,"losses":37,"wins":0},"gpt-6.1-terra-pro":{"draws":5,"losses":36,"wins":1},"inception/mercury-2.5-preview":{"draws":6,"losses":3,"wins":19},"inception/mercury-3":{"draws":9,"losses":14,"wins":7},"inclusionai/ling-3.0-flash":{"draws":12,"losses":8,"wins":10},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":17,"wins":21},"meta/muse-glimmer-30b":{"draws":10,"losses":12,"wins":14},"meta/muse-spark-1.2":{"draws":7,"losses":24,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":33,"wins":4},"meta/muse-spark-open":{"draws":7,"losses":28,"wins":7},"meta/muse-wonder":{"draws":6,"losses":30,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":12,"wins":8},"minimax/minimax-m3.1-flash":{"draws":5,"losses":18,"wins":13},"mistralai/mistral-large-4-0":{"draws":6,"losses":16,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":6,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":21,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":36,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":9,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":11,"wins":6},"o3":{"draws":6,"losses":36,"wins":20},"openai/gpt-oss-120b":{"draws":11,"losses":13,"wins":14},"poolside/laguna-s-2.1":{"draws":14,"losses":16,"wins":14},"qwen/qwen3.7-max":{"draws":7,"losses":13,"wins":6},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":25,"wins":5},"qwen/qwen3.8-27b":{"draws":8,"losses":17,"wins":5},"qwen/qwen3.8-flash":{"draws":7,"losses":17,"wins":4},"qwen/qwen3.8-max":{"draws":11,"losses":24,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":30,"wins":5},"recursive/flint-v1.0":{"draws":2,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":22,"wins":10},"stealth/ox-alpha":{"draws":27,"losses":80,"wins":33},"stealth/space-bunny-alpha":{"draws":4,"losses":12,"wins":16},"stepfun/step-3.7-flash":{"draws":3,"losses":14,"wins":15},"stepfun/step-5-preview":{"draws":0,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":9,"losses":24,"wins":7},"thinkingmachines/inkling":{"draws":12,"losses":21,"wins":23},"thinkingmachines/inkling-small":{"draws":15,"losses":8,"wins":19},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":7,"losses":28,"wins":7},"x-ai/grok-4.6":{"draws":8,"losses":28,"wins":6},"x-ai/grok-4.7":{"draws":3,"losses":32,"wins":3},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":7},"xiaomi/mimo-v2.5":{"draws":19,"losses":21,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":15,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":20,"wins":3},"z-ai/glm-5.2":{"draws":25,"losses":37,"wins":22},"z-ai/glm-5.3":{"draws":7,"losses":29,"wins":4},"z-ai/glm-5.3-flash":{"draws":11,"losses":22,"wins":9},"z-ai/glm-5.3-flashx":{"draws":5,"losses":30,"wins":7}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":15,"wins":9},"claude-fable-5":{"draws":7,"losses":25,"wins":4},"claude-fable-5-1":{"draws":2,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":15,"wins":7},"claude-opus-4-5":{"draws":18,"losses":33,"wins":7},"claude-opus-4-8":{"draws":9,"losses":17,"wins":6},"claude-opus-5":{"draws":9,"losses":51,"wins":8},"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":4,"losses":6,"wins":6},"deepseek/deepseek-v4-flash":{"draws":16,"losses":12,"wins":24},"deepseek/deepseek-v4-pro":{"draws":5,"losses":14,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":15,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":27,"wins":5},"elorian/glimpse":{"draws":7,"losses":11,"wins":4},"fireworks/ember-1":{"draws":8,"losses":21,"wins":7},"gemini-3.1-pro-preview":{"draws":6,"losses":22,"wins":8},"gemini-4-argon":{"draws":3,"losses":32,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":14},"google/gemini-3.5-flash":{"draws":8,"losses":25,"wins":13},"google/gemini-3.5-flash-lite":{"draws":22,"losses":21,"wins":21},"google/gemini-3.6-flash":{"draws":20,"losses":38,"wins":12},"google/gemini-3.8-flash":{"draws":8,"losses":20,"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":11,"losses":15,"wins":8},"gpt-5.4":{"draws":6,"losses":19,"wins":11},"gpt-5.4-mini":{"draws":7,"losses":8,"wins":9},"gpt-5.4-nano":{"draws":1,"losses":22,"wins":11},"gpt-5.5":{"draws":12,"losses":18,"wins":6},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":28,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":13,"wins":7},"gpt-6-astra":{"draws":2,"losses":34,"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},"gpt-6.1-terra":{"draws":1,"losses":35,"wins":0},"gpt-6.1-terra-pro":{"draws":2,"losses":32,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":6,"wins":9},"inception/mercury-3":{"draws":5,"losses":11,"wins":6},"inclusionai/ling-3.0-flash":{"draws":11,"losses":7,"wins":6},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":11,"wins":19},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":11},"meta/muse-spark-1.2":{"draws":4,"losses":22,"wins":10},"meta/muse-spark-1.3":{"draws":5,"losses":25,"wins":6},"meta/muse-spark-open":{"draws":6,"losses":23,"wins":7},"meta/muse-wonder":{"draws":2,"losses":27,"wins":7},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":11},"minimax/minimax-m3.1-flash":{"draws":10,"losses":12,"wins":10},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":7,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":28,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":11,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":5},"o3":{"draws":6,"losses":26,"wins":20},"openai/gpt-oss-120b":{"draws":11,"losses":10,"wins":11},"poolside/laguna-s-2.1":{"draws":9,"losses":21,"wins":6},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":7,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":18,"wins":7},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":13,"wins":6},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":17,"wins":7},"recursive/flint-v1.0":{"draws":2,"losses":5,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":17,"wins":11},"stealth/ox-alpha":{"draws":29,"losses":66,"wins":31},"stealth/space-bunny-alpha":{"draws":8,"losses":12,"wins":10},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":11},"stepfun/step-5-preview":{"draws":0,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":9,"losses":19,"wins":8},"thinkingmachines/inkling":{"draws":19,"losses":14,"wins":19},"thinkingmachines/inkling-small":{"draws":13,"losses":11,"wins":12},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":14,"losses":20,"wins":2},"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":21,"losses":13,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":8,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":9,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":22,"losses":32,"wins":18},"z-ai/glm-5.3":{"draws":6,"losses":24,"wins":4},"z-ai/glm-5.3-flash":{"draws":3,"losses":26,"wins":7},"z-ai/glm-5.3-flashx":{"draws":10,"losses":21,"wins":5}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":13,"wins":9},"claude-fable-5":{"draws":6,"losses":27,"wins":3},"claude-fable-5-1":{"draws":1,"losses":41,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":3},"claude-opus-4-5":{"draws":19,"losses":29,"wins":10},"claude-opus-4-8":{"draws":7,"losses":22,"wins":3},"claude-opus-5":{"draws":6,"losses":45,"wins":7},"claude-opus-5-5":{"draws":4,"losses":36,"wins":0},"claude-sonnet-5":{"draws":9,"losses":19,"wins":8},"claude-sonnet-5-5":{"draws":5,"losses":26,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":14,"losses":22,"wins":18},"deepseek/deepseek-v4-pro":{"draws":12,"losses":11,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":14,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":22,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":24,"wins":4},"elorian/glimpse":{"draws":7,"losses":11,"wins":4},"fireworks/ember-1":{"draws":9,"losses":19,"wins":8},"gemini-3.1-pro-preview":{"draws":13,"losses":13,"wins":10},"gemini-4-argon":{"draws":7,"losses":29,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":11},"google/gemini-3.5-flash":{"draws":10,"losses":27,"wins":9},"google/gemini-3.5-flash-lite":{"draws":21,"losses":25,"wins":18},"google/gemini-3.6-flash":{"draws":12,"losses":42,"wins":16},"google/gemini-3.8-flash":{"draws":7,"losses":26,"wins":3},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":9},"gpt-4.1":{"draws":2,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":19,"wins":6},"gpt-5.4":{"draws":9,"losses":20,"wins":7},"gpt-5.4-mini":{"draws":9,"losses":8,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":16,"wins":13},"gpt-5.5":{"draws":10,"losses":17,"wins":7},"gpt-5.6-luna":{"draws":11,"losses":12,"wins":13},"gpt-5.6-sol":{"draws":5,"losses":25,"wins":6},"gpt-5.6-terra":{"draws":10,"losses":21,"wins":5},"gpt-6-astra":{"draws":2,"losses":33,"wins":1},"gpt-6-luna":{"draws":9,"losses":17,"wins":10},"gpt-6-sol":{"draws":3,"losses":30,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":34,"wins":1},"gpt-6.1-terra":{"draws":5,"losses":30,"wins":1},"gpt-6.1-terra-pro":{"draws":4,"losses":30,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":6,"wins":10},"inception/mercury-3":{"draws":5,"losses":14,"wins":5},"inclusionai/ling-3.0-flash":{"draws":10,"losses":11,"wins":9},"inclusionai/ling-3.1-flash":{"draws":5,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":12,"losses":16,"wins":12},"meta/muse-glimmer-30b":{"draws":11,"losses":10,"wins":11},"meta/muse-spark-1.2":{"draws":5,"losses":23,"wins":6},"meta/muse-spark-1.3":{"draws":4,"losses":26,"wins":6},"meta/muse-spark-open":{"draws":6,"losses":25,"wins":5},"meta/muse-wonder":{"draws":6,"losses":23,"wins":7},"minimax/minimax-m3":{"draws":2,"losses":10,"wins":6},"minimax/minimax-m3.1-flash":{"draws":8,"losses":14,"wins":10},"mistralai/mistral-large-4-0":{"draws":9,"losses":8,"wins":5},"mistralai/mistral-medium-3-5":{"draws":5,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":13,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":29,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":7,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":10,"wins":4},"o3":{"draws":9,"losses":22,"wins":21},"openai/gpt-oss-120b":{"draws":9,"losses":11,"wins":10},"poolside/laguna-s-2.1":{"draws":9,"losses":15,"wins":8},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":9,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":22,"wins":7},"qwen/qwen3.8-27b":{"draws":9,"losses":10,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":9,"wins":7},"qwen/qwen3.8-max":{"draws":5,"losses":24,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":21,"wins":8},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":14,"wins":7},"stealth/ox-alpha":{"draws":34,"losses":66,"wins":24},"stealth/space-bunny-alpha":{"draws":7,"losses":14,"wins":7},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":4},"tencent/hy4-preview":{"draws":10,"losses":20,"wins":6},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":12},"thinkingmachines/inkling-small":{"draws":15,"losses":7,"wins":14},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":10,"losses":18,"wins":8},"x-ai/grok-4.6":{"draws":14,"losses":17,"wins":5},"x-ai/grok-4.7":{"draws":3,"losses":21,"wins":6},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":17,"losses":19,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":28,"losses":21,"wins":23},"z-ai/glm-5.3":{"draws":5,"losses":27,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":21,"wins":8},"z-ai/glm-5.3-flashx":{"draws":4,"losses":26,"wins":6}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":20,"wins":10},"claude-fable-5":{"draws":10,"losses":33,"wins":5},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":27,"wins":5},"claude-opus-4-5":{"draws":28,"losses":37,"wins":13},"claude-opus-4-8":{"draws":12,"losses":25,"wins":7},"claude-opus-5":{"draws":14,"losses":63,"wins":5},"claude-opus-5-5":{"draws":1,"losses":50,"wins":1},"claude-sonnet-5":{"draws":16,"losses":28,"wins":4},"claude-sonnet-5-5":{"draws":12,"losses":33,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":23,"losses":23,"wins":26},"deepseek/deepseek-v4-pro":{"draws":14,"losses":21,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":17,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":18,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":31,"wins":5},"elorian/glimpse":{"draws":7,"losses":13,"wins":6},"fireworks/ember-1":{"draws":15,"losses":28,"wins":5},"gemini-3.1-pro-preview":{"draws":11,"losses":26,"wins":11},"gemini-4-argon":{"draws":0,"losses":47,"wins":1},"google/gemini-3.1-flash-lite":{"draws":13,"losses":8,"wins":11},"google/gemini-3.5-flash":{"draws":15,"losses":33,"wins":12},"google/gemini-3.5-flash-lite":{"draws":28,"losses":40,"wins":16},"google/gemini-3.6-flash":{"draws":27,"losses":53,"wins":12},"google/gemini-3.8-flash":{"draws":11,"losses":34,"wins":3},"google/gemma-4-31b-it":{"draws":13,"losses":8,"wins":7},"gpt-4.1":{"draws":4,"losses":9,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":10,"losses":16,"wins":16},"gpt-5.4":{"draws":15,"losses":27,"wins":4},"gpt-5.4-mini":{"draws":13,"losses":14,"wins":5},"gpt-5.4-nano":{"draws":11,"losses":22,"wins":15},"gpt-5.5":{"draws":18,"losses":18,"wins":8},"gpt-5.6-luna":{"draws":16,"losses":21,"wins":11},"gpt-5.6-sol":{"draws":6,"losses":34,"wins":8},"gpt-5.6-terra":{"draws":16,"losses":20,"wins":10},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":15,"losses":24,"wins":9},"gpt-6-sol":{"draws":9,"losses":33,"wins":6},"gpt-6.1-sol":{"draws":5,"losses":42,"wins":1},"gpt-6.1-terra":{"draws":8,"losses":39,"wins":1},"gpt-6.1-terra-pro":{"draws":7,"losses":38,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":7,"wins":14},"inception/mercury-3":{"draws":11,"losses":17,"wins":4},"inclusionai/ling-3.0-flash":{"draws":19,"losses":6,"wins":9},"inclusionai/ling-3.1-flash":{"draws":0,"losses":3,"wins":1},"meituan/longcat-2.0":{"draws":10,"losses":21,"wins":21},"meta/muse-glimmer-30b":{"draws":18,"losses":11,"wins":13},"meta/muse-spark-1.2":{"draws":12,"losses":26,"wins":8},"meta/muse-spark-1.3":{"draws":7,"losses":32,"wins":9},"meta/muse-spark-open":{"draws":12,"losses":29,"wins":7},"meta/muse-wonder":{"draws":9,"losses":35,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":11,"wins":10},"minimax/minimax-m3.1-flash":{"draws":13,"losses":14,"wins":15},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":9,"losses":8,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":23,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":38,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":8,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":11,"wins":4},"o3":{"draws":15,"losses":37,"wins":14},"openai/gpt-oss-120b":{"draws":13,"losses":19,"wins":10},"poolside/laguna-s-2.1":{"draws":21,"losses":15,"wins":10},"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":14,"losses":27,"wins":7},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":8},"qwen/qwen3.8-flash":{"draws":13,"losses":14,"wins":5},"qwen/qwen3.8-max":{"draws":13,"losses":26,"wins":9},"qwen/qwen3.8-max-0902":{"draws":14,"losses":26,"wins":8},"recursive/flint-v1.0":{"draws":5,"losses":2,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":17,"losses":18,"wins":9},"stealth/ox-alpha":{"draws":40,"losses":83,"wins":35},"stealth/space-bunny-alpha":{"draws":11,"losses":16,"wins":11},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":19},"stepfun/step-5-preview":{"draws":3,"losses":9,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":12,"wins":6},"tencent/hy4-preview":{"draws":17,"losses":24,"wins":5},"thinkingmachines/inkling":{"draws":23,"losses":14,"wins":27},"thinkingmachines/inkling-small":{"draws":14,"losses":17,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":10,"losses":34,"wins":4},"x-ai/grok-4.6":{"draws":11,"losses":32,"wins":5},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":5},"x-ai/grok-build-0.1":{"draws":8,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":24,"losses":24,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":19,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":20,"wins":4},"z-ai/glm-5.2":{"draws":37,"losses":39,"wins":20},"z-ai/glm-5.3":{"draws":8,"losses":34,"wins":4},"z-ai/glm-5.3-flash":{"draws":11,"losses":30,"wins":7},"z-ai/glm-5.3-flashx":{"draws":9,"losses":32,"wins":7}},"deepseek/deepseek-v4.1-flash-1017":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":6,"wins":26},"claude-fable-5":{"draws":9,"losses":31,"wins":8},"claude-fable-5-1":{"draws":1,"losses":48,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":23,"wins":13},"claude-opus-4-5":{"draws":22,"losses":26,"wins":30},"claude-opus-4-8":{"draws":9,"losses":22,"wins":13},"claude-opus-5":{"draws":14,"losses":52,"wins":16},"claude-opus-5-5":{"draws":2,"losses":47,"wins":3},"claude-sonnet-5":{"draws":14,"losses":14,"wins":20},"claude-sonnet-5-5":{"draws":12,"losses":21,"wins":15},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":21,"losses":11,"wins":40},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":15,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":21,"wins":4},"elorian/glimpse":{"draws":7,"losses":11,"wins":8},"fireworks/ember-1":{"draws":15,"losses":15,"wins":18},"gemini-3.1-pro-preview":{"draws":12,"losses":16,"wins":20},"gemini-4-argon":{"draws":4,"losses":39,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":12,"losses":24,"wins":24},"google/gemini-3.5-flash-lite":{"draws":22,"losses":15,"wins":47},"google/gemini-3.6-flash":{"draws":18,"losses":45,"wins":29},"google/gemini-3.8-flash":{"draws":11,"losses":26,"wins":11},"google/gemma-4-31b-it":{"draws":10,"losses":2,"wins":16},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":14,"wins":16},"gpt-5.4":{"draws":10,"losses":24,"wins":12},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":9,"losses":16,"wins":23},"gpt-5.5":{"draws":18,"losses":16,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":13,"wins":20},"gpt-5.6-sol":{"draws":10,"losses":25,"wins":13},"gpt-5.6-terra":{"draws":16,"losses":16,"wins":14},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":15,"losses":16,"wins":17},"gpt-6-sol":{"draws":4,"losses":32,"wins":12},"gpt-6.1-sol":{"draws":3,"losses":37,"wins":8},"gpt-6.1-terra":{"draws":6,"losses":32,"wins":10},"gpt-6.1-terra-pro":{"draws":5,"losses":36,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":0,"wins":21},"inception/mercury-3":{"draws":12,"losses":8,"wins":12},"inclusionai/ling-3.0-flash":{"draws":10,"losses":2,"wins":22},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":12,"losses":12,"wins":28},"meta/muse-glimmer-30b":{"draws":14,"losses":7,"wins":21},"meta/muse-spark-1.2":{"draws":10,"losses":17,"wins":19},"meta/muse-spark-1.3":{"draws":6,"losses":31,"wins":11},"meta/muse-spark-open":{"draws":13,"losses":16,"wins":19},"meta/muse-wonder":{"draws":11,"losses":26,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":16},"minimax/minimax-m3.1-flash":{"draws":12,"losses":15,"wins":15},"mistralai/mistral-large-4-0":{"draws":5,"losses":10,"wins":15},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":17,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":37,"wins":5},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":4,"wins":11},"o3":{"draws":6,"losses":30,"wins":30},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":14,"losses":6,"wins":26},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":12},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":20,"wins":14},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":15},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":12},"qwen/qwen3.8-max":{"draws":15,"losses":15,"wins":18},"qwen/qwen3.8-max-0902":{"draws":13,"losses":18,"wins":17},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":14,"wins":17},"stealth/ox-alpha":{"draws":38,"losses":66,"wins":54},"stealth/space-bunny-alpha":{"draws":10,"losses":8,"wins":20},"stepfun/step-3.7-flash":{"draws":5,"losses":10,"wins":19},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":9,"losses":4,"wins":13},"tencent/hy4-preview":{"draws":9,"losses":21,"wins":16},"thinkingmachines/inkling":{"draws":19,"losses":12,"wins":33},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":26},"unbiased/pareto-26.10":{"draws":0,"losses":15,"wins":1},"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":14,"losses":26,"wins":8},"x-ai/grok-4.6":{"draws":19,"losses":20,"wins":9},"x-ai/grok-4.7":{"draws":7,"losses":25,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":8},"xiaomi/mimo-v2.5":{"draws":21,"losses":10,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":11,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":18,"wins":10},"z-ai/glm-5.2":{"draws":31,"losses":26,"wins":39},"z-ai/glm-5.3":{"draws":8,"losses":29,"wins":9},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":9,"losses":27,"wins":12}},"elorian/glimpse":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":15,"wins":6},"claude-fable-5":{"draws":4,"losses":23,"wins":3},"claude-fable-5-1":{"draws":2,"losses":34,"wins":0},"claude-haiku-5-5":{"draws":2,"losses":22,"wins":4},"claude-opus-4-5":{"draws":6,"losses":32,"wins":10},"claude-opus-4-8":{"draws":5,"losses":20,"wins":1},"claude-opus-5":{"draws":9,"losses":42,"wins":5},"claude-opus-5-5":{"draws":5,"losses":29,"wins":0},"claude-sonnet-5":{"draws":9,"losses":18,"wins":3},"claude-sonnet-5-5":{"draws":4,"losses":25,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":5},"deepseek/deepseek-v4-flash":{"draws":7,"losses":22,"wins":15},"deepseek/deepseek-v4-pro":{"draws":9,"losses":11,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":18,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":17,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":19,"wins":7},"elorian/glimpse":{"draws":1,"losses":7,"wins":2},"fireworks/ember-1":{"draws":5,"losses":21,"wins":4},"gemini-3.1-pro-preview":{"draws":2,"losses":21,"wins":7},"gemini-4-argon":{"draws":1,"losses":29,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":6,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":22,"wins":10},"google/gemini-3.5-flash-lite":{"draws":15,"losses":23,"wins":14},"google/gemini-3.6-flash":{"draws":11,"losses":37,"wins":10},"google/gemini-3.8-flash":{"draws":3,"losses":23,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":6,"wins":7},"gpt-4.1":{"draws":3,"losses":7,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":7,"losses":14,"wins":7},"gpt-5.4":{"draws":5,"losses":15,"wins":10},"gpt-5.4-mini":{"draws":4,"losses":11,"wins":5},"gpt-5.4-nano":{"draws":3,"losses":18,"wins":5},"gpt-5.5":{"draws":5,"losses":22,"wins":3},"gpt-5.6-luna":{"draws":8,"losses":15,"wins":7},"gpt-5.6-sol":{"draws":1,"losses":26,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":18,"wins":6},"gpt-6-astra":{"draws":2,"losses":28,"wins":0},"gpt-6-luna":{"draws":5,"losses":17,"wins":8},"gpt-6-sol":{"draws":2,"losses":27,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":29,"wins":0},"gpt-6.1-terra":{"draws":2,"losses":28,"wins":0},"gpt-6.1-terra-pro":{"draws":0,"losses":30,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":5,"wins":9},"inception/mercury-3":{"draws":0,"losses":16,"wins":4},"inclusionai/ling-3.0-flash":{"draws":7,"losses":8,"wins":9},"inclusionai/ling-3.1-flash":{"draws":3,"losses":4,"wins":1},"meituan/longcat-2.0":{"draws":6,"losses":16,"wins":10},"meta/muse-glimmer-30b":{"draws":9,"losses":13,"wins":8},"meta/muse-spark-1.2":{"draws":5,"losses":24,"wins":1},"meta/muse-spark-1.3":{"draws":5,"losses":23,"wins":2},"meta/muse-spark-open":{"draws":4,"losses":21,"wins":5},"meta/muse-wonder":{"draws":3,"losses":24,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":8,"wins":6},"minimax/minimax-m3.1-flash":{"draws":5,"losses":11,"wins":10},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":3},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":19,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":28,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":8,"wins":3},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":4,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":9,"wins":3},"o3":{"draws":7,"losses":28,"wins":5},"openai/gpt-oss-120b":{"draws":4,"losses":13,"wins":9},"poolside/laguna-s-2.1":{"draws":5,"losses":11,"wins":12},"qwen/qwen3.7-max":{"draws":2,"losses":10,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":6,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":21,"wins":3},"qwen/qwen3.8-27b":{"draws":2,"losses":15,"wins":3},"qwen/qwen3.8-flash":{"draws":5,"losses":11,"wins":4},"qwen/qwen3.8-max":{"draws":5,"losses":20,"wins":5},"qwen/qwen3.8-max-0902":{"draws":4,"losses":21,"wins":5},"recursive/flint-v1.0":{"draws":2,"losses":4,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":16,"wins":6},"stealth/ox-alpha":{"draws":18,"losses":67,"wins":23},"stealth/space-bunny-alpha":{"draws":5,"losses":13,"wins":6},"stepfun/step-3.7-flash":{"draws":1,"losses":10,"wins":11},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":8,"wins":5},"tencent/hy4-preview":{"draws":4,"losses":20,"wins":6},"thinkingmachines/inkling":{"draws":6,"losses":23,"wins":13},"thinkingmachines/inkling-small":{"draws":5,"losses":12,"wins":13},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":22,"wins":3},"x-ai/grok-4.6":{"draws":6,"losses":21,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":22,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":13,"losses":20,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":12,"wins":4},"z-ai/glm-5.2":{"draws":8,"losses":35,"wins":17},"z-ai/glm-5.3":{"draws":2,"losses":23,"wins":3},"z-ai/glm-5.3-flash":{"draws":2,"losses":20,"wins":8},"z-ai/glm-5.3-flashx":{"draws":5,"losses":20,"wins":5}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":18,"wins":13},"claude-fable-5":{"draws":12,"losses":35,"wins":1},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":30,"losses":31,"wins":17},"claude-opus-4-8":{"draws":16,"losses":26,"wins":2},"claude-opus-5":{"draws":9,"losses":69,"wins":4},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":15,"losses":20,"wins":13},"claude-sonnet-5-5":{"draws":11,"losses":30,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":23,"losses":29,"wins":20},"deepseek/deepseek-v4-pro":{"draws":14,"losses":20,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":24,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":25,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":31,"wins":4},"elorian/glimpse":{"draws":6,"losses":14,"wins":6},"fireworks/ember-1":{"draws":10,"losses":22,"wins":0},"gemini-3.1-pro-preview":{"draws":14,"losses":21,"wins":13},"gemini-4-argon":{"draws":3,"losses":45,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":17,"losses":34,"wins":9},"google/gemini-3.5-flash-lite":{"draws":31,"losses":30,"wins":23},"google/gemini-3.6-flash":{"draws":32,"losses":42,"wins":18},"google/gemini-3.8-flash":{"draws":11,"losses":31,"wins":6},"google/gemma-4-31b-it":{"draws":14,"losses":6,"wins":8},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":15,"losses":19,"wins":8},"gpt-5.4":{"draws":15,"losses":28,"wins":3},"gpt-5.4-mini":{"draws":15,"losses":10,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":14,"wins":24},"gpt-5.5":{"draws":13,"losses":24,"wins":7},"gpt-5.6-luna":{"draws":18,"losses":21,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":35,"wins":7},"gpt-5.6-terra":{"draws":16,"losses":22,"wins":8},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":14,"losses":23,"wins":11},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":4},"gpt-6.1-terra":{"draws":3,"losses":40,"wins":5},"gpt-6.1-terra-pro":{"draws":7,"losses":37,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":4,"wins":14},"inception/mercury-3":{"draws":13,"losses":18,"wins":1},"inclusionai/ling-3.0-flash":{"draws":20,"losses":7,"wins":7},"inclusionai/ling-3.1-flash":{"draws":2,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":16,"losses":14,"wins":22},"meta/muse-glimmer-30b":{"draws":18,"losses":9,"wins":15},"meta/muse-spark-1.2":{"draws":14,"losses":25,"wins":7},"meta/muse-spark-1.3":{"draws":8,"losses":31,"wins":9},"meta/muse-spark-open":{"draws":12,"losses":29,"wins":7},"meta/muse-wonder":{"draws":17,"losses":28,"wins":3},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":12},"minimax/minimax-m3.1-flash":{"draws":11,"losses":20,"wins":11},"mistralai/mistral-large-4-0":{"draws":11,"losses":14,"wins":5},"mistralai/mistral-medium-3-5":{"draws":11,"losses":5,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":20,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":40,"wins":2},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":16,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":11,"wins":5},"o3":{"draws":16,"losses":31,"wins":19},"openai/gpt-oss-120b":{"draws":17,"losses":15,"wins":10},"poolside/laguna-s-2.1":{"draws":20,"losses":16,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":13,"wins":8},"qwen/qwen3.7-plus":{"draws":8,"losses":7,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":23,"wins":7},"qwen/qwen3.8-27b":{"draws":11,"losses":18,"wins":5},"qwen/qwen3.8-flash":{"draws":13,"losses":15,"wins":4},"qwen/qwen3.8-max":{"draws":14,"losses":20,"wins":14},"qwen/qwen3.8-max-0902":{"draws":14,"losses":27,"wins":7},"recursive/flint-v1.0":{"draws":1,"losses":5,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":19,"wins":12},"stealth/ox-alpha":{"draws":43,"losses":91,"wins":24},"stealth/space-bunny-alpha":{"draws":12,"losses":14,"wins":12},"stepfun/step-3.7-flash":{"draws":8,"losses":11,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":9,"losses":9,"wins":8},"tencent/hy4-preview":{"draws":17,"losses":20,"wins":9},"thinkingmachines/inkling":{"draws":23,"losses":20,"wins":21},"thinkingmachines/inkling-small":{"draws":16,"losses":12,"wins":20},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":13,"losses":28,"wins":7},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":27,"losses":22,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":9,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":19,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":19,"wins":6},"z-ai/glm-5.2":{"draws":35,"losses":39,"wins":22},"z-ai/glm-5.3":{"draws":8,"losses":34,"wins":4},"z-ai/glm-5.3-flash":{"draws":9,"losses":31,"wins":8},"z-ai/glm-5.3-flashx":{"draws":9,"losses":31,"wins":8}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":19,"wins":11},"claude-fable-5":{"draws":12,"losses":36,"wins":0},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":23,"losses":48,"wins":7},"claude-opus-4-8":{"draws":11,"losses":28,"wins":5},"claude-opus-5":{"draws":8,"losses":71,"wins":3},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":13,"losses":28,"wins":7},"claude-sonnet-5-5":{"draws":8,"losses":33,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":10,"wins":4},"deepseek/deepseek-v4-flash":{"draws":22,"losses":31,"wins":19},"deepseek/deepseek-v4-pro":{"draws":11,"losses":23,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":24,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":30,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":36,"wins":4},"elorian/glimpse":{"draws":5,"losses":16,"wins":5},"fireworks/ember-1":{"draws":15,"losses":29,"wins":4},"gemini-3.1-pro-preview":{"draws":8,"losses":19,"wins":5},"gemini-4-argon":{"draws":2,"losses":46,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":11,"wins":12},"google/gemini-3.5-flash":{"draws":13,"losses":38,"wins":9},"google/gemini-3.5-flash-lite":{"draws":29,"losses":30,"wins":25},"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":10,"losses":8,"wins":10},"gpt-4.1":{"draws":5,"losses":9,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":16,"losses":18,"wins":8},"gpt-5.4":{"draws":13,"losses":30,"wins":3},"gpt-5.4-mini":{"draws":13,"losses":12,"wins":7},"gpt-5.4-nano":{"draws":12,"losses":17,"wins":19},"gpt-5.5":{"draws":17,"losses":25,"wins":2},"gpt-5.6-luna":{"draws":15,"losses":23,"wins":10},"gpt-5.6-sol":{"draws":6,"losses":39,"wins":3},"gpt-5.6-terra":{"draws":19,"losses":24,"wins":3},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":11,"losses":24,"wins":13},"gpt-6-sol":{"draws":7,"losses":37,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":47,"wins":0},"gpt-6.1-terra":{"draws":6,"losses":42,"wins":0},"gpt-6.1-terra-pro":{"draws":1,"losses":44,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":13,"wins":8},"inception/mercury-3":{"draws":12,"losses":18,"wins":4},"inclusionai/ling-3.0-flash":{"draws":14,"losses":10,"wins":10},"inclusionai/ling-3.1-flash":{"draws":1,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":16,"losses":25,"wins":11},"meta/muse-glimmer-30b":{"draws":20,"losses":12,"wins":10},"meta/muse-spark-1.2":{"draws":13,"losses":28,"wins":5},"meta/muse-spark-1.3":{"draws":8,"losses":37,"wins":3},"meta/muse-spark-open":{"draws":14,"losses":33,"wins":1},"meta/muse-wonder":{"draws":8,"losses":38,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":12,"wins":8},"minimax/minimax-m3.1-flash":{"draws":12,"losses":23,"wins":7},"mistralai/mistral-large-4-0":{"draws":9,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":14,"losses":5,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":24,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":41,"wins":2},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":6,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":18,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":12,"wins":3},"o3":{"draws":13,"losses":47,"wins":6},"openai/gpt-oss-120b":{"draws":12,"losses":19,"wins":11},"poolside/laguna-s-2.1":{"draws":16,"losses":20,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":14,"wins":8},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":30,"wins":2},"qwen/qwen3.8-27b":{"draws":9,"losses":20,"wins":5},"qwen/qwen3.8-flash":{"draws":11,"losses":18,"wins":3},"qwen/qwen3.8-max":{"draws":16,"losses":26,"wins":6},"qwen/qwen3.8-max-0902":{"draws":11,"losses":33,"wins":4},"recursive/flint-v1.0":{"draws":3,"losses":3,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":27,"wins":4},"stealth/ox-alpha":{"draws":33,"losses":109,"wins":16},"stealth/space-bunny-alpha":{"draws":9,"losses":20,"wins":9},"stepfun/step-3.7-flash":{"draws":9,"losses":19,"wins":6},"stepfun/step-5-preview":{"draws":3,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":13,"wins":6},"tencent/hy4-preview":{"draws":14,"losses":27,"wins":5},"thinkingmachines/inkling":{"draws":24,"losses":25,"wins":15},"thinkingmachines/inkling-small":{"draws":13,"losses":18,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":13,"losses":33,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":35,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":8,"wins":4},"xiaomi/mimo-v2.5":{"draws":22,"losses":33,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":25,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":23,"wins":5},"z-ai/glm-5.2":{"draws":34,"losses":42,"wins":20},"z-ai/glm-5.3":{"draws":10,"losses":36,"wins":0},"z-ai/glm-5.3-flash":{"draws":11,"losses":32,"wins":5},"z-ai/glm-5.3-flashx":{"draws":9,"losses":34,"wins":5}},"gemini-4-argon":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":42},"claude-fable-5":{"draws":6,"losses":10,"wins":32},"claude-fable-5-1":{"draws":5,"losses":36,"wins":13},"claude-haiku-5-5":{"draws":5,"losses":9,"wins":32},"claude-opus-4-5":{"draws":3,"losses":9,"wins":66},"claude-opus-4-8":{"draws":4,"losses":12,"wins":28},"claude-opus-5":{"draws":10,"losses":40,"wins":32},"claude-opus-5-5":{"draws":3,"losses":38,"wins":11},"claude-sonnet-5":{"draws":4,"losses":2,"wins":42},"claude-sonnet-5-5":{"draws":5,"losses":18,"wins":25},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":66},"deepseek/deepseek-v4-pro":{"draws":4,"losses":7,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":5,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":8,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":6,"wins":38},"elorian/glimpse":{"draws":2,"losses":4,"wins":20},"fireworks/ember-1":{"draws":2,"losses":6,"wins":40},"gemini-3.1-pro-preview":{"draws":5,"losses":6,"wins":37},"gemini-4-argon":{"draws":4,"losses":20,"wins":8},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":53},"google/gemini-3.5-flash-lite":{"draws":5,"losses":6,"wins":73},"google/gemini-3.6-flash":{"draws":6,"losses":13,"wins":73},"google/gemini-3.8-flash":{"draws":5,"losses":11,"wins":32},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":7,"wins":33},"gpt-5.4":{"draws":4,"losses":5,"wins":37},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":42},"gpt-5.5":{"draws":2,"losses":10,"wins":32},"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":4,"losses":5,"wins":37},"gpt-6-astra":{"draws":10,"losses":30,"wins":8},"gpt-6-luna":{"draws":4,"losses":2,"wins":42},"gpt-6-sol":{"draws":5,"losses":25,"wins":18},"gpt-6.1-sol":{"draws":5,"losses":32,"wins":11},"gpt-6.1-terra":{"draws":10,"losses":24,"wins":14},"gpt-6.1-terra-pro":{"draws":9,"losses":26,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inception/mercury-3":{"draws":3,"losses":3,"wins":26},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":30},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":7},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":48},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":38},"meta/muse-spark-1.2":{"draws":3,"losses":4,"wins":39},"meta/muse-spark-1.3":{"draws":5,"losses":9,"wins":34},"meta/muse-spark-open":{"draws":8,"losses":9,"wins":31},"meta/muse-wonder":{"draws":5,"losses":10,"wins":33},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":24},"minimax/minimax-m3.1-flash":{"draws":2,"losses":3,"wins":37},"mistralai/mistral-large-4-0":{"draws":4,"losses":5,"wins":21},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":2,"losses":6,"wins":38},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":26,"wins":18},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":1,"wins":20},"o3":{"draws":1,"losses":5,"wins":60},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":41},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":41},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"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":4,"losses":1,"wins":27},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-max-0902":{"draws":6,"losses":5,"wins":37},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":6,"wins":35},"stealth/ox-alpha":{"draws":17,"losses":17,"wins":124},"stealth/space-bunny-alpha":{"draws":2,"losses":2,"wins":34},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":25},"tencent/hy4-preview":{"draws":4,"losses":10,"wins":32},"thinkingmachines/inkling":{"draws":5,"losses":4,"wins":55},"thinkingmachines/inkling-small":{"draws":7,"losses":1,"wins":40},"unbiased/pareto-26.10":{"draws":2,"losses":10,"wins":4},"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":1,"losses":9,"wins":38},"x-ai/grok-4.6":{"draws":5,"losses":7,"wins":36},"x-ai/grok-4.7":{"draws":4,"losses":16,"wins":22},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":13},"xiaomi/mimo-v2.5":{"draws":5,"losses":1,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":3,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":10,"losses":6,"wins":80},"z-ai/glm-5.3":{"draws":7,"losses":14,"wins":25},"z-ai/glm-5.3-flash":{"draws":2,"losses":11,"wins":35},"z-ai/glm-5.3-flashx":{"draws":6,"losses":8,"wins":34}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":16,"wins":4},"claude-fable-5":{"draws":2,"losses":27,"wins":1},"claude-fable-5-1":{"draws":1,"losses":31,"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":4,"losses":41,"wins":1},"claude-opus-5-5":{"draws":1,"losses":29,"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":29,"wins":6},"deepseek/deepseek-v4-pro":{"draws":6,"losses":19,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":19,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":26,"wins":0},"elorian/glimpse":{"draws":2,"losses":10,"wins":2},"fireworks/ember-1":{"draws":8,"losses":22,"wins":0},"gemini-3.1-pro-preview":{"draws":7,"losses":20,"wins":3},"gemini-4-argon":{"draws":1,"losses":29,"wins":0},"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":8,"losses":39,"wins":5},"google/gemini-3.6-flash":{"draws":10,"losses":45,"wins":3},"google/gemini-3.8-flash":{"draws":4,"losses":26,"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":4,"losses":22,"wins":0},"gpt-5.4":{"draws":4,"losses":24,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":14,"wins":1},"gpt-5.4-nano":{"draws":8,"losses":21,"wins":7},"gpt-5.5":{"draws":6,"losses":19,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":19,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":26,"wins":1},"gpt-5.6-terra":{"draws":6,"losses":21,"wins":1},"gpt-6-astra":{"draws":2,"losses":28,"wins":0},"gpt-6-luna":{"draws":7,"losses":20,"wins":3},"gpt-6-sol":{"draws":4,"losses":26,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":27,"wins":0},"gpt-6.1-terra":{"draws":4,"losses":26,"wins":0},"gpt-6.1-terra-pro":{"draws":3,"losses":27,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":11,"wins":5},"inception/mercury-3":{"draws":8,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":3,"losses":12,"wins":5},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"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":5,"losses":25,"wins":0},"meta/muse-spark-open":{"draws":6,"losses":23,"wins":1},"meta/muse-wonder":{"draws":3,"losses":25,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":10,"wins":4},"minimax/minimax-m3.1-flash":{"draws":4,"losses":22,"wins":2},"mistralai/mistral-large-4-0":{"draws":4,"losses":14,"wins":0},"mistralai/mistral-medium-3-5":{"draws":5,"losses":9,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":20,"wins":0},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":29,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":11,"wins":1},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":18,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":9,"wins":1},"o3":{"draws":2,"losses":44,"wins":2},"openai/gpt-oss-120b":{"draws":6,"losses":16,"wins":4},"poolside/laguna-s-2.1":{"draws":8,"losses":16,"wins":4},"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":4,"losses":17,"wins":3},"qwen/qwen3.8-flash":{"draws":4,"losses":15,"wins":1},"qwen/qwen3.8-max":{"draws":7,"losses":23,"wins":0},"qwen/qwen3.8-max-0902":{"draws":7,"losses":23,"wins":0},"recursive/flint-v1.0":{"draws":2,"losses":6,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":21,"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":5,"losses":18,"wins":1},"stepfun/step-5-preview":{"draws":0,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":2},"tencent/hy4-preview":{"draws":2,"losses":26,"wins":0},"thinkingmachines/inkling":{"draws":11,"losses":20,"wins":9},"thinkingmachines/inkling-small":{"draws":9,"losses":16,"wins":5},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"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":15,"losses":27,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":10,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":1},"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":7,"losses":22,"wins":1}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":33,"wins":26},"claude-fable-5":{"draws":12,"losses":66,"wins":6},"claude-fable-5-1":{"draws":4,"losses":89,"wins":1},"claude-haiku-5-5":{"draws":18,"losses":45,"wins":19},"claude-opus-4-5":{"draws":32,"losses":78,"wins":28},"claude-opus-4-8":{"draws":19,"losses":52,"wins":9},"claude-opus-5":{"draws":14,"losses":118,"wins":8},"claude-opus-5-5":{"draws":4,"losses":88,"wins":0},"claude-sonnet-5":{"draws":26,"losses":36,"wins":22},"claude-sonnet-5-5":{"draws":17,"losses":58,"wins":9},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":17},"deepseek/deepseek-v4-flash":{"draws":28,"losses":49,"wins":49},"deepseek/deepseek-v4-pro":{"draws":20,"losses":34,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":38,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":48,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":60,"wins":10},"elorian/glimpse":{"draws":7,"losses":26,"wins":13},"fireworks/ember-1":{"draws":27,"losses":41,"wins":16},"gemini-3.1-pro-preview":{"draws":19,"losses":41,"wins":24},"gemini-4-argon":{"draws":2,"losses":79,"wins":3},"google/gemini-3.1-flash-lite":{"draws":16,"losses":12,"wins":34},"google/gemini-3.5-flash":{"draws":14,"losses":52,"wins":14},"google/gemini-3.5-flash-lite":{"draws":35,"losses":68,"wins":47},"google/gemini-3.6-flash":{"draws":37,"losses":88,"wins":37},"google/gemini-3.8-flash":{"draws":18,"losses":61,"wins":5},"google/gemma-4-31b-it":{"draws":18,"losses":12,"wins":20},"gpt-4.1":{"draws":8,"losses":14,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":18,"losses":35,"wins":21},"gpt-5.4":{"draws":8,"losses":56,"wins":18},"gpt-5.4-mini":{"draws":16,"losses":19,"wins":21},"gpt-5.4-nano":{"draws":12,"losses":35,"wins":41},"gpt-5.5":{"draws":22,"losses":43,"wins":13},"gpt-5.6-luna":{"draws":20,"losses":37,"wins":27},"gpt-5.6-sol":{"draws":7,"losses":70,"wins":7},"gpt-5.6-terra":{"draws":22,"losses":45,"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},"gpt-6.1-terra":{"draws":8,"losses":73,"wins":3},"gpt-6.1-terra-pro":{"draws":3,"losses":78,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":16,"wins":24},"inception/mercury-3":{"draws":13,"losses":29,"wins":12},"inclusionai/ling-3.0-flash":{"draws":20,"losses":13,"wins":27},"inclusionai/ling-3.1-flash":{"draws":4,"losses":7,"wins":1},"meituan/longcat-2.0":{"draws":20,"losses":28,"wins":46},"meta/muse-glimmer-30b":{"draws":20,"losses":23,"wins":31},"meta/muse-spark-1.2":{"draws":15,"losses":50,"wins":15},"meta/muse-spark-1.3":{"draws":15,"losses":57,"wins":12},"meta/muse-spark-open":{"draws":12,"losses":63,"wins":9},"meta/muse-wonder":{"draws":10,"losses":69,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":19,"wins":19},"minimax/minimax-m3.1-flash":{"draws":14,"losses":38,"wins":22},"mistralai/mistral-large-4-0":{"draws":19,"losses":24,"wins":9},"mistralai/mistral-medium-3-5":{"draws":12,"losses":13,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":26,"losses":37,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":75,"wins":5},"nex-agi/nex-n2-pro":{"draws":8,"losses":15,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":9,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":27,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":21,"wins":12},"o3":{"draws":19,"losses":61,"wins":46},"openai/gpt-oss-120b":{"draws":20,"losses":26,"wins":26},"poolside/laguna-s-2.1":{"draws":19,"losses":27,"wins":32},"qwen/qwen3.7-max":{"draws":10,"losses":28,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":14,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":50,"wins":7},"qwen/qwen3.8-27b":{"draws":9,"losses":36,"wins":15},"qwen/qwen3.8-flash":{"draws":15,"losses":24,"wins":17},"qwen/qwen3.8-max":{"draws":24,"losses":40,"wins":20},"qwen/qwen3.8-max-0902":{"draws":21,"losses":49,"wins":14},"recursive/flint-v1.0":{"draws":5,"losses":6,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":22,"losses":41,"wins":13},"stealth/ox-alpha":{"draws":44,"losses":171,"wins":45},"stealth/space-bunny-alpha":{"draws":20,"losses":30,"wins":18},"stepfun/step-3.7-flash":{"draws":13,"losses":17,"wins":32},"stepfun/step-5-preview":{"draws":2,"losses":8,"wins":6},"tencent/hy3-preview":{"draws":15,"losses":20,"wins":11},"tencent/hy4-preview":{"draws":20,"losses":45,"wins":17},"thinkingmachines/inkling":{"draws":22,"losses":37,"wins":53},"thinkingmachines/inkling-small":{"draws":22,"losses":24,"wins":38},"unbiased/pareto-26.10":{"draws":2,"losses":26,"wins":0},"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":19,"losses":57,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":62,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":8,"wins":14},"xiaomi/mimo-v2.5":{"draws":40,"losses":42,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":19,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":36,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":34,"wins":13},"z-ai/glm-5.2":{"draws":45,"losses":75,"wins":48},"z-ai/glm-5.3":{"draws":12,"losses":64,"wins":4},"z-ai/glm-5.3-flash":{"draws":11,"losses":58,"wins":15},"z-ai/glm-5.3-flashx":{"draws":12,"losses":60,"wins":12}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":27,"wins":30},"claude-fable-5":{"draws":14,"losses":63,"wins":13},"claude-fable-5-1":{"draws":6,"losses":92,"wins":2},"claude-haiku-5-5":{"draws":18,"losses":53,"wins":17},"claude-opus-4-5":{"draws":42,"losses":61,"wins":45},"claude-opus-4-8":{"draws":18,"losses":54,"wins":14},"claude-opus-5":{"draws":20,"losses":120,"wins":12},"claude-opus-5-5":{"draws":4,"losses":93,"wins":1},"claude-sonnet-5":{"draws":24,"losses":45,"wins":21},"claude-sonnet-5-5":{"draws":17,"losses":58,"wins":15},"cohere/north-mini-code":{"draws":11,"losses":9,"wins":14},"deepseek/deepseek-v4-flash":{"draws":32,"losses":50,"wins":54},"deepseek/deepseek-v4-pro":{"draws":21,"losses":32,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":38,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":46,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":62,"wins":15},"elorian/glimpse":{"draws":15,"losses":21,"wins":12},"fireworks/ember-1":{"draws":27,"losses":38,"wins":25},"gemini-3.1-pro-preview":{"draws":33,"losses":31,"wins":26},"gemini-4-argon":{"draws":2,"losses":82,"wins":6},"google/gemini-3.1-flash-lite":{"draws":13,"losses":14,"wins":37},"google/gemini-3.5-flash":{"draws":25,"losses":52,"wins":37},"google/gemini-3.5-flash-lite":{"draws":36,"losses":39,"wins":53},"google/gemini-3.6-flash":{"draws":42,"losses":86,"wins":44},"google/gemini-3.8-flash":{"draws":16,"losses":66,"wins":8},"google/gemma-4-31b-it":{"draws":20,"losses":9,"wins":25},"gpt-4.1":{"draws":7,"losses":7,"wins":16},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":19,"losses":34,"wins":25},"gpt-5.4":{"draws":21,"losses":49,"wins":16},"gpt-5.4-mini":{"draws":15,"losses":21,"wins":24},"gpt-5.4-nano":{"draws":16,"losses":35,"wins":43},"gpt-5.5":{"draws":29,"losses":40,"wins":13},"gpt-5.6-luna":{"draws":21,"losses":34,"wins":35},"gpt-5.6-sol":{"draws":9,"losses":68,"wins":13},"gpt-5.6-terra":{"draws":22,"losses":39,"wins":25},"gpt-6-astra":{"draws":4,"losses":86,"wins":0},"gpt-6-luna":{"draws":28,"losses":36,"wins":26},"gpt-6-sol":{"draws":13,"losses":68,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":82,"wins":1},"gpt-6.1-terra":{"draws":8,"losses":81,"wins":1},"gpt-6.1-terra-pro":{"draws":6,"losses":83,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":27,"losses":9,"wins":30},"inception/mercury-3":{"draws":20,"losses":30,"wins":10},"inclusionai/ling-3.0-flash":{"draws":23,"losses":8,"wins":33},"inclusionai/ling-3.1-flash":{"draws":4,"losses":5,"wins":5},"meituan/longcat-2.0":{"draws":23,"losses":27,"wins":48},"meta/muse-glimmer-30b":{"draws":26,"losses":20,"wins":32},"meta/muse-spark-1.2":{"draws":24,"losses":42,"wins":20},"meta/muse-spark-1.3":{"draws":19,"losses":55,"wins":16},"meta/muse-spark-open":{"draws":21,"losses":53,"wins":16},"meta/muse-wonder":{"draws":18,"losses":60,"wins":12},"minimax/minimax-m3":{"draws":13,"losses":17,"wins":20},"minimax/minimax-m3.1-flash":{"draws":19,"losses":32,"wins":27},"mistralai/mistral-large-4-0":{"draws":21,"losses":26,"wins":9},"mistralai/mistral-medium-3-5":{"draws":13,"losses":12,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":27,"losses":38,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":75,"wins":3},"nex-agi/nex-n2-pro":{"draws":9,"losses":16,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":3,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":19,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":18,"wins":10},"o3":{"draws":22,"losses":55,"wins":51},"openai/gpt-oss-120b":{"draws":20,"losses":26,"wins":32},"poolside/laguna-s-2.1":{"draws":18,"losses":31,"wins":35},"qwen/qwen3.7-max":{"draws":13,"losses":21,"wins":20},"qwen/qwen3.7-plus":{"draws":11,"losses":15,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":43,"wins":20},"qwen/qwen3.8-27b":{"draws":12,"losses":31,"wins":21},"qwen/qwen3.8-flash":{"draws":13,"losses":27,"wins":20},"qwen/qwen3.8-max":{"draws":21,"losses":44,"wins":25},"qwen/qwen3.8-max-0902":{"draws":26,"losses":47,"wins":17},"recursive/flint-v1.0":{"draws":7,"losses":3,"wins":18},"reflection/beam-1.0-501b-a23b":{"draws":26,"losses":37,"wins":19},"stealth/ox-alpha":{"draws":64,"losses":144,"wins":68},"stealth/space-bunny-alpha":{"draws":22,"losses":20,"wins":30},"stepfun/step-3.7-flash":{"draws":17,"losses":11,"wins":36},"stepfun/step-5-preview":{"draws":3,"losses":10,"wins":7},"tencent/hy3-preview":{"draws":21,"losses":20,"wins":9},"tencent/hy4-preview":{"draws":23,"losses":42,"wins":21},"thinkingmachines/inkling":{"draws":33,"losses":29,"wins":56},"thinkingmachines/inkling-small":{"draws":26,"losses":19,"wins":45},"unbiased/pareto-26.10":{"draws":3,"losses":27,"wins":0},"unbiased/pareto-26.10-preview":{"draws":3,"losses":27,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":6,"wins":13},"x-ai/grok-4.5":{"draws":21,"losses":49,"wins":20},"x-ai/grok-4.6":{"draws":17,"losses":57,"wins":16},"x-ai/grok-4.7":{"draws":10,"losses":59,"wins":11},"x-ai/grok-build-0.1":{"draws":9,"losses":7,"wins":14},"xiaomi/mimo-v2.5":{"draws":39,"losses":42,"wins":65},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":10,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":39,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":36,"wins":14},"z-ai/glm-5.2":{"draws":57,"losses":62,"wins":61},"z-ai/glm-5.3":{"draws":11,"losses":70,"wins":5},"z-ai/glm-5.3-flash":{"draws":14,"losses":54,"wins":22},"z-ai/glm-5.3-flashx":{"draws":27,"losses":43,"wins":20}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":34,"wins":31},"claude-fable-5":{"draws":17,"losses":68,"wins":11},"claude-fable-5-1":{"draws":7,"losses":99,"wins":2},"claude-haiku-5-5":{"draws":28,"losses":47,"wins":17},"claude-opus-4-5":{"draws":48,"losses":67,"wins":41},"claude-opus-4-8":{"draws":21,"losses":42,"wins":25},"claude-opus-5":{"draws":20,"losses":127,"wins":17},"claude-opus-5-5":{"draws":3,"losses":99,"wins":2},"claude-sonnet-5":{"draws":29,"losses":44,"wins":23},"claude-sonnet-5-5":{"draws":19,"losses":60,"wins":17},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":23},"deepseek/deepseek-v4-flash":{"draws":40,"losses":42,"wins":62},"deepseek/deepseek-v4-pro":{"draws":26,"losses":41,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":43,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":44,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":62,"wins":19},"elorian/glimpse":{"draws":11,"losses":28,"wins":13},"fireworks/ember-1":{"draws":35,"losses":44,"wins":17},"gemini-3.1-pro-preview":{"draws":30,"losses":37,"wins":29},"gemini-4-argon":{"draws":7,"losses":86,"wins":3},"google/gemini-3.1-flash-lite":{"draws":18,"losses":14,"wins":32},"google/gemini-3.5-flash":{"draws":26,"losses":67,"wins":27},"google/gemini-3.5-flash-lite":{"draws":42,"losses":62,"wins":64},"google/gemini-3.6-flash":{"draws":39,"losses":89,"wins":24},"google/gemini-3.8-flash":{"draws":19,"losses":61,"wins":16},"google/gemma-4-31b-it":{"draws":23,"losses":11,"wins":22},"gpt-4.1":{"draws":10,"losses":11,"wins":11},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":3},"gpt-5":{"draws":22,"losses":46,"wins":16},"gpt-5.4":{"draws":18,"losses":50,"wins":24},"gpt-5.4-mini":{"draws":17,"losses":18,"wins":29},"gpt-5.4-nano":{"draws":19,"losses":37,"wins":40},"gpt-5.5":{"draws":30,"losses":41,"wins":17},"gpt-5.6-luna":{"draws":29,"losses":33,"wins":34},"gpt-5.6-sol":{"draws":12,"losses":75,"wins":9},"gpt-5.6-terra":{"draws":30,"losses":38,"wins":24},"gpt-6-astra":{"draws":7,"losses":89,"wins":0},"gpt-6-luna":{"draws":32,"losses":32,"wins":32},"gpt-6-sol":{"draws":14,"losses":75,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":91,"wins":0},"gpt-6.1-terra":{"draws":11,"losses":85,"wins":0},"gpt-6.1-terra-pro":{"draws":8,"losses":82,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":8,"wins":34},"inception/mercury-3":{"draws":17,"losses":28,"wins":19},"inclusionai/ling-3.0-flash":{"draws":28,"losses":15,"wins":25},"inclusionai/ling-3.1-flash":{"draws":4,"losses":7,"wins":3},"meituan/longcat-2.0":{"draws":21,"losses":33,"wins":50},"meta/muse-glimmer-30b":{"draws":30,"losses":19,"wins":35},"meta/muse-spark-1.2":{"draws":22,"losses":51,"wins":19},"meta/muse-spark-1.3":{"draws":23,"losses":56,"wins":17},"meta/muse-spark-open":{"draws":21,"losses":52,"wins":23},"meta/muse-wonder":{"draws":16,"losses":68,"wins":12},"minimax/minimax-m3":{"draws":12,"losses":14,"wins":26},"minimax/minimax-m3.1-flash":{"draws":24,"losses":33,"wins":27},"mistralai/mistral-large-4-0":{"draws":18,"losses":25,"wins":17},"mistralai/mistral-medium-3-5":{"draws":18,"losses":12,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":27,"losses":45,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":77,"wins":5},"nex-agi/nex-n2-pro":{"draws":12,"losses":11,"wins":25},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":20,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":22,"wins":10},"o3":{"draws":17,"losses":81,"wins":34},"openai/gpt-oss-120b":{"draws":28,"losses":21,"wins":35},"poolside/laguna-s-2.1":{"draws":25,"losses":31,"wins":36},"qwen/qwen3.7-max":{"draws":11,"losses":25,"wins":20},"qwen/qwen3.7-plus":{"draws":16,"losses":15,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":46,"wins":22},"qwen/qwen3.8-27b":{"draws":16,"losses":35,"wins":17},"qwen/qwen3.8-flash":{"draws":20,"losses":24,"wins":20},"qwen/qwen3.8-max":{"draws":23,"losses":50,"wins":23},"qwen/qwen3.8-max-0902":{"draws":28,"losses":43,"wins":25},"recursive/flint-v1.0":{"draws":10,"losses":6,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":25,"losses":40,"wins":23},"stealth/ox-alpha":{"draws":75,"losses":167,"wins":74},"stealth/space-bunny-alpha":{"draws":21,"losses":31,"wins":24},"stepfun/step-3.7-flash":{"draws":17,"losses":20,"wins":31},"stepfun/step-5-preview":{"draws":3,"losses":13,"wins":6},"tencent/hy3-preview":{"draws":17,"losses":16,"wins":19},"tencent/hy4-preview":{"draws":16,"losses":54,"wins":22},"thinkingmachines/inkling":{"draws":40,"losses":24,"wins":64},"thinkingmachines/inkling-small":{"draws":28,"losses":29,"wins":39},"unbiased/pareto-26.10":{"draws":3,"losses":29,"wins":0},"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":23,"losses":62,"wins":11},"x-ai/grok-4.7":{"draws":3,"losses":70,"wins":11},"x-ai/grok-build-0.1":{"draws":9,"losses":6,"wins":17},"xiaomi/mimo-v2.5":{"draws":47,"losses":46,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":14,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":38,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":38,"wins":13},"z-ai/glm-5.2":{"draws":57,"losses":87,"wins":48},"z-ai/glm-5.3":{"draws":17,"losses":71,"wins":4},"z-ai/glm-5.3-flash":{"draws":17,"losses":59,"wins":20},"z-ai/glm-5.3-flashx":{"draws":24,"losses":50,"wins":22}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":9,"wins":22},"claude-fable-5":{"draws":7,"losses":31,"wins":10},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":16,"wins":17},"claude-opus-4-5":{"draws":29,"losses":15,"wins":34},"claude-opus-4-8":{"draws":10,"losses":19,"wins":15},"claude-opus-5":{"draws":11,"losses":59,"wins":12},"claude-opus-5-5":{"draws":4,"losses":44,"wins":4},"claude-sonnet-5":{"draws":13,"losses":13,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":27,"wins":13},"elorian/glimpse":{"draws":7,"losses":12,"wins":7},"fireworks/ember-1":{"draws":12,"losses":18,"wins":18},"gemini-3.1-pro-preview":{"draws":10,"losses":16,"wins":22},"gemini-4-argon":{"draws":1,"losses":44,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":12,"losses":23,"wins":25},"google/gemini-3.5-flash-lite":{"draws":19,"losses":8,"wins":57},"google/gemini-3.6-flash":{"draws":23,"losses":31,"wins":38},"google/gemini-3.8-flash":{"draws":8,"losses":16,"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":11,"losses":17,"wins":18},"gpt-5.4-mini":{"draws":9,"losses":8,"wins":15},"gpt-5.4-nano":{"draws":9,"losses":7,"wins":32},"gpt-5.5":{"draws":14,"losses":14,"wins":16},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":25},"gpt-5.6-sol":{"draws":6,"losses":29,"wins":13},"gpt-5.6-terra":{"draws":17,"losses":11,"wins":18},"gpt-6-astra":{"draws":4,"losses":40,"wins":4},"gpt-6-luna":{"draws":15,"losses":13,"wins":20},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":6,"losses":40,"wins":2},"gpt-6.1-terra":{"draws":9,"losses":37,"wins":2},"gpt-6.1-terra-pro":{"draws":8,"losses":37,"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},"inception/mercury-3":{"draws":10,"losses":6,"wins":16},"inclusionai/ling-3.0-flash":{"draws":13,"losses":0,"wins":21},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":35},"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-spark-open":{"draws":15,"losses":19,"wins":14},"meta/muse-wonder":{"draws":12,"losses":24,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":16},"minimax/minimax-m3.1-flash":{"draws":14,"losses":6,"wins":22},"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":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":13,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":38,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":6,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":2,"wins":13},"o3":{"draws":8,"losses":16,"wins":42},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":9,"losses":4,"wins":33},"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":14,"losses":17,"wins":17},"qwen/qwen3.8-27b":{"draws":10,"losses":8,"wins":16},"qwen/qwen3.8-flash":{"draws":8,"losses":10,"wins":14},"qwen/qwen3.8-max":{"draws":13,"losses":16,"wins":19},"qwen/qwen3.8-max-0902":{"draws":10,"losses":22,"wins":16},"recursive/flint-v1.0":{"draws":5,"losses":1,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":15,"wins":18},"stealth/ox-alpha":{"draws":37,"losses":67,"wins":54},"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":2,"losses":2,"wins":12},"tencent/hy3-preview":{"draws":13,"losses":2,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":19,"wins":13},"thinkingmachines/inkling":{"draws":17,"losses":8,"wins":39},"thinkingmachines/inkling-small":{"draws":16,"losses":5,"wins":27},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":23,"wins":15},"x-ai/grok-4.6":{"draws":15,"losses":19,"wins":14},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":27,"losses":2,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"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":23,"wins":17}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":7},"claude-fable-5":{"draws":9,"losses":27,"wins":0},"claude-fable-5-1":{"draws":4,"losses":34,"wins":2},"claude-haiku-5-5":{"draws":10,"losses":23,"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":7,"losses":48,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":29,"wins":1},"elorian/glimpse":{"draws":6,"losses":10,"wins":2},"fireworks/ember-1":{"draws":12,"losses":20,"wins":4},"gemini-3.1-pro-preview":{"draws":12,"losses":19,"wins":5},"gemini-4-argon":{"draws":0,"losses":36,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":10,"wins":11},"google/gemini-3.5-flash":{"draws":18,"losses":24,"wins":4},"google/gemini-3.5-flash-lite":{"draws":28,"losses":27,"wins":9},"google/gemini-3.6-flash":{"draws":22,"losses":41,"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},"gpt-6.1-terra":{"draws":4,"losses":32,"wins":0},"gpt-6.1-terra-pro":{"draws":1,"losses":35,"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},"inception/mercury-3":{"draws":6,"losses":16,"wins":2},"inclusionai/ling-3.0-flash":{"draws":14,"losses":6,"wins":4},"inclusionai/ling-3.1-flash":{"draws":1,"losses":3,"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":12,"losses":20,"wins":2},"meta/muse-spark-1.3":{"draws":11,"losses":23,"wins":2},"meta/muse-spark-open":{"draws":10,"losses":24,"wins":2},"meta/muse-wonder":{"draws":7,"losses":27,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":3},"minimax/minimax-m3.1-flash":{"draws":10,"losses":18,"wins":2},"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":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":19,"wins":1},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":33,"wins":0},"nex-agi/nex-n2-pro":{"draws":7,"losses":8,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":12,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":10,"wins":3},"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},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":26,"wins":2},"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":5,"wins":3},"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":{"draws":1,"losses":11,"wins":0},"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":7,"losses":7,"wins":4},"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":14,"losses":11,"wins":19},"claude-fable-5":{"draws":8,"losses":28,"wins":12},"claude-fable-5-1":{"draws":5,"losses":47,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":24,"wins":8},"claude-opus-4-5":{"draws":26,"losses":35,"wins":17},"claude-opus-4-8":{"draws":10,"losses":27,"wins":7},"claude-opus-5":{"draws":11,"losses":67,"wins":4},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":12,"losses":21,"wins":15},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":5,"losses":3,"wins":10},"deepseek/deepseek-v4-flash":{"draws":18,"losses":17,"wins":37},"deepseek/deepseek-v4-pro":{"draws":12,"losses":23,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":20,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":25,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":30,"wins":7},"elorian/glimpse":{"draws":6,"losses":12,"wins":8},"fireworks/ember-1":{"draws":13,"losses":21,"wins":14},"gemini-3.1-pro-preview":{"draws":11,"losses":18,"wins":19},"gemini-4-argon":{"draws":5,"losses":43,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":19},"google/gemini-3.5-flash":{"draws":13,"losses":30,"wins":17},"google/gemini-3.5-flash-lite":{"draws":23,"losses":28,"wins":33},"google/gemini-3.6-flash":{"draws":23,"losses":50,"wins":19},"google/gemini-3.8-flash":{"draws":14,"losses":26,"wins":8},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":16,"wins":15},"gpt-5.4":{"draws":9,"losses":22,"wins":15},"gpt-5.4-mini":{"draws":12,"losses":14,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":18,"wins":21},"gpt-5.5":{"draws":8,"losses":25,"wins":11},"gpt-5.6-luna":{"draws":13,"losses":14,"wins":21},"gpt-5.6-sol":{"draws":8,"losses":35,"wins":5},"gpt-5.6-terra":{"draws":16,"losses":15,"wins":15},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":9,"losses":20,"wins":19},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"gpt-6.1-terra":{"draws":3,"losses":44,"wins":1},"gpt-6.1-terra-pro":{"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":8,"wins":14},"inception/mercury-3":{"draws":8,"losses":15,"wins":9},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":20},"inclusionai/ling-3.1-flash":{"draws":6,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":12,"wins":30},"meta/muse-glimmer-30b":{"draws":15,"losses":10,"wins":17},"meta/muse-spark-1.2":{"draws":16,"losses":21,"wins":9},"meta/muse-spark-1.3":{"draws":14,"losses":28,"wins":6},"meta/muse-spark-open":{"draws":9,"losses":28,"wins":11},"meta/muse-wonder":{"draws":7,"losses":35,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":15},"minimax/minimax-m3.1-flash":{"draws":8,"losses":17,"wins":17},"mistralai/mistral-large-4-0":{"draws":12,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":10,"losses":5,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":22,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":43,"wins":3},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":9,"wins":7},"o3":{"draws":11,"losses":26,"wins":29},"openai/gpt-oss-120b":{"draws":11,"losses":9,"wins":22},"poolside/laguna-s-2.1":{"draws":14,"losses":13,"wins":19},"qwen/qwen3.7-max":{"draws":11,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":23,"wins":8},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":11},"qwen/qwen3.8-flash":{"draws":9,"losses":15,"wins":8},"qwen/qwen3.8-max":{"draws":16,"losses":18,"wins":14},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":18,"wins":13},"stealth/ox-alpha":{"draws":39,"losses":81,"wins":38},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":12},"tencent/hy4-preview":{"draws":13,"losses":23,"wins":10},"thinkingmachines/inkling":{"draws":16,"losses":20,"wins":28},"thinkingmachines/inkling-small":{"draws":13,"losses":15,"wins":20},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":28,"wins":9},"x-ai/grok-4.6":{"draws":17,"losses":24,"wins":7},"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":24,"losses":16,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":17,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":33,"losses":40,"wins":23},"z-ai/glm-5.3":{"draws":6,"losses":32,"wins":8},"z-ai/glm-5.3-flash":{"draws":5,"losses":28,"wins":15},"z-ai/glm-5.3-flashx":{"draws":8,"losses":30,"wins":10}},"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":6,"losses":20,"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":7,"losses":10,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":10,"wins":0},"elorian/glimpse":{"draws":6,"losses":2,"wins":0},"fireworks/ember-1":{"draws":8,"losses":9,"wins":1},"gemini-3.1-pro-preview":{"draws":11,"losses":4,"wins":3},"gemini-4-argon":{"draws":0,"losses":18,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":2},"google/gemini-3.5-flash":{"draws":9,"losses":10,"wins":1},"google/gemini-3.5-flash-lite":{"draws":17,"losses":10,"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},"gpt-6.1-terra":{"draws":5,"losses":13,"wins":0},"gpt-6.1-terra-pro":{"draws":4,"losses":14,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":3,"wins":5},"inception/mercury-3":{"draws":8,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"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-spark-open":{"draws":9,"losses":6,"wins":1},"meta/muse-wonder":{"draws":9,"losses":9,"wins":0},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":1},"minimax/minimax-m3.1-flash":{"draws":9,"losses":6,"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},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":15,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":2,"wins":0},"o3":{"draws":6,"losses":11,"wins":1},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":13,"losses":3,"wins":2},"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},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":7,"wins":0},"stealth/ox-alpha":{"draws":33,"losses":35,"wins":4},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":0},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":6,"losses":10,"wins":0},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":1},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":2},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"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":6,"losses":4,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":7,"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":8,"losses":14,"wins":10},"claude-fable-5":{"draws":7,"losses":26,"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":14,"losses":27,"wins":17},"claude-opus-4-8":{"draws":6,"losses":18,"wins":8},"claude-opus-5":{"draws":7,"losses":57,"wins":4},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":7,"losses":25,"wins":4},"claude-sonnet-5-5":{"draws":9,"losses":19,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":12,"losses":22,"wins":22},"deepseek/deepseek-v4-pro":{"draws":4,"losses":19,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":13,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":17,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":23,"wins":8},"elorian/glimpse":{"draws":2,"losses":12,"wins":6},"fireworks/ember-1":{"draws":10,"losses":20,"wins":6},"gemini-3.1-pro-preview":{"draws":13,"losses":13,"wins":10},"gemini-4-argon":{"draws":0,"losses":35,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":17},"google/gemini-3.5-flash":{"draws":7,"losses":24,"wins":13},"google/gemini-3.5-flash-lite":{"draws":10,"losses":18,"wins":32},"google/gemini-3.6-flash":{"draws":12,"losses":33,"wins":23},"google/gemini-3.8-flash":{"draws":6,"losses":19,"wins":11},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":7},"gpt-4.1":{"draws":3,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":11,"wins":9},"gpt-5.4":{"draws":3,"losses":23,"wins":8},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":8},"gpt-5.4-nano":{"draws":6,"losses":14,"wins":18},"gpt-5.5":{"draws":11,"losses":19,"wins":4},"gpt-5.6-luna":{"draws":7,"losses":11,"wins":18},"gpt-5.6-sol":{"draws":6,"losses":26,"wins":4},"gpt-5.6-terra":{"draws":6,"losses":19,"wins":9},"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},"gpt-6.1-terra":{"draws":5,"losses":30,"wins":1},"gpt-6.1-terra-pro":{"draws":6,"losses":29,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":5,"wins":9},"inception/mercury-3":{"draws":5,"losses":12,"wins":9},"inclusionai/ling-3.0-flash":{"draws":6,"losses":8,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":13,"wins":19},"meta/muse-glimmer-30b":{"draws":6,"losses":9,"wins":19},"meta/muse-spark-1.2":{"draws":6,"losses":25,"wins":5},"meta/muse-spark-1.3":{"draws":4,"losses":27,"wins":5},"meta/muse-spark-open":{"draws":6,"losses":26,"wins":4},"meta/muse-wonder":{"draws":7,"losses":23,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":12},"minimax/minimax-m3.1-flash":{"draws":4,"losses":11,"wins":15},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":7,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":19,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":28,"wins":7},"nex-agi/nex-n2-pro":{"draws":1,"losses":8,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":8,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":8,"wins":7},"o3":{"draws":6,"losses":21,"wins":23},"openai/gpt-oss-120b":{"draws":7,"losses":7,"wins":20},"poolside/laguna-s-2.1":{"draws":9,"losses":13,"wins":18},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":8},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":18,"wins":10},"qwen/qwen3.8-27b":{"draws":4,"losses":13,"wins":7},"qwen/qwen3.8-flash":{"draws":1,"losses":13,"wins":10},"qwen/qwen3.8-max":{"draws":7,"losses":21,"wins":8},"qwen/qwen3.8-max-0902":{"draws":8,"losses":18,"wins":10},"recursive/flint-v1.0":{"draws":1,"losses":3,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":20,"wins":10},"stealth/ox-alpha":{"draws":20,"losses":71,"wins":33},"stealth/space-bunny-alpha":{"draws":6,"losses":11,"wins":11},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":14},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":6},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":4},"tencent/hy4-preview":{"draws":7,"losses":18,"wins":9},"thinkingmachines/inkling":{"draws":8,"losses":15,"wins":27},"thinkingmachines/inkling-small":{"draws":10,"losses":9,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"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":9,"losses":21,"wins":6},"x-ai/grok-4.7":{"draws":2,"losses":25,"wins":7},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":9,"losses":14,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":17,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":13,"wins":8},"z-ai/glm-5.2":{"draws":16,"losses":29,"wins":27},"z-ai/glm-5.3":{"draws":3,"losses":27,"wins":4},"z-ai/glm-5.3-flash":{"draws":3,"losses":22,"wins":11},"z-ai/glm-5.3-flashx":{"draws":7,"losses":20,"wins":9}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":14,"wins":18},"claude-fable-5":{"draws":10,"losses":29,"wins":9},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":12,"losses":20,"wins":14},"claude-opus-4-5":{"draws":23,"losses":32,"wins":23},"claude-opus-4-8":{"draws":11,"losses":17,"wins":16},"claude-opus-5":{"draws":14,"losses":62,"wins":6},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":10,"losses":17,"wins":21},"claude-sonnet-5-5":{"draws":10,"losses":27,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":21,"losses":17,"wins":34},"deepseek/deepseek-v4-pro":{"draws":10,"losses":18,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":17,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":21,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":29,"wins":9},"elorian/glimpse":{"draws":8,"losses":9,"wins":9},"fireworks/ember-1":{"draws":18,"losses":16,"wins":14},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":17},"gemini-4-argon":{"draws":3,"losses":42,"wins":3},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":23},"google/gemini-3.5-flash":{"draws":8,"losses":26,"wins":26},"google/gemini-3.5-flash-lite":{"draws":21,"losses":22,"wins":41},"google/gemini-3.6-flash":{"draws":19,"losses":46,"wins":27},"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":3,"losses":7,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":17,"wins":17},"gpt-5.4":{"draws":7,"losses":22,"wins":1},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":18},"gpt-5.4-nano":{"draws":7,"losses":16,"wins":25},"gpt-5.5":{"draws":16,"losses":16,"wins":12},"gpt-5.6-luna":{"draws":17,"losses":13,"wins":18},"gpt-5.6-sol":{"draws":9,"losses":27,"wins":12},"gpt-5.6-terra":{"draws":15,"losses":20,"wins":11},"gpt-6-astra":{"draws":1,"losses":43,"wins":4},"gpt-6-luna":{"draws":20,"losses":14,"wins":14},"gpt-6-sol":{"draws":7,"losses":36,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"gpt-6.1-terra":{"draws":6,"losses":42,"wins":0},"gpt-6.1-terra-pro":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":4,"wins":17},"inception/mercury-3":{"draws":7,"losses":17,"wins":8},"inclusionai/ling-3.0-flash":{"draws":8,"losses":8,"wins":18},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":14,"losses":12,"wins":26},"meta/muse-glimmer-30b":{"draws":8,"losses":15,"wins":19},"meta/muse-spark-1.2":{"draws":7,"losses":25,"wins":14},"meta/muse-spark-1.3":{"draws":7,"losses":29,"wins":12},"meta/muse-spark-open":{"draws":12,"losses":23,"wins":13},"meta/muse-wonder":{"draws":9,"losses":29,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":13},"minimax/minimax-m3.1-flash":{"draws":7,"losses":14,"wins":21},"mistralai/mistral-large-4-0":{"draws":14,"losses":8,"wins":8},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":17,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":37,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":10,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":9},"o3":{"draws":9,"losses":29,"wins":28},"openai/gpt-oss-120b":{"draws":10,"losses":12,"wins":20},"poolside/laguna-s-2.1":{"draws":13,"losses":12,"wins":21},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":11},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":20,"wins":14},"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":21,"wins":17},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":16,"wins":17},"stealth/ox-alpha":{"draws":36,"losses":82,"wins":40},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":8,"losses":8,"wins":18},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":3},"tencent/hy3-preview":{"draws":10,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":11,"losses":23,"wins":12},"thinkingmachines/inkling":{"draws":17,"losses":12,"wins":35},"thinkingmachines/inkling-small":{"draws":16,"losses":9,"wins":23},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":29,"wins":7},"x-ai/grok-4.7":{"draws":4,"losses":33,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":19,"losses":13,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":14,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":15,"wins":10},"z-ai/glm-5.2":{"draws":26,"losses":30,"wins":40},"z-ai/glm-5.3":{"draws":8,"losses":29,"wins":9},"z-ai/glm-5.3-flash":{"draws":6,"losses":27,"wins":15},"z-ai/glm-5.3-flashx":{"draws":15,"losses":21,"wins":12}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":22,"wins":5},"claude-fable-5":{"draws":10,"losses":37,"wins":1},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":30,"wins":2},"claude-opus-4-5":{"draws":34,"losses":37,"wins":7},"claude-opus-4-8":{"draws":10,"losses":31,"wins":3},"claude-opus-5":{"draws":20,"losses":58,"wins":4},"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":5,"losses":8,"wins":5},"deepseek/deepseek-v4-flash":{"draws":30,"losses":28,"wins":14},"deepseek/deepseek-v4-pro":{"draws":14,"losses":22,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":24,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":21,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":32,"wins":2},"elorian/glimpse":{"draws":8,"losses":14,"wins":4},"fireworks/ember-1":{"draws":23,"losses":22,"wins":3},"gemini-3.1-pro-preview":{"draws":18,"losses":24,"wins":6},"gemini-4-argon":{"draws":7,"losses":41,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":5,"wins":17},"google/gemini-3.5-flash":{"draws":16,"losses":39,"wins":5},"google/gemini-3.5-flash-lite":{"draws":29,"losses":37,"wins":18},"google/gemini-3.6-flash":{"draws":30,"losses":56,"wins":6},"google/gemini-3.8-flash":{"draws":13,"losses":34,"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":15,"losses":23,"wins":4},"gpt-5.4":{"draws":16,"losses":30,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":9,"wins":2},"gpt-5.4-nano":{"draws":14,"losses":27,"wins":7},"gpt-5.5":{"draws":16,"losses":20,"wins":8},"gpt-5.6-luna":{"draws":20,"losses":20,"wins":8},"gpt-5.6-sol":{"draws":10,"losses":37,"wins":1},"gpt-5.6-terra":{"draws":20,"losses":22,"wins":4},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":21,"losses":23,"wins":4},"gpt-6-sol":{"draws":6,"losses":40,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"gpt-6.1-terra":{"draws":12,"losses":35,"wins":1},"gpt-6.1-terra-pro":{"draws":8,"losses":40,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":10,"wins":8},"inception/mercury-3":{"draws":13,"losses":16,"wins":3},"inclusionai/ling-3.0-flash":{"draws":17,"losses":13,"wins":4},"inclusionai/ling-3.1-flash":{"draws":2,"losses":4,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":23,"wins":9},"meta/muse-glimmer-30b":{"draws":20,"losses":15,"wins":7},"meta/muse-spark-1.2":{"draws":16,"losses":27,"wins":3},"meta/muse-spark-1.3":{"draws":11,"losses":36,"wins":1},"meta/muse-spark-open":{"draws":16,"losses":30,"wins":2},"meta/muse-wonder":{"draws":14,"losses":32,"wins":2},"minimax/minimax-m3":{"draws":7,"losses":15,"wins":4},"minimax/minimax-m3.1-flash":{"draws":19,"losses":20,"wins":3},"mistralai/mistral-large-4-0":{"draws":16,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":12,"losses":9,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":27,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":42,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":12,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":22,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":14,"wins":0},"o3":{"draws":14,"losses":45,"wins":7},"openai/gpt-oss-120b":{"draws":21,"losses":15,"wins":6},"poolside/laguna-s-2.1":{"draws":17,"losses":24,"wins":5},"qwen/qwen3.7-max":{"draws":6,"losses":16,"wins":6},"qwen/qwen3.7-plus":{"draws":6,"losses":14,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":28,"wins":2},"qwen/qwen3.8-27b":{"draws":9,"losses":19,"wins":6},"qwen/qwen3.8-flash":{"draws":12,"losses":16,"wins":4},"qwen/qwen3.8-max":{"draws":24,"losses":18,"wins":6},"qwen/qwen3.8-max-0902":{"draws":24,"losses":23,"wins":1},"recursive/flint-v1.0":{"draws":4,"losses":8,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":23,"wins":3},"stealth/ox-alpha":{"draws":52,"losses":92,"wins":14},"stealth/space-bunny-alpha":{"draws":12,"losses":25,"wins":1},"stepfun/step-3.7-flash":{"draws":12,"losses":15,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":13,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":11,"wins":3},"tencent/hy4-preview":{"draws":15,"losses":29,"wins":2},"thinkingmachines/inkling":{"draws":24,"losses":26,"wins":14},"thinkingmachines/inkling-small":{"draws":21,"losses":19,"wins":8},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":6,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":30,"losses":28,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":10,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":20,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":21,"wins":1},"z-ai/glm-5.2":{"draws":41,"losses":50,"wins":5},"z-ai/glm-5.3":{"draws":15,"losses":30,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":29,"wins":7},"z-ai/glm-5.3-flashx":{"draws":13,"losses":33,"wins":2}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":30,"wins":22},"claude-fable-5":{"draws":10,"losses":58,"wins":4},"claude-fable-5-1":{"draws":0,"losses":76,"wins":0},"claude-haiku-5-5":{"draws":19,"losses":36,"wins":15},"claude-opus-4-5":{"draws":31,"losses":64,"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":3,"losses":7,"wins":16},"deepseek/deepseek-v4-flash":{"draws":28,"losses":45,"wins":41},"deepseek/deepseek-v4-pro":{"draws":9,"losses":31,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":33,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":36,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":50,"wins":11},"elorian/glimpse":{"draws":8,"losses":21,"wins":7},"fireworks/ember-1":{"draws":17,"losses":45,"wins":10},"gemini-3.1-pro-preview":{"draws":18,"losses":39,"wins":15},"gemini-4-argon":{"draws":0,"losses":68,"wins":4},"google/gemini-3.1-flash-lite":{"draws":11,"losses":13,"wins":26},"google/gemini-3.5-flash":{"draws":12,"losses":62,"wins":16},"google/gemini-3.5-flash-lite":{"draws":29,"losses":53,"wins":42},"google/gemini-3.6-flash":{"draws":24,"losses":85,"wins":27},"google/gemini-3.8-flash":{"draws":16,"losses":49,"wins":7},"google/gemma-4-31b-it":{"draws":15,"losses":10,"wins":17},"gpt-4.1":{"draws":6,"losses":10,"wins":8},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":3},"gpt-5":{"draws":9,"losses":38,"wins":17},"gpt-5.4":{"draws":9,"losses":46,"wins":13},"gpt-5.4-mini":{"draws":13,"losses":17,"wins":18},"gpt-5.4-nano":{"draws":12,"losses":26,"wins":22},"gpt-5.5":{"draws":15,"losses":36,"wins":13},"gpt-5.6-luna":{"draws":19,"losses":31,"wins":22},"gpt-5.6-sol":{"draws":6,"losses":59,"wins":7},"gpt-5.6-terra":{"draws":15,"losses":39,"wins":14},"gpt-6-astra":{"draws":3,"losses":69,"wins":0},"gpt-6-luna":{"draws":17,"losses":41,"wins":14},"gpt-6-sol":{"draws":8,"losses":56,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":67,"wins":2},"gpt-6.1-terra":{"draws":6,"losses":63,"wins":3},"gpt-6.1-terra-pro":{"draws":8,"losses":59,"wins":5},"inception/mercury-2.5-preview":{"draws":16,"losses":10,"wins":24},"inception/mercury-3":{"draws":15,"losses":25,"wins":12},"inclusionai/ling-3.0-flash":{"draws":13,"losses":12,"wins":27},"inclusionai/ling-3.1-flash":{"draws":3,"losses":4,"wins":5},"meituan/longcat-2.0":{"draws":16,"losses":29,"wins":33},"meta/muse-glimmer-30b":{"draws":14,"losses":23,"wins":23},"meta/muse-spark-1.2":{"draws":12,"losses":37,"wins":19},"meta/muse-spark-1.3":{"draws":11,"losses":53,"wins":8},"meta/muse-spark-open":{"draws":12,"losses":52,"wins":8},"meta/muse-wonder":{"draws":9,"losses":51,"wins":12},"minimax/minimax-m3":{"draws":8,"losses":14,"wins":20},"minimax/minimax-m3.1-flash":{"draws":8,"losses":30,"wins":22},"mistralai/mistral-large-4-0":{"draws":9,"losses":24,"wins":11},"mistralai/mistral-medium-3-5":{"draws":8,"losses":13,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":38,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":65,"wins":1},"nex-agi/nex-n2-pro":{"draws":6,"losses":16,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":6,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":24,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":15,"wins":9},"o3":{"draws":9,"losses":61,"wins":38},"openai/gpt-oss-120b":{"draws":24,"losses":24,"wins":16},"poolside/laguna-s-2.1":{"draws":20,"losses":35,"wins":21},"qwen/qwen3.7-max":{"draws":14,"losses":20,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":18,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":44,"wins":11},"qwen/qwen3.8-27b":{"draws":13,"losses":26,"wins":13},"qwen/qwen3.8-flash":{"draws":10,"losses":27,"wins":11},"qwen/qwen3.8-max":{"draws":15,"losses":37,"wins":20},"qwen/qwen3.8-max-0902":{"draws":21,"losses":36,"wins":15},"recursive/flint-v1.0":{"draws":7,"losses":7,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":39,"wins":10},"stealth/ox-alpha":{"draws":42,"losses":128,"wins":52},"stealth/space-bunny-alpha":{"draws":10,"losses":30,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":19,"wins":26},"stepfun/step-5-preview":{"draws":2,"losses":13,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":21,"wins":7},"tencent/hy4-preview":{"draws":9,"losses":51,"wins":8},"thinkingmachines/inkling":{"draws":22,"losses":41,"wins":31},"thinkingmachines/inkling-small":{"draws":22,"losses":23,"wins":27},"unbiased/pareto-26.10":{"draws":1,"losses":23,"wins":0},"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":17,"losses":46,"wins":9},"x-ai/grok-4.6":{"draws":13,"losses":46,"wins":13},"x-ai/grok-4.7":{"draws":8,"losses":56,"wins":2},"x-ai/grok-build-0.1":{"draws":3,"losses":10,"wins":11},"xiaomi/mimo-v2.5":{"draws":27,"losses":40,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":17,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":27,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":35,"wins":6},"z-ai/glm-5.2":{"draws":35,"losses":71,"wins":38},"z-ai/glm-5.3":{"draws":12,"losses":49,"wins":7},"z-ai/glm-5.3-flash":{"draws":11,"losses":46,"wins":15},"z-ai/glm-5.3-flashx":{"draws":18,"losses":39,"wins":15}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":10,"wins":13},"claude-fable-5":{"draws":12,"losses":23,"wins":7},"claude-fable-5-1":{"draws":3,"losses":43,"wins":2},"claude-haiku-5-5":{"draws":17,"losses":17,"wins":6},"claude-opus-4-5":{"draws":34,"losses":24,"wins":10},"claude-opus-4-8":{"draws":15,"losses":17,"wins":6},"claude-opus-5":{"draws":14,"losses":65,"wins":1},"claude-opus-5-5":{"draws":7,"losses":39,"wins":0},"claude-sonnet-5":{"draws":18,"losses":14,"wins":10},"claude-sonnet-5-5":{"draws":11,"losses":21,"wins":10},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":26,"losses":13,"wins":23},"deepseek/deepseek-v4-pro":{"draws":19,"losses":12,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":15,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":21,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":20,"wins":8},"elorian/glimpse":{"draws":5,"losses":8,"wins":11},"fireworks/ember-1":{"draws":13,"losses":20,"wins":9},"gemini-3.1-pro-preview":{"draws":14,"losses":15,"wins":13},"gemini-4-argon":{"draws":4,"losses":38,"wins":0},"google/gemini-3.1-flash-lite":{"draws":12,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":16,"losses":21,"wins":15},"google/gemini-3.5-flash-lite":{"draws":32,"losses":14,"wins":26},"google/gemini-3.6-flash":{"draws":27,"losses":35,"wins":18},"google/gemini-3.8-flash":{"draws":17,"losses":17,"wins":8},"google/gemma-4-31b-it":{"draws":13,"losses":3,"wins":8},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":17,"losses":14,"wins":7},"gpt-5.4":{"draws":10,"losses":19,"wins":11},"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":15,"losses":12,"wins":15},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":7},"gpt-5.6-terra":{"draws":19,"losses":13,"wins":8},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":14,"losses":15,"wins":13},"gpt-6-sol":{"draws":10,"losses":30,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":0},"gpt-6.1-terra":{"draws":6,"losses":32,"wins":4},"gpt-6.1-terra-pro":{"draws":10,"losses":32,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":3,"wins":11},"inception/mercury-3":{"draws":12,"losses":10,"wins":6},"inclusionai/ling-3.0-flash":{"draws":19,"losses":2,"wins":7},"inclusionai/ling-3.1-flash":{"draws":6,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":11,"wins":19},"meta/muse-glimmer-30b":{"draws":16,"losses":7,"wins":17},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":24,"wins":7},"meta/muse-spark-open":{"draws":12,"losses":25,"wins":5},"meta/muse-wonder":{"draws":17,"losses":19,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":9},"minimax/minimax-m3.1-flash":{"draws":17,"losses":9,"wins":10},"mistralai/mistral-large-4-0":{"draws":14,"losses":8,"wins":6},"mistralai/mistral-medium-3-5":{"draws":12,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":18,"losses":16,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":35,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":8,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":6,"wins":5},"o3":{"draws":14,"losses":20,"wins":20},"openai/gpt-oss-120b":{"draws":17,"losses":6,"wins":15},"poolside/laguna-s-2.1":{"draws":23,"losses":9,"wins":10},"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":10,"losses":14,"wins":4},"qwen/qwen3.8-flash":{"draws":13,"losses":9,"wins":6},"qwen/qwen3.8-max":{"draws":15,"losses":17,"wins":10},"qwen/qwen3.8-max-0902":{"draws":16,"losses":20,"wins":6},"recursive/flint-v1.0":{"draws":6,"losses":0,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":17,"wins":11},"stealth/ox-alpha":{"draws":43,"losses":70,"wins":29},"stealth/space-bunny-alpha":{"draws":15,"losses":9,"wins":10},"stepfun/step-3.7-flash":{"draws":11,"losses":5,"wins":12},"stepfun/step-5-preview":{"draws":0,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":12,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":18,"losses":18,"wins":4},"thinkingmachines/inkling":{"draws":26,"losses":7,"wins":25},"thinkingmachines/inkling-small":{"draws":17,"losses":10,"wins":15},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":13,"losses":25,"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":29,"losses":11,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":7,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":14,"wins":5},"z-ai/glm-5.2":{"draws":35,"losses":24,"wins":25},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":6},"z-ai/glm-5.3-flash":{"draws":12,"losses":21,"wins":9},"z-ai/glm-5.3-flashx":{"draws":14,"losses":21,"wins":7}},"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":12,"losses":30,"wins":2},"claude-opus-5":{"draws":10,"losses":68,"wins":4},"claude-opus-5-5":{"draws":3,"losses":49,"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":3,"losses":8,"wins":7},"deepseek/deepseek-v4-flash":{"draws":26,"losses":34,"wins":12},"deepseek/deepseek-v4-pro":{"draws":13,"losses":26,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":25,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":29,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":36,"wins":3},"elorian/glimpse":{"draws":6,"losses":15,"wins":5},"fireworks/ember-1":{"draws":15,"losses":28,"wins":5},"gemini-3.1-pro-preview":{"draws":11,"losses":29,"wins":8},"gemini-4-argon":{"draws":3,"losses":45,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":17,"wins":8},"google/gemini-3.5-flash":{"draws":11,"losses":43,"wins":6},"google/gemini-3.5-flash-lite":{"draws":22,"losses":45,"wins":17},"google/gemini-3.6-flash":{"draws":23,"losses":66,"wins":3},"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":12,"losses":16,"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":10,"losses":18,"wins":4},"gpt-5.6-sol":{"draws":4,"losses":40,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":25,"wins":7},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":16,"losses":25,"wins":7},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"gpt-6.1-terra":{"draws":7,"losses":39,"wins":2},"gpt-6.1-terra-pro":{"draws":5,"losses":43,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":15,"wins":6},"inception/mercury-3":{"draws":13,"losses":16,"wins":3},"inclusionai/ling-3.0-flash":{"draws":17,"losses":13,"wins":4},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":32,"wins":6},"meta/muse-glimmer-30b":{"draws":17,"losses":22,"wins":3},"meta/muse-spark-1.2":{"draws":16,"losses":24,"wins":6},"meta/muse-spark-1.3":{"draws":12,"losses":34,"wins":2},"meta/muse-spark-open":{"draws":13,"losses":31,"wins":4},"meta/muse-wonder":{"draws":9,"losses":36,"wins":3},"minimax/minimax-m3":{"draws":8,"losses":13,"wins":5},"minimax/minimax-m3.1-flash":{"draws":11,"losses":22,"wins":9},"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":4,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":26,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":42,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":10,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":7,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":18,"wins":5},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":14,"wins":2},"o3":{"draws":8,"losses":52,"wins":6},"openai/gpt-oss-120b":{"draws":15,"losses":18,"wins":9},"poolside/laguna-s-2.1":{"draws":14,"losses":26,"wins":6},"qwen/qwen3.7-max":{"draws":9,"losses":16,"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":30,"wins":6},"qwen/qwen3.8-max-0902":{"draws":13,"losses":32,"wins":3},"recursive/flint-v1.0":{"draws":4,"losses":7,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":22,"wins":7},"stealth/ox-alpha":{"draws":49,"losses":99,"wins":10},"stealth/space-bunny-alpha":{"draws":13,"losses":21,"wins":4},"stepfun/step-3.7-flash":{"draws":9,"losses":16,"wins":9},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":19,"wins":0},"tencent/hy4-preview":{"draws":13,"losses":31,"wins":2},"thinkingmachines/inkling":{"draws":22,"losses":26,"wins":16},"thinkingmachines/inkling-small":{"draws":17,"losses":24,"wins":7},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":14,"losses":33,"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":23,"losses":40,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":13,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":21,"wins":4},"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":8,"losses":37,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":30,"wins":6},"z-ai/glm-5.3-flashx":{"draws":11,"losses":35,"wins":2}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":5,"wins":27},"claude-fable-5":{"draws":7,"losses":30,"wins":11},"claude-fable-5-1":{"draws":3,"losses":47,"wins":4},"claude-haiku-5-5":{"draws":4,"losses":21,"wins":21},"claude-opus-4-5":{"draws":21,"losses":15,"wins":42},"claude-opus-4-8":{"draws":10,"losses":21,"wins":13},"claude-opus-5":{"draws":9,"losses":65,"wins":8},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":14,"losses":10,"wins":24},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":17},"cohere/north-mini-code":{"draws":1,"losses":4,"wins":13},"deepseek/deepseek-v4-flash":{"draws":14,"losses":11,"wins":47},"deepseek/deepseek-v4-pro":{"draws":11,"losses":15,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":16,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":23,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":27,"wins":9},"elorian/glimpse":{"draws":6,"losses":9,"wins":11},"fireworks/ember-1":{"draws":11,"losses":18,"wins":19},"gemini-3.1-pro-preview":{"draws":9,"losses":14,"wins":25},"gemini-4-argon":{"draws":4,"losses":40,"wins":4},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":12,"losses":17,"wins":31},"google/gemini-3.5-flash-lite":{"draws":20,"losses":11,"wins":53},"google/gemini-3.6-flash":{"draws":18,"losses":32,"wins":42},"google/gemini-3.8-flash":{"draws":10,"losses":24,"wins":14},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":4,"losses":3,"wins":9},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":12,"wins":21},"gpt-5.4":{"draws":11,"losses":21,"wins":14},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":15},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":34},"gpt-5.5":{"draws":10,"losses":22,"wins":12},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":24},"gpt-5.6-sol":{"draws":2,"losses":19,"wins":11},"gpt-5.6-terra":{"draws":13,"losses":14,"wins":19},"gpt-6-astra":{"draws":3,"losses":42,"wins":3},"gpt-6-luna":{"draws":10,"losses":13,"wins":25},"gpt-6-sol":{"draws":3,"losses":37,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":41,"wins":5},"gpt-6.1-terra":{"draws":3,"losses":40,"wins":5},"gpt-6.1-terra-pro":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":22},"inception/mercury-3":{"draws":7,"losses":9,"wins":16},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":4,"wins":38},"meta/muse-glimmer-30b":{"draws":13,"losses":4,"wins":25},"meta/muse-spark-1.2":{"draws":10,"losses":16,"wins":20},"meta/muse-spark-1.3":{"draws":8,"losses":22,"wins":18},"meta/muse-spark-open":{"draws":13,"losses":19,"wins":16},"meta/muse-wonder":{"draws":10,"losses":27,"wins":11},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"minimax/minimax-m3.1-flash":{"draws":9,"losses":13,"wins":20},"mistralai/mistral-large-4-0":{"draws":8,"losses":9,"wins":13},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k3":{"draws":11,"losses":16,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":42,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":3,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":10},"o3":{"draws":6,"losses":14,"wins":46},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":29},"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":5,"losses":3,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":20,"wins":17},"qwen/qwen3.8-27b":{"draws":8,"losses":6,"wins":20},"qwen/qwen3.8-flash":{"draws":10,"losses":7,"wins":15},"qwen/qwen3.8-max":{"draws":10,"losses":15,"wins":23},"qwen/qwen3.8-max-0902":{"draws":13,"losses":15,"wins":20},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":11,"wins":21},"stealth/ox-alpha":{"draws":33,"losses":62,"wins":63},"stealth/space-bunny-alpha":{"draws":10,"losses":6,"wins":22},"stepfun/step-3.7-flash":{"draws":6,"losses":4,"wins":24},"stepfun/step-5-preview":{"draws":4,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":15},"tencent/hy4-preview":{"draws":10,"losses":19,"wins":17},"thinkingmachines/inkling":{"draws":18,"losses":5,"wins":41},"thinkingmachines/inkling-small":{"draws":14,"losses":4,"wins":30},"unbiased/pareto-26.10":{"draws":0,"losses":15,"wins":1},"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":23,"wins":12},"x-ai/grok-4.7":{"draws":6,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":21,"losses":3,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":18},"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":17,"wins":21}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":10,"wins":19},"claude-fable-5":{"draws":10,"losses":31,"wins":1},"claude-fable-5-1":{"draws":3,"losses":44,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":20,"wins":5},"claude-opus-4-5":{"draws":25,"losses":32,"wins":11},"claude-opus-4-8":{"draws":15,"losses":18,"wins":5},"claude-opus-5":{"draws":7,"losses":53,"wins":10},"claude-opus-5-5":{"draws":3,"losses":42,"wins":1},"claude-sonnet-5":{"draws":16,"losses":18,"wins":8},"claude-sonnet-5-5":{"draws":12,"losses":23,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":10},"deepseek/deepseek-v4-flash":{"draws":21,"losses":14,"wins":29},"deepseek/deepseek-v4-pro":{"draws":12,"losses":17,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":18,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":20,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":29,"wins":1},"elorian/glimpse":{"draws":7,"losses":13,"wins":4},"fireworks/ember-1":{"draws":14,"losses":24,"wins":4},"gemini-3.1-pro-preview":{"draws":18,"losses":17,"wins":7},"gemini-4-argon":{"draws":4,"losses":38,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":15},"google/gemini-3.5-flash":{"draws":17,"losses":24,"wins":11},"google/gemini-3.5-flash-lite":{"draws":21,"losses":22,"wins":29},"google/gemini-3.6-flash":{"draws":22,"losses":47,"wins":11},"google/gemini-3.8-flash":{"draws":12,"losses":25,"wins":5},"google/gemma-4-31b-it":{"draws":15,"losses":1,"wins":8},"gpt-4.1":{"draws":4,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":19,"wins":8},"gpt-5.4":{"draws":10,"losses":19,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":10,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":15,"wins":16},"gpt-5.5":{"draws":17,"losses":14,"wins":7},"gpt-5.6-luna":{"draws":14,"losses":14,"wins":14},"gpt-5.6-sol":{"draws":10,"losses":29,"wins":3},"gpt-5.6-terra":{"draws":13,"losses":7,"wins":8},"gpt-6-astra":{"draws":5,"losses":37,"wins":0},"gpt-6-luna":{"draws":16,"losses":19,"wins":7},"gpt-6-sol":{"draws":7,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":0},"gpt-6.1-terra":{"draws":8,"losses":32,"wins":2},"gpt-6.1-terra-pro":{"draws":6,"losses":32,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":15},"inception/mercury-3":{"draws":13,"losses":14,"wins":5},"inclusionai/ling-3.0-flash":{"draws":10,"losses":6,"wins":18},"inclusionai/ling-3.1-flash":{"draws":4,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":14,"wins":15},"meta/muse-glimmer-30b":{"draws":13,"losses":6,"wins":17},"meta/muse-spark-1.2":{"draws":15,"losses":18,"wins":7},"meta/muse-spark-1.3":{"draws":11,"losses":22,"wins":9},"meta/muse-spark-open":{"draws":14,"losses":24,"wins":4},"meta/muse-wonder":{"draws":10,"losses":26,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":9},"minimax/minimax-m3.1-flash":{"draws":9,"losses":12,"wins":15},"mistralai/mistral-large-4-0":{"draws":16,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":18,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":35,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":8,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":6,"wins":4},"o3":{"draws":12,"losses":24,"wins":18},"openai/gpt-oss-120b":{"draws":15,"losses":1,"wins":20},"poolside/laguna-s-2.1":{"draws":17,"losses":6,"wins":15},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":18,"wins":7},"qwen/qwen3.8-27b":{"draws":13,"losses":14,"wins":3},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":16,"losses":17,"wins":9},"qwen/qwen3.8-max-0902":{"draws":17,"losses":19,"wins":6},"recursive/flint-v1.0":{"draws":5,"losses":1,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":18,"wins":6},"stealth/ox-alpha":{"draws":43,"losses":76,"wins":21},"stealth/space-bunny-alpha":{"draws":15,"losses":14,"wins":3},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":11},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":1},"tencent/hy3-preview":{"draws":11,"losses":6,"wins":5},"tencent/hy4-preview":{"draws":14,"losses":18,"wins":8},"thinkingmachines/inkling":{"draws":17,"losses":17,"wins":20},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":20},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":14,"losses":25,"wins":3},"x-ai/grok-4.6":{"draws":14,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":3},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":25,"losses":11,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":3,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":14,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":17,"wins":3},"z-ai/glm-5.2":{"draws":36,"losses":26,"wins":22},"z-ai/glm-5.3":{"draws":11,"losses":26,"wins":3},"z-ai/glm-5.3-flash":{"draws":12,"losses":25,"wins":5},"z-ai/glm-5.3-flashx":{"draws":10,"losses":25,"wins":7}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":4,"wins":35},"claude-fable-5":{"draws":6,"losses":9,"wins":33},"claude-fable-5-1":{"draws":4,"losses":29,"wins":21},"claude-haiku-5-5":{"draws":4,"losses":3,"wins":39},"claude-opus-4-5":{"draws":8,"losses":5,"wins":65},"claude-opus-4-8":{"draws":4,"losses":6,"wins":34},"claude-opus-5":{"draws":11,"losses":23,"wins":48},"claude-opus-5-5":{"draws":8,"losses":28,"wins":16},"claude-sonnet-5":{"draws":6,"losses":6,"wins":36},"claude-sonnet-5-5":{"draws":5,"losses":12,"wins":31},"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":10,"losses":2,"wins":36},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":7,"wins":38},"elorian/glimpse":{"draws":5,"losses":4,"wins":17},"fireworks/ember-1":{"draws":9,"losses":2,"wins":37},"gemini-3.1-pro-preview":{"draws":4,"losses":1,"wins":43},"gemini-4-argon":{"draws":8,"losses":17,"wins":23},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":5,"losses":1,"wins":54},"google/gemini-3.5-flash-lite":{"draws":9,"losses":0,"wins":75},"google/gemini-3.6-flash":{"draws":12,"losses":6,"wins":74},"google/gemini-3.8-flash":{"draws":7,"losses":7,"wins":34},"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":4,"losses":2,"wins":38},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":39},"gpt-5.6-sol":{"draws":7,"losses":3,"wins":38},"gpt-5.6-terra":{"draws":10,"losses":1,"wins":35},"gpt-6-astra":{"draws":5,"losses":18,"wins":9},"gpt-6-luna":{"draws":7,"losses":4,"wins":37},"gpt-6-sol":{"draws":4,"losses":15,"wins":29},"gpt-6.1-sol":{"draws":6,"losses":24,"wins":18},"gpt-6.1-terra":{"draws":7,"losses":21,"wins":20},"gpt-6.1-terra-pro":{"draws":7,"losses":18,"wins":23},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":30},"inception/mercury-3":{"draws":7,"losses":0,"wins":25},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":29},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":9},"meituan/longcat-2.0":{"draws":4,"losses":3,"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":6,"wins":35},"meta/muse-spark-open":{"draws":5,"losses":2,"wins":41},"meta/muse-wonder":{"draws":9,"losses":6,"wins":33},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":25},"minimax/minimax-m3.1-flash":{"draws":8,"losses":0,"wins":34},"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":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":5,"losses":5,"wins":36},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":19,"wins":24},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":20},"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":0,"wins":24},"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":8,"losses":1,"wins":23},"qwen/qwen3.8-max":{"draws":7,"losses":3,"wins":38},"qwen/qwen3.8-max-0902":{"draws":7,"losses":4,"wins":37},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":3,"wins":33},"stealth/ox-alpha":{"draws":19,"losses":12,"wins":127},"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":2,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":9,"losses":3,"wins":34},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":56},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":43},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":6},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":10},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":4,"losses":5,"wins":39},"x-ai/grok-4.6":{"draws":7,"losses":5,"wins":36},"x-ai/grok-4.7":{"draws":5,"losses":11,"wins":26},"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":5,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":3,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":3,"wins":26},"z-ai/glm-5.2":{"draws":15,"losses":5,"wins":76},"z-ai/glm-5.3":{"draws":10,"losses":4,"wins":32},"z-ai/glm-5.3-flash":{"draws":8,"losses":5,"wins":35},"z-ai/glm-5.3-flashx":{"draws":10,"losses":2,"wins":36}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":12,"wins":16},"claude-fable-5":{"draws":11,"losses":31,"wins":6},"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":14,"losses":62,"wins":6},"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":14,"losses":14,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":20,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":25,"wins":9},"elorian/glimpse":{"draws":4,"losses":13,"wins":9},"fireworks/ember-1":{"draws":16,"losses":21,"wins":11},"gemini-3.1-pro-preview":{"draws":19,"losses":19,"wins":10},"gemini-4-argon":{"draws":2,"losses":45,"wins":1},"google/gemini-3.1-flash-lite":{"draws":13,"losses":4,"wins":15},"google/gemini-3.5-flash":{"draws":25,"losses":21,"wins":14},"google/gemini-3.5-flash-lite":{"draws":40,"losses":16,"wins":28},"google/gemini-3.6-flash":{"draws":37,"losses":39,"wins":16},"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":6,"wins":8},"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},"gpt-6.1-terra":{"draws":9,"losses":34,"wins":5},"gpt-6.1-terra-pro":{"draws":8,"losses":37,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"wins":17},"inception/mercury-3":{"draws":10,"losses":12,"wins":10},"inclusionai/ling-3.0-flash":{"draws":19,"losses":4,"wins":11},"inclusionai/ling-3.1-flash":{"draws":7,"losses":3,"wins":4},"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":14,"losses":21,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":32,"wins":5},"meta/muse-spark-open":{"draws":13,"losses":21,"wins":12},"meta/muse-wonder":{"draws":15,"losses":25,"wins":8},"minimax/minimax-m3":{"draws":12,"losses":2,"wins":12},"minimax/minimax-m3.1-flash":{"draws":10,"losses":13,"wins":19},"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":4,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":19,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":42,"wins":4},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":5,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":3,"wins":12},"o3":{"draws":17,"losses":24,"wins":25},"openai/gpt-oss-120b":{"draws":20,"losses":9,"wins":13},"poolside/laguna-s-2.1":{"draws":24,"losses":9,"wins":13},"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},"recursive/flint-v1.0":{"draws":6,"losses":0,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":17,"wins":15},"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":1,"losses":6,"wins":1},"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":{"draws":1,"losses":15,"wins":0},"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":36,"losses":6,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":4,"wins":11},"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":5,"wins":33},"claude-fable-5":{"draws":8,"losses":21,"wins":19},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":9,"losses":14,"wins":23},"claude-opus-4-5":{"draws":15,"losses":9,"wins":54},"claude-opus-4-8":{"draws":7,"losses":16,"wins":21},"claude-opus-5":{"draws":12,"losses":59,"wins":11},"claude-opus-5-5":{"draws":2,"losses":43,"wins":7},"claude-sonnet-5":{"draws":12,"losses":6,"wins":30},"claude-sonnet-5-5":{"draws":3,"losses":23,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":5,"wins":54},"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":17,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":21,"wins":19},"elorian/glimpse":{"draws":4,"losses":6,"wins":16},"fireworks/ember-1":{"draws":10,"losses":11,"wins":27},"gemini-3.1-pro-preview":{"draws":8,"losses":12,"wins":28},"gemini-4-argon":{"draws":6,"losses":30,"wins":12},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":9,"losses":16,"wins":35},"google/gemini-3.5-flash-lite":{"draws":13,"losses":8,"wins":63},"google/gemini-3.6-flash":{"draws":17,"losses":27,"wins":48},"google/gemini-3.8-flash":{"draws":8,"losses":19,"wins":21},"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":6,"losses":7,"wins":29},"gpt-5.4":{"draws":5,"losses":9,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":4,"wins":22},"gpt-5.4-nano":{"draws":7,"losses":3,"wins":38},"gpt-5.5":{"draws":10,"losses":13,"wins":21},"gpt-5.6-luna":{"draws":11,"losses":5,"wins":32},"gpt-5.6-sol":{"draws":5,"losses":23,"wins":20},"gpt-5.6-terra":{"draws":11,"losses":6,"wins":29},"gpt-6-astra":{"draws":5,"losses":39,"wins":4},"gpt-6-luna":{"draws":9,"losses":6,"wins":33},"gpt-6-sol":{"draws":4,"losses":19,"wins":9},"gpt-6.1-sol":{"draws":3,"losses":37,"wins":8},"gpt-6.1-terra":{"draws":6,"losses":34,"wins":8},"gpt-6.1-terra-pro":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":23},"inception/mercury-3":{"draws":10,"losses":5,"wins":17},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":28},"inclusionai/ling-3.1-flash":{"draws":2,"losses":1,"wins":7},"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":9,"losses":10,"wins":27},"meta/muse-spark-1.3":{"draws":10,"losses":10,"wins":28},"meta/muse-spark-open":{"draws":7,"losses":8,"wins":31},"meta/muse-wonder":{"draws":11,"losses":22,"wins":15},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"minimax/minimax-m3.1-flash":{"draws":8,"losses":5,"wins":29},"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":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":27},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":35,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":3,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":3,"wins":15},"o3":{"draws":3,"losses":4,"wins":59},"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":11,"losses":11,"wins":26},"qwen/qwen3.8-max-0902":{"draws":13,"losses":10,"wins":25},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":7,"wins":28},"stealth/ox-alpha":{"draws":24,"losses":33,"wins":101},"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":4,"losses":3,"wins":7},"tencent/hy3-preview":{"draws":8,"losses":1,"wins":17},"tencent/hy4-preview":{"draws":7,"losses":13,"wins":26},"thinkingmachines/inkling":{"draws":12,"losses":4,"wins":48},"thinkingmachines/inkling-small":{"draws":10,"losses":5,"wins":33},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":12,"losses":14,"wins":22},"x-ai/grok-4.6":{"draws":11,"losses":15,"wins":22},"x-ai/grok-4.7":{"draws":4,"losses":26,"wins":12},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":17,"losses":3,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":9,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":15},"z-ai/glm-5.2":{"draws":21,"losses":15,"wins":60},"z-ai/glm-5.3":{"draws":8,"losses":20,"wins":18},"z-ai/glm-5.3-flash":{"draws":7,"losses":17,"wins":24},"z-ai/glm-5.3-flashx":{"draws":5,"losses":24,"wins":19}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":4,"wins":31},"claude-fable-5":{"draws":4,"losses":20,"wins":24},"claude-fable-5-1":{"draws":3,"losses":32,"wins":19},"claude-haiku-5-5":{"draws":7,"losses":5,"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":12,"losses":34,"wins":36},"claude-opus-5-5":{"draws":9,"losses":28,"wins":15},"claude-sonnet-5":{"draws":5,"losses":6,"wins":37},"claude-sonnet-5-5":{"draws":1,"losses":16,"wins":31},"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":2,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":5,"wins":35},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":12,"wins":31},"elorian/glimpse":{"draws":3,"losses":3,"wins":20},"fireworks/ember-1":{"draws":10,"losses":7,"wins":31},"gemini-3.1-pro-preview":{"draws":2,"losses":7,"wins":39},"gemini-4-argon":{"draws":10,"losses":19,"wins":19},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":5,"losses":11,"wins":44},"google/gemini-3.5-flash-lite":{"draws":9,"losses":1,"wins":74},"google/gemini-3.6-flash":{"draws":9,"losses":13,"wins":70},"google/gemini-3.8-flash":{"draws":11,"losses":9,"wins":28},"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":3,"wins":34},"gpt-5.4":{"draws":5,"losses":10,"wins":31},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":28},"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":7,"losses":11,"wins":30},"gpt-5.6-terra":{"draws":7,"losses":3,"wins":36},"gpt-6-astra":{"draws":4,"losses":34,"wins":10},"gpt-6-luna":{"draws":10,"losses":4,"wins":34},"gpt-6-sol":{"draws":7,"losses":24,"wins":17},"gpt-6.1-sol":{"draws":1,"losses":25,"wins":6},"gpt-6.1-terra":{"draws":8,"losses":23,"wins":17},"gpt-6.1-terra-pro":{"draws":5,"losses":30,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":27},"inception/mercury-3":{"draws":7,"losses":2,"wins":23},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.1-flash":{"draws":1,"losses":2,"wins":7},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":44},"meta/muse-glimmer-30b":{"draws":7,"losses":1,"wins":34},"meta/muse-spark-1.2":{"draws":8,"losses":7,"wins":31},"meta/muse-spark-1.3":{"draws":5,"losses":9,"wins":34},"meta/muse-spark-open":{"draws":9,"losses":5,"wins":34},"meta/muse-wonder":{"draws":8,"losses":14,"wins":26},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"minimax/minimax-m3.1-flash":{"draws":11,"losses":2,"wins":29},"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":1,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":34},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":24,"wins":18},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":4,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"wins":18},"o3":{"draws":2,"losses":6,"wins":58},"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":2,"losses":2,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":10,"wins":32},"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":3,"wins":39},"qwen/qwen3.8-max-0902":{"draws":9,"losses":8,"wins":31},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":2,"wins":37},"stealth/ox-alpha":{"draws":25,"losses":17,"wins":116},"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":1,"losses":0,"wins":7},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":19},"tencent/hy4-preview":{"draws":5,"losses":7,"wins":34},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":52},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":44},"unbiased/pareto-26.10":{"draws":3,"losses":10,"wins":3},"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":12,"losses":4,"wins":32},"x-ai/grok-4.7":{"draws":3,"losses":20,"wins":19},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":14,"losses":6,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":0,"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":8,"losses":14,"wins":24},"z-ai/glm-5.3-flash":{"draws":5,"losses":9,"wins":34},"z-ai/glm-5.3-flashx":{"draws":11,"losses":9,"wins":28}},"gpt-6.1-terra":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":4,"wins":33},"claude-fable-5":{"draws":7,"losses":13,"wins":28},"claude-fable-5-1":{"draws":7,"losses":34,"wins":13},"claude-haiku-5-5":{"draws":6,"losses":7,"wins":33},"claude-opus-4-5":{"draws":13,"losses":4,"wins":61},"claude-opus-4-8":{"draws":5,"losses":7,"wins":32},"claude-opus-5":{"draws":10,"losses":33,"wins":39},"claude-opus-5-5":{"draws":4,"losses":33,"wins":15},"claude-sonnet-5":{"draws":8,"losses":3,"wins":37},"claude-sonnet-5-5":{"draws":6,"losses":14,"wins":28},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":66},"deepseek/deepseek-v4-pro":{"draws":5,"losses":2,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":2,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":5,"wins":36},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":9,"wins":37},"elorian/glimpse":{"draws":2,"losses":5,"wins":19},"fireworks/ember-1":{"draws":4,"losses":8,"wins":36},"gemini-3.1-pro-preview":{"draws":6,"losses":5,"wins":37},"gemini-4-argon":{"draws":7,"losses":17,"wins":24},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":50},"google/gemini-3.5-flash-lite":{"draws":5,"losses":2,"wins":77},"google/gemini-3.6-flash":{"draws":10,"losses":11,"wins":71},"google/gemini-3.8-flash":{"draws":8,"losses":6,"wins":34},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":23},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":6,"losses":2,"wins":34},"gpt-5.4":{"draws":4,"losses":9,"wins":33},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":22},"gpt-5.4-nano":{"draws":1,"losses":1,"wins":46},"gpt-5.5":{"draws":5,"losses":9,"wins":30},"gpt-5.6-luna":{"draws":6,"losses":3,"wins":39},"gpt-5.6-sol":{"draws":7,"losses":8,"wins":33},"gpt-5.6-terra":{"draws":8,"losses":3,"wins":35},"gpt-6-astra":{"draws":8,"losses":28,"wins":12},"gpt-6-luna":{"draws":8,"losses":4,"wins":36},"gpt-6-sol":{"draws":5,"losses":21,"wins":22},"gpt-6.1-sol":{"draws":7,"losses":31,"wins":10},"gpt-6.1-terra":{"draws":6,"losses":17,"wins":9},"gpt-6.1-terra-pro":{"draws":7,"losses":28,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":0,"wins":29},"inception/mercury-3":{"draws":8,"losses":1,"wins":23},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":8},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":45},"meta/muse-glimmer-30b":{"draws":4,"losses":1,"wins":37},"meta/muse-spark-1.2":{"draws":7,"losses":3,"wins":36},"meta/muse-spark-1.3":{"draws":4,"losses":4,"wins":40},"meta/muse-spark-open":{"draws":7,"losses":5,"wins":36},"meta/muse-wonder":{"draws":11,"losses":13,"wins":24},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":24},"minimax/minimax-m3.1-flash":{"draws":7,"losses":0,"wins":35},"mistralai/mistral-large-4-0":{"draws":8,"losses":4,"wins":18},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":36},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":21,"wins":19},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"wins":18},"o3":{"draws":2,"losses":1,"wins":63},"openai/gpt-oss-120b":{"draws":7,"losses":0,"wins":35},"poolside/laguna-s-2.1":{"draws":7,"losses":0,"wins":39},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":23},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":7,"wins":38},"qwen/qwen3.8-27b":{"draws":5,"losses":1,"wins":28},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":26},"qwen/qwen3.8-max":{"draws":5,"losses":7,"wins":36},"qwen/qwen3.8-max-0902":{"draws":3,"losses":3,"wins":42},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":4,"wins":37},"stealth/ox-alpha":{"draws":22,"losses":18,"wins":118},"stealth/space-bunny-alpha":{"draws":5,"losses":2,"wins":31},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":1,"losses":0,"wins":5},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":21},"tencent/hy4-preview":{"draws":1,"losses":4,"wins":41},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":55},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":46},"unbiased/pareto-26.10":{"draws":2,"losses":13,"wins":1},"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":4,"losses":10,"wins":34},"x-ai/grok-4.6":{"draws":8,"losses":1,"wins":39},"x-ai/grok-4.7":{"draws":4,"losses":19,"wins":19},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":10,"losses":0,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":2,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":8,"wins":17},"z-ai/glm-5.2":{"draws":14,"losses":9,"wins":73},"z-ai/glm-5.3":{"draws":11,"losses":8,"wins":27},"z-ai/glm-5.3-flash":{"draws":10,"losses":4,"wins":34},"z-ai/glm-5.3-flashx":{"draws":9,"losses":5,"wins":34}},"gpt-6.1-terra-pro":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":1,"wins":36},"claude-fable-5":{"draws":7,"losses":6,"wins":35},"claude-fable-5-1":{"draws":7,"losses":33,"wins":14},"claude-haiku-5-5":{"draws":7,"losses":0,"wins":39},"claude-opus-4-5":{"draws":19,"losses":1,"wins":58},"claude-opus-4-8":{"draws":6,"losses":3,"wins":35},"claude-opus-5":{"draws":14,"losses":27,"wins":41},"claude-opus-5-5":{"draws":6,"losses":25,"wins":21},"claude-sonnet-5":{"draws":6,"losses":0,"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":8,"losses":1,"wins":63},"deepseek/deepseek-v4-pro":{"draws":5,"losses":1,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":0,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":3,"wins":38},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":3,"wins":36},"elorian/glimpse":{"draws":2,"losses":2,"wins":22},"fireworks/ember-1":{"draws":10,"losses":2,"wins":36},"gemini-3.1-pro-preview":{"draws":3,"losses":2,"wins":43},"gemini-4-argon":{"draws":5,"losses":20,"wins":23},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":28},"google/gemini-3.5-flash":{"draws":5,"losses":5,"wins":50},"google/gemini-3.5-flash-lite":{"draws":8,"losses":1,"wins":75},"google/gemini-3.6-flash":{"draws":12,"losses":6,"wins":74},"google/gemini-3.8-flash":{"draws":8,"losses":5,"wins":35},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":25},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":6,"losses":0,"wins":36},"gpt-5.4":{"draws":9,"losses":4,"wins":33},"gpt-5.4-mini":{"draws":5,"losses":2,"wins":25},"gpt-5.4-nano":{"draws":8,"losses":1,"wins":39},"gpt-5.5":{"draws":5,"losses":4,"wins":35},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":42},"gpt-5.6-sol":{"draws":10,"losses":8,"wins":30},"gpt-5.6-terra":{"draws":5,"losses":1,"wins":40},"gpt-6-astra":{"draws":7,"losses":26,"wins":15},"gpt-6-luna":{"draws":8,"losses":2,"wins":38},"gpt-6-sol":{"draws":8,"losses":12,"wins":28},"gpt-6.1-sol":{"draws":7,"losses":22,"wins":19},"gpt-6.1-terra":{"draws":6,"losses":15,"wins":27},"gpt-6.1-terra-pro":{"draws":3,"losses":17,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":5,"losses":0,"wins":29},"inception/mercury-3":{"draws":7,"losses":1,"wins":24},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":6,"losses":1,"wins":45},"meta/muse-glimmer-30b":{"draws":3,"losses":1,"wins":38},"meta/muse-spark-1.2":{"draws":6,"losses":3,"wins":37},"meta/muse-spark-1.3":{"draws":5,"losses":3,"wins":40},"meta/muse-spark-open":{"draws":8,"losses":5,"wins":35},"meta/muse-wonder":{"draws":8,"losses":13,"wins":27},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"minimax/minimax-m3.1-flash":{"draws":6,"losses":0,"wins":36},"mistralai/mistral-large-4-0":{"draws":5,"losses":2,"wins":23},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":2,"wins":37},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":17,"wins":26},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":20},"o3":{"draws":6,"losses":1,"wins":59},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":37},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":40},"qwen/qwen3.7-max":{"draws":5,"losses":0,"wins":23},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":5,"wins":33},"qwen/qwen3.8-27b":{"draws":6,"losses":1,"wins":27},"qwen/qwen3.8-flash":{"draws":4,"losses":2,"wins":26},"qwen/qwen3.8-max":{"draws":5,"losses":6,"wins":37},"qwen/qwen3.8-max-0902":{"draws":7,"losses":0,"wins":41},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":1,"wins":40},"stealth/ox-alpha":{"draws":24,"losses":12,"wins":122},"stealth/space-bunny-alpha":{"draws":5,"losses":2,"wins":31},"stepfun/step-3.7-flash":{"draws":5,"losses":0,"wins":29},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":9},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":22},"tencent/hy4-preview":{"draws":1,"losses":1,"wins":44},"thinkingmachines/inkling":{"draws":9,"losses":1,"wins":54},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":42},"unbiased/pareto-26.10":{"draws":1,"losses":12,"wins":3},"unbiased/pareto-26.10-preview":{"draws":2,"losses":8,"wins":6},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":8,"losses":5,"wins":35},"x-ai/grok-4.6":{"draws":7,"losses":4,"wins":37},"x-ai/grok-4.7":{"draws":6,"losses":14,"wins":22},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":15},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":1,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":6,"wins":17},"z-ai/glm-5.2":{"draws":15,"losses":2,"wins":79},"z-ai/glm-5.3":{"draws":9,"losses":10,"wins":27},"z-ai/glm-5.3-flash":{"draws":8,"losses":2,"wins":38},"z-ai/glm-5.3-flashx":{"draws":5,"losses":4,"wins":39}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":10,"wins":8},"claude-fable-5":{"draws":9,"losses":16,"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":9,"wins":6},"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":13,"wins":13},"deepseek/deepseek-v4-pro":{"draws":11,"losses":9,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":13,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":13,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":14,"wins":4},"elorian/glimpse":{"draws":7,"losses":7,"wins":0},"fireworks/ember-1":{"draws":13,"losses":12,"wins":5},"gemini-3.1-pro-preview":{"draws":10,"losses":9,"wins":11},"gemini-4-argon":{"draws":3,"losses":27,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":8},"google/gemini-3.5-flash":{"draws":12,"losses":13,"wins":11},"google/gemini-3.5-flash-lite":{"draws":20,"losses":10,"wins":24},"google/gemini-3.6-flash":{"draws":19,"losses":31,"wins":8},"google/gemini-3.8-flash":{"draws":11,"losses":18,"wins":1},"google/gemma-4-31b-it":{"draws":9,"losses":3,"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":14,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":11,"losses":4,"wins":5},"gpt-5.4-nano":{"draws":6,"losses":13,"wins":7},"gpt-5.5":{"draws":11,"losses":10,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":10,"wins":6},"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},"gpt-6.1-terra":{"draws":4,"losses":25,"wins":1},"gpt-6.1-terra-pro":{"draws":3,"losses":27,"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},"inception/mercury-3":{"draws":10,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":8,"losses":3,"wins":7},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":1},"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":10,"losses":11,"wins":7},"meta/muse-spark-1.3":{"draws":7,"losses":18,"wins":5},"meta/muse-spark-open":{"draws":10,"losses":16,"wins":4},"meta/muse-wonder":{"draws":10,"losses":17,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":5},"minimax/minimax-m3.1-flash":{"draws":11,"losses":10,"wins":7},"mistralai/mistral-large-4-0":{"draws":6,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":10},"moonshotai/kimi-k3":{"draws":10,"losses":14,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":20,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":5,"wins":1},"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":6,"wins":2},"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":11,"losses":14,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":15,"wins":3},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":14,"wins":3},"stealth/ox-alpha":{"draws":35,"losses":54,"wins":19},"stealth/space-bunny-alpha":{"draws":8,"losses":11,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":5},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":2},"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":13,"losses":6,"wins":11},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"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":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":20,"losses":15,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":4,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"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":18,"wins":3},"z-ai/glm-5.3-flashx":{"draws":8,"losses":21,"wins":1}},"inception/mercury-3":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":17,"wins":14},"claude-fable-5":{"draws":10,"losses":37,"wins":1},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":24,"wins":9},"claude-opus-4-5":{"draws":25,"losses":34,"wins":19},"claude-opus-4-8":{"draws":11,"losses":27,"wins":6},"claude-opus-5":{"draws":8,"losses":67,"wins":7},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":15,"losses":21,"wins":12},"claude-sonnet-5-5":{"draws":11,"losses":27,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":10},"deepseek/deepseek-v4-flash":{"draws":21,"losses":30,"wins":21},"deepseek/deepseek-v4-pro":{"draws":12,"losses":24,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":23,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":29,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":36,"wins":4},"elorian/glimpse":{"draws":4,"losses":13,"wins":9},"fireworks/ember-1":{"draws":15,"losses":19,"wins":14},"gemini-3.1-pro-preview":{"draws":17,"losses":17,"wins":14},"gemini-4-argon":{"draws":5,"losses":42,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":17},"google/gemini-3.5-flash":{"draws":11,"losses":33,"wins":16},"google/gemini-3.5-flash-lite":{"draws":23,"losses":24,"wins":37},"google/gemini-3.6-flash":{"draws":29,"losses":52,"wins":11},"google/gemini-3.8-flash":{"draws":13,"losses":33,"wins":2},"google/gemma-4-31b-it":{"draws":8,"losses":7,"wins":13},"gpt-4.1":{"draws":4,"losses":6,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":20,"wins":13},"gpt-5.4":{"draws":7,"losses":27,"wins":12},"gpt-5.4-mini":{"draws":11,"losses":8,"wins":13},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":21},"gpt-5.5":{"draws":13,"losses":24,"wins":7},"gpt-5.6-luna":{"draws":14,"losses":19,"wins":15},"gpt-5.6-sol":{"draws":5,"losses":39,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":24,"wins":8},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":12,"losses":28,"wins":8},"gpt-6-sol":{"draws":7,"losses":37,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":44,"wins":1},"gpt-6.1-terra":{"draws":9,"losses":38,"wins":1},"gpt-6.1-terra-pro":{"draws":6,"losses":41,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":8,"wins":12},"inception/mercury-3":{"draws":5,"losses":10,"wins":1},"inclusionai/ling-3.0-flash":{"draws":9,"losses":13,"wins":12},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":24,"wins":15},"meta/muse-glimmer-30b":{"draws":11,"losses":15,"wins":16},"meta/muse-spark-1.2":{"draws":12,"losses":26,"wins":8},"meta/muse-spark-1.3":{"draws":8,"losses":33,"wins":7},"meta/muse-spark-open":{"draws":9,"losses":29,"wins":8},"meta/muse-wonder":{"draws":11,"losses":31,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":8,"wins":11},"minimax/minimax-m3.1-flash":{"draws":9,"losses":15,"wins":18},"mistralai/mistral-large-4-0":{"draws":8,"losses":14,"wins":8},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":21,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":39,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":10,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":9,"wins":6},"o3":{"draws":11,"losses":26,"wins":29},"openai/gpt-oss-120b":{"draws":10,"losses":17,"wins":15},"poolside/laguna-s-2.1":{"draws":9,"losses":16,"wins":21},"qwen/qwen3.7-max":{"draws":6,"losses":15,"wins":7},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"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":10,"losses":15,"wins":7},"qwen/qwen3.8-max":{"draws":16,"losses":23,"wins":9},"qwen/qwen3.8-max-0902":{"draws":12,"losses":26,"wins":10},"recursive/flint-v1.0":{"draws":2,"losses":5,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":23,"wins":7},"stealth/ox-alpha":{"draws":40,"losses":80,"wins":38},"stealth/space-bunny-alpha":{"draws":7,"losses":18,"wins":13},"stepfun/step-3.7-flash":{"draws":9,"losses":9,"wins":16},"stepfun/step-5-preview":{"draws":1,"losses":6,"wins":1},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":12,"losses":24,"wins":10},"thinkingmachines/inkling":{"draws":21,"losses":22,"wins":21},"thinkingmachines/inkling-small":{"draws":14,"losses":11,"wins":23},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":16,"losses":23,"wins":9},"x-ai/grok-4.6":{"draws":12,"losses":27,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":19,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":9,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":14,"wins":8},"z-ai/glm-5.2":{"draws":30,"losses":38,"wins":28},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":6},"z-ai/glm-5.3-flash":{"draws":13,"losses":24,"wins":11},"z-ai/glm-5.3-flashx":{"draws":10,"losses":30,"wins":8}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":30,"wins":10},"claude-fable-5":{"draws":13,"losses":50,"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":20,"losses":38,"wins":0},"claude-opus-5":{"draws":17,"losses":89,"wins":6},"claude-opus-5-5":{"draws":5,"losses":73,"wins":0},"claude-sonnet-5":{"draws":22,"losses":40,"wins":4},"claude-sonnet-5-5":{"draws":16,"losses":47,"wins":3},"cohere/north-mini-code":{"draws":10,"losses":7,"wins":5},"deepseek/deepseek-v4-flash":{"draws":41,"losses":36,"wins":25},"deepseek/deepseek-v4-pro":{"draws":22,"losses":22,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":29,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":29,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":51,"wins":2},"elorian/glimpse":{"draws":9,"losses":23,"wins":6},"fireworks/ember-1":{"draws":28,"losses":35,"wins":3},"gemini-3.1-pro-preview":{"draws":23,"losses":30,"wins":13},"gemini-4-argon":{"draws":6,"losses":58,"wins":2},"google/gemini-3.1-flash-lite":{"draws":15,"losses":14,"wins":9},"google/gemini-3.5-flash":{"draws":25,"losses":48,"wins":9},"google/gemini-3.5-flash-lite":{"draws":39,"losses":48,"wins":27},"google/gemini-3.6-flash":{"draws":39,"losses":71,"wins":14},"google/gemini-3.8-flash":{"draws":17,"losses":48,"wins":1},"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":19,"losses":23,"wins":16},"gpt-5.4":{"draws":16,"losses":37,"wins":11},"gpt-5.4-mini":{"draws":16,"losses":18,"wins":10},"gpt-5.4-nano":{"draws":16,"losses":36,"wins":16},"gpt-5.5":{"draws":28,"losses":27,"wins":5},"gpt-5.6-luna":{"draws":37,"losses":22,"wins":7},"gpt-5.6-sol":{"draws":8,"losses":56,"wins":2},"gpt-5.6-terra":{"draws":22,"losses":41,"wins":3},"gpt-6-astra":{"draws":3,"losses":62,"wins":1},"gpt-6-luna":{"draws":24,"losses":33,"wins":9},"gpt-6-sol":{"draws":10,"losses":50,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":63,"wins":1},"gpt-6.1-terra":{"draws":6,"losses":59,"wins":1},"gpt-6.1-terra-pro":{"draws":1,"losses":61,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":23,"losses":13,"wins":8},"inception/mercury-3":{"draws":10,"losses":29,"wins":11},"inclusionai/ling-3.0-flash":{"draws":14,"losses":10,"wins":12},"inclusionai/ling-3.1-flash":{"draws":6,"losses":4,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":25,"wins":12},"meta/muse-glimmer-30b":{"draws":32,"losses":12,"wins":12},"meta/muse-spark-1.2":{"draws":16,"losses":42,"wins":4},"meta/muse-spark-1.3":{"draws":15,"losses":47,"wins":4},"meta/muse-spark-open":{"draws":12,"losses":49,"wins":5},"meta/muse-wonder":{"draws":9,"losses":52,"wins":5},"minimax/minimax-m3":{"draws":9,"losses":17,"wins":8},"minimax/minimax-m3.1-flash":{"draws":13,"losses":27,"wins":12},"mistralai/mistral-large-4-0":{"draws":21,"losses":14,"wins":5},"mistralai/mistral-medium-3-5":{"draws":12,"losses":14,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":19,"losses":36,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":53,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":14,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":19,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":15,"wins":5},"o3":{"draws":21,"losses":55,"wins":12},"openai/gpt-oss-120b":{"draws":29,"losses":25,"wins":2},"poolside/laguna-s-2.1":{"draws":23,"losses":20,"wins":25},"qwen/qwen3.7-max":{"draws":14,"losses":15,"wins":9},"qwen/qwen3.7-plus":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":43,"wins":1},"qwen/qwen3.8-27b":{"draws":10,"losses":27,"wins":9},"qwen/qwen3.8-flash":{"draws":14,"losses":25,"wins":5},"qwen/qwen3.8-max":{"draws":24,"losses":36,"wins":6},"qwen/qwen3.8-max-0902":{"draws":27,"losses":36,"wins":3},"recursive/flint-v1.0":{"draws":4,"losses":10,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":36,"wins":4},"stealth/ox-alpha":{"draws":62,"losses":147,"wins":17},"stealth/space-bunny-alpha":{"draws":20,"losses":18,"wins":8},"stepfun/step-3.7-flash":{"draws":21,"losses":14,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":13,"wins":3},"tencent/hy3-preview":{"draws":14,"losses":18,"wins":4},"tencent/hy4-preview":{"draws":24,"losses":32,"wins":8},"thinkingmachines/inkling":{"draws":27,"losses":36,"wins":21},"thinkingmachines/inkling-small":{"draws":29,"losses":18,"wins":19},"unbiased/pareto-26.10":{"draws":1,"losses":21,"wins":0},"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":22,"losses":41,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":48,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":12,"wins":2},"xiaomi/mimo-v2.5":{"draws":42,"losses":34,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":9,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":24,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":34,"wins":3},"z-ai/glm-5.2":{"draws":63,"losses":43,"wins":26},"z-ai/glm-5.3":{"draws":16,"losses":43,"wins":3},"z-ai/glm-5.3-flash":{"draws":19,"losses":35,"wins":12},"z-ai/glm-5.3-flashx":{"draws":25,"losses":35,"wins":6}},"inclusionai/ling-3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":4,"wins":7},"claude-fable-5":{"draws":2,"losses":12,"wins":2},"claude-fable-5-1":{"draws":0,"losses":22,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":4,"wins":5},"claude-opus-4-5":{"draws":16,"losses":15,"wins":7},"claude-opus-4-8":{"draws":2,"losses":8,"wins":4},"claude-opus-5":{"draws":8,"losses":28,"wins":2},"claude-opus-5-5":{"draws":2,"losses":24,"wins":0},"claude-sonnet-5":{"draws":5,"losses":5,"wins":8},"claude-sonnet-5-5":{"draws":5,"losses":12,"wins":3},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":16,"losses":4,"wins":6},"deepseek/deepseek-v4-pro":{"draws":12,"losses":9,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":8,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":8,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":19,"wins":5},"elorian/glimpse":{"draws":3,"losses":4,"wins":5},"fireworks/ember-1":{"draws":8,"losses":4,"wins":2},"gemini-3.1-pro-preview":{"draws":5,"losses":5,"wins":6},"gemini-4-argon":{"draws":1,"losses":23,"wins":2},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":5},"google/gemini-3.5-flash":{"draws":8,"losses":16,"wins":8},"google/gemini-3.5-flash-lite":{"draws":16,"losses":9,"wins":25},"google/gemini-3.6-flash":{"draws":9,"losses":21,"wins":10},"google/gemini-3.8-flash":{"draws":10,"losses":10,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":7},"gpt-4.1":{"draws":6,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":8,"losses":5,"wins":7},"gpt-5.4":{"draws":7,"losses":17,"wins":4},"gpt-5.4-mini":{"draws":6,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":8},"gpt-5.5":{"draws":10,"losses":8,"wins":6},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":14,"wins":4},"gpt-5.6-terra":{"draws":8,"losses":3,"wins":5},"gpt-6-astra":{"draws":1,"losses":23,"wins":0},"gpt-6-luna":{"draws":14,"losses":13,"wins":9},"gpt-6-sol":{"draws":6,"losses":22,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":24,"wins":2},"gpt-6.1-terra":{"draws":3,"losses":20,"wins":1},"gpt-6.1-terra-pro":{"draws":2,"losses":18,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":5},"inception/mercury-3":{"draws":2,"losses":7,"wins":3},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":6},"meituan/longcat-2.0":{"draws":6,"losses":6,"wins":10},"meta/muse-glimmer-30b":{"draws":6,"losses":8,"wins":8},"meta/muse-spark-1.2":{"draws":11,"losses":7,"wins":6},"meta/muse-spark-1.3":{"draws":7,"losses":15,"wins":4},"meta/muse-spark-open":{"draws":8,"losses":7,"wins":3},"meta/muse-wonder":{"draws":10,"losses":20,"wins":2},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":8},"minimax/minimax-m3.1-flash":{"draws":5,"losses":8,"wins":7},"mistralai/mistral-large-4-0":{"draws":6,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":5,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":19,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":10,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":5,"wins":4},"o3":{"draws":2,"losses":14,"wins":16},"openai/gpt-oss-120b":{"draws":3,"losses":6,"wins":9},"poolside/laguna-s-2.1":{"draws":13,"losses":4,"wins":5},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":8,"wins":3},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":2},"qwen/qwen3.8-flash":{"draws":7,"losses":5,"wins":2},"qwen/qwen3.8-max":{"draws":8,"losses":10,"wins":8},"qwen/qwen3.8-max-0902":{"draws":8,"losses":6,"wins":4},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":6,"wins":7},"stealth/ox-alpha":{"draws":25,"losses":30,"wins":13},"stealth/space-bunny-alpha":{"draws":6,"losses":10,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":8,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":6},"tencent/hy4-preview":{"draws":7,"losses":14,"wins":3},"thinkingmachines/inkling":{"draws":18,"losses":5,"wins":15},"thinkingmachines/inkling-small":{"draws":7,"losses":6,"wins":9},"unbiased/pareto-26.10":{"draws":0,"losses":6,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":4,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":8,"losses":10,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":12,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":12,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":3},"xiaomi/mimo-v2.5":{"draws":9,"losses":8,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":7,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":4,"wins":4},"z-ai/glm-5.2":{"draws":13,"losses":12,"wins":17},"z-ai/glm-5.3":{"draws":7,"losses":13,"wins":4},"z-ai/glm-5.3-flash":{"draws":8,"losses":14,"wins":4},"z-ai/glm-5.3-flashx":{"draws":6,"losses":9,"wins":1}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":37,"wins":23},"claude-fable-5":{"draws":8,"losses":67,"wins":9},"claude-fable-5-1":{"draws":1,"losses":90,"wins":3},"claude-haiku-5-5":{"draws":18,"losses":52,"wins":10},"claude-opus-4-5":{"draws":32,"losses":86,"wins":18},"claude-opus-4-8":{"draws":14,"losses":51,"wins":11},"claude-opus-5":{"draws":13,"losses":118,"wins":9},"claude-opus-5-5":{"draws":5,"losses":85,"wins":2},"claude-sonnet-5":{"draws":19,"losses":47,"wins":18},"claude-sonnet-5-5":{"draws":11,"losses":59,"wins":14},"cohere/north-mini-code":{"draws":6,"losses":8,"wins":20},"deepseek/deepseek-v4-flash":{"draws":22,"losses":61,"wins":45},"deepseek/deepseek-v4-pro":{"draws":14,"losses":46,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":39,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":51,"wins":19},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":60,"wins":9},"elorian/glimpse":{"draws":6,"losses":30,"wins":10},"fireworks/ember-1":{"draws":22,"losses":50,"wins":12},"gemini-3.1-pro-preview":{"draws":20,"losses":41,"wins":23},"gemini-4-argon":{"draws":3,"losses":77,"wins":4},"google/gemini-3.1-flash-lite":{"draws":7,"losses":17,"wins":34},"google/gemini-3.5-flash":{"draws":18,"losses":66,"wins":22},"google/gemini-3.5-flash-lite":{"draws":34,"losses":72,"wins":42},"google/gemini-3.6-flash":{"draws":28,"losses":109,"wins":25},"google/gemini-3.8-flash":{"draws":11,"losses":66,"wins":7},"google/gemma-4-31b-it":{"draws":20,"losses":11,"wins":17},"gpt-4.1":{"draws":4,"losses":19,"wins":5},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":3},"gpt-5":{"draws":11,"losses":42,"wins":23},"gpt-5.4":{"draws":17,"losses":55,"wins":10},"gpt-5.4-mini":{"draws":20,"losses":22,"wins":14},"gpt-5.4-nano":{"draws":13,"losses":46,"wins":29},"gpt-5.5":{"draws":27,"losses":38,"wins":13},"gpt-5.6-luna":{"draws":17,"losses":40,"wins":27},"gpt-5.6-sol":{"draws":9,"losses":69,"wins":6},"gpt-5.6-terra":{"draws":20,"losses":42,"wins":18},"gpt-6-astra":{"draws":5,"losses":79,"wins":0},"gpt-6-luna":{"draws":22,"losses":45,"wins":17},"gpt-6-sol":{"draws":7,"losses":69,"wins":8},"gpt-6.1-sol":{"draws":1,"losses":78,"wins":5},"gpt-6.1-terra":{"draws":7,"losses":73,"wins":4},"gpt-6.1-terra-pro":{"draws":9,"losses":70,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":23,"wins":18},"inception/mercury-3":{"draws":15,"losses":29,"wins":14},"inclusionai/ling-3.0-flash":{"draws":23,"losses":17,"wins":20},"inclusionai/ling-3.1-flash":{"draws":2,"losses":6,"wins":4},"meituan/longcat-2.0":{"draws":12,"losses":33,"wins":21},"meta/muse-glimmer-30b":{"draws":24,"losses":28,"wins":22},"meta/muse-spark-1.2":{"draws":14,"losses":55,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":61,"wins":12},"meta/muse-spark-open":{"draws":18,"losses":57,"wins":9},"meta/muse-wonder":{"draws":20,"losses":53,"wins":11},"minimax/minimax-m3":{"draws":7,"losses":19,"wins":20},"minimax/minimax-m3.1-flash":{"draws":13,"losses":36,"wins":25},"mistralai/mistral-large-4-0":{"draws":18,"losses":27,"wins":7},"mistralai/mistral-medium-3-5":{"draws":14,"losses":16,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":22,"losses":43,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":70,"wins":8},"nex-agi/nex-n2-pro":{"draws":6,"losses":16,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":10,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":23,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":23,"wins":5},"o3":{"draws":17,"losses":79,"wins":30},"openai/gpt-oss-120b":{"draws":14,"losses":30,"wins":30},"poolside/laguna-s-2.1":{"draws":27,"losses":37,"wins":20},"qwen/qwen3.7-max":{"draws":11,"losses":26,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":19,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":51,"wins":10},"qwen/qwen3.8-27b":{"draws":13,"losses":37,"wins":10},"qwen/qwen3.8-flash":{"draws":15,"losses":28,"wins":13},"qwen/qwen3.8-max":{"draws":19,"losses":45,"wins":20},"qwen/qwen3.8-max-0902":{"draws":14,"losses":54,"wins":16},"recursive/flint-v1.0":{"draws":5,"losses":9,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":49,"wins":13},"stealth/ox-alpha":{"draws":50,"losses":186,"wins":46},"stealth/space-bunny-alpha":{"draws":15,"losses":41,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":22,"wins":32},"stepfun/step-5-preview":{"draws":1,"losses":10,"wins":3},"tencent/hy3-preview":{"draws":9,"losses":22,"wins":13},"tencent/hy4-preview":{"draws":19,"losses":51,"wins":12},"thinkingmachines/inkling":{"draws":26,"losses":44,"wins":44},"thinkingmachines/inkling-small":{"draws":24,"losses":29,"wins":31},"unbiased/pareto-26.10":{"draws":0,"losses":28,"wins":0},"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":15,"losses":54,"wins":15},"x-ai/grok-4.6":{"draws":20,"losses":54,"wins":10},"x-ai/grok-4.7":{"draws":5,"losses":64,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":11,"wins":11},"xiaomi/mimo-v2.5":{"draws":25,"losses":54,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":29,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":38,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":38,"wins":5},"z-ai/glm-5.2":{"draws":46,"losses":82,"wins":40},"z-ai/glm-5.3":{"draws":10,"losses":65,"wins":5},"z-ai/glm-5.3-flash":{"draws":13,"losses":52,"wins":19},"z-ai/glm-5.3-flashx":{"draws":10,"losses":65,"wins":9}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":17,"wins":7},"claude-fable-5":{"draws":6,"losses":27,"wins":3},"claude-fable-5-1":{"draws":1,"losses":41,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":24,"wins":3},"claude-opus-4-5":{"draws":15,"losses":38,"wins":5},"claude-opus-4-8":{"draws":5,"losses":23,"wins":4},"claude-opus-5":{"draws":2,"losses":58,"wins":8},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":7,"losses":25,"wins":4},"claude-sonnet-5-5":{"draws":4,"losses":28,"wins":4},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":12,"losses":26,"wins":14},"deepseek/deepseek-v4-pro":{"draws":9,"losses":17,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":19,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":20,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":23,"wins":3},"elorian/glimpse":{"draws":7,"losses":11,"wins":4},"fireworks/ember-1":{"draws":12,"losses":22,"wins":2},"gemini-3.1-pro-preview":{"draws":13,"losses":20,"wins":3},"gemini-4-argon":{"draws":3,"losses":31,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":8,"wins":10},"google/gemini-3.5-flash":{"draws":8,"losses":31,"wins":7},"google/gemini-3.5-flash-lite":{"draws":14,"losses":31,"wins":19},"google/gemini-3.6-flash":{"draws":16,"losses":45,"wins":9},"google/gemini-3.8-flash":{"draws":8,"losses":23,"wins":5},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":7},"gpt-4.1":{"draws":3,"losses":8,"wins":1},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":6,"losses":19,"wins":9},"gpt-5.4":{"draws":8,"losses":23,"wins":5},"gpt-5.4-mini":{"draws":8,"losses":12,"wins":4},"gpt-5.4-nano":{"draws":1,"losses":21,"wins":12},"gpt-5.5":{"draws":11,"losses":20,"wins":5},"gpt-5.6-luna":{"draws":9,"losses":16,"wins":11},"gpt-5.6-sol":{"draws":4,"losses":31,"wins":1},"gpt-5.6-terra":{"draws":8,"losses":22,"wins":4},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":10,"losses":19,"wins":7},"gpt-6-sol":{"draws":5,"losses":29,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"gpt-6.1-terra":{"draws":6,"losses":30,"wins":0},"gpt-6.1-terra-pro":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":8,"wins":7},"inception/mercury-3":{"draws":6,"losses":12,"wins":4},"inclusionai/ling-3.0-flash":{"draws":7,"losses":6,"wins":11},"inclusionai/ling-3.1-flash":{"draws":4,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":21,"wins":11},"meta/muse-glimmer-30b":{"draws":11,"losses":10,"wins":3},"meta/muse-spark-1.2":{"draws":7,"losses":26,"wins":3},"meta/muse-spark-1.3":{"draws":6,"losses":27,"wins":3},"meta/muse-spark-open":{"draws":8,"losses":25,"wins":3},"meta/muse-wonder":{"draws":6,"losses":26,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":12,"wins":6},"minimax/minimax-m3.1-flash":{"draws":9,"losses":16,"wins":7},"mistralai/mistral-large-4-0":{"draws":8,"losses":10,"wins":6},"mistralai/mistral-medium-3-5":{"draws":4,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":23,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":27,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":8,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":8,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":9,"wins":4},"o3":{"draws":6,"losses":32,"wins":14},"openai/gpt-oss-120b":{"draws":6,"losses":15,"wins":11},"poolside/laguna-s-2.1":{"draws":6,"losses":19,"wins":11},"qwen/qwen3.7-max":{"draws":4,"losses":12,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":20,"wins":4},"qwen/qwen3.8-27b":{"draws":4,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":7},"qwen/qwen3.8-max":{"draws":7,"losses":24,"wins":5},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":4},"recursive/flint-v1.0":{"draws":2,"losses":3,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":21,"losses":88,"wins":17},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":8,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":7,"wins":5},"tencent/hy3-preview":{"draws":4,"losses":14,"wins":2},"tencent/hy4-preview":{"draws":10,"losses":22,"wins":4},"thinkingmachines/inkling":{"draws":14,"losses":19,"wins":19},"thinkingmachines/inkling-small":{"draws":11,"losses":10,"wins":15},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":11,"losses":24,"wins":1},"x-ai/grok-4.7":{"draws":3,"losses":25,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":17,"losses":22,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":11,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":18,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":4},"z-ai/glm-5.2":{"draws":22,"losses":32,"wins":18},"z-ai/glm-5.3":{"draws":3,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":4,"losses":28,"wins":4},"z-ai/glm-5.3-flashx":{"draws":5,"losses":25,"wins":6}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":14},"claude-fable-5":{"draws":5,"losses":37,"wins":6},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":29,"wins":6},"claude-opus-4-5":{"draws":22,"losses":31,"wins":25},"claude-opus-4-8":{"draws":12,"losses":26,"wins":6},"claude-opus-5":{"draws":9,"losses":62,"wins":11},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":15,"losses":20,"wins":13},"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":20,"wins":31},"deepseek/deepseek-v4-pro":{"draws":9,"losses":21,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":21,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":25,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":30,"wins":8},"elorian/glimpse":{"draws":6,"losses":9,"wins":11},"fireworks/ember-1":{"draws":14,"losses":25,"wins":9},"gemini-3.1-pro-preview":{"draws":13,"losses":21,"wins":14},"gemini-4-argon":{"draws":3,"losses":41,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":15,"losses":28,"wins":17},"google/gemini-3.5-flash-lite":{"draws":26,"losses":22,"wins":36},"google/gemini-3.6-flash":{"draws":24,"losses":51,"wins":17},"google/gemini-3.8-flash":{"draws":11,"losses":26,"wins":11},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":10},"gpt-4.1":{"draws":4,"losses":6,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":9,"losses":18,"wins":15},"gpt-5.4":{"draws":6,"losses":24,"wins":16},"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":18,"wins":19},"gpt-5.6-sol":{"draws":6,"losses":38,"wins":4},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":15},"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},"gpt-6.1-terra":{"draws":2,"losses":45,"wins":1},"gpt-6.1-terra-pro":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"inception/mercury-3":{"draws":10,"losses":15,"wins":7},"inclusionai/ling-3.0-flash":{"draws":12,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":4,"losses":4,"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":8,"losses":17,"wins":5},"meta/muse-spark-1.3":{"draws":12,"losses":26,"wins":10},"meta/muse-spark-open":{"draws":12,"losses":29,"wins":7},"meta/muse-wonder":{"draws":9,"losses":32,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":13},"minimax/minimax-m3.1-flash":{"draws":10,"losses":19,"wins":13},"mistralai/mistral-large-4-0":{"draws":7,"losses":13,"wins":10},"mistralai/mistral-medium-3-5":{"draws":10,"losses":3,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":21,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":39,"wins":4},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":7,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":8,"wins":7},"o3":{"draws":8,"losses":34,"wins":24},"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":20,"wins":4},"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":25,"wins":12},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":20,"wins":12},"stealth/ox-alpha":{"draws":38,"losses":85,"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":1,"losses":7,"wins":4},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":9,"losses":26,"wins":11},"thinkingmachines/inkling":{"draws":23,"losses":15,"wins":26},"thinkingmachines/inkling-small":{"draws":13,"losses":14,"wins":21},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":5,"losses":6,"wins":13},"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":15,"losses":10,"wins":19},"claude-fable-5":{"draws":9,"losses":36,"wins":3},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":29,"wins":4},"claude-opus-4-5":{"draws":27,"losses":31,"wins":20},"claude-opus-4-8":{"draws":11,"losses":27,"wins":6},"claude-opus-5":{"draws":13,"losses":63,"wins":6},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":15,"losses":19,"wins":14},"claude-sonnet-5-5":{"draws":10,"losses":31,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":17,"losses":22,"wins":33},"deepseek/deepseek-v4-pro":{"draws":11,"losses":22,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":21,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":27,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":32,"wins":11},"elorian/glimpse":{"draws":6,"losses":13,"wins":7},"fireworks/ember-1":{"draws":14,"losses":23,"wins":11},"gemini-3.1-pro-preview":{"draws":11,"losses":18,"wins":19},"gemini-4-argon":{"draws":2,"losses":45,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":14,"losses":28,"wins":18},"google/gemini-3.5-flash-lite":{"draws":20,"losses":25,"wins":39},"google/gemini-3.6-flash":{"draws":17,"losses":50,"wins":25},"google/gemini-3.8-flash":{"draws":12,"losses":31,"wins":5},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":13},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":21,"wins":14},"gpt-5.4":{"draws":10,"losses":26,"wins":10},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":14,"losses":14,"wins":20},"gpt-5.5":{"draws":15,"losses":21,"wins":8},"gpt-5.6-luna":{"draws":17,"losses":17,"wins":14},"gpt-5.6-sol":{"draws":6,"losses":41,"wins":1},"gpt-5.6-terra":{"draws":11,"losses":22,"wins":13},"gpt-6-astra":{"draws":3,"losses":44,"wins":1},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":7,"losses":39,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"gpt-6.1-terra":{"draws":5,"losses":42,"wins":1},"gpt-6.1-terra-pro":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"inception/mercury-3":{"draws":10,"losses":11,"wins":11},"inclusionai/ling-3.0-flash":{"draws":12,"losses":5,"wins":17},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":14,"wins":27},"meta/muse-glimmer-30b":{"draws":18,"losses":9,"wins":15},"meta/muse-spark-1.2":{"draws":14,"losses":25,"wins":7},"meta/muse-spark-1.3":{"draws":5,"losses":25,"wins":2},"meta/muse-spark-open":{"draws":12,"losses":31,"wins":5},"meta/muse-wonder":{"draws":10,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":19},"minimax/minimax-m3.1-flash":{"draws":6,"losses":15,"wins":21},"mistralai/mistral-large-4-0":{"draws":11,"losses":13,"wins":6},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":14,"losses":24,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":41,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":6,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":11,"wins":5},"o3":{"draws":10,"losses":34,"wins":22},"openai/gpt-oss-120b":{"draws":11,"losses":8,"wins":23},"poolside/laguna-s-2.1":{"draws":15,"losses":17,"wins":14},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":19,"wins":10},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":8},"qwen/qwen3.8-flash":{"draws":9,"losses":14,"wins":9},"qwen/qwen3.8-max":{"draws":19,"losses":15,"wins":14},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":21,"wins":12},"stealth/ox-alpha":{"draws":36,"losses":87,"wins":35},"stealth/space-bunny-alpha":{"draws":5,"losses":14,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":3,"losses":3,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":13},"tencent/hy4-preview":{"draws":11,"losses":27,"wins":8},"thinkingmachines/inkling":{"draws":21,"losses":9,"wins":34},"thinkingmachines/inkling-small":{"draws":19,"losses":9,"wins":20},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":10,"losses":33,"wins":5},"x-ai/grok-4.6":{"draws":13,"losses":25,"wins":10},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":23,"losses":21,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":6,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":18,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":23,"wins":6},"z-ai/glm-5.2":{"draws":28,"losses":39,"wins":29},"z-ai/glm-5.3":{"draws":7,"losses":37,"wins":2},"z-ai/glm-5.3-flash":{"draws":10,"losses":34,"wins":4},"z-ai/glm-5.3-flashx":{"draws":7,"losses":30,"wins":11}},"meta/muse-spark-open":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":8,"wins":28},"claude-fable-5":{"draws":8,"losses":34,"wins":6},"claude-fable-5-1":{"draws":1,"losses":49,"wins":4},"claude-haiku-5-5":{"draws":8,"losses":19,"wins":19},"claude-opus-4-5":{"draws":23,"losses":22,"wins":33},"claude-opus-4-8":{"draws":10,"losses":21,"wins":13},"claude-opus-5":{"draws":12,"losses":51,"wins":19},"claude-opus-5-5":{"draws":4,"losses":44,"wins":4},"claude-sonnet-5":{"draws":11,"losses":13,"wins":24},"claude-sonnet-5-5":{"draws":9,"losses":22,"wins":17},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":16,"losses":13,"wins":43},"deepseek/deepseek-v4-pro":{"draws":10,"losses":10,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":11,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":22,"wins":19},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":30,"wins":7},"elorian/glimpse":{"draws":4,"losses":13,"wins":9},"fireworks/ember-1":{"draws":12,"losses":14,"wins":22},"gemini-3.1-pro-preview":{"draws":13,"losses":14,"wins":21},"gemini-4-argon":{"draws":2,"losses":39,"wins":7},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":23},"google/gemini-3.5-flash":{"draws":10,"losses":24,"wins":26},"google/gemini-3.5-flash-lite":{"draws":17,"losses":15,"wins":52},"google/gemini-3.6-flash":{"draws":20,"losses":42,"wins":30},"google/gemini-3.8-flash":{"draws":8,"losses":25,"wins":15},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":21},"gpt-4.1":{"draws":3,"losses":4,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":9,"wins":22},"gpt-5.4":{"draws":8,"losses":21,"wins":17},"gpt-5.4-mini":{"draws":8,"losses":5,"wins":19},"gpt-5.4-nano":{"draws":10,"losses":9,"wins":29},"gpt-5.5":{"draws":11,"losses":17,"wins":16},"gpt-5.6-luna":{"draws":13,"losses":10,"wins":25},"gpt-5.6-sol":{"draws":9,"losses":26,"wins":13},"gpt-5.6-terra":{"draws":15,"losses":14,"wins":17},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":9,"losses":16,"wins":23},"gpt-6-sol":{"draws":4,"losses":36,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":4},"gpt-6.1-terra":{"draws":8,"losses":34,"wins":6},"gpt-6.1-terra-pro":{"draws":5,"losses":36,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":20},"inception/mercury-3":{"draws":9,"losses":7,"wins":16},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":24},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":37},"meta/muse-glimmer-30b":{"draws":10,"losses":5,"wins":27},"meta/muse-spark-1.2":{"draws":10,"losses":16,"wins":20},"meta/muse-spark-1.3":{"draws":8,"losses":27,"wins":13},"meta/muse-spark-open":{"draws":6,"losses":10,"wins":14},"meta/muse-wonder":{"draws":8,"losses":25,"wins":15},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":17},"minimax/minimax-m3.1-flash":{"draws":9,"losses":12,"wins":21},"mistralai/mistral-large-4-0":{"draws":6,"losses":8,"wins":16},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":12,"losses":14,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":40,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":9,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":2,"wins":15},"o3":{"draws":8,"losses":16,"wins":42},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":12,"losses":6,"wins":28},"qwen/qwen3.7-max":{"draws":6,"losses":8,"wins":14},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":15,"wins":17},"qwen/qwen3.8-27b":{"draws":7,"losses":10,"wins":17},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":15},"qwen/qwen3.8-max":{"draws":10,"losses":15,"wins":23},"qwen/qwen3.8-max-0902":{"draws":13,"losses":22,"wins":13},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":13,"wins":23},"stealth/ox-alpha":{"draws":28,"losses":60,"wins":70},"stealth/space-bunny-alpha":{"draws":10,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":3,"losses":5,"wins":26},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":4},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":8,"losses":17,"wins":21},"thinkingmachines/inkling":{"draws":15,"losses":8,"wins":41},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":32},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":11,"losses":18,"wins":19},"x-ai/grok-4.6":{"draws":13,"losses":22,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":32,"wins":7},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":19,"losses":6,"wins":49},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":12,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":12},"z-ai/glm-5.2":{"draws":27,"losses":23,"wins":46},"z-ai/glm-5.3":{"draws":7,"losses":26,"wins":13},"z-ai/glm-5.3-flash":{"draws":6,"losses":19,"wins":23},"z-ai/glm-5.3-flashx":{"draws":10,"losses":21,"wins":17}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":23},"claude-fable-5":{"draws":11,"losses":28,"wins":9},"claude-fable-5-1":{"draws":3,"losses":40,"wins":11},"claude-haiku-5-5":{"draws":15,"losses":12,"wins":19},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":21,"wins":14},"elorian/glimpse":{"draws":5,"losses":10,"wins":11},"fireworks/ember-1":{"draws":18,"losses":10,"wins":20},"gemini-3.1-pro-preview":{"draws":9,"losses":12,"wins":27},"gemini-4-argon":{"draws":4,"losses":38,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":13,"losses":14,"wins":33},"google/gemini-3.5-flash-lite":{"draws":20,"losses":12,"wins":52},"google/gemini-3.6-flash":{"draws":28,"losses":30,"wins":34},"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":10,"losses":9,"wins":29},"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":6,"losses":40,"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},"gpt-6.1-terra":{"draws":9,"losses":31,"wins":8},"gpt-6.1-terra-pro":{"draws":5,"losses":35,"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},"inception/mercury-3":{"draws":11,"losses":11,"wins":10},"inclusionai/ling-3.0-flash":{"draws":7,"losses":3,"wins":24},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":14,"losses":7,"wins":31},"meta/muse-glimmer-30b":{"draws":14,"losses":5,"wins":23},"meta/muse-spark-1.2":{"draws":15,"losses":16,"wins":15},"meta/muse-spark-1.3":{"draws":13,"losses":21,"wins":14},"meta/muse-spark-open":{"draws":9,"losses":21,"wins":16},"meta/muse-wonder":{"draws":7,"losses":19,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":14},"minimax/minimax-m3.1-flash":{"draws":9,"losses":12,"wins":21},"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":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":13,"losses":8,"wins":25},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":32,"wins":10},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":1,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":3,"wins":11},"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":10,"losses":1,"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},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":11,"wins":24},"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":6,"losses":6,"wins":22},"stepfun/step-5-preview":{"draws":1,"losses":7,"wins":2},"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":{"draws":0,"losses":13,"wins":3},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"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":6,"losses":5,"wins":13},"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":0,"losses":39,"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":8,"losses":57,"wins":3},"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":11,"losses":17,"wins":28},"deepseek/deepseek-v4-pro":{"draws":4,"losses":19,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":13,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":20,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":30,"wins":3},"elorian/glimpse":{"draws":3,"losses":11,"wins":6},"fireworks/ember-1":{"draws":7,"losses":25,"wins":4},"gemini-3.1-pro-preview":{"draws":6,"losses":15,"wins":15},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":17},"google/gemini-3.5-flash":{"draws":5,"losses":23,"wins":16},"google/gemini-3.5-flash-lite":{"draws":15,"losses":16,"wins":29},"google/gemini-3.6-flash":{"draws":11,"losses":40,"wins":17},"google/gemini-3.8-flash":{"draws":4,"losses":28,"wins":4},"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":17,"wins":10},"gpt-5.4":{"draws":4,"losses":18,"wins":12},"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":19,"wins":7},"gpt-5.6-luna":{"draws":11,"losses":14,"wins":11},"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":35,"wins":1},"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},"gpt-6.1-terra":{"draws":3,"losses":30,"wins":3},"gpt-6.1-terra-pro":{"draws":5,"losses":28,"wins":3},"inception/mercury-2.5-preview":{"draws":10,"losses":1,"wins":11},"inception/mercury-3":{"draws":9,"losses":8,"wins":9},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":8,"losses":13,"wins":17},"meta/muse-glimmer-30b":{"draws":9,"losses":6,"wins":19},"meta/muse-spark-1.2":{"draws":5,"losses":24,"wins":7},"meta/muse-spark-1.3":{"draws":2,"losses":29,"wins":5},"meta/muse-spark-open":{"draws":7,"losses":25,"wins":4},"meta/muse-wonder":{"draws":5,"losses":23,"wins":8},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":6},"minimax/minimax-m3.1-flash":{"draws":4,"losses":13,"wins":13},"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":2,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":24,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":33,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":7,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":4,"wins":9},"o3":{"draws":6,"losses":28,"wins":16},"openai/gpt-oss-120b":{"draws":8,"losses":11,"wins":15},"poolside/laguna-s-2.1":{"draws":11,"losses":12,"wins":17},"qwen/qwen3.7-max":{"draws":6,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":5,"losses":5,"wins":8},"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":11,"wins":10},"qwen/qwen3.8-max":{"draws":8,"losses":21,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":25,"wins":4},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":21,"wins":7},"stealth/ox-alpha":{"draws":29,"losses":67,"wins":28},"stealth/space-bunny-alpha":{"draws":5,"losses":12,"wins":11},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":6,"losses":21,"wins":7},"thinkingmachines/inkling":{"draws":12,"losses":13,"wins":25},"thinkingmachines/inkling-small":{"draws":8,"losses":7,"wins":21},"unbiased/pareto-26.10":{"draws":0,"losses":11,"wins":1},"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":29,"wins":0},"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":11,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"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":4,"losses":24,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":19,"wins":9},"z-ai/glm-5.3-flashx":{"draws":6,"losses":20,"wins":10}},"minimax/minimax-m3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":18,"wins":9},"claude-fable-5":{"draws":11,"losses":29,"wins":2},"claude-fable-5-1":{"draws":3,"losses":43,"wins":2},"claude-haiku-5-5":{"draws":11,"losses":22,"wins":7},"claude-opus-4-5":{"draws":22,"losses":32,"wins":14},"claude-opus-4-8":{"draws":9,"losses":25,"wins":4},"claude-opus-5":{"draws":10,"losses":55,"wins":5},"claude-opus-5-5":{"draws":3,"losses":39,"wins":0},"claude-sonnet-5":{"draws":14,"losses":21,"wins":7},"claude-sonnet-5-5":{"draws":13,"losses":25,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":18,"losses":19,"wins":25},"deepseek/deepseek-v4-pro":{"draws":12,"losses":22,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":22,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":26,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":27,"wins":7},"elorian/glimpse":{"draws":8,"losses":10,"wins":4},"fireworks/ember-1":{"draws":12,"losses":21,"wins":9},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":11},"gemini-4-argon":{"draws":5,"losses":36,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":5,"wins":18},"google/gemini-3.5-flash":{"draws":16,"losses":28,"wins":8},"google/gemini-3.5-flash-lite":{"draws":22,"losses":21,"wins":31},"google/gemini-3.6-flash":{"draws":24,"losses":50,"wins":8},"google/gemini-3.8-flash":{"draws":10,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":8,"losses":8,"wins":8},"gpt-4.1":{"draws":4,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":21,"wins":4},"gpt-5.4":{"draws":12,"losses":25,"wins":3},"gpt-5.4-mini":{"draws":14,"losses":7,"wins":7},"gpt-5.4-nano":{"draws":7,"losses":15,"wins":18},"gpt-5.5":{"draws":12,"losses":21,"wins":5},"gpt-5.6-luna":{"draws":16,"losses":16,"wins":10},"gpt-5.6-sol":{"draws":7,"losses":31,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":18,"wins":8},"gpt-6-astra":{"draws":5,"losses":37,"wins":0},"gpt-6-luna":{"draws":8,"losses":25,"wins":9},"gpt-6-sol":{"draws":7,"losses":33,"wins":2},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":0},"gpt-6.1-terra":{"draws":6,"losses":36,"wins":0},"gpt-6.1-terra-pro":{"draws":4,"losses":36,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":14},"inception/mercury-3":{"draws":7,"losses":14,"wins":5},"inclusionai/ling-3.0-flash":{"draws":10,"losses":9,"wins":9},"inclusionai/ling-3.1-flash":{"draws":1,"losses":3,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":18,"wins":15},"meta/muse-glimmer-30b":{"draws":12,"losses":14,"wins":10},"meta/muse-spark-1.2":{"draws":10,"losses":25,"wins":5},"meta/muse-spark-1.3":{"draws":6,"losses":31,"wins":5},"meta/muse-spark-open":{"draws":14,"losses":23,"wins":5},"meta/muse-wonder":{"draws":9,"losses":27,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":10,"wins":6},"minimax/minimax-m3.1-flash":{"draws":5,"losses":12,"wins":9},"mistralai/mistral-large-4-0":{"draws":8,"losses":14,"wins":4},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":34,"wins":3},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":9,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":8,"wins":3},"o3":{"draws":7,"losses":32,"wins":17},"openai/gpt-oss-120b":{"draws":12,"losses":13,"wins":11},"poolside/laguna-s-2.1":{"draws":13,"losses":14,"wins":11},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":24,"wins":4},"qwen/qwen3.8-27b":{"draws":9,"losses":13,"wins":10},"qwen/qwen3.8-flash":{"draws":6,"losses":16,"wins":6},"qwen/qwen3.8-max":{"draws":13,"losses":21,"wins":8},"qwen/qwen3.8-max-0902":{"draws":12,"losses":22,"wins":8},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":18,"wins":10},"stealth/ox-alpha":{"draws":39,"losses":77,"wins":26},"stealth/space-bunny-alpha":{"draws":10,"losses":17,"wins":7},"stepfun/step-3.7-flash":{"draws":7,"losses":11,"wins":12},"stepfun/step-5-preview":{"draws":1,"losses":7,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":11,"wins":3},"tencent/hy4-preview":{"draws":9,"losses":19,"wins":12},"thinkingmachines/inkling":{"draws":16,"losses":23,"wins":19},"thinkingmachines/inkling-small":{"draws":12,"losses":14,"wins":16},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":15,"losses":19,"wins":8},"x-ai/grok-4.6":{"draws":16,"losses":22,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":28,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":22,"losses":18,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":6,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":16,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":25,"losses":42,"wins":17},"z-ai/glm-5.3":{"draws":5,"losses":30,"wins":5},"z-ai/glm-5.3-flash":{"draws":7,"losses":25,"wins":10},"z-ai/glm-5.3-flashx":{"draws":9,"losses":27,"wins":6}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":14,"wins":10},"claude-fable-5":{"draws":8,"losses":26,"wins":8},"claude-fable-5-1":{"draws":3,"losses":43,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":18,"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":12,"losses":61,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":29,"wins":4},"elorian/glimpse":{"draws":5,"losses":11,"wins":8},"fireworks/ember-1":{"draws":16,"losses":17,"wins":9},"gemini-3.1-pro-preview":{"draws":14,"losses":19,"wins":9},"gemini-4-argon":{"draws":1,"losses":40,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":15},"google/gemini-3.5-flash":{"draws":17,"losses":22,"wins":13},"google/gemini-3.5-flash-lite":{"draws":35,"losses":16,"wins":21},"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":5,"wins":6},"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},"gpt-6.1-terra":{"draws":7,"losses":34,"wins":1},"gpt-6.1-terra-pro":{"draws":5,"losses":34,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":6,"wins":8},"inception/mercury-3":{"draws":11,"losses":11,"wins":6},"inclusionai/ling-3.0-flash":{"draws":14,"losses":5,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":3,"wins":1},"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":12,"losses":23,"wins":7},"meta/muse-spark-1.3":{"draws":10,"losses":27,"wins":5},"meta/muse-spark-open":{"draws":11,"losses":21,"wins":10},"meta/muse-wonder":{"draws":7,"losses":26,"wins":9},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":6},"minimax/minimax-m3.1-flash":{"draws":10,"losses":14,"wins":12},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":4},"mistralai/mistral-medium-3-5":{"draws":14,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":15,"losses":16,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":36,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":5,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":10,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":8,"wins":5},"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},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":20,"wins":6},"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":4,"losses":4,"wins":6},"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":{"draws":1,"losses":13,"wins":0},"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":5,"losses":5,"wins":6},"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":15,"losses":17,"wins":8},"claude-fable-5":{"draws":5,"losses":35,"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":22,"losses":45,"wins":1},"claude-opus-4-8":{"draws":11,"losses":23,"wins":4},"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":6,"losses":33,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":26,"losses":26,"wins":10},"deepseek/deepseek-v4-pro":{"draws":7,"losses":24,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":25,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":24,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":33,"wins":3},"elorian/glimpse":{"draws":4,"losses":16,"wins":2},"fireworks/ember-1":{"draws":12,"losses":27,"wins":3},"gemini-3.1-pro-preview":{"draws":14,"losses":25,"wins":3},"gemini-4-argon":{"draws":2,"losses":40,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":7,"wins":10},"google/gemini-3.5-flash":{"draws":11,"losses":36,"wins":5},"google/gemini-3.5-flash-lite":{"draws":17,"losses":38,"wins":19},"google/gemini-3.6-flash":{"draws":23,"losses":48,"wins":9},"google/gemini-3.8-flash":{"draws":6,"losses":34,"wins":2},"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":9,"losses":20,"wins":7},"gpt-5.4":{"draws":8,"losses":23,"wins":9},"gpt-5.4-mini":{"draws":12,"losses":11,"wins":5},"gpt-5.4-nano":{"draws":8,"losses":28,"wins":6},"gpt-5.5":{"draws":11,"losses":22,"wins":5},"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":10,"losses":27,"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},"gpt-6.1-terra":{"draws":3,"losses":38,"wins":1},"gpt-6.1-terra-pro":{"draws":4,"losses":38,"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},"inception/mercury-3":{"draws":8,"losses":18,"wins":2},"inclusionai/ling-3.0-flash":{"draws":11,"losses":11,"wins":8},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":19,"wins":11},"meta/muse-glimmer-30b":{"draws":15,"losses":15,"wins":6},"meta/muse-spark-1.2":{"draws":9,"losses":27,"wins":4},"meta/muse-spark-1.3":{"draws":7,"losses":34,"wins":1},"meta/muse-spark-open":{"draws":9,"losses":31,"wins":2},"meta/muse-wonder":{"draws":8,"losses":31,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":10,"wins":6},"minimax/minimax-m3.1-flash":{"draws":8,"losses":22,"wins":6},"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":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":30,"wins":2},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":39,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":18,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":9,"wins":3},"o3":{"draws":9,"losses":39,"wins":6},"openai/gpt-oss-120b":{"draws":15,"losses":18,"wins":3},"poolside/laguna-s-2.1":{"draws":11,"losses":20,"wins":11},"qwen/qwen3.7-max":{"draws":10,"losses":12,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":32,"wins":1},"qwen/qwen3.8-27b":{"draws":9,"losses":20,"wins":1},"qwen/qwen3.8-flash":{"draws":6,"losses":18,"wins":4},"qwen/qwen3.8-max":{"draws":9,"losses":29,"wins":4},"qwen/qwen3.8-max-0902":{"draws":13,"losses":27,"wins":2},"recursive/flint-v1.0":{"draws":4,"losses":5,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":27,"wins":3},"stealth/ox-alpha":{"draws":31,"losses":93,"wins":16},"stealth/space-bunny-alpha":{"draws":10,"losses":17,"wins":5},"stepfun/step-3.7-flash":{"draws":8,"losses":12,"wins":8},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":4},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":4},"tencent/hy4-preview":{"draws":7,"losses":28,"wins":5},"thinkingmachines/inkling":{"draws":19,"losses":27,"wins":10},"thinkingmachines/inkling-small":{"draws":16,"losses":14,"wins":12},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":11,"losses":27,"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":26,"losses":27,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":13,"wins":5},"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":29,"losses":44,"wins":11},"z-ai/glm-5.3":{"draws":6,"losses":33,"wins":1},"z-ai/glm-5.3-flash":{"draws":13,"losses":24,"wins":5},"z-ai/glm-5.3-flashx":{"draws":5,"losses":33,"wins":4}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":8,"wins":22},"claude-fable-5":{"draws":5,"losses":30,"wins":13},"claude-fable-5-1":{"draws":2,"losses":49,"wins":3},"claude-haiku-5-5":{"draws":12,"losses":19,"wins":15},"claude-opus-4-5":{"draws":28,"losses":18,"wins":32},"claude-opus-4-8":{"draws":12,"losses":15,"wins":17},"claude-opus-5":{"draws":11,"losses":55,"wins":16},"claude-opus-5-5":{"draws":1,"losses":48,"wins":3},"claude-sonnet-5":{"draws":14,"losses":12,"wins":22},"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":16,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":20,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":22,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":29,"wins":15},"elorian/glimpse":{"draws":8,"losses":11,"wins":7},"fireworks/ember-1":{"draws":12,"losses":23,"wins":13},"gemini-3.1-pro-preview":{"draws":9,"losses":16,"wins":23},"gemini-4-argon":{"draws":0,"losses":42,"wins":6},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":16,"losses":23,"wins":21},"google/gemini-3.5-flash-lite":{"draws":23,"losses":19,"wins":42},"google/gemini-3.6-flash":{"draws":28,"losses":33,"wins":31},"google/gemini-3.8-flash":{"draws":11,"losses":25,"wins":12},"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":9,"wins":11},"gpt-5.4-nano":{"draws":11,"losses":9,"wins":28},"gpt-5.5":{"draws":10,"losses":16,"wins":18},"gpt-5.6-luna":{"draws":14,"losses":9,"wins":25},"gpt-5.6-sol":{"draws":11,"losses":27,"wins":10},"gpt-5.6-terra":{"draws":12,"losses":16,"wins":18},"gpt-6-astra":{"draws":4,"losses":40,"wins":4},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":4,"losses":32,"wins":12},"gpt-6.1-sol":{"draws":2,"losses":38,"wins":8},"gpt-6.1-terra":{"draws":7,"losses":34,"wins":7},"gpt-6.1-terra-pro":{"draws":5,"losses":36,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"inception/mercury-3":{"draws":12,"losses":9,"wins":11},"inclusionai/ling-3.0-flash":{"draws":13,"losses":2,"wins":19},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":28},"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-spark-open":{"draws":14,"losses":22,"wins":12},"meta/muse-wonder":{"draws":8,"losses":29,"wins":11},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":20},"minimax/minimax-m3.1-flash":{"draws":11,"losses":13,"wins":18},"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":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":38,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":2,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":3,"wins":11},"o3":{"draws":9,"losses":26,"wins":31},"openai/gpt-oss-120b":{"draws":11,"losses":8,"wins":23},"poolside/laguna-s-2.1":{"draws":15,"losses":9,"wins":22},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":14},"qwen/qwen3.7-plus":{"draws":11,"losses":5,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":17,"wins":19},"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":12,"losses":18,"wins":18},"qwen/qwen3.8-max-0902":{"draws":10,"losses":26,"wins":12},"recursive/flint-v1.0":{"draws":5,"losses":0,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":12,"wins":20},"stealth/ox-alpha":{"draws":40,"losses":66,"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":1,"losses":10,"wins":3},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":10,"losses":20,"wins":16},"thinkingmachines/inkling":{"draws":21,"losses":14,"wins":29},"thinkingmachines/inkling-small":{"draws":14,"losses":10,"wins":24},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":12,"losses":21,"wins":15},"x-ai/grok-4.6":{"draws":7,"losses":27,"wins":14},"x-ai/grok-4.7":{"draws":1,"losses":31,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":26,"losses":11,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"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":37,"losses":19,"wins":40},"z-ai/glm-5.3":{"draws":11,"losses":23,"wins":12},"z-ai/glm-5.3-flash":{"draws":9,"losses":26,"wins":13},"z-ai/glm-5.3-flashx":{"draws":13,"losses":23,"wins":12}},"moonshotai/kimi-k3.1-pro":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":1,"wins":37},"claude-fable-5":{"draws":4,"losses":12,"wins":32},"claude-fable-5-1":{"draws":6,"losses":38,"wins":10},"claude-haiku-5-5":{"draws":6,"losses":9,"wins":31},"claude-opus-4-5":{"draws":7,"losses":6,"wins":65},"claude-opus-4-8":{"draws":6,"losses":4,"wins":34},"claude-opus-5":{"draws":8,"losses":30,"wins":44},"claude-opus-5-5":{"draws":3,"losses":30,"wins":19},"claude-sonnet-5":{"draws":5,"losses":4,"wins":39},"claude-sonnet-5-5":{"draws":4,"losses":11,"wins":33},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":6,"losses":3,"wins":63},"deepseek/deepseek-v4-pro":{"draws":3,"losses":5,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":5,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":7,"wins":35},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":11,"wins":35},"elorian/glimpse":{"draws":4,"losses":4,"wins":18},"fireworks/ember-1":{"draws":5,"losses":3,"wins":40},"gemini-3.1-pro-preview":{"draws":5,"losses":9,"wins":34},"gemini-4-argon":{"draws":3,"losses":24,"wins":21},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":2,"losses":8,"wins":50},"google/gemini-3.5-flash-lite":{"draws":16,"losses":1,"wins":67},"google/gemini-3.6-flash":{"draws":11,"losses":11,"wins":70},"google/gemini-3.8-flash":{"draws":4,"losses":8,"wins":36},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":24},"gpt-4.1":{"draws":0,"losses":1,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":5,"wins":37},"gpt-5.4":{"draws":2,"losses":9,"wins":35},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":29},"gpt-5.4-nano":{"draws":5,"losses":1,"wins":42},"gpt-5.5":{"draws":4,"losses":8,"wins":32},"gpt-5.6-luna":{"draws":3,"losses":5,"wins":40},"gpt-5.6-sol":{"draws":0,"losses":13,"wins":35},"gpt-5.6-terra":{"draws":2,"losses":6,"wins":38},"gpt-6-astra":{"draws":1,"losses":34,"wins":13},"gpt-6-luna":{"draws":5,"losses":3,"wins":40},"gpt-6-sol":{"draws":8,"losses":14,"wins":26},"gpt-6.1-sol":{"draws":6,"losses":26,"wins":16},"gpt-6.1-terra":{"draws":9,"losses":23,"wins":16},"gpt-6.1-terra-pro":{"draws":3,"losses":25,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":27},"inception/mercury-3":{"draws":3,"losses":5,"wins":24},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":26},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":6,"losses":3,"wins":43},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":37},"meta/muse-spark-1.2":{"draws":2,"losses":6,"wins":38},"meta/muse-spark-1.3":{"draws":4,"losses":10,"wins":34},"meta/muse-spark-open":{"draws":6,"losses":4,"wins":38},"meta/muse-wonder":{"draws":4,"losses":14,"wins":30},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":24},"minimax/minimax-m3.1-flash":{"draws":3,"losses":8,"wins":31},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":26},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":5,"wins":37},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":10,"wins":18},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":4,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":19},"o3":{"draws":1,"losses":11,"wins":54},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":36},"poolside/laguna-s-2.1":{"draws":8,"losses":2,"wins":36},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":24},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":6,"wins":34},"qwen/qwen3.8-27b":{"draws":5,"losses":3,"wins":26},"qwen/qwen3.8-flash":{"draws":2,"losses":6,"wins":24},"qwen/qwen3.8-max":{"draws":0,"losses":8,"wins":40},"qwen/qwen3.8-max-0902":{"draws":1,"losses":9,"wins":38},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":2,"wins":41},"stealth/ox-alpha":{"draws":19,"losses":19,"wins":120},"stealth/space-bunny-alpha":{"draws":2,"losses":4,"wins":32},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":21},"tencent/hy4-preview":{"draws":5,"losses":5,"wins":36},"thinkingmachines/inkling":{"draws":3,"losses":2,"wins":59},"thinkingmachines/inkling-small":{"draws":2,"losses":5,"wins":41},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":6},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":6},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":6,"losses":10,"wins":32},"x-ai/grok-4.6":{"draws":4,"losses":9,"wins":35},"x-ai/grok-4.7":{"draws":2,"losses":16,"wins":24},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":11,"losses":3,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":3,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":14,"losses":7,"wins":75},"z-ai/glm-5.3":{"draws":8,"losses":12,"wins":26},"z-ai/glm-5.3-flash":{"draws":6,"losses":7,"wins":35},"z-ai/glm-5.3-flashx":{"draws":4,"losses":10,"wins":34}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":16,"wins":11},"claude-fable-5":{"draws":8,"losses":32,"wins":2},"claude-fable-5-1":{"draws":3,"losses":44,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":20,"wins":7},"claude-opus-4-5":{"draws":24,"losses":32,"wins":12},"claude-opus-4-8":{"draws":10,"losses":23,"wins":5},"claude-opus-5":{"draws":4,"losses":63,"wins":3},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":15,"losses":21,"wins":6},"claude-sonnet-5-5":{"draws":12,"losses":22,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":16,"losses":28,"wins":18},"deepseek/deepseek-v4-pro":{"draws":13,"losses":13,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":18,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":25,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":29,"wins":3},"elorian/glimpse":{"draws":8,"losses":9,"wins":5},"fireworks/ember-1":{"draws":17,"losses":18,"wins":7},"gemini-3.1-pro-preview":{"draws":16,"losses":20,"wins":6},"gemini-4-argon":{"draws":8,"losses":30,"wins":4},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":17},"google/gemini-3.5-flash":{"draws":14,"losses":21,"wins":17},"google/gemini-3.5-flash-lite":{"draws":20,"losses":20,"wins":34},"google/gemini-3.6-flash":{"draws":21,"losses":40,"wins":19},"google/gemini-3.8-flash":{"draws":12,"losses":24,"wins":6},"google/gemma-4-31b-it":{"draws":13,"losses":6,"wins":7},"gpt-4.1":{"draws":3,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":9,"losses":11,"wins":16},"gpt-5.4":{"draws":12,"losses":17,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":9,"losses":16,"wins":15},"gpt-5.5":{"draws":13,"losses":18,"wins":7},"gpt-5.6-luna":{"draws":11,"losses":19,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":30,"wins":5},"gpt-5.6-terra":{"draws":12,"losses":17,"wins":11},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":11,"losses":22,"wins":9},"gpt-6-sol":{"draws":7,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"gpt-6.1-terra":{"draws":4,"losses":38,"wins":0},"gpt-6.1-terra-pro":{"draws":4,"losses":38,"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},"inception/mercury-3":{"draws":10,"losses":11,"wins":7},"inclusionai/ling-3.0-flash":{"draws":12,"losses":7,"wins":9},"inclusionai/ling-3.1-flash":{"draws":5,"losses":5,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":18,"wins":21},"meta/muse-glimmer-30b":{"draws":14,"losses":5,"wins":17},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":9},"meta/muse-spark-1.3":{"draws":9,"losses":25,"wins":8},"meta/muse-spark-open":{"draws":11,"losses":23,"wins":8},"meta/muse-wonder":{"draws":12,"losses":27,"wins":3},"minimax/minimax-m3":{"draws":5,"losses":7,"wins":10},"minimax/minimax-m3.1-flash":{"draws":14,"losses":12,"wins":10},"mistralai/mistral-large-4-0":{"draws":12,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":11,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":19,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":33,"wins":2},"nex-agi/nex-n2-pro":{"draws":1,"losses":2,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":9,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":5,"wins":7},"o3":{"draws":7,"losses":31,"wins":18},"openai/gpt-oss-120b":{"draws":11,"losses":9,"wins":18},"poolside/laguna-s-2.1":{"draws":11,"losses":9,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":12,"wins":6},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":8,"losses":13,"wins":7},"qwen/qwen3.8-flash":{"draws":10,"losses":11,"wins":7},"qwen/qwen3.8-max":{"draws":14,"losses":24,"wins":4},"qwen/qwen3.8-max-0902":{"draws":14,"losses":20,"wins":8},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":20,"wins":9},"stealth/ox-alpha":{"draws":39,"losses":79,"wins":24},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":6,"losses":14,"wins":8},"stepfun/step-5-preview":{"draws":4,"losses":9,"wins":3},"tencent/hy3-preview":{"draws":10,"losses":2,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":17,"losses":18,"wins":19},"thinkingmachines/inkling-small":{"draws":14,"losses":12,"wins":16},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":12,"losses":26,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":19,"losses":18,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":3,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":32,"losses":30,"wins":22},"z-ai/glm-5.3":{"draws":9,"losses":29,"wins":4},"z-ai/glm-5.3-flash":{"draws":10,"losses":23,"wins":9},"z-ai/glm-5.3-flashx":{"draws":8,"losses":25,"wins":9}},"nex-agi/nex-n2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":9,"wins":6},"claude-fable-5":{"draws":2,"losses":18,"wins":4},"claude-fable-5-1":{"draws":0,"losses":27,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":12,"wins":4},"claude-opus-4-5":{"draws":11,"losses":22,"wins":5},"claude-opus-4-8":{"draws":3,"losses":13,"wins":4},"claude-opus-5":{"draws":4,"losses":39,"wins":1},"claude-opus-5-5":{"draws":3,"losses":25,"wins":0},"claude-sonnet-5":{"draws":8,"losses":11,"wins":5},"claude-sonnet-5-5":{"draws":6,"losses":14,"wins":4},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":7},"deepseek/deepseek-v4-flash":{"draws":10,"losses":12,"wins":16},"deepseek/deepseek-v4-pro":{"draws":7,"losses":10,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":12,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":13,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":18,"wins":1},"elorian/glimpse":{"draws":3,"losses":9,"wins":2},"fireworks/ember-1":{"draws":5,"losses":16,"wins":3},"gemini-3.1-pro-preview":{"draws":6,"losses":12,"wins":6},"gemini-4-argon":{"draws":0,"losses":24,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":5,"losses":15,"wins":8},"google/gemini-3.5-flash-lite":{"draws":13,"losses":15,"wins":10},"google/gemini-3.6-flash":{"draws":9,"losses":25,"wins":10},"google/gemini-3.8-flash":{"draws":6,"losses":14,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":7},"gpt-4.1":{"draws":4,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":7,"losses":10,"wins":5},"gpt-5.4":{"draws":8,"losses":6,"wins":8},"gpt-5.4-mini":{"draws":6,"losses":6,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":7,"wins":9},"gpt-5.5":{"draws":5,"losses":11,"wins":6},"gpt-5.6-luna":{"draws":11,"losses":4,"wins":9},"gpt-5.6-sol":{"draws":2,"losses":21,"wins":1},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":7},"gpt-6-astra":{"draws":1,"losses":23,"wins":0},"gpt-6-luna":{"draws":7,"losses":11,"wins":6},"gpt-6-sol":{"draws":1,"losses":21,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":23,"wins":0},"gpt-6.1-terra":{"draws":1,"losses":21,"wins":2},"gpt-6.1-terra-pro":{"draws":2,"losses":22,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":3,"wins":5},"inception/mercury-3":{"draws":6,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":5,"losses":10,"wins":3},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":8,"wins":13},"meta/muse-glimmer-30b":{"draws":8,"losses":7,"wins":7},"meta/muse-spark-1.2":{"draws":7,"losses":14,"wins":3},"meta/muse-spark-1.3":{"draws":3,"losses":17,"wins":4},"meta/muse-spark-open":{"draws":6,"losses":15,"wins":3},"meta/muse-wonder":{"draws":6,"losses":13,"wins":5},"minimax/minimax-m3":{"draws":5,"losses":6,"wins":3},"minimax/minimax-m3.1-flash":{"draws":6,"losses":7,"wins":5},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":2},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":21,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":4,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":4,"wins":5},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":4,"wins":5},"o3":{"draws":3,"losses":20,"wins":5},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":12},"poolside/laguna-s-2.1":{"draws":10,"losses":9,"wins":7},"qwen/qwen3.7-max":{"draws":3,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":13,"wins":4},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":3},"qwen/qwen3.8-flash":{"draws":5,"losses":5,"wins":6},"qwen/qwen3.8-max":{"draws":8,"losses":9,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":14,"wins":3},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":13,"wins":5},"stealth/ox-alpha":{"draws":26,"losses":49,"wins":15},"stealth/space-bunny-alpha":{"draws":4,"losses":11,"wins":3},"stepfun/step-3.7-flash":{"draws":3,"losses":5,"wins":8},"stepfun/step-5-preview":{"draws":3,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":3},"tencent/hy4-preview":{"draws":4,"losses":14,"wins":4},"thinkingmachines/inkling":{"draws":9,"losses":12,"wins":9},"thinkingmachines/inkling-small":{"draws":9,"losses":9,"wins":6},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":6,"losses":15,"wins":3},"x-ai/grok-4.6":{"draws":5,"losses":17,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":21,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":3},"xiaomi/mimo-v2.5":{"draws":11,"losses":7,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":3,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":10,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":12,"wins":0},"z-ai/glm-5.2":{"draws":16,"losses":15,"wins":17},"z-ai/glm-5.3":{"draws":3,"losses":19,"wins":2},"z-ai/glm-5.3-flash":{"draws":4,"losses":15,"wins":5},"z-ai/glm-5.3-flashx":{"draws":5,"losses":12,"wins":7}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":17,"wins":14},"claude-fable-5":{"draws":6,"losses":30,"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":16,"losses":41,"wins":11},"claude-opus-4-8":{"draws":4,"losses":24,"wins":10},"claude-opus-5":{"draws":9,"losses":59,"wins":2},"claude-opus-5-5":{"draws":2,"losses":43,"wins":1},"claude-sonnet-5":{"draws":10,"losses":19,"wins":13},"claude-sonnet-5-5":{"draws":5,"losses":31,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":7,"wins":6},"deepseek/deepseek-v4-flash":{"draws":10,"losses":32,"wins":20},"deepseek/deepseek-v4-pro":{"draws":12,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":23,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":24,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":33,"wins":3},"elorian/glimpse":{"draws":6,"losses":14,"wins":4},"fireworks/ember-1":{"draws":9,"losses":22,"wins":11},"gemini-3.1-pro-preview":{"draws":11,"losses":21,"wins":10},"gemini-4-argon":{"draws":2,"losses":40,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":13,"wins":13},"google/gemini-3.5-flash":{"draws":8,"losses":33,"wins":13},"google/gemini-3.5-flash-lite":{"draws":18,"losses":29,"wins":29},"google/gemini-3.6-flash":{"draws":15,"losses":51,"wins":16},"google/gemini-3.8-flash":{"draws":8,"losses":29,"wins":5},"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":10,"losses":20,"wins":8},"gpt-5.4":{"draws":11,"losses":26,"wins":5},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":12},"gpt-5.4-nano":{"draws":2,"losses":22,"wins":18},"gpt-5.5":{"draws":16,"losses":20,"wins":4},"gpt-5.6-luna":{"draws":8,"losses":19,"wins":15},"gpt-5.6-sol":{"draws":3,"losses":35,"wins":4},"gpt-5.6-terra":{"draws":12,"losses":21,"wins":7},"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},"gpt-6.1-terra":{"draws":3,"losses":38,"wins":1},"gpt-6.1-terra-pro":{"draws":2,"losses":36,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":14,"wins":7},"inception/mercury-3":{"draws":4,"losses":14,"wins":8},"inclusionai/ling-3.0-flash":{"draws":9,"losses":10,"wins":11},"inclusionai/ling-3.1-flash":{"draws":5,"losses":5,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":25,"wins":11},"meta/muse-glimmer-30b":{"draws":11,"losses":12,"wins":15},"meta/muse-spark-1.2":{"draws":9,"losses":21,"wins":10},"meta/muse-spark-1.3":{"draws":5,"losses":33,"wins":4},"meta/muse-spark-open":{"draws":10,"losses":24,"wins":8},"meta/muse-wonder":{"draws":9,"losses":30,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":10,"wins":9},"minimax/minimax-m3.1-flash":{"draws":6,"losses":19,"wins":13},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":7},"mistralai/mistral-medium-3-5":{"draws":7,"losses":8,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":25,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":36,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":5,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":9,"wins":6},"o3":{"draws":8,"losses":36,"wins":20},"openai/gpt-oss-120b":{"draws":8,"losses":16,"wins":12},"poolside/laguna-s-2.1":{"draws":11,"losses":13,"wins":16},"qwen/qwen3.7-max":{"draws":4,"losses":11,"wins":9},"qwen/qwen3.7-plus":{"draws":1,"losses":9,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":25,"wins":6},"qwen/qwen3.8-27b":{"draws":7,"losses":16,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":12,"wins":8},"qwen/qwen3.8-max":{"draws":8,"losses":26,"wins":8},"qwen/qwen3.8-max-0902":{"draws":10,"losses":26,"wins":6},"recursive/flint-v1.0":{"draws":2,"losses":4,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":23,"wins":8},"stealth/ox-alpha":{"draws":22,"losses":94,"wins":26},"stealth/space-bunny-alpha":{"draws":10,"losses":15,"wins":9},"stepfun/step-3.7-flash":{"draws":10,"losses":12,"wins":10},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":7},"tencent/hy4-preview":{"draws":8,"losses":26,"wins":8},"thinkingmachines/inkling":{"draws":15,"losses":20,"wins":23},"thinkingmachines/inkling-small":{"draws":9,"losses":16,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":10,"losses":29,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":28,"wins":3},"x-ai/grok-4.7":{"draws":0,"losses":34,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":3},"xiaomi/mimo-v2.5":{"draws":14,"losses":27,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":9},"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":17,"losses":37,"wins":30},"z-ai/glm-5.3":{"draws":5,"losses":32,"wins":3},"z-ai/glm-5.3-flash":{"draws":2,"losses":28,"wins":12},"z-ai/glm-5.3-flashx":{"draws":6,"losses":28,"wins":8}},"nvidia/nemotron-3.5-super-vl":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":9,"wins":1},"claude-fable-5":{"draws":4,"losses":14,"wins":0},"claude-fable-5-1":{"draws":1,"losses":21,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":11,"wins":4},"claude-opus-4-5":{"draws":9,"losses":18,"wins":3},"claude-opus-4-8":{"draws":5,"losses":12,"wins":1},"claude-opus-5":{"draws":4,"losses":25,"wins":3},"claude-opus-5-5":{"draws":1,"losses":21,"wins":0},"claude-sonnet-5":{"draws":6,"losses":11,"wins":1},"claude-sonnet-5-5":{"draws":4,"losses":13,"wins":1},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":7},"deepseek/deepseek-v4-flash":{"draws":4,"losses":16,"wins":6},"deepseek/deepseek-v4-pro":{"draws":5,"losses":10,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":8,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":12,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":14,"wins":0},"elorian/glimpse":{"draws":4,"losses":5,"wins":3},"fireworks/ember-1":{"draws":4,"losses":10,"wins":4},"gemini-3.1-pro-preview":{"draws":3,"losses":12,"wins":3},"gemini-4-argon":{"draws":0,"losses":16,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":5,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":12,"wins":6},"google/gemini-3.5-flash-lite":{"draws":12,"losses":14,"wins":6},"google/gemini-3.6-flash":{"draws":10,"losses":20,"wins":4},"google/gemini-3.8-flash":{"draws":2,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":6},"gpt-4.1":{"draws":2,"losses":4,"wins":0},"gpt-5":{"draws":4,"losses":11,"wins":1},"gpt-5.4":{"draws":6,"losses":8,"wins":4},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":1,"losses":11,"wins":4},"gpt-5.5":{"draws":6,"losses":11,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":6,"wins":7},"gpt-5.6-sol":{"draws":1,"losses":16,"wins":1},"gpt-5.6-terra":{"draws":5,"losses":10,"wins":3},"gpt-6-astra":{"draws":0,"losses":18,"wins":0},"gpt-6-luna":{"draws":5,"losses":11,"wins":2},"gpt-6-sol":{"draws":2,"losses":16,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":15,"wins":0},"gpt-6.1-terra":{"draws":0,"losses":18,"wins":0},"gpt-6.1-terra-pro":{"draws":1,"losses":17,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":5,"wins":3},"inception/mercury-3":{"draws":2,"losses":8,"wins":2},"inclusionai/ling-3.0-flash":{"draws":4,"losses":6,"wins":4},"inclusionai/ling-3.1-flash":{"draws":2,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":6,"losses":11,"wins":5},"meta/muse-glimmer-30b":{"draws":5,"losses":8,"wins":5},"meta/muse-spark-1.2":{"draws":6,"losses":12,"wins":0},"meta/muse-spark-1.3":{"draws":4,"losses":13,"wins":1},"meta/muse-spark-open":{"draws":3,"losses":15,"wins":0},"meta/muse-wonder":{"draws":3,"losses":13,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":2},"minimax/minimax-m3.1-flash":{"draws":6,"losses":5,"wins":3},"mistralai/mistral-large-4-0":{"draws":3,"losses":6,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":16,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":5},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":4,"wins":1},"o3":{"draws":3,"losses":20,"wins":3},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":9},"poolside/laguna-s-2.1":{"draws":2,"losses":8,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":12,"wins":1},"qwen/qwen3.8-27b":{"draws":2,"losses":7,"wins":1},"qwen/qwen3.8-flash":{"draws":3,"losses":5,"wins":4},"qwen/qwen3.8-max":{"draws":3,"losses":13,"wins":2},"qwen/qwen3.8-max-0902":{"draws":5,"losses":9,"wins":4},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":12,"wins":3},"stealth/ox-alpha":{"draws":14,"losses":31,"wins":7},"stealth/space-bunny-alpha":{"draws":6,"losses":8,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":3},"tencent/hy4-preview":{"draws":3,"losses":10,"wins":5},"thinkingmachines/inkling":{"draws":8,"losses":7,"wins":7},"thinkingmachines/inkling-small":{"draws":5,"losses":5,"wins":8},"unbiased/pareto-26.10":{"draws":1,"losses":5,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":13,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":14,"wins":1},"x-ai/grok-4.7":{"draws":1,"losses":15,"wins":0},"x-ai/grok-build-0.1":{"draws":1,"losses":2,"wins":3},"xiaomi/mimo-v2.5":{"draws":12,"losses":11,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":8,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":10,"wins":1},"z-ai/glm-5.2":{"draws":11,"losses":18,"wins":7},"z-ai/glm-5.3":{"draws":2,"losses":16,"wins":0},"z-ai/glm-5.3-flash":{"draws":2,"losses":11,"wins":5},"z-ai/glm-5.3-flashx":{"draws":2,"losses":14,"wins":2}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":11,"wins":14},"claude-fable-5":{"draws":11,"losses":30,"wins":7},"claude-fable-5-1":{"draws":0,"losses":53,"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":12,"losses":24,"wins":8},"claude-opus-5":{"draws":11,"losses":66,"wins":5},"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":17,"losses":21,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":25,"wins":13},"elorian/glimpse":{"draws":6,"losses":12,"wins":8},"fireworks/ember-1":{"draws":17,"losses":24,"wins":7},"gemini-3.1-pro-preview":{"draws":14,"losses":19,"wins":15},"gemini-4-argon":{"draws":1,"losses":47,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":20,"losses":24,"wins":16},"google/gemini-3.5-flash-lite":{"draws":28,"losses":21,"wins":35},"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},"gpt-6.1-terra":{"draws":3,"losses":45,"wins":0},"gpt-6.1-terra-pro":{"draws":4,"losses":40,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":5,"wins":15},"inception/mercury-3":{"draws":8,"losses":19,"wins":5},"inclusionai/ling-3.0-flash":{"draws":17,"losses":4,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":2},"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":14,"losses":26,"wins":6},"meta/muse-spark-1.3":{"draws":13,"losses":29,"wins":6},"meta/muse-spark-open":{"draws":12,"losses":26,"wins":8},"meta/muse-wonder":{"draws":7,"losses":36,"wins":5},"minimax/minimax-m3":{"draws":9,"losses":8,"wins":9},"minimax/minimax-m3.1-flash":{"draws":13,"losses":15,"wins":14},"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":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":19,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":46,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":10,"wins":7},"o3":{"draws":9,"losses":22,"wins":19},"openai/gpt-oss-120b":{"draws":14,"losses":7,"wins":21},"poolside/laguna-s-2.1":{"draws":21,"losses":9,"wins":16},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":7,"wins":9},"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},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":22,"wins":11},"stealth/ox-alpha":{"draws":43,"losses":83,"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":1,"losses":7,"wins":6},"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":{"draws":0,"losses":16,"wins":0},"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":24,"losses":21,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":9,"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":6,"losses":18,"wins":8},"claude-fable-5":{"draws":6,"losses":27,"wins":3},"claude-fable-5-1":{"draws":2,"losses":38,"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":7,"losses":22,"wins":3},"claude-opus-5":{"draws":4,"losses":60,"wins":4},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":11,"losses":21,"wins":4},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":15,"losses":21,"wins":20},"deepseek/deepseek-v4-pro":{"draws":8,"losses":20,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":16,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":21,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":23,"wins":6},"elorian/glimpse":{"draws":3,"losses":12,"wins":5},"fireworks/ember-1":{"draws":11,"losses":21,"wins":4},"gemini-3.1-pro-preview":{"draws":9,"losses":22,"wins":5},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":7,"wins":11},"google/gemini-3.5-flash":{"draws":7,"losses":27,"wins":10},"google/gemini-3.5-flash-lite":{"draws":13,"losses":28,"wins":19},"google/gemini-3.6-flash":{"draws":18,"losses":40,"wins":10},"google/gemini-3.8-flash":{"draws":7,"losses":27,"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":7,"losses":20,"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":10,"losses":19,"wins":5},"gpt-5.6-luna":{"draws":9,"losses":17,"wins":10},"gpt-5.6-sol":{"draws":2,"losses":33,"wins":1},"gpt-5.6-terra":{"draws":8,"losses":23,"wins":3},"gpt-6-astra":{"draws":4,"losses":32,"wins":0},"gpt-6-luna":{"draws":10,"losses":17,"wins":9},"gpt-6-sol":{"draws":6,"losses":28,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"gpt-6.1-terra":{"draws":6,"losses":30,"wins":0},"gpt-6.1-terra-pro":{"draws":4,"losses":29,"wins":3},"inception/mercury-2.5-preview":{"draws":6,"losses":8,"wins":8},"inception/mercury-3":{"draws":8,"losses":12,"wins":6},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":10},"inclusionai/ling-3.1-flash":{"draws":1,"losses":5,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":20,"wins":11},"meta/muse-glimmer-30b":{"draws":11,"losses":11,"wins":12},"meta/muse-spark-1.2":{"draws":7,"losses":28,"wins":1},"meta/muse-spark-1.3":{"draws":9,"losses":23,"wins":4},"meta/muse-spark-open":{"draws":8,"losses":26,"wins":2},"meta/muse-wonder":{"draws":4,"losses":28,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":9,"wins":8},"minimax/minimax-m3.1-flash":{"draws":4,"losses":15,"wins":11},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":5},"mistralai/mistral-medium-3-5":{"draws":6,"losses":5,"wins":9},"moonshotai/kimi-k3":{"draws":9,"losses":21,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":29,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":9,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":11,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":10,"wins":4},"o3":{"draws":7,"losses":36,"wins":7},"openai/gpt-oss-120b":{"draws":4,"losses":8,"wins":10},"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":7,"losses":12,"wins":5},"qwen/qwen3.8-max":{"draws":10,"losses":23,"wins":3},"qwen/qwen3.8-max-0902":{"draws":10,"losses":22,"wins":4},"recursive/flint-v1.0":{"draws":2,"losses":3,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":20,"wins":4},"stealth/ox-alpha":{"draws":29,"losses":83,"wins":12},"stealth/space-bunny-alpha":{"draws":4,"losses":18,"wins":6},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":9},"stepfun/step-5-preview":{"draws":1,"losses":8,"wins":1},"tencent/hy3-preview":{"draws":4,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":19,"wins":4},"thinkingmachines/inkling":{"draws":11,"losses":25,"wins":14},"thinkingmachines/inkling-small":{"draws":10,"losses":7,"wins":19},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":7,"losses":27,"wins":2},"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":13,"losses":20,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":30,"losses":30,"wins":12},"z-ai/glm-5.3":{"draws":8,"losses":24,"wins":2},"z-ai/glm-5.3-flash":{"draws":9,"losses":20,"wins":7},"z-ai/glm-5.3-flashx":{"draws":7,"losses":25,"wins":4}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":22,"wins":26},"claude-fable-5":{"draws":6,"losses":53,"wins":13},"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":30,"losses":61,"wins":25},"claude-opus-4-8":{"draws":10,"losses":41,"wins":13},"claude-opus-5":{"draws":8,"losses":111,"wins":7},"claude-opus-5-5":{"draws":5,"losses":75,"wins":0},"claude-sonnet-5":{"draws":17,"losses":35,"wins":20},"claude-sonnet-5-5":{"draws":10,"losses":47,"wins":15},"cohere/north-mini-code":{"draws":5,"losses":11,"wins":14},"deepseek/deepseek-v4-flash":{"draws":22,"losses":41,"wins":49},"deepseek/deepseek-v4-pro":{"draws":9,"losses":29,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":35,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":32,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":50,"wins":11},"elorian/glimpse":{"draws":7,"losses":22,"wins":11},"fireworks/ember-1":{"draws":17,"losses":38,"wins":17},"gemini-3.1-pro-preview":{"draws":19,"losses":32,"wins":21},"gemini-4-argon":{"draws":2,"losses":69,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":12,"wins":27},"google/gemini-3.5-flash":{"draws":8,"losses":60,"wins":22},"google/gemini-3.5-flash-lite":{"draws":16,"losses":39,"wins":69},"google/gemini-3.6-flash":{"draws":24,"losses":73,"wins":41},"google/gemini-3.8-flash":{"draws":9,"losses":51,"wins":12},"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":11,"losses":28,"wins":29},"gpt-5.4":{"draws":13,"losses":44,"wins":13},"gpt-5.4-mini":{"draws":13,"losses":16,"wins":19},"gpt-5.4-nano":{"draws":9,"losses":32,"wins":37},"gpt-5.5":{"draws":21,"losses":32,"wins":15},"gpt-5.6-luna":{"draws":17,"losses":27,"wins":28},"gpt-5.6-sol":{"draws":8,"losses":57,"wins":7},"gpt-5.6-terra":{"draws":17,"losses":39,"wins":12},"gpt-6-astra":{"draws":2,"losses":70,"wins":0},"gpt-6-luna":{"draws":18,"losses":25,"wins":29},"gpt-6-sol":{"draws":10,"losses":54,"wins":8},"gpt-6.1-sol":{"draws":4,"losses":67,"wins":1},"gpt-6.1-terra":{"draws":10,"losses":61,"wins":1},"gpt-6.1-terra-pro":{"draws":4,"losses":60,"wins":8},"inception/mercury-2.5-preview":{"draws":12,"losses":12,"wins":20},"inception/mercury-3":{"draws":11,"losses":27,"wins":12},"inclusionai/ling-3.0-flash":{"draws":10,"losses":16,"wins":24},"inclusionai/ling-3.1-flash":{"draws":5,"losses":3,"wins":4},"meituan/longcat-2.0":{"draws":20,"losses":26,"wins":34},"meta/muse-glimmer-30b":{"draws":15,"losses":23,"wins":28},"meta/muse-spark-1.2":{"draws":9,"losses":43,"wins":18},"meta/muse-spark-1.3":{"draws":9,"losses":44,"wins":19},"meta/muse-spark-open":{"draws":10,"losses":47,"wins":15},"meta/muse-wonder":{"draws":10,"losses":57,"wins":5},"minimax/minimax-m3":{"draws":6,"losses":15,"wins":21},"minimax/minimax-m3.1-flash":{"draws":9,"losses":28,"wins":25},"mistralai/mistral-large-4-0":{"draws":13,"losses":17,"wins":16},"mistralai/mistral-medium-3-5":{"draws":7,"losses":11,"wins":22},"moonshotai/kimi-k3":{"draws":17,"losses":33,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":57,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":11,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":13,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":17,"wins":11},"o3":{"draws":12,"losses":55,"wins":43},"openai/gpt-oss-120b":{"draws":15,"losses":17,"wins":34},"poolside/laguna-s-2.1":{"draws":14,"losses":16,"wins":24},"qwen/qwen3.7-max":{"draws":9,"losses":22,"wins":13},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":46,"wins":10},"qwen/qwen3.8-27b":{"draws":9,"losses":25,"wins":16},"qwen/qwen3.8-flash":{"draws":9,"losses":21,"wins":18},"qwen/qwen3.8-max":{"draws":14,"losses":35,"wins":23},"qwen/qwen3.8-max-0902":{"draws":19,"losses":35,"wins":18},"recursive/flint-v1.0":{"draws":2,"losses":5,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":35,"wins":21},"stealth/ox-alpha":{"draws":44,"losses":140,"wins":64},"stealth/space-bunny-alpha":{"draws":11,"losses":26,"wins":19},"stepfun/step-3.7-flash":{"draws":13,"losses":15,"wins":28},"stepfun/step-5-preview":{"draws":0,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":8,"losses":14,"wins":16},"tencent/hy4-preview":{"draws":10,"losses":37,"wins":23},"thinkingmachines/inkling":{"draws":18,"losses":28,"wins":54},"thinkingmachines/inkling-small":{"draws":16,"losses":12,"wins":44},"unbiased/pareto-26.10":{"draws":0,"losses":24,"wins":0},"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":18,"losses":42,"wins":12},"x-ai/grok-4.7":{"draws":4,"losses":53,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":10,"wins":10},"xiaomi/mimo-v2.5":{"draws":16,"losses":35,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":11,"wins":25},"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":36,"losses":55,"wins":53},"z-ai/glm-5.3":{"draws":6,"losses":54,"wins":8},"z-ai/glm-5.3-flash":{"draws":12,"losses":40,"wins":20},"z-ai/glm-5.3-flashx":{"draws":13,"losses":44,"wins":15}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":20,"wins":10},"claude-fable-5":{"draws":5,"losses":32,"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":17,"losses":38,"wins":13},"claude-opus-4-8":{"draws":9,"losses":20,"wins":9},"claude-opus-5":{"draws":9,"losses":58,"wins":3},"claude-opus-5-5":{"draws":5,"losses":41,"wins":0},"claude-sonnet-5":{"draws":13,"losses":21,"wins":8},"claude-sonnet-5-5":{"draws":13,"losses":18,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":7},"deepseek/deepseek-v4-flash":{"draws":14,"losses":26,"wins":26},"deepseek/deepseek-v4-pro":{"draws":8,"losses":21,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":25,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":23,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":29,"wins":6},"elorian/glimpse":{"draws":5,"losses":11,"wins":6},"fireworks/ember-1":{"draws":11,"losses":24,"wins":7},"gemini-3.1-pro-preview":{"draws":10,"losses":20,"wins":12},"gemini-4-argon":{"draws":0,"losses":40,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":7,"wins":17},"google/gemini-3.5-flash":{"draws":9,"losses":25,"wins":18},"google/gemini-3.5-flash-lite":{"draws":11,"losses":26,"wins":35},"google/gemini-3.6-flash":{"draws":16,"losses":48,"wins":16},"google/gemini-3.8-flash":{"draws":12,"losses":21,"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":11,"losses":17,"wins":10},"gpt-5.4":{"draws":7,"losses":23,"wins":10},"gpt-5.4-mini":{"draws":5,"losses":8,"wins":15},"gpt-5.4-nano":{"draws":10,"losses":19,"wins":17},"gpt-5.5":{"draws":11,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":11,"losses":13,"wins":18},"gpt-5.6-sol":{"draws":5,"losses":31,"wins":6},"gpt-5.6-terra":{"draws":11,"losses":24,"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},"gpt-6.1-terra":{"draws":6,"losses":35,"wins":1},"gpt-6.1-terra-pro":{"draws":6,"losses":32,"wins":4},"inception/mercury-2.5-preview":{"draws":8,"losses":11,"wins":9},"inception/mercury-3":{"draws":6,"losses":15,"wins":9},"inclusionai/ling-3.0-flash":{"draws":7,"losses":7,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":15,"wins":23},"meta/muse-glimmer-30b":{"draws":12,"losses":9,"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-spark-open":{"draws":11,"losses":25,"wins":6},"meta/muse-wonder":{"draws":5,"losses":28,"wins":9},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":13},"minimax/minimax-m3.1-flash":{"draws":3,"losses":19,"wins":14},"mistralai/mistral-large-4-0":{"draws":12,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":10},"moonshotai/kimi-k3":{"draws":8,"losses":24,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":31,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":12,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":9,"wins":6},"o3":{"draws":6,"losses":38,"wins":18},"openai/gpt-oss-120b":{"draws":10,"losses":13,"wins":15},"poolside/laguna-s-2.1":{"draws":14,"losses":15,"wins":15},"qwen/qwen3.7-max":{"draws":1,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":7,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":20,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":11,"wins":11},"qwen/qwen3.8-flash":{"draws":4,"losses":15,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":21,"wins":7},"qwen/qwen3.8-max-0902":{"draws":11,"losses":22,"wins":9},"recursive/flint-v1.0":{"draws":2,"losses":4,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":17,"wins":11},"stealth/ox-alpha":{"draws":27,"losses":84,"wins":29},"stealth/space-bunny-alpha":{"draws":8,"losses":13,"wins":11},"stepfun/step-3.7-flash":{"draws":7,"losses":11,"wins":14},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":1},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":7,"losses":24,"wins":9},"thinkingmachines/inkling":{"draws":14,"losses":13,"wins":29},"thinkingmachines/inkling-small":{"draws":8,"losses":13,"wins":21},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":12,"losses":22,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":26,"wins":5},"x-ai/grok-build-0.1":{"draws":3,"losses":6,"wins":5},"xiaomi/mimo-v2.5":{"draws":15,"losses":19,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":9},"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":23,"losses":34,"wins":27},"z-ai/glm-5.3":{"draws":6,"losses":29,"wins":5},"z-ai/glm-5.3-flash":{"draws":8,"losses":26,"wins":8},"z-ai/glm-5.3-flashx":{"draws":7,"losses":28,"wins":7}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":13,"wins":7},"claude-fable-5":{"draws":7,"losses":26,"wins":3},"claude-fable-5-1":{"draws":3,"losses":37,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":28,"wins":1},"claude-opus-4-5":{"draws":25,"losses":29,"wins":6},"claude-opus-4-8":{"draws":10,"losses":23,"wins":3},"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":21,"wins":4},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":26,"wins":3},"elorian/glimpse":{"draws":6,"losses":8,"wins":4},"fireworks/ember-1":{"draws":12,"losses":22,"wins":2},"gemini-3.1-pro-preview":{"draws":13,"losses":21,"wins":2},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":8,"wins":13},"google/gemini-3.5-flash":{"draws":11,"losses":30,"wins":5},"google/gemini-3.5-flash-lite":{"draws":19,"losses":35,"wins":10},"google/gemini-3.6-flash":{"draws":21,"losses":46,"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":15,"losses":15,"wins":6},"gpt-5.6-sol":{"draws":7,"losses":27,"wins":2},"gpt-5.6-terra":{"draws":12,"losses":20,"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},"gpt-6.1-terra":{"draws":4,"losses":32,"wins":0},"gpt-6.1-terra-pro":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":8,"wins":8},"inception/mercury-3":{"draws":8,"losses":13,"wins":1},"inclusionai/ling-3.0-flash":{"draws":9,"losses":12,"wins":3},"inclusionai/ling-3.1-flash":{"draws":5,"losses":3,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":21,"wins":9},"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-spark-open":{"draws":10,"losses":23,"wins":3},"meta/muse-wonder":{"draws":4,"losses":30,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":9,"wins":5},"minimax/minimax-m3.1-flash":{"draws":8,"losses":22,"wins":4},"mistralai/mistral-large-4-0":{"draws":4,"losses":17,"wins":1},"mistralai/mistral-medium-3-5":{"draws":9,"losses":8,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":17,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":31,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":12,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":10,"wins":1},"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":17,"wins":3},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":2},"recursive/flint-v1.0":{"draws":4,"losses":5,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":17,"wins":6},"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},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":3},"tencent/hy4-preview":{"draws":8,"losses":20,"wins":6},"thinkingmachines/inkling":{"draws":16,"losses":23,"wins":9},"thinkingmachines/inkling-small":{"draws":15,"losses":18,"wins":3},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":25,"wins":3},"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":23,"losses":29,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":11,"wins":3},"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":2},"z-ai/glm-5.3-flash":{"draws":8,"losses":24,"wins":4},"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":13,"wins":19},"claude-fable-5":{"draws":10,"losses":30,"wins":8},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":14},"claude-opus-4-5":{"draws":26,"losses":25,"wins":27},"claude-opus-4-8":{"draws":14,"losses":17,"wins":13},"claude-opus-5":{"draws":8,"losses":62,"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":22,"wins":18},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":21,"losses":12,"wins":39},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":15,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":23,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":24,"wins":12},"elorian/glimpse":{"draws":7,"losses":11,"wins":8},"fireworks/ember-1":{"draws":12,"losses":20,"wins":16},"gemini-3.1-pro-preview":{"draws":13,"losses":16,"wins":19},"gemini-4-argon":{"draws":3,"losses":38,"wins":7},"google/gemini-3.1-flash-lite":{"draws":9,"losses":1,"wins":22},"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":19,"losses":46,"wins":27},"google/gemini-3.8-flash":{"draws":10,"losses":24,"wins":14},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":4,"losses":5,"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":12,"losses":10,"wins":26},"gpt-5.5":{"draws":12,"losses":16,"wins":16},"gpt-5.6-luna":{"draws":17,"losses":11,"wins":20},"gpt-5.6-sol":{"draws":7,"losses":32,"wins":9},"gpt-5.6-terra":{"draws":14,"losses":12,"wins":20},"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},"gpt-6.1-terra":{"draws":7,"losses":39,"wins":2},"gpt-6.1-terra-pro":{"draws":7,"losses":37,"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},"inception/mercury-3":{"draws":10,"losses":10,"wins":12},"inclusionai/ling-3.0-flash":{"draws":13,"losses":2,"wins":19},"inclusionai/ling-3.1-flash":{"draws":5,"losses":2,"wins":3},"meituan/longcat-2.0":{"draws":14,"losses":7,"wins":31},"meta/muse-glimmer-30b":{"draws":14,"losses":11,"wins":17},"meta/muse-spark-1.2":{"draws":13,"losses":12,"wins":21},"meta/muse-spark-1.3":{"draws":12,"losses":19,"wins":17},"meta/muse-spark-open":{"draws":9,"losses":21,"wins":16},"meta/muse-wonder":{"draws":10,"losses":24,"wins":14},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":18},"minimax/minimax-m3.1-flash":{"draws":9,"losses":13,"wins":20},"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":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":20,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":40,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":3,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":13},"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":10,"losses":5,"wins":13},"qwen/qwen3.7-plus":{"draws":10,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":13,"wins":8},"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":26,"wins":11},"qwen/qwen3.8-max-0902":{"draws":13,"losses":19,"wins":16},"recursive/flint-v1.0":{"draws":5,"losses":1,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":13,"wins":19},"stealth/ox-alpha":{"draws":37,"losses":65,"wins":56},"stealth/space-bunny-alpha":{"draws":13,"losses":13,"wins":12},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":4},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":13,"losses":20,"wins":13},"thinkingmachines/inkling":{"draws":19,"losses":12,"wins":33},"thinkingmachines/inkling-small":{"draws":14,"losses":5,"wins":29},"unbiased/pareto-26.10":{"draws":3,"losses":13,"wins":0},"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":22,"wins":16},"x-ai/grok-4.6":{"draws":12,"losses":21,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":5,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":14,"wins":10},"z-ai/glm-5.2":{"draws":27,"losses":28,"wins":41},"z-ai/glm-5.3":{"draws":8,"losses":30,"wins":8},"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":6,"losses":16,"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":7,"losses":29,"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":8,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":9,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":10,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":15,"wins":2},"elorian/glimpse":{"draws":2,"losses":7,"wins":3},"fireworks/ember-1":{"draws":12,"losses":11,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":8,"wins":8},"gemini-4-argon":{"draws":1,"losses":23,"wins":0},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":5},"google/gemini-3.5-flash":{"draws":5,"losses":19,"wins":4},"google/gemini-3.5-flash-lite":{"draws":10,"losses":18,"wins":12},"google/gemini-3.6-flash":{"draws":15,"losses":25,"wins":6},"google/gemini-3.8-flash":{"draws":7,"losses":16,"wins":1},"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},"gpt-6.1-terra":{"draws":5,"losses":17,"wins":2},"gpt-6.1-terra-pro":{"draws":10,"losses":14,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":8},"inception/mercury-3":{"draws":8,"losses":7,"wins":3},"inclusionai/ling-3.0-flash":{"draws":5,"losses":6,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":0},"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-spark-open":{"draws":6,"losses":15,"wins":3},"meta/muse-wonder":{"draws":6,"losses":14,"wins":4},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":2},"minimax/minimax-m3.1-flash":{"draws":4,"losses":12,"wins":6},"mistralai/mistral-large-4-0":{"draws":3,"losses":9,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":9,"losses":11,"wins":2},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":18,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":7,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":4,"wins":1},"o3":{"draws":4,"losses":19,"wins":5},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":7},"poolside/laguna-s-2.1":{"draws":10,"losses":9,"wins":5},"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},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":11,"wins":1},"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":{"draws":1,"losses":7,"wins":0},"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":14,"losses":15,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"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":14,"losses":17,"wins":13},"claude-fable-5":{"draws":8,"losses":38,"wins":2},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":32,"wins":2},"claude-opus-4-5":{"draws":29,"losses":41,"wins":8},"claude-opus-4-8":{"draws":11,"losses":31,"wins":2},"claude-opus-5":{"draws":11,"losses":67,"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":4,"losses":8,"wins":6},"deepseek/deepseek-v4-flash":{"draws":21,"losses":26,"wins":25},"deepseek/deepseek-v4-pro":{"draws":11,"losses":22,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":24,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":25,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":32,"wins":8},"elorian/glimpse":{"draws":7,"losses":15,"wins":4},"fireworks/ember-1":{"draws":15,"losses":25,"wins":8},"gemini-3.1-pro-preview":{"draws":17,"losses":20,"wins":11},"gemini-4-argon":{"draws":2,"losses":46,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":10,"wins":13},"google/gemini-3.5-flash":{"draws":10,"losses":41,"wins":9},"google/gemini-3.5-flash-lite":{"draws":25,"losses":33,"wins":26},"google/gemini-3.6-flash":{"draws":28,"losses":56,"wins":8},"google/gemini-3.8-flash":{"draws":8,"losses":39,"wins":1},"google/gemma-4-31b-it":{"draws":13,"losses":5,"wins":10},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":28,"wins":9},"gpt-5.4":{"draws":8,"losses":28,"wins":10},"gpt-5.4-mini":{"draws":10,"losses":12,"wins":10},"gpt-5.4-nano":{"draws":9,"losses":21,"wins":18},"gpt-5.5":{"draws":16,"losses":23,"wins":5},"gpt-5.6-luna":{"draws":17,"losses":22,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":37,"wins":5},"gpt-5.6-terra":{"draws":11,"losses":26,"wins":9},"gpt-6-astra":{"draws":6,"losses":42,"wins":0},"gpt-6-luna":{"draws":14,"losses":25,"wins":9},"gpt-6-sol":{"draws":3,"losses":40,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"gpt-6.1-terra":{"draws":5,"losses":41,"wins":2},"gpt-6.1-terra-pro":{"draws":6,"losses":42,"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},"inception/mercury-3":{"draws":8,"losses":17,"wins":7},"inclusionai/ling-3.0-flash":{"draws":10,"losses":8,"wins":16},"inclusionai/ling-3.1-flash":{"draws":4,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":18,"losses":17,"wins":17},"meta/muse-glimmer-30b":{"draws":17,"losses":16,"wins":9},"meta/muse-spark-1.2":{"draws":11,"losses":29,"wins":6},"meta/muse-spark-1.3":{"draws":10,"losses":32,"wins":6},"meta/muse-spark-open":{"draws":11,"losses":32,"wins":5},"meta/muse-wonder":{"draws":11,"losses":35,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":16,"wins":4},"minimax/minimax-m3.1-flash":{"draws":12,"losses":18,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":18,"wins":1},"mistralai/mistral-medium-3-5":{"draws":10,"losses":6,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":27,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":42,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":7,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":15,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":12,"wins":3},"o3":{"draws":11,"losses":39,"wins":16},"openai/gpt-oss-120b":{"draws":12,"losses":17,"wins":13},"poolside/laguna-s-2.1":{"draws":12,"losses":25,"wins":9},"qwen/qwen3.7-max":{"draws":7,"losses":15,"wins":6},"qwen/qwen3.7-plus":{"draws":6,"losses":13,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":30,"wins":4},"qwen/qwen3.8-27b":{"draws":6,"losses":17,"wins":11},"qwen/qwen3.8-flash":{"draws":7,"losses":9,"wins":0},"qwen/qwen3.8-max":{"draws":17,"losses":25,"wins":6},"qwen/qwen3.8-max-0902":{"draws":16,"losses":23,"wins":9},"recursive/flint-v1.0":{"draws":5,"losses":3,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":25,"wins":7},"stealth/ox-alpha":{"draws":39,"losses":93,"wins":26},"stealth/space-bunny-alpha":{"draws":13,"losses":16,"wins":9},"stepfun/step-3.7-flash":{"draws":7,"losses":14,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":6},"tencent/hy4-preview":{"draws":9,"losses":32,"wins":5},"thinkingmachines/inkling":{"draws":22,"losses":18,"wins":24},"thinkingmachines/inkling-small":{"draws":16,"losses":14,"wins":18},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":15,"losses":30,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":37,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":28,"losses":30,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":17,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":23,"wins":3},"z-ai/glm-5.2":{"draws":30,"losses":50,"wins":16},"z-ai/glm-5.3":{"draws":11,"losses":32,"wins":3},"z-ai/glm-5.3-flash":{"draws":12,"losses":29,"wins":7},"z-ai/glm-5.3-flashx":{"draws":16,"losses":29,"wins":3}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":14,"wins":14},"claude-fable-5":{"draws":9,"losses":25,"wins":14},"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":21,"losses":34,"wins":23},"claude-opus-4-8":{"draws":9,"losses":19,"wins":16},"claude-opus-5":{"draws":14,"losses":57,"wins":11},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":17,"losses":15,"wins":16},"claude-sonnet-5-5":{"draws":5,"losses":30,"wins":13},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":28,"losses":11,"wins":33},"deepseek/deepseek-v4-pro":{"draws":14,"losses":12,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":15,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":21,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":24,"wins":15},"elorian/glimpse":{"draws":5,"losses":10,"wins":11},"fireworks/ember-1":{"draws":12,"losses":21,"wins":15},"gemini-3.1-pro-preview":{"draws":13,"losses":18,"wins":17},"gemini-4-argon":{"draws":3,"losses":39,"wins":6},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":23},"google/gemini-3.5-flash":{"draws":19,"losses":20,"wins":21},"google/gemini-3.5-flash-lite":{"draws":27,"losses":20,"wins":37},"google/gemini-3.6-flash":{"draws":20,"losses":39,"wins":33},"google/gemini-3.8-flash":{"draws":8,"losses":21,"wins":19},"google/gemma-4-31b-it":{"draws":14,"losses":4,"wins":10},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":12,"losses":6,"wins":24},"gpt-5.4":{"draws":14,"losses":16,"wins":16},"gpt-5.4-mini":{"draws":14,"losses":8,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":20},"gpt-5.5":{"draws":13,"losses":17,"wins":14},"gpt-5.6-luna":{"draws":17,"losses":12,"wins":19},"gpt-5.6-sol":{"draws":6,"losses":32,"wins":10},"gpt-5.6-terra":{"draws":13,"losses":13,"wins":20},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":12,"losses":18,"wins":18},"gpt-6-sol":{"draws":5,"losses":31,"wins":12},"gpt-6.1-sol":{"draws":2,"losses":44,"wins":2},"gpt-6.1-terra":{"draws":2,"losses":41,"wins":5},"gpt-6.1-terra-pro":{"draws":3,"losses":39,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":5,"wins":18},"inception/mercury-3":{"draws":8,"losses":11,"wins":13},"inclusionai/ling-3.0-flash":{"draws":10,"losses":7,"wins":17},"inclusionai/ling-3.1-flash":{"draws":4,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":17,"losses":7,"wins":28},"meta/muse-glimmer-30b":{"draws":11,"losses":8,"wins":23},"meta/muse-spark-1.2":{"draws":13,"losses":17,"wins":16},"meta/muse-spark-1.3":{"draws":10,"losses":21,"wins":17},"meta/muse-spark-open":{"draws":14,"losses":24,"wins":10},"meta/muse-wonder":{"draws":11,"losses":25,"wins":12},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":13},"minimax/minimax-m3.1-flash":{"draws":12,"losses":10,"wins":20},"mistralai/mistral-large-4-0":{"draws":12,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":1},"moonshotai/kimi-k3":{"draws":13,"losses":16,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":35,"wins":10},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":5,"wins":9},"o3":{"draws":15,"losses":20,"wins":31},"openai/gpt-oss-120b":{"draws":14,"losses":4,"wins":24},"poolside/laguna-s-2.1":{"draws":16,"losses":12,"wins":18},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"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":9,"losses":10,"wins":13},"qwen/qwen3.8-max":{"draws":8,"losses":18,"wins":6},"qwen/qwen3.8-max-0902":{"draws":11,"losses":20,"wins":17},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":14,"wins":18},"stealth/ox-alpha":{"draws":46,"losses":68,"wins":44},"stealth/space-bunny-alpha":{"draws":11,"losses":11,"wins":16},"stepfun/step-3.7-flash":{"draws":9,"losses":7,"wins":18},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":5,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":21,"wins":13},"thinkingmachines/inkling":{"draws":19,"losses":12,"wins":33},"thinkingmachines/inkling-small":{"draws":15,"losses":14,"wins":19},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":22,"wins":14},"x-ai/grok-4.6":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":23,"losses":17,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":5,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":12,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":16,"wins":8},"z-ai/glm-5.2":{"draws":32,"losses":24,"wins":40},"z-ai/glm-5.3":{"draws":10,"losses":26,"wins":10},"z-ai/glm-5.3-flash":{"draws":6,"losses":23,"wins":19},"z-ai/glm-5.3-flashx":{"draws":11,"losses":17,"wins":20}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":7,"wins":21},"claude-fable-5":{"draws":10,"losses":30,"wins":8},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":22,"wins":10},"claude-opus-4-5":{"draws":28,"losses":26,"wins":24},"claude-opus-4-8":{"draws":14,"losses":13,"wins":17},"claude-opus-5":{"draws":10,"losses":69,"wins":3},"claude-opus-5-5":{"draws":1,"losses":49,"wins":2},"claude-sonnet-5":{"draws":13,"losses":15,"wins":20},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":20,"losses":13,"wins":39},"deepseek/deepseek-v4-pro":{"draws":13,"losses":13,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":14,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":18,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":28,"wins":11},"elorian/glimpse":{"draws":8,"losses":11,"wins":7},"fireworks/ember-1":{"draws":15,"losses":12,"wins":21},"gemini-3.1-pro-preview":{"draws":11,"losses":15,"wins":22},"gemini-4-argon":{"draws":3,"losses":44,"wins":1},"google/gemini-3.1-flash-lite":{"draws":11,"losses":0,"wins":21},"google/gemini-3.5-flash":{"draws":15,"losses":16,"wins":29},"google/gemini-3.5-flash-lite":{"draws":28,"losses":9,"wins":47},"google/gemini-3.6-flash":{"draws":33,"losses":34,"wins":25},"google/gemini-3.8-flash":{"draws":14,"losses":23,"wins":11},"google/gemma-4-31b-it":{"draws":12,"losses":4,"wins":12},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":11,"wins":18},"gpt-5.4":{"draws":10,"losses":23,"wins":13},"gpt-5.4-mini":{"draws":13,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":17,"losses":8,"wins":23},"gpt-5.5":{"draws":20,"losses":14,"wins":10},"gpt-5.6-luna":{"draws":17,"losses":14,"wins":17},"gpt-5.6-sol":{"draws":5,"losses":35,"wins":8},"gpt-5.6-terra":{"draws":15,"losses":15,"wins":16},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":17,"losses":16,"wins":15},"gpt-6-sol":{"draws":8,"losses":34,"wins":6},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"gpt-6.1-terra":{"draws":6,"losses":42,"wins":0},"gpt-6.1-terra-pro":{"draws":6,"losses":39,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":6,"wins":14},"inception/mercury-3":{"draws":11,"losses":8,"wins":13},"inclusionai/ling-3.0-flash":{"draws":17,"losses":4,"wins":13},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":8,"wins":34},"meta/muse-glimmer-30b":{"draws":14,"losses":3,"wins":25},"meta/muse-spark-1.2":{"draws":12,"losses":17,"wins":17},"meta/muse-spark-1.3":{"draws":13,"losses":22,"wins":13},"meta/muse-spark-open":{"draws":13,"losses":17,"wins":18},"meta/muse-wonder":{"draws":13,"losses":29,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":17},"minimax/minimax-m3.1-flash":{"draws":11,"losses":9,"wins":22},"mistralai/mistral-large-4-0":{"draws":13,"losses":5,"wins":12},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":9,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":39,"wins":4},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":5,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":6,"wins":9},"o3":{"draws":14,"losses":21,"wins":31},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":24},"poolside/laguna-s-2.1":{"draws":17,"losses":8,"wins":21},"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":15,"losses":17,"wins":16},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":13},"qwen/qwen3.8-flash":{"draws":9,"losses":9,"wins":14},"qwen/qwen3.8-max":{"draws":13,"losses":17,"wins":18},"qwen/qwen3.8-max-0902":{"draws":7,"losses":15,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":13,"wins":20},"stealth/ox-alpha":{"draws":36,"losses":65,"wins":57},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":22},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":20},"stepfun/step-5-preview":{"draws":4,"losses":8,"wins":4},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":22,"wins":10},"thinkingmachines/inkling":{"draws":21,"losses":11,"wins":32},"thinkingmachines/inkling-small":{"draws":17,"losses":2,"wins":29},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":13,"losses":28,"wins":7},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":8},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":27,"losses":8,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":2,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":17,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":40,"losses":17,"wins":39},"z-ai/glm-5.3":{"draws":11,"losses":28,"wins":7},"z-ai/glm-5.3-flash":{"draws":11,"losses":20,"wins":17},"z-ai/glm-5.3-flashx":{"draws":7,"losses":26,"wins":15}},"reflection/beam-1.0-501b-a23b":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":11,"wins":13},"claude-fable-5":{"draws":9,"losses":22,"wins":11},"claude-fable-5-1":{"draws":1,"losses":46,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":19,"wins":11},"claude-opus-4-5":{"draws":30,"losses":19,"wins":19},"claude-opus-4-8":{"draws":12,"losses":15,"wins":11},"claude-opus-5":{"draws":11,"losses":58,"wins":11},"claude-opus-5-5":{"draws":5,"losses":37,"wins":4},"claude-sonnet-5":{"draws":18,"losses":13,"wins":11},"claude-sonnet-5-5":{"draws":13,"losses":19,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":17,"losses":14,"wins":31},"deepseek/deepseek-v4-pro":{"draws":12,"losses":12,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":11,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":15,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":26,"wins":6},"elorian/glimpse":{"draws":6,"losses":10,"wins":8},"fireworks/ember-1":{"draws":15,"losses":12,"wins":15},"gemini-3.1-pro-preview":{"draws":12,"losses":18,"wins":12},"gemini-4-argon":{"draws":1,"losses":38,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":16},"google/gemini-3.5-flash":{"draws":14,"losses":21,"wins":17},"google/gemini-3.5-flash-lite":{"draws":29,"losses":17,"wins":26},"google/gemini-3.6-flash":{"draws":24,"losses":34,"wins":22},"google/gemini-3.8-flash":{"draws":7,"losses":22,"wins":13},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":10},"gpt-4.1":{"draws":5,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":9,"losses":14,"wins":15},"gpt-5.4":{"draws":9,"losses":17,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":13,"losses":8,"wins":19},"gpt-5.5":{"draws":11,"losses":22,"wins":7},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":13},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":8},"gpt-5.6-terra":{"draws":14,"losses":13,"wins":13},"gpt-6-astra":{"draws":4,"losses":35,"wins":3},"gpt-6-luna":{"draws":10,"losses":18,"wins":14},"gpt-6-sol":{"draws":8,"losses":26,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":35,"wins":5},"gpt-6.1-terra":{"draws":5,"losses":34,"wins":3},"gpt-6.1-terra-pro":{"draws":1,"losses":37,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":12},"inception/mercury-3":{"draws":13,"losses":7,"wins":9},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":8},"inclusionai/ling-3.1-flash":{"draws":4,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":12,"wins":18},"meta/muse-glimmer-30b":{"draws":15,"losses":8,"wins":17},"meta/muse-spark-1.2":{"draws":10,"losses":18,"wins":14},"meta/muse-spark-1.3":{"draws":8,"losses":23,"wins":11},"meta/muse-spark-open":{"draws":9,"losses":16,"wins":15},"meta/muse-wonder":{"draws":8,"losses":24,"wins":10},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":14},"minimax/minimax-m3.1-flash":{"draws":12,"losses":10,"wins":14},"mistralai/mistral-large-4-0":{"draws":9,"losses":6,"wins":13},"mistralai/mistral-medium-3-5":{"draws":10,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":17,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":36,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":5,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":7,"wins":5},"o3":{"draws":14,"losses":18,"wins":22},"openai/gpt-oss-120b":{"draws":15,"losses":9,"wins":14},"poolside/laguna-s-2.1":{"draws":16,"losses":8,"wins":18},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":3,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":23,"wins":9},"qwen/qwen3.8-27b":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":9,"losses":18,"wins":15},"qwen/qwen3.8-max-0902":{"draws":11,"losses":21,"wins":10},"recursive/flint-v1.0":{"draws":5,"losses":0,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":8,"wins":10},"stealth/ox-alpha":{"draws":34,"losses":61,"wins":47},"stealth/space-bunny-alpha":{"draws":14,"losses":7,"wins":13},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":16},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":4},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":21,"wins":7},"thinkingmachines/inkling":{"draws":21,"losses":11,"wins":26},"thinkingmachines/inkling-small":{"draws":15,"losses":10,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":24,"wins":5},"x-ai/grok-4.6":{"draws":11,"losses":24,"wins":7},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":28,"losses":11,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":3,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":14,"wins":8},"z-ai/glm-5.2":{"draws":26,"losses":27,"wins":31},"z-ai/glm-5.3":{"draws":8,"losses":24,"wins":8},"z-ai/glm-5.3-flash":{"draws":11,"losses":20,"wins":11},"z-ai/glm-5.3-flashx":{"draws":9,"losses":21,"wins":12}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":49,"losses":39,"wins":68},"claude-fable-5":{"draws":32,"losses":111,"wins":25},"claude-fable-5-1":{"draws":7,"losses":188,"wins":1},"claude-haiku-5-5":{"draws":46,"losses":73,"wins":33},"claude-opus-4-5":{"draws":95,"losses":96,"wins":73},"claude-opus-4-8":{"draws":32,"losses":66,"wins":38},"claude-opus-5":{"draws":49,"losses":222,"wins":23},"claude-opus-5-5":{"draws":18,"losses":158,"wins":0},"claude-sonnet-5":{"draws":50,"losses":63,"wins":55},"claude-sonnet-5-5":{"draws":35,"losses":92,"wins":41},"cohere/north-mini-code":{"draws":14,"losses":12,"wins":34},"deepseek/deepseek-v4-flash":{"draws":90,"losses":66,"wins":90},"deepseek/deepseek-v4-pro":{"draws":57,"losses":51,"wins":48},"deepseek/deepseek-v4-pro-0813":{"draws":47,"losses":68,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":50,"losses":79,"wins":39},"deepseek/deepseek-v4.1-flash-1017":{"draws":37,"losses":92,"wins":39},"elorian/glimpse":{"draws":35,"losses":41,"wins":18},"fireworks/ember-1":{"draws":55,"losses":77,"wins":36},"gemini-3.1-pro-preview":{"draws":41,"losses":62,"wins":65},"gemini-4-argon":{"draws":13,"losses":147,"wins":8},"google/gemini-3.1-flash-lite":{"draws":20,"losses":11,"wins":61},"google/gemini-3.5-flash":{"draws":40,"losses":101,"wins":61},"google/gemini-3.5-flash-lite":{"draws":88,"losses":81,"wins":123},"google/gemini-3.6-flash":{"draws":78,"losses":155,"wins":93},"google/gemini-3.8-flash":{"draws":43,"losses":97,"wins":28},"google/gemma-4-31b-it":{"draws":35,"losses":15,"wins":40},"gpt-4.1":{"draws":21,"losses":19,"wins":16},"gpt-4.1-nano":{"draws":16,"losses":2,"wins":10},"gpt-5":{"draws":49,"losses":59,"wins":42},"gpt-5.4":{"draws":55,"losses":77,"wins":30},"gpt-5.4-mini":{"draws":43,"losses":33,"wins":36},"gpt-5.4-nano":{"draws":37,"losses":52,"wins":57},"gpt-5.5":{"draws":58,"losses":62,"wins":36},"gpt-5.6-luna":{"draws":67,"losses":50,"wins":51},"gpt-5.6-sol":{"draws":30,"losses":115,"wins":23},"gpt-5.6-terra":{"draws":65,"losses":52,"wins":45},"gpt-6-astra":{"draws":12,"losses":156,"wins":0},"gpt-6-luna":{"draws":52,"losses":69,"wins":47},"gpt-6-sol":{"draws":20,"losses":134,"wins":14},"gpt-6.1-sol":{"draws":10,"losses":152,"wins":6},"gpt-6.1-terra":{"draws":25,"losses":136,"wins":7},"gpt-6.1-terra-pro":{"draws":25,"losses":138,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":46,"losses":13,"wins":49},"inception/mercury-3":{"draws":42,"losses":45,"wins":23},"inclusionai/ling-3.0-flash":{"draws":51,"losses":18,"wins":47},"inclusionai/ling-3.1-flash":{"draws":15,"losses":3,"wins":6},"meituan/longcat-2.0":{"draws":58,"losses":39,"wins":81},"meta/muse-glimmer-30b":{"draws":52,"losses":31,"wins":67},"meta/muse-spark-1.2":{"draws":47,"losses":71,"wins":44},"meta/muse-spark-1.3":{"draws":35,"losses":103,"wins":30},"meta/muse-spark-open":{"draws":48,"losses":87,"wins":33},"meta/muse-wonder":{"draws":44,"losses":101,"wins":23},"minimax/minimax-m3":{"draws":21,"losses":20,"wins":43},"minimax/minimax-m3.1-flash":{"draws":47,"losses":43,"wins":64},"mistralai/mistral-large-4-0":{"draws":50,"losses":34,"wins":22},"mistralai/mistral-medium-3-5":{"draws":37,"losses":16,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":49,"losses":68,"wins":45},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":135,"wins":19},"nex-agi/nex-n2-pro":{"draws":31,"losses":12,"wins":45},"nex-agi/nex-n2.5-pro":{"draws":14,"losses":10,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":25,"wins":57},"nvidia/nemotron-3.5-super-vl":{"draws":27,"losses":24,"wins":21},"o3":{"draws":41,"losses":99,"wins":68},"openai/gpt-oss-120b":{"draws":58,"losses":30,"wins":62},"poolside/laguna-s-2.1":{"draws":65,"losses":42,"wins":63},"qwen/qwen3.7-max":{"draws":29,"losses":29,"wins":32},"qwen/qwen3.7-plus":{"draws":20,"losses":13,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":57,"losses":72,"wins":39},"qwen/qwen3.8-27b":{"draws":43,"losses":46,"wins":31},"qwen/qwen3.8-flash":{"draws":44,"losses":44,"wins":24},"qwen/qwen3.8-max":{"draws":52,"losses":76,"wins":40},"qwen/qwen3.8-max-0902":{"draws":54,"losses":75,"wins":39},"recursive/flint-v1.0":{"draws":11,"losses":6,"wins":23},"reflection/beam-1.0-501b-a23b":{"draws":52,"losses":69,"wins":35},"stealth/ox-alpha":{"draws":135,"losses":303,"wins":164},"stealth/space-bunny-alpha":{"draws":48,"losses":41,"wins":41},"stepfun/step-3.7-flash":{"draws":36,"losses":22,"wins":60},"stepfun/step-5-preview":{"draws":8,"losses":19,"wins":9},"tencent/hy3-preview":{"draws":31,"losses":22,"wins":31},"tencent/hy4-preview":{"draws":45,"losses":79,"wins":38},"thinkingmachines/inkling":{"draws":83,"losses":55,"wins":98},"thinkingmachines/inkling-small":{"draws":63,"losses":30,"wins":75},"unbiased/pareto-26.10":{"draws":3,"losses":52,"wins":1},"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":61,"losses":77,"wins":30},"x-ai/grok-4.7":{"draws":18,"losses":106,"wins":16},"x-ai/grok-build-0.1":{"draws":18,"losses":13,"wins":25},"xiaomi/mimo-v2.5":{"draws":75,"losses":51,"wins":96},"xiaomi/mimo-v2.5-pro":{"draws":29,"losses":23,"wins":32},"xiaomi/mimo-v2.6-flash":{"draws":24,"losses":55,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":64,"wins":23},"z-ai/glm-5.2":{"draws":128,"losses":102,"wins":106},"z-ai/glm-5.3":{"draws":32,"losses":110,"wins":20},"z-ai/glm-5.3-flash":{"draws":29,"losses":96,"wins":43},"z-ai/glm-5.3-flashx":{"draws":38,"losses":97,"wins":33}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":12,"wins":9},"claude-fable-5":{"draws":10,"losses":22,"wins":4},"claude-fable-5-1":{"draws":3,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":4},"claude-opus-4-5":{"draws":16,"losses":32,"wins":10},"claude-opus-4-8":{"draws":9,"losses":16,"wins":7},"claude-opus-5":{"draws":10,"losses":54,"wins":4},"claude-opus-5-5":{"draws":4,"losses":36,"wins":0},"claude-sonnet-5":{"draws":9,"losses":20,"wins":7},"claude-sonnet-5-5":{"draws":9,"losses":21,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":10},"deepseek/deepseek-v4-flash":{"draws":20,"losses":17,"wins":15},"deepseek/deepseek-v4-pro":{"draws":10,"losses":17,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":15,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":20,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":24,"wins":6},"elorian/glimpse":{"draws":6,"losses":10,"wins":4},"fireworks/ember-1":{"draws":11,"losses":19,"wins":6},"gemini-3.1-pro-preview":{"draws":10,"losses":18,"wins":8},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":13},"google/gemini-3.5-flash":{"draws":16,"losses":19,"wins":9},"google/gemini-3.5-flash-lite":{"draws":21,"losses":18,"wins":23},"google/gemini-3.6-flash":{"draws":17,"losses":42,"wins":9},"google/gemini-3.8-flash":{"draws":7,"losses":23,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":5},"gpt-4.1":{"draws":3,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":11,"losses":14,"wins":7},"gpt-5.4":{"draws":15,"losses":13,"wins":6},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":10},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":14},"gpt-5.5":{"draws":18,"losses":14,"wins":2},"gpt-5.6-luna":{"draws":14,"losses":9,"wins":13},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":0},"gpt-5.6-terra":{"draws":12,"losses":12,"wins":10},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":12,"losses":17,"wins":7},"gpt-6-sol":{"draws":6,"losses":30,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"gpt-6.1-terra":{"draws":7,"losses":29,"wins":0},"gpt-6.1-terra-pro":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":6,"wins":7},"inception/mercury-3":{"draws":7,"losses":12,"wins":5},"inclusionai/ling-3.0-flash":{"draws":11,"losses":8,"wins":3},"inclusionai/ling-3.1-flash":{"draws":1,"losses":2,"wins":3},"meituan/longcat-2.0":{"draws":10,"losses":11,"wins":19},"meta/muse-glimmer-30b":{"draws":17,"losses":10,"wins":7},"meta/muse-spark-1.2":{"draws":12,"losses":21,"wins":3},"meta/muse-spark-1.3":{"draws":8,"losses":26,"wins":2},"meta/muse-spark-open":{"draws":11,"losses":21,"wins":4},"meta/muse-wonder":{"draws":9,"losses":23,"wins":4},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":7},"minimax/minimax-m3.1-flash":{"draws":9,"losses":12,"wins":9},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":3},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":32,"wins":3},"nex-agi/nex-n2-pro":{"draws":8,"losses":1,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":1,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":8,"wins":4},"o3":{"draws":10,"losses":26,"wins":8},"openai/gpt-oss-120b":{"draws":12,"losses":8,"wins":14},"poolside/laguna-s-2.1":{"draws":20,"losses":8,"wins":8},"qwen/qwen3.7-max":{"draws":4,"losses":12,"wins":4},"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":9,"losses":7,"wins":8},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":5},"qwen/qwen3.8-max-0902":{"draws":11,"losses":21,"wins":4},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":18,"wins":7},"stealth/ox-alpha":{"draws":40,"losses":70,"wins":16},"stealth/space-bunny-alpha":{"draws":5,"losses":8,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":7},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":10},"tencent/hy4-preview":{"draws":15,"losses":18,"wins":1},"thinkingmachines/inkling":{"draws":18,"losses":14,"wins":16},"thinkingmachines/inkling-small":{"draws":14,"losses":10,"wins":12},"unbiased/pareto-26.10":{"draws":2,"losses":10,"wins":0},"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":12,"losses":20,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":21,"losses":13,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":17,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":14,"wins":3},"z-ai/glm-5.2":{"draws":28,"losses":26,"wins":18},"z-ai/glm-5.3":{"draws":7,"losses":29,"wins":0},"z-ai/glm-5.3-flash":{"draws":12,"losses":19,"wins":5},"z-ai/glm-5.3-flashx":{"draws":11,"losses":20,"wins":5}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":11},"claude-fable-5":{"draws":9,"losses":26,"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":10,"losses":18,"wins":4},"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":11,"losses":15,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":16,"wins":8},"elorian/glimpse":{"draws":5,"losses":9,"wins":6},"fireworks/ember-1":{"draws":13,"losses":15,"wins":8},"gemini-3.1-pro-preview":{"draws":16,"losses":11,"wins":9},"gemini-4-argon":{"draws":0,"losses":34,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":14},"google/gemini-3.5-flash":{"draws":14,"losses":23,"wins":7},"google/gemini-3.5-flash-lite":{"draws":30,"losses":17,"wins":15},"google/gemini-3.6-flash":{"draws":21,"losses":38,"wins":11},"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},"gpt-6.1-terra":{"draws":6,"losses":29,"wins":1},"gpt-6.1-terra-pro":{"draws":5,"losses":31,"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},"inception/mercury-3":{"draws":11,"losses":10,"wins":3},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":4},"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-spark-open":{"draws":12,"losses":19,"wins":3},"meta/muse-wonder":{"draws":10,"losses":20,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":7,"wins":6},"minimax/minimax-m3.1-flash":{"draws":11,"losses":16,"wins":7},"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":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":15,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":32,"wins":1},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":7,"wins":1},"o3":{"draws":10,"losses":20,"wins":14},"openai/gpt-oss-120b":{"draws":17,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":16,"losses":6,"wins":8},"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},"recursive/flint-v1.0":{"draws":3,"losses":4,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":9,"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":2,"losses":4,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":0},"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":{"draws":3,"losses":9,"wins":0},"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":5,"losses":3,"wins":8},"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":26,"losses":27,"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":6,"losses":9,"wins":17},"claude-fable-5":{"draws":4,"losses":20,"wins":4},"claude-fable-5-1":{"draws":1,"losses":38,"wins":1},"claude-haiku-5-5":{"draws":7,"losses":12,"wins":15},"claude-opus-4-5":{"draws":11,"losses":15,"wins":16},"claude-opus-4-8":{"draws":4,"losses":15,"wins":15},"claude-opus-5":{"draws":6,"losses":47,"wins":5},"claude-opus-5-5":{"draws":4,"losses":33,"wins":3},"claude-sonnet-5":{"draws":6,"losses":15,"wins":15},"claude-sonnet-5-5":{"draws":2,"losses":21,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":11},"deepseek/deepseek-v4-flash":{"draws":6,"losses":15,"wins":39},"deepseek/deepseek-v4-pro":{"draws":3,"losses":9,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":7,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":17,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":14,"wins":12},"elorian/glimpse":{"draws":2,"losses":8,"wins":4},"fireworks/ember-1":{"draws":3,"losses":18,"wins":13},"gemini-3.1-pro-preview":{"draws":5,"losses":14,"wins":11},"gemini-4-argon":{"draws":3,"losses":27,"wins":4},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":15},"google/gemini-3.5-flash":{"draws":4,"losses":25,"wins":15},"google/gemini-3.5-flash-lite":{"draws":10,"losses":19,"wins":33},"google/gemini-3.6-flash":{"draws":8,"losses":36,"wins":28},"google/gemini-3.8-flash":{"draws":3,"losses":22,"wins":11},"google/gemma-4-31b-it":{"draws":5,"losses":5,"wins":10},"gpt-4.1":{"draws":2,"losses":6,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":5},"gpt-5":{"draws":4,"losses":11,"wins":9},"gpt-5.4":{"draws":5,"losses":17,"wins":12},"gpt-5.4-mini":{"draws":3,"losses":6,"wins":21},"gpt-5.4-nano":{"draws":2,"losses":9,"wins":17},"gpt-5.5":{"draws":2,"losses":16,"wins":10},"gpt-5.6-luna":{"draws":2,"losses":7,"wins":19},"gpt-5.6-sol":{"draws":6,"losses":16,"wins":8},"gpt-5.6-terra":{"draws":6,"losses":16,"wins":10},"gpt-6-astra":{"draws":2,"losses":30,"wins":0},"gpt-6-luna":{"draws":5,"losses":11,"wins":18},"gpt-6-sol":{"draws":7,"losses":26,"wins":7},"gpt-6.1-sol":{"draws":1,"losses":25,"wins":0},"gpt-6.1-terra":{"draws":4,"losses":22,"wins":2},"gpt-6.1-terra-pro":{"draws":4,"losses":22,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":4,"wins":9},"inception/mercury-3":{"draws":2,"losses":8,"wins":12},"inclusionai/ling-3.0-flash":{"draws":4,"losses":4,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":3,"losses":9,"wins":24},"meta/muse-glimmer-30b":{"draws":2,"losses":13,"wins":25},"meta/muse-spark-1.2":{"draws":5,"losses":12,"wins":17},"meta/muse-spark-1.3":{"draws":6,"losses":15,"wins":9},"meta/muse-spark-open":{"draws":4,"losses":15,"wins":13},"meta/muse-wonder":{"draws":5,"losses":20,"wins":9},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":15},"minimax/minimax-m3.1-flash":{"draws":2,"losses":6,"wins":18},"mistralai/mistral-large-4-0":{"draws":6,"losses":13,"wins":9},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":16,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":28,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":11,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":7,"wins":8},"o3":{"draws":4,"losses":14,"wins":18},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":18},"poolside/laguna-s-2.1":{"draws":2,"losses":10,"wins":12},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":11},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":17,"wins":14},"qwen/qwen3.8-27b":{"draws":4,"losses":10,"wins":8},"qwen/qwen3.8-flash":{"draws":5,"losses":6,"wins":11},"qwen/qwen3.8-max":{"draws":4,"losses":14,"wins":10},"qwen/qwen3.8-max-0902":{"draws":5,"losses":15,"wins":18},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":11,"wins":19},"stealth/ox-alpha":{"draws":16,"losses":41,"wins":45},"stealth/space-bunny-alpha":{"draws":4,"losses":6,"wins":8},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":18},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":10},"tencent/hy4-preview":{"draws":3,"losses":18,"wins":15},"thinkingmachines/inkling":{"draws":5,"losses":4,"wins":31},"thinkingmachines/inkling-small":{"draws":9,"losses":4,"wins":15},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":5,"losses":9,"wins":14},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":10},"x-ai/grok-4.7":{"draws":2,"losses":23,"wins":7},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":4,"losses":10,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":5,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":15,"wins":9},"z-ai/glm-5.2":{"draws":8,"losses":24,"wins":26},"z-ai/glm-5.3":{"draws":5,"losses":21,"wins":10},"z-ai/glm-5.3-flash":{"draws":5,"losses":15,"wins":16},"z-ai/glm-5.3-flashx":{"draws":3,"losses":16,"wins":15}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":15,"wins":10},"claude-fable-5":{"draws":11,"losses":19,"wins":6},"claude-fable-5-1":{"draws":3,"losses":34,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":14,"wins":7},"claude-opus-4-5":{"draws":21,"losses":25,"wins":12},"claude-opus-4-8":{"draws":9,"losses":17,"wins":6},"claude-opus-5":{"draws":12,"losses":51,"wins":9},"claude-opus-5-5":{"draws":5,"losses":35,"wins":0},"claude-sonnet-5":{"draws":11,"losses":16,"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":17,"losses":18,"wins":17},"deepseek/deepseek-v4-pro":{"draws":13,"losses":13,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":10,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":21,"wins":4},"elorian/glimpse":{"draws":6,"losses":10,"wins":4},"fireworks/ember-1":{"draws":12,"losses":16,"wins":8},"gemini-3.1-pro-preview":{"draws":8,"losses":18,"wins":10},"gemini-4-argon":{"draws":1,"losses":33,"wins":2},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":6},"google/gemini-3.5-flash":{"draws":12,"losses":19,"wins":13},"google/gemini-3.5-flash-lite":{"draws":27,"losses":10,"wins":25},"google/gemini-3.6-flash":{"draws":20,"losses":34,"wins":14},"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":16,"losses":13,"wins":5},"gpt-5.4-mini":{"draws":12,"losses":7,"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":10,"losses":10,"wins":16},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":2},"gpt-5.6-terra":{"draws":15,"losses":12,"wins":7},"gpt-6-astra":{"draws":6,"losses":30,"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},"gpt-6.1-terra":{"draws":4,"losses":29,"wins":3},"gpt-6.1-terra-pro":{"draws":2,"losses":30,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":5,"wins":6},"inception/mercury-3":{"draws":9,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":14,"losses":1,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":4,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":12,"wins":11},"meta/muse-glimmer-30b":{"draws":12,"losses":9,"wins":13},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":5},"meta/muse-spark-1.3":{"draws":7,"losses":23,"wins":6},"meta/muse-spark-open":{"draws":10,"losses":17,"wins":9},"meta/muse-wonder":{"draws":9,"losses":21,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":8},"minimax/minimax-m3.1-flash":{"draws":9,"losses":8,"wins":13},"mistralai/mistral-large-4-0":{"draws":12,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":8,"losses":7,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":26,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":3},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":11,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":6,"wins":3},"o3":{"draws":12,"losses":18,"wins":12},"openai/gpt-oss-120b":{"draws":12,"losses":9,"wins":11},"poolside/laguna-s-2.1":{"draws":14,"losses":13,"wins":11},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":7},"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":15,"losses":16,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":18,"wins":6},"recursive/flint-v1.0":{"draws":4,"losses":1,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":20,"wins":5},"stealth/ox-alpha":{"draws":34,"losses":69,"wins":21},"stealth/space-bunny-alpha":{"draws":12,"losses":12,"wins":4},"stepfun/step-3.7-flash":{"draws":11,"losses":4,"wins":7},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":13,"losses":14,"wins":7},"thinkingmachines/inkling":{"draws":15,"losses":16,"wins":19},"thinkingmachines/inkling-small":{"draws":17,"losses":6,"wins":13},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":3,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":26,"losses":13,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":7},"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":29,"losses":25,"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":12,"losses":9,"wins":23},"claude-fable-5":{"draws":7,"losses":39,"wins":2},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":20,"wins":15},"claude-opus-4-5":{"draws":27,"losses":29,"wins":22},"claude-opus-4-8":{"draws":12,"losses":21,"wins":11},"claude-opus-5":{"draws":9,"losses":64,"wins":9},"claude-opus-5-5":{"draws":2,"losses":49,"wins":1},"claude-sonnet-5":{"draws":14,"losses":19,"wins":15},"claude-sonnet-5-5":{"draws":10,"losses":27,"wins":11},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":18,"wins":33},"deepseek/deepseek-v4-pro":{"draws":10,"losses":20,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":21,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":17,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":31,"wins":7},"elorian/glimpse":{"draws":5,"losses":14,"wins":7},"fireworks/ember-1":{"draws":18,"losses":20,"wins":10},"gemini-3.1-pro-preview":{"draws":15,"losses":17,"wins":16},"gemini-4-argon":{"draws":1,"losses":45,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":14,"losses":31,"wins":15},"google/gemini-3.5-flash-lite":{"draws":23,"losses":27,"wins":34},"google/gemini-3.6-flash":{"draws":26,"losses":43,"wins":23},"google/gemini-3.8-flash":{"draws":11,"losses":28,"wins":9},"google/gemma-4-31b-it":{"draws":11,"losses":7,"wins":10},"gpt-4.1":{"draws":7,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":16,"wins":15},"gpt-5.4":{"draws":12,"losses":27,"wins":7},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":16},"gpt-5.4-nano":{"draws":8,"losses":15,"wins":25},"gpt-5.5":{"draws":16,"losses":18,"wins":10},"gpt-5.6-luna":{"draws":20,"losses":11,"wins":17},"gpt-5.6-sol":{"draws":8,"losses":34,"wins":6},"gpt-5.6-terra":{"draws":15,"losses":20,"wins":11},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":19,"losses":19,"wins":10},"gpt-6-sol":{"draws":9,"losses":37,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"gpt-6.1-terra":{"draws":2,"losses":45,"wins":1},"gpt-6.1-terra-pro":{"draws":5,"losses":40,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":7,"wins":14},"inception/mercury-3":{"draws":10,"losses":15,"wins":7},"inclusionai/ling-3.0-flash":{"draws":11,"losses":7,"wins":16},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":17,"losses":10,"wins":25},"meta/muse-glimmer-30b":{"draws":14,"losses":6,"wins":22},"meta/muse-spark-1.2":{"draws":13,"losses":22,"wins":11},"meta/muse-spark-1.3":{"draws":9,"losses":28,"wins":11},"meta/muse-spark-open":{"draws":11,"losses":28,"wins":9},"meta/muse-wonder":{"draws":12,"losses":31,"wins":5},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":16},"minimax/minimax-m3.1-flash":{"draws":13,"losses":15,"wins":14},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":18,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":39,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":9},"o3":{"draws":8,"losses":38,"wins":20},"openai/gpt-oss-120b":{"draws":16,"losses":10,"wins":16},"poolside/laguna-s-2.1":{"draws":7,"losses":16,"wins":23},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":7,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":23,"wins":9},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":11},"qwen/qwen3.8-flash":{"draws":9,"losses":13,"wins":10},"qwen/qwen3.8-max":{"draws":16,"losses":16,"wins":16},"qwen/qwen3.8-max-0902":{"draws":15,"losses":22,"wins":11},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":14,"wins":15},"stealth/ox-alpha":{"draws":32,"losses":86,"wins":40},"stealth/space-bunny-alpha":{"draws":13,"losses":14,"wins":11},"stepfun/step-3.7-flash":{"draws":6,"losses":10,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":5,"losses":18,"wins":7},"thinkingmachines/inkling":{"draws":16,"losses":13,"wins":35},"thinkingmachines/inkling-small":{"draws":16,"losses":9,"wins":23},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":16,"losses":24,"wins":8},"x-ai/grok-4.6":{"draws":14,"losses":27,"wins":7},"x-ai/grok-4.7":{"draws":4,"losses":32,"wins":6},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":28,"losses":15,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":9},"z-ai/glm-5.2":{"draws":23,"losses":33,"wins":40},"z-ai/glm-5.3":{"draws":8,"losses":31,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":24,"wins":15},"z-ai/glm-5.3-flashx":{"draws":15,"losses":23,"wins":10}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":20,"wins":21},"claude-fable-5":{"draws":16,"losses":49,"wins":7},"claude-fable-5-1":{"draws":6,"losses":75,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":42,"wins":12},"claude-opus-4-5":{"draws":40,"losses":51,"wins":25},"claude-opus-4-8":{"draws":19,"losses":35,"wins":10},"claude-opus-5":{"draws":17,"losses":97,"wins":16},"claude-opus-5-5":{"draws":7,"losses":69,"wins":0},"claude-sonnet-5":{"draws":24,"losses":36,"wins":12},"claude-sonnet-5-5":{"draws":15,"losses":43,"wins":14},"cohere/north-mini-code":{"draws":7,"losses":9,"wins":10},"deepseek/deepseek-v4-flash":{"draws":36,"losses":36,"wins":32},"deepseek/deepseek-v4-pro":{"draws":21,"losses":31,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":23,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":31,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":45,"wins":11},"elorian/glimpse":{"draws":13,"losses":18,"wins":9},"fireworks/ember-1":{"draws":24,"losses":34,"wins":14},"gemini-3.1-pro-preview":{"draws":21,"losses":30,"wins":21},"gemini-4-argon":{"draws":5,"losses":62,"wins":5},"google/gemini-3.1-flash-lite":{"draws":11,"losses":16,"wins":19},"google/gemini-3.5-flash":{"draws":19,"losses":52,"wins":19},"google/gemini-3.5-flash-lite":{"draws":31,"losses":53,"wins":44},"google/gemini-3.6-flash":{"draws":46,"losses":77,"wins":17},"google/gemini-3.8-flash":{"draws":13,"losses":49,"wins":10},"google/gemma-4-31b-it":{"draws":17,"losses":12,"wins":11},"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":16,"losses":17,"wins":15},"gpt-5.4-nano":{"draws":11,"losses":31,"wins":26},"gpt-5.5":{"draws":18,"losses":38,"wins":12},"gpt-5.6-luna":{"draws":23,"losses":30,"wins":19},"gpt-5.6-sol":{"draws":11,"losses":54,"wins":7},"gpt-5.6-terra":{"draws":21,"losses":30,"wins":17},"gpt-6-astra":{"draws":4,"losses":68,"wins":0},"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":67,"wins":1},"gpt-6.1-terra":{"draws":6,"losses":63,"wins":3},"gpt-6.1-terra-pro":{"draws":8,"losses":64,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":14,"wins":17},"inception/mercury-3":{"draws":16,"losses":22,"wins":8},"inclusionai/ling-3.0-flash":{"draws":17,"losses":12,"wins":19},"inclusionai/ling-3.1-flash":{"draws":8,"losses":7,"wins":3},"meituan/longcat-2.0":{"draws":20,"losses":24,"wins":32},"meta/muse-glimmer-30b":{"draws":25,"losses":17,"wins":24},"meta/muse-spark-1.2":{"draws":21,"losses":31,"wins":18},"meta/muse-spark-1.3":{"draws":16,"losses":47,"wins":9},"meta/muse-spark-open":{"draws":16,"losses":42,"wins":14},"meta/muse-wonder":{"draws":12,"losses":47,"wins":13},"minimax/minimax-m3":{"draws":10,"losses":13,"wins":15},"minimax/minimax-m3.1-flash":{"draws":15,"losses":31,"wins":20},"mistralai/mistral-large-4-0":{"draws":16,"losses":20,"wins":10},"mistralai/mistral-medium-3-5":{"draws":14,"losses":10,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":22,"losses":30,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":61,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":20,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":14,"wins":8},"o3":{"draws":12,"losses":61,"wins":23},"openai/gpt-oss-120b":{"draws":15,"losses":24,"wins":23},"poolside/laguna-s-2.1":{"draws":19,"losses":29,"wins":22},"qwen/qwen3.7-max":{"draws":14,"losses":19,"wins":7},"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":23,"losses":36,"wins":13},"qwen/qwen3.8-max-0902":{"draws":19,"losses":41,"wins":12},"recursive/flint-v1.0":{"draws":6,"losses":7,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":36,"wins":12},"stealth/ox-alpha":{"draws":57,"losses":140,"wins":53},"stealth/space-bunny-alpha":{"draws":19,"losses":21,"wins":18},"stepfun/step-3.7-flash":{"draws":11,"losses":28,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":8,"wins":2},"tencent/hy3-preview":{"draws":13,"losses":17,"wins":10},"tencent/hy4-preview":{"draws":25,"losses":38,"wins":7},"thinkingmachines/inkling":{"draws":30,"losses":20,"wins":28},"thinkingmachines/inkling-small":{"draws":25,"losses":21,"wins":26},"unbiased/pareto-26.10":{"draws":1,"losses":23,"wins":0},"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":35,"wins":10},"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":36,"losses":45,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":12,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":26,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":31,"wins":4},"z-ai/glm-5.2":{"draws":51,"losses":56,"wins":37},"z-ai/glm-5.3":{"draws":15,"losses":43,"wins":10},"z-ai/glm-5.3-flash":{"draws":19,"losses":40,"wins":13},"z-ai/glm-5.3-flashx":{"draws":15,"losses":44,"wins":13}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":21,"wins":7},"claude-fable-5":{"draws":6,"losses":37,"wins":5},"claude-fable-5-1":{"draws":5,"losses":49,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":29,"wins":5},"claude-opus-4-5":{"draws":23,"losses":48,"wins":7},"claude-opus-4-8":{"draws":11,"losses":31,"wins":2},"claude-opus-5":{"draws":11,"losses":68,"wins":3},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":14,"losses":27,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":32,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":9,"wins":4},"deepseek/deepseek-v4-flash":{"draws":26,"losses":34,"wins":12},"deepseek/deepseek-v4-pro":{"draws":16,"losses":22,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":22,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":31,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":35,"wins":3},"elorian/glimpse":{"draws":6,"losses":15,"wins":5},"fireworks/ember-1":{"draws":13,"losses":30,"wins":5},"gemini-3.1-pro-preview":{"draws":14,"losses":28,"wins":6},"gemini-4-argon":{"draws":8,"losses":39,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":16,"wins":8},"google/gemini-3.5-flash":{"draws":16,"losses":36,"wins":8},"google/gemini-3.5-flash-lite":{"draws":20,"losses":39,"wins":25},"google/gemini-3.6-flash":{"draws":22,"losses":51,"wins":19},"google/gemini-3.8-flash":{"draws":11,"losses":33,"wins":4},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":10},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":15,"losses":21,"wins":6},"gpt-5.4":{"draws":13,"losses":27,"wins":6},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":14,"losses":20,"wins":14},"gpt-5.5":{"draws":12,"losses":27,"wins":5},"gpt-5.6-luna":{"draws":19,"losses":21,"wins":8},"gpt-5.6-sol":{"draws":10,"losses":36,"wins":2},"gpt-5.6-terra":{"draws":15,"losses":28,"wins":3},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":12,"losses":25,"wins":11},"gpt-6-sol":{"draws":4,"losses":44,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"gpt-6.1-terra":{"draws":1,"losses":47,"wins":0},"gpt-6.1-terra-pro":{"draws":4,"losses":42,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":10,"wins":11},"inception/mercury-3":{"draws":11,"losses":18,"wins":3},"inclusionai/ling-3.0-flash":{"draws":14,"losses":12,"wins":8},"inclusionai/ling-3.1-flash":{"draws":0,"losses":6,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":27,"wins":12},"meta/muse-glimmer-30b":{"draws":16,"losses":18,"wins":8},"meta/muse-spark-1.2":{"draws":13,"losses":26,"wins":7},"meta/muse-spark-1.3":{"draws":12,"losses":32,"wins":4},"meta/muse-spark-open":{"draws":14,"losses":32,"wins":2},"meta/muse-wonder":{"draws":12,"losses":34,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":12,"wins":8},"minimax/minimax-m3.1-flash":{"draws":15,"losses":23,"wins":4},"mistralai/mistral-large-4-0":{"draws":12,"losses":14,"wins":4},"mistralai/mistral-medium-3-5":{"draws":14,"losses":7,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":25,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":39,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":9,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":13,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":13,"wins":3},"o3":{"draws":11,"losses":41,"wins":14},"openai/gpt-oss-120b":{"draws":12,"losses":21,"wins":9},"poolside/laguna-s-2.1":{"draws":15,"losses":23,"wins":8},"qwen/qwen3.7-max":{"draws":8,"losses":15,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":33,"wins":4},"qwen/qwen3.8-27b":{"draws":8,"losses":20,"wins":6},"qwen/qwen3.8-flash":{"draws":10,"losses":17,"wins":5},"qwen/qwen3.8-max":{"draws":13,"losses":21,"wins":14},"qwen/qwen3.8-max-0902":{"draws":15,"losses":29,"wins":4},"recursive/flint-v1.0":{"draws":4,"losses":6,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":24,"wins":9},"stealth/ox-alpha":{"draws":39,"losses":92,"wins":27},"stealth/space-bunny-alpha":{"draws":10,"losses":21,"wins":7},"stepfun/step-3.7-flash":{"draws":7,"losses":13,"wins":14},"stepfun/step-5-preview":{"draws":6,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":10,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":12,"losses":28,"wins":6},"thinkingmachines/inkling":{"draws":26,"losses":27,"wins":11},"thinkingmachines/inkling-small":{"draws":12,"losses":12,"wins":8},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":11,"losses":33,"wins":4},"x-ai/grok-4.7":{"draws":6,"losses":36,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":6,"wins":5},"xiaomi/mimo-v2.5":{"draws":22,"losses":34,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":13,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":23,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":24,"wins":4},"z-ai/glm-5.2":{"draws":33,"losses":47,"wins":16},"z-ai/glm-5.3":{"draws":7,"losses":38,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":31,"wins":9},"z-ai/glm-5.3-flashx":{"draws":9,"losses":32,"wins":7}},"unbiased/pareto-26.10":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":42},"claude-fable-5":{"draws":1,"losses":4,"wins":43},"claude-fable-5-1":{"draws":7,"losses":21,"wins":26},"claude-haiku-5-5":{"draws":4,"losses":4,"wins":38},"claude-opus-4-5":{"draws":6,"losses":0,"wins":72},"claude-opus-4-8":{"draws":4,"losses":4,"wins":36},"claude-opus-5":{"draws":7,"losses":24,"wins":51},"claude-opus-5-5":{"draws":4,"losses":27,"wins":21},"claude-sonnet-5":{"draws":4,"losses":1,"wins":43},"claude-sonnet-5-5":{"draws":4,"losses":8,"wins":36},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":68},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":1,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":1,"wins":44},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":2,"wins":40},"elorian/glimpse":{"draws":1,"losses":0,"wins":25},"fireworks/ember-1":{"draws":2,"losses":1,"wins":45},"gemini-3.1-pro-preview":{"draws":3,"losses":3,"wins":42},"gemini-4-argon":{"draws":4,"losses":13,"wins":31},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":7,"losses":3,"wins":50},"google/gemini-3.5-flash-lite":{"draws":5,"losses":0,"wins":79},"google/gemini-3.6-flash":{"draws":8,"losses":3,"wins":81},"google/gemini-3.8-flash":{"draws":4,"losses":5,"wins":39},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":26},"gpt-4.1":{"draws":1,"losses":1,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":0,"wins":41},"gpt-5.4":{"draws":4,"losses":4,"wins":38},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":30},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":43},"gpt-5.5":{"draws":2,"losses":5,"wins":37},"gpt-5.6-luna":{"draws":3,"losses":1,"wins":44},"gpt-5.6-sol":{"draws":4,"losses":3,"wins":41},"gpt-5.6-terra":{"draws":3,"losses":1,"wins":42},"gpt-6-astra":{"draws":8,"losses":22,"wins":18},"gpt-6-luna":{"draws":3,"losses":1,"wins":44},"gpt-6-sol":{"draws":3,"losses":7,"wins":38},"gpt-6.1-sol":{"draws":6,"losses":17,"wins":25},"gpt-6.1-terra":{"draws":7,"losses":8,"wins":33},"gpt-6.1-terra-pro":{"draws":5,"losses":12,"wins":31},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inception/mercury-3":{"draws":2,"losses":1,"wins":29},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":51},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":40},"meta/muse-spark-1.2":{"draws":2,"losses":0,"wins":44},"meta/muse-spark-1.3":{"draws":3,"losses":0,"wins":45},"meta/muse-spark-open":{"draws":3,"losses":2,"wins":43},"meta/muse-wonder":{"draws":6,"losses":8,"wins":34},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"minimax/minimax-m3.1-flash":{"draws":1,"losses":1,"wins":40},"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":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":3,"losses":1,"wins":42},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":15,"wins":28},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":20},"o3":{"draws":0,"losses":0,"wins":66},"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":5,"losses":1,"wins":42},"qwen/qwen3.8-27b":{"draws":2,"losses":0,"wins":32},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":28},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":47},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":44},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":0,"wins":42},"stealth/ox-alpha":{"draws":11,"losses":4,"wins":143},"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":14},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":25},"tencent/hy4-preview":{"draws":3,"losses":2,"wins":41},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":63},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":45},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":8},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":3,"losses":1,"wins":44},"x-ai/grok-4.6":{"draws":6,"losses":2,"wins":40},"x-ai/grok-4.7":{"draws":5,"losses":10,"wins":27},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":15},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":1,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":30},"z-ai/glm-5.2":{"draws":4,"losses":1,"wins":91},"z-ai/glm-5.3":{"draws":5,"losses":4,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":39},"z-ai/glm-5.3-flashx":{"draws":4,"losses":5,"wins":39}},"unbiased/pareto-26.10-preview":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":42},"claude-fable-5":{"draws":5,"losses":11,"wins":32},"claude-fable-5-1":{"draws":0,"losses":24,"wins":30},"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":1,"losses":2,"wins":41},"claude-opus-5":{"draws":5,"losses":30,"wins":47},"claude-opus-5-5":{"draws":1,"losses":25,"wins":26},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"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":0,"losses":1,"wins":71},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":43},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":10,"wins":37},"elorian/glimpse":{"draws":0,"losses":2,"wins":24},"fireworks/ember-1":{"draws":1,"losses":1,"wins":46},"gemini-3.1-pro-preview":{"draws":1,"losses":1,"wins":46},"gemini-4-argon":{"draws":3,"losses":18,"wins":27},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":2,"losses":5,"wins":53},"google/gemini-3.5-flash-lite":{"draws":3,"losses":0,"wins":81},"google/gemini-3.6-flash":{"draws":1,"losses":9,"wins":82},"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":0,"losses":7,"wins":39},"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":2,"losses":3,"wins":43},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":44},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":39},"gpt-6-astra":{"draws":3,"losses":24,"wins":21},"gpt-6-luna":{"draws":3,"losses":1,"wins":44},"gpt-6-sol":{"draws":2,"losses":11,"wins":35},"gpt-6.1-sol":{"draws":1,"losses":19,"wins":28},"gpt-6.1-terra":{"draws":6,"losses":13,"wins":29},"gpt-6.1-terra-pro":{"draws":4,"losses":18,"wins":26},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inception/mercury-3":{"draws":0,"losses":2,"wins":32},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"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":3,"losses":5,"wins":40},"meta/muse-spark-open":{"draws":0,"losses":3,"wins":45},"meta/muse-wonder":{"draws":2,"losses":9,"wins":37},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"minimax/minimax-m3.1-flash":{"draws":1,"losses":1,"wins":40},"mistralai/mistral-large-4-0":{"draws":2,"losses":3,"wins":25},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":43},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":16,"wins":27},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":37},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":19},"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":1,"losses":5,"wins":26},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":41},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":0,"wins":43},"stealth/ox-alpha":{"draws":8,"losses":8,"wins":142},"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":2,"wins":8},"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},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":8},"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":3,"losses":4,"wins":41},"x-ai/grok-4.7":{"draws":2,"losses":8,"wins":32},"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":0,"wins":28},"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":3,"wins":89},"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":1,"losses":5,"wins":42}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":3,"losses":3,"wins":0},"claude-fable-5-1":{"draws":2,"losses":6,"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":6,"losses":6,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":2,"wins":0},"elorian/glimpse":{"draws":4,"losses":0,"wins":0},"fireworks/ember-1":{"draws":5,"losses":1,"wins":0},"gemini-3.1-pro-preview":{"draws":3,"losses":3,"wins":0},"gemini-4-argon":{"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":10,"losses":2,"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},"gpt-6.1-terra":{"draws":0,"losses":6,"wins":0},"gpt-6.1-terra-pro":{"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},"inception/mercury-3":{"draws":2,"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":1,"losses":2,"wins":3},"meta/muse-spark-open":{"draws":2,"losses":2,"wins":2},"meta/muse-wonder":{"draws":3,"losses":3,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3.1-flash":{"draws":6,"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-k3":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":6,"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},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"wins":0},"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},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":0},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":2,"wins":0},"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},"stepfun/step-5-preview":{"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":{"draws":0,"losses":2,"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":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":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":10,"wins":22},"claude-fable-5":{"draws":9,"losses":31,"wins":8},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":27,"losses":25,"wins":26},"claude-opus-4-8":{"draws":17,"losses":15,"wins":12},"claude-opus-5":{"draws":15,"losses":53,"wins":14},"claude-opus-5-5":{"draws":4,"losses":41,"wins":7},"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":16,"wins":39},"deepseek/deepseek-v4-pro":{"draws":12,"losses":18,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":18,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":17,"wins":19},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":25,"wins":14},"elorian/glimpse":{"draws":5,"losses":11,"wins":10},"fireworks/ember-1":{"draws":16,"losses":13,"wins":19},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"gemini-4-argon":{"draws":5,"losses":33,"wins":10},"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":43,"wins":27},"google/gemini-3.8-flash":{"draws":12,"losses":20,"wins":16},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":17},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":17,"wins":17},"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":9,"wins":28},"gpt-5.5":{"draws":11,"losses":20,"wins":13},"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":39,"wins":5},"gpt-6-luna":{"draws":17,"losses":15,"wins":16},"gpt-6-sol":{"draws":6,"losses":31,"wins":11},"gpt-6.1-sol":{"draws":5,"losses":40,"wins":3},"gpt-6.1-terra":{"draws":5,"losses":34,"wins":9},"gpt-6.1-terra-pro":{"draws":2,"losses":38,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":2,"wins":18},"inception/mercury-3":{"draws":12,"losses":9,"wins":11},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":20},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":13,"wins":25},"meta/muse-glimmer-30b":{"draws":14,"losses":6,"wins":22},"meta/muse-spark-1.2":{"draws":14,"losses":15,"wins":17},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":16},"meta/muse-spark-open":{"draws":13,"losses":20,"wins":15},"meta/muse-wonder":{"draws":9,"losses":28,"wins":11},"minimax/minimax-m3":{"draws":8,"losses":3,"wins":15},"minimax/minimax-m3.1-flash":{"draws":12,"losses":13,"wins":17},"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":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":18,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":33,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":5,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":4,"wins":9},"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":17,"wins":16},"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":18,"wins":15},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":14},"recursive/flint-v1.0":{"draws":6,"losses":0,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":18,"wins":12},"stealth/ox-alpha":{"draws":39,"losses":69,"wins":50},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":4,"losses":10,"wins":20},"stepfun/step-5-preview":{"draws":1,"losses":7,"wins":4},"tencent/hy3-preview":{"draws":11,"losses":5,"wins":10},"tencent/hy4-preview":{"draws":11,"losses":22,"wins":13},"thinkingmachines/inkling":{"draws":19,"losses":12,"wins":33},"thinkingmachines/inkling-small":{"draws":16,"losses":5,"wins":27},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":10,"losses":16,"wins":6},"x-ai/grok-4.6":{"draws":17,"losses":22,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":31,"wins":6},"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":3,"losses":10,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":9},"z-ai/glm-5.2":{"draws":27,"losses":29,"wins":40},"z-ai/glm-5.3":{"draws":10,"losses":28,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":29,"wins":13},"z-ai/glm-5.3-flashx":{"draws":12,"losses":23,"wins":13}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":7,"wins":19},"claude-fable-5":{"draws":13,"losses":30,"wins":5},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":16,"losses":17,"wins":13},"claude-opus-4-5":{"draws":26,"losses":23,"wins":29},"claude-opus-4-8":{"draws":10,"losses":21,"wins":13},"claude-opus-5":{"draws":17,"losses":59,"wins":6},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":17,"losses":18,"wins":13},"claude-sonnet-5-5":{"draws":13,"losses":27,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":23,"losses":16,"wins":33},"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":15,"losses":22,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":26,"wins":6},"elorian/glimpse":{"draws":7,"losses":12,"wins":7},"fireworks/ember-1":{"draws":17,"losses":23,"wins":8},"gemini-3.1-pro-preview":{"draws":16,"losses":14,"wins":18},"gemini-4-argon":{"draws":5,"losses":42,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":18,"losses":20,"wins":22},"google/gemini-3.5-flash-lite":{"draws":27,"losses":17,"wins":40},"google/gemini-3.6-flash":{"draws":32,"losses":38,"wins":22},"google/gemini-3.8-flash":{"draws":15,"losses":25,"wins":8},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":11},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":14,"losses":13,"wins":15},"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":18,"losses":17,"wins":9},"gpt-5.6-luna":{"draws":15,"losses":12,"wins":21},"gpt-5.6-sol":{"draws":10,"losses":29,"wins":9},"gpt-5.6-terra":{"draws":21,"losses":11,"wins":14},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":20,"losses":11,"wins":17},"gpt-6-sol":{"draws":10,"losses":30,"wins":8},"gpt-6.1-sol":{"draws":7,"losses":41,"wins":0},"gpt-6.1-terra":{"draws":9,"losses":36,"wins":3},"gpt-6.1-terra-pro":{"draws":6,"losses":38,"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},"inception/mercury-3":{"draws":12,"losses":10,"wins":10},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":16,"losses":17,"wins":19},"meta/muse-glimmer-30b":{"draws":18,"losses":3,"wins":21},"meta/muse-spark-1.2":{"draws":14,"losses":15,"wins":17},"meta/muse-spark-1.3":{"draws":13,"losses":23,"wins":12},"meta/muse-spark-open":{"draws":16,"losses":23,"wins":9},"meta/muse-wonder":{"draws":20,"losses":26,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":2,"wins":16},"minimax/minimax-m3.1-flash":{"draws":14,"losses":15,"wins":13},"mistralai/mistral-large-4-0":{"draws":13,"losses":7,"wins":10},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":10,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":41,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":10,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":6,"wins":8},"o3":{"draws":12,"losses":25,"wins":29},"openai/gpt-oss-120b":{"draws":16,"losses":8,"wins":18},"poolside/laguna-s-2.1":{"draws":21,"losses":10,"wins":15},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":10},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":10},"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":13,"losses":11,"wins":8},"qwen/qwen3.8-max":{"draws":19,"losses":19,"wins":10},"qwen/qwen3.8-max-0902":{"draws":17,"losses":15,"wins":16},"recursive/flint-v1.0":{"draws":3,"losses":3,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":12,"wins":14},"stealth/ox-alpha":{"draws":58,"losses":74,"wins":26},"stealth/space-bunny-alpha":{"draws":12,"losses":11,"wins":15},"stepfun/step-3.7-flash":{"draws":9,"losses":11,"wins":14},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":18,"losses":18,"wins":10},"thinkingmachines/inkling":{"draws":25,"losses":12,"wins":27},"thinkingmachines/inkling-small":{"draws":16,"losses":10,"wins":22},"unbiased/pareto-26.10":{"draws":4,"losses":12,"wins":0},"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":9,"losses":3,"wins":4},"xiaomi/mimo-v2.5":{"draws":25,"losses":17,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":4,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":19,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":22,"wins":5},"z-ai/glm-5.2":{"draws":35,"losses":28,"wins":33},"z-ai/glm-5.3":{"draws":11,"losses":30,"wins":5},"z-ai/glm-5.3-flash":{"draws":15,"losses":24,"wins":9},"z-ai/glm-5.3-flashx":{"draws":10,"losses":31,"wins":7}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":13,"wins":20},"claude-fable-5":{"draws":6,"losses":25,"wins":11},"claude-fable-5-1":{"draws":4,"losses":39,"wins":3},"claude-haiku-5-5":{"draws":12,"losses":12,"wins":18},"claude-opus-4-5":{"draws":13,"losses":27,"wins":30},"claude-opus-4-8":{"draws":10,"losses":19,"wins":13},"claude-opus-5":{"draws":7,"losses":47,"wins":16},"claude-opus-5-5":{"draws":4,"losses":36,"wins":6},"claude-sonnet-5":{"draws":9,"losses":14,"wins":19},"claude-sonnet-5-5":{"draws":11,"losses":18,"wins":13},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":16,"losses":10,"wins":38},"deepseek/deepseek-v4-pro":{"draws":5,"losses":12,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":16,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":19,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":24,"wins":11},"elorian/glimpse":{"draws":4,"losses":12,"wins":6},"fireworks/ember-1":{"draws":6,"losses":13,"wins":23},"gemini-3.1-pro-preview":{"draws":7,"losses":15,"wins":20},"gemini-4-argon":{"draws":8,"losses":29,"wins":5},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":28},"google/gemini-3.5-flash":{"draws":11,"losses":16,"wins":27},"google/gemini-3.5-flash-lite":{"draws":15,"losses":19,"wins":40},"google/gemini-3.6-flash":{"draws":10,"losses":40,"wins":30},"google/gemini-3.8-flash":{"draws":8,"losses":14,"wins":20},"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":5,"losses":15,"wins":16},"gpt-5.4":{"draws":8,"losses":14,"wins":18},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":17},"gpt-5.4-nano":{"draws":10,"losses":7,"wins":29},"gpt-5.5":{"draws":7,"losses":20,"wins":11},"gpt-5.6-luna":{"draws":9,"losses":10,"wins":23},"gpt-5.6-sol":{"draws":5,"losses":26,"wins":11},"gpt-5.6-terra":{"draws":7,"losses":15,"wins":18},"gpt-6-astra":{"draws":2,"losses":35,"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":31,"wins":8},"gpt-6.1-terra":{"draws":3,"losses":28,"wins":11},"gpt-6.1-terra-pro":{"draws":3,"losses":34,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":20},"inception/mercury-3":{"draws":6,"losses":7,"wins":15},"inclusionai/ling-3.0-flash":{"draws":8,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"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":6,"losses":20,"wins":14},"meta/muse-spark-1.3":{"draws":7,"losses":20,"wins":15},"meta/muse-spark-open":{"draws":7,"losses":16,"wins":17},"meta/muse-wonder":{"draws":10,"losses":18,"wins":14},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":15},"minimax/minimax-m3.1-flash":{"draws":5,"losses":16,"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":1,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":18,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":35,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":6,"wins":10},"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":5,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":18,"wins":15},"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":8,"losses":15,"wins":19},"qwen/qwen3.8-max-0902":{"draws":11,"losses":16,"wins":15},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":6,"wins":23},"stealth/ox-alpha":{"draws":25,"losses":45,"wins":48},"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":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":19,"wins":13},"thinkingmachines/inkling":{"draws":11,"losses":9,"wins":34},"thinkingmachines/inkling-small":{"draws":10,"losses":1,"wins":31},"unbiased/pareto-26.10":{"draws":2,"losses":11,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":9,"losses":19,"wins":14},"x-ai/grok-4.6":{"draws":8,"losses":17,"wins":17},"x-ai/grok-4.7":{"draws":1,"losses":18,"wins":5},"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":4,"losses":3,"wins":13},"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":10,"losses":19,"wins":13},"z-ai/glm-5.3-flashx":{"draws":9,"losses":17,"wins":16}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":38,"wins":36},"claude-fable-5":{"draws":13,"losses":87,"wins":2},"claude-fable-5-1":{"draws":6,"losses":104,"wins":2},"claude-haiku-5-5":{"draws":17,"losses":63,"wins":20},"claude-opus-4-5":{"draws":41,"losses":92,"wins":35},"claude-opus-4-8":{"draws":13,"losses":65,"wins":20},"claude-opus-5":{"draws":22,"losses":138,"wins":6},"claude-opus-5-5":{"draws":6,"losses":104,"wins":0},"claude-sonnet-5":{"draws":20,"losses":58,"wins":24},"claude-sonnet-5-5":{"draws":13,"losses":74,"wins":15},"cohere/north-mini-code":{"draws":6,"losses":15,"wins":19},"deepseek/deepseek-v4-flash":{"draws":31,"losses":63,"wins":60},"deepseek/deepseek-v4-pro":{"draws":26,"losses":50,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":47,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":64,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":79,"wins":10},"elorian/glimpse":{"draws":13,"losses":33,"wins":8},"fireworks/ember-1":{"draws":23,"losses":55,"wins":24},"gemini-3.1-pro-preview":{"draws":19,"losses":50,"wins":33},"gemini-4-argon":{"draws":7,"losses":95,"wins":0},"google/gemini-3.1-flash-lite":{"draws":13,"losses":23,"wins":42},"google/gemini-3.5-flash":{"draws":21,"losses":75,"wins":36},"google/gemini-3.5-flash-lite":{"draws":34,"losses":73,"wins":77},"google/gemini-3.6-flash":{"draws":37,"losses":121,"wins":40},"google/gemini-3.8-flash":{"draws":21,"losses":70,"wins":11},"google/gemma-4-31b-it":{"draws":19,"losses":16,"wins":25},"gpt-4.1":{"draws":6,"losses":20,"wins":8},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":6},"gpt-5":{"draws":17,"losses":48,"wins":25},"gpt-5.4":{"draws":18,"losses":73,"wins":9},"gpt-5.4-mini":{"draws":19,"losses":25,"wins":24},"gpt-5.4-nano":{"draws":19,"losses":53,"wins":40},"gpt-5.5":{"draws":34,"losses":46,"wins":14},"gpt-5.6-luna":{"draws":21,"losses":47,"wins":34},"gpt-5.6-sol":{"draws":11,"losses":82,"wins":9},"gpt-5.6-terra":{"draws":22,"losses":63,"wins":11},"gpt-6-astra":{"draws":7,"losses":94,"wins":1},"gpt-6-luna":{"draws":22,"losses":63,"wins":17},"gpt-6-sol":{"draws":15,"losses":77,"wins":10},"gpt-6.1-sol":{"draws":5,"losses":91,"wins":6},"gpt-6.1-terra":{"draws":11,"losses":89,"wins":2},"gpt-6.1-terra-pro":{"draws":9,"losses":85,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":16,"wins":38},"inception/mercury-3":{"draws":17,"losses":34,"wins":13},"inclusionai/ling-3.0-flash":{"draws":26,"losses":18,"wins":28},"inclusionai/ling-3.1-flash":{"draws":4,"losses":7,"wins":5},"meituan/longcat-2.0":{"draws":19,"losses":46,"wins":49},"meta/muse-glimmer-30b":{"draws":24,"losses":29,"wins":35},"meta/muse-spark-1.2":{"draws":22,"losses":58,"wins":16},"meta/muse-spark-1.3":{"draws":15,"losses":72,"wins":15},"meta/muse-spark-open":{"draws":19,"losses":71,"wins":12},"meta/muse-wonder":{"draws":10,"losses":83,"wins":9},"minimax/minimax-m3":{"draws":11,"losses":18,"wins":27},"minimax/minimax-m3.1-flash":{"draws":16,"losses":49,"wins":27},"mistralai/mistral-large-4-0":{"draws":20,"losses":30,"wins":12},"mistralai/mistral-medium-3-5":{"draws":15,"losses":15,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":26,"losses":54,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":86,"wins":5},"nex-agi/nex-n2-pro":{"draws":9,"losses":16,"wins":25},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":9,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":26,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":22,"wins":13},"o3":{"draws":18,"losses":98,"wins":44},"openai/gpt-oss-120b":{"draws":15,"losses":37,"wins":34},"poolside/laguna-s-2.1":{"draws":26,"losses":40,"wins":30},"qwen/qwen3.7-max":{"draws":15,"losses":28,"wins":19},"qwen/qwen3.7-plus":{"draws":11,"losses":22,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":56,"wins":15},"qwen/qwen3.8-27b":{"draws":10,"losses":46,"wins":20},"qwen/qwen3.8-flash":{"draws":15,"losses":33,"wins":20},"qwen/qwen3.8-max":{"draws":21,"losses":57,"wins":24},"qwen/qwen3.8-max-0902":{"draws":26,"losses":62,"wins":14},"recursive/flint-v1.0":{"draws":4,"losses":12,"wins":16},"reflection/beam-1.0-501b-a23b":{"draws":21,"losses":51,"wins":18},"stealth/ox-alpha":{"draws":56,"losses":201,"wins":53},"stealth/space-bunny-alpha":{"draws":19,"losses":35,"wins":28},"stepfun/step-3.7-flash":{"draws":14,"losses":29,"wins":35},"stepfun/step-5-preview":{"draws":1,"losses":12,"wins":3},"tencent/hy3-preview":{"draws":14,"losses":23,"wins":19},"tencent/hy4-preview":{"draws":23,"losses":64,"wins":13},"thinkingmachines/inkling":{"draws":27,"losses":41,"wins":70},"thinkingmachines/inkling-small":{"draws":26,"losses":25,"wins":51},"unbiased/pareto-26.10":{"draws":0,"losses":34,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":32,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":17,"wins":9},"x-ai/grok-4.5":{"draws":18,"losses":72,"wins":12},"x-ai/grok-4.6":{"draws":30,"losses":60,"wins":12},"x-ai/grok-4.7":{"draws":7,"losses":74,"wins":9},"x-ai/grok-build-0.1":{"draws":10,"losses":14,"wins":10},"xiaomi/mimo-v2.5":{"draws":31,"losses":47,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":22,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":49,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":51,"wins":6},"z-ai/glm-5.2":{"draws":58,"losses":94,"wins":52},"z-ai/glm-5.3":{"draws":8,"losses":84,"wins":4},"z-ai/glm-5.3-flash":{"draws":17,"losses":62,"wins":23},"z-ai/glm-5.3-flashx":{"draws":12,"losses":76,"wins":14}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":14,"wins":8},"claude-fable-5":{"draws":5,"losses":34,"wins":3},"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":8,"losses":28,"wins":6},"claude-sonnet-5-5":{"draws":9,"losses":26,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":19,"losses":28,"wins":19},"deepseek/deepseek-v4-pro":{"draws":7,"losses":22,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":23,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":27,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":31,"wins":4},"elorian/glimpse":{"draws":3,"losses":13,"wins":6},"fireworks/ember-1":{"draws":12,"losses":22,"wins":8},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":11},"gemini-4-argon":{"draws":2,"losses":39,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":22},"google/gemini-3.5-flash":{"draws":9,"losses":29,"wins":14},"google/gemini-3.5-flash-lite":{"draws":20,"losses":33,"wins":19},"google/gemini-3.6-flash":{"draws":15,"losses":50,"wins":15},"google/gemini-3.8-flash":{"draws":9,"losses":27,"wins":6},"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":9,"losses":17,"wins":12},"gpt-5.4":{"draws":6,"losses":28,"wins":6},"gpt-5.4-mini":{"draws":6,"losses":16,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":22,"wins":15},"gpt-5.5":{"draws":12,"losses":18,"wins":8},"gpt-5.6-luna":{"draws":19,"losses":11,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":32,"wins":6},"gpt-5.6-terra":{"draws":7,"losses":29,"wins":4},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":10,"losses":25,"wins":7},"gpt-6-sol":{"draws":1,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":0},"gpt-6.1-terra":{"draws":7,"losses":34,"wins":1},"gpt-6.1-terra-pro":{"draws":3,"losses":37,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":8,"wins":10},"inception/mercury-3":{"draws":10,"losses":12,"wins":8},"inclusionai/ling-3.0-flash":{"draws":10,"losses":9,"wins":11},"inclusionai/ling-3.1-flash":{"draws":0,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":11,"losses":17,"wins":18},"meta/muse-glimmer-30b":{"draws":10,"losses":12,"wins":14},"meta/muse-spark-1.2":{"draws":8,"losses":26,"wins":6},"meta/muse-spark-1.3":{"draws":5,"losses":35,"wins":2},"meta/muse-spark-open":{"draws":8,"losses":30,"wins":4},"meta/muse-wonder":{"draws":4,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":11},"minimax/minimax-m3.1-flash":{"draws":4,"losses":18,"wins":14},"mistralai/mistral-large-4-0":{"draws":8,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":7,"losses":6,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":22,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":35,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":11,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":11,"wins":3},"o3":{"draws":9,"losses":40,"wins":13},"openai/gpt-oss-120b":{"draws":11,"losses":17,"wins":10},"poolside/laguna-s-2.1":{"draws":8,"losses":28,"wins":8},"qwen/qwen3.7-max":{"draws":7,"losses":11,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":27,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":18,"wins":6},"qwen/qwen3.8-flash":{"draws":6,"losses":17,"wins":5},"qwen/qwen3.8-max":{"draws":8,"losses":24,"wins":10},"qwen/qwen3.8-max-0902":{"draws":10,"losses":24,"wins":8},"recursive/flint-v1.0":{"draws":1,"losses":6,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":23,"wins":9},"stealth/ox-alpha":{"draws":29,"losses":87,"wins":24},"stealth/space-bunny-alpha":{"draws":11,"losses":17,"wins":4},"stepfun/step-3.7-flash":{"draws":7,"losses":11,"wins":14},"stepfun/step-5-preview":{"draws":1,"losses":11,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":8,"wins":8},"tencent/hy4-preview":{"draws":8,"losses":26,"wins":6},"thinkingmachines/inkling":{"draws":14,"losses":15,"wins":27},"thinkingmachines/inkling-small":{"draws":14,"losses":10,"wins":18},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":28,"wins":6},"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":22,"losses":19,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":18,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":5},"z-ai/glm-5.2":{"draws":26,"losses":38,"wins":20},"z-ai/glm-5.3":{"draws":9,"losses":31,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":32,"wins":4},"z-ai/glm-5.3-flashx":{"draws":8,"losses":29,"wins":5}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":11,"wins":17},"claude-fable-5":{"draws":11,"losses":27,"wins":4},"claude-fable-5-1":{"draws":2,"losses":41,"wins":3},"claude-haiku-5-5":{"draws":12,"losses":18,"wins":10},"claude-opus-4-5":{"draws":21,"losses":27,"wins":20},"claude-opus-4-8":{"draws":9,"losses":15,"wins":14},"claude-opus-5":{"draws":8,"losses":56,"wins":6},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":8,"losses":16,"wins":18},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":11},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":13,"losses":22,"wins":31},"deepseek/deepseek-v4-pro":{"draws":10,"losses":18,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":19,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":27,"wins":6},"elorian/glimpse":{"draws":3,"losses":8,"wins":11},"fireworks/ember-1":{"draws":9,"losses":18,"wins":15},"gemini-3.1-pro-preview":{"draws":7,"losses":16,"wins":19},"gemini-4-argon":{"draws":2,"losses":38,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":10,"losses":24,"wins":18},"google/gemini-3.5-flash-lite":{"draws":14,"losses":12,"wins":46},"google/gemini-3.6-flash":{"draws":14,"losses":39,"wins":27},"google/gemini-3.8-flash":{"draws":11,"losses":24,"wins":7},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":12},"gpt-4.1":{"draws":4,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":17,"wins":14},"gpt-5.4":{"draws":13,"losses":20,"wins":7},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":12},"gpt-5.4-nano":{"draws":14,"losses":9,"wins":23},"gpt-5.5":{"draws":16,"losses":16,"wins":6},"gpt-5.6-luna":{"draws":6,"losses":17,"wins":19},"gpt-5.6-sol":{"draws":7,"losses":30,"wins":5},"gpt-5.6-terra":{"draws":12,"losses":19,"wins":9},"gpt-6-astra":{"draws":1,"losses":39,"wins":2},"gpt-6-luna":{"draws":12,"losses":19,"wins":11},"gpt-6-sol":{"draws":3,"losses":31,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":6},"gpt-6.1-terra":{"draws":4,"losses":35,"wins":3},"gpt-6.1-terra-pro":{"draws":4,"losses":34,"wins":4},"inception/mercury-2.5-preview":{"draws":6,"losses":4,"wins":18},"inception/mercury-3":{"draws":9,"losses":17,"wins":6},"inclusionai/ling-3.0-flash":{"draws":9,"losses":4,"wins":17},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":8,"wins":27},"meta/muse-glimmer-30b":{"draws":8,"losses":7,"wins":21},"meta/muse-spark-1.2":{"draws":5,"losses":25,"wins":10},"meta/muse-spark-1.3":{"draws":3,"losses":31,"wins":8},"meta/muse-spark-open":{"draws":7,"losses":24,"wins":11},"meta/muse-wonder":{"draws":4,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":6,"wins":13},"minimax/minimax-m3.1-flash":{"draws":9,"losses":15,"wins":12},"mistralai/mistral-large-4-0":{"draws":8,"losses":12,"wins":6},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":16,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":36,"wins":3},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":7,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":5},"o3":{"draws":7,"losses":21,"wins":34},"openai/gpt-oss-120b":{"draws":9,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":15,"losses":9,"wins":20},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":8},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":17,"wins":12},"qwen/qwen3.8-27b":{"draws":12,"losses":12,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":14,"wins":9},"qwen/qwen3.8-max":{"draws":13,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":8,"losses":20,"wins":14},"recursive/flint-v1.0":{"draws":0,"losses":3,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":18,"wins":10},"stealth/ox-alpha":{"draws":33,"losses":71,"wins":36},"stealth/space-bunny-alpha":{"draws":7,"losses":10,"wins":15},"stepfun/step-3.7-flash":{"draws":9,"losses":7,"wins":16},"stepfun/step-5-preview":{"draws":0,"losses":7,"wins":1},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":7,"losses":18,"wins":15},"thinkingmachines/inkling":{"draws":16,"losses":13,"wins":27},"thinkingmachines/inkling-small":{"draws":11,"losses":7,"wins":24},"unbiased/pareto-26.10":{"draws":1,"losses":12,"wins":1},"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":26,"wins":6},"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":19,"losses":5,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":3,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":8,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":20,"losses":33,"wins":31},"z-ai/glm-5.3":{"draws":5,"losses":26,"wins":9},"z-ai/glm-5.3-flash":{"draws":7,"losses":26,"wins":9},"z-ai/glm-5.3-flashx":{"draws":7,"losses":24,"wins":11}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":19},"claude-fable-5":{"draws":6,"losses":33,"wins":9},"claude-fable-5-1":{"draws":6,"losses":45,"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":7,"losses":24,"wins":13},"claude-opus-5":{"draws":10,"losses":58,"wins":14},"claude-opus-5-5":{"draws":5,"losses":42,"wins":5},"claude-sonnet-5":{"draws":15,"losses":16,"wins":17},"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":8,"losses":18,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":27,"wins":17},"elorian/glimpse":{"draws":4,"losses":13,"wins":9},"fireworks/ember-1":{"draws":14,"losses":18,"wins":16},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":20},"gemini-4-argon":{"draws":4,"losses":39,"wins":5},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":12,"losses":26,"wins":22},"google/gemini-3.5-flash-lite":{"draws":21,"losses":18,"wins":45},"google/gemini-3.6-flash":{"draws":29,"losses":41,"wins":22},"google/gemini-3.8-flash":{"draws":13,"losses":22,"wins":13},"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":8,"losses":15,"wins":19},"gpt-5.4":{"draws":10,"losses":24,"wins":12},"gpt-5.4-mini":{"draws":13,"losses":4,"wins":15},"gpt-5.4-nano":{"draws":13,"losses":9,"wins":26},"gpt-5.5":{"draws":13,"losses":20,"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":16,"wins":15},"gpt-6-astra":{"draws":4,"losses":43,"wins":1},"gpt-6-luna":{"draws":11,"losses":16,"wins":21},"gpt-6-sol":{"draws":10,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":35,"wins":7},"gpt-6.1-terra":{"draws":5,"losses":35,"wins":8},"gpt-6.1-terra-pro":{"draws":7,"losses":33,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":1,"wins":19},"inception/mercury-3":{"draws":8,"losses":13,"wins":11},"inclusionai/ling-3.0-flash":{"draws":12,"losses":3,"wins":19},"inclusionai/ling-3.1-flash":{"draws":6,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":17,"losses":4,"wins":31},"meta/muse-glimmer-30b":{"draws":15,"losses":6,"wins":21},"meta/muse-spark-1.2":{"draws":8,"losses":18,"wins":20},"meta/muse-spark-1.3":{"draws":10,"losses":23,"wins":15},"meta/muse-spark-open":{"draws":12,"losses":22,"wins":14},"meta/muse-wonder":{"draws":8,"losses":28,"wins":12},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":15},"minimax/minimax-m3.1-flash":{"draws":12,"losses":11,"wins":19},"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":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":15,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":34,"wins":8},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":11},"o3":{"draws":10,"losses":17,"wins":39},"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":6,"losses":10,"wins":12},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":17,"wins":15},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":13},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":12},"qwen/qwen3.8-max":{"draws":19,"losses":13,"wins":16},"qwen/qwen3.8-max-0902":{"draws":11,"losses":18,"wins":19},"recursive/flint-v1.0":{"draws":4,"losses":1,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":19,"wins":14},"stealth/ox-alpha":{"draws":42,"losses":69,"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":4,"wins":6},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":10,"losses":23,"wins":13},"thinkingmachines/inkling":{"draws":21,"losses":9,"wins":34},"thinkingmachines/inkling-small":{"draws":13,"losses":8,"wins":27},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":24,"wins":13},"x-ai/grok-4.6":{"draws":12,"losses":22,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":31,"wins":6},"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":9,"losses":4,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":13,"wins":2},"z-ai/glm-5.2":{"draws":39,"losses":22,"wins":35},"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":48,"losses":46,"wins":38},"claude-fable-5":{"draws":24,"losses":100,"wins":20},"claude-fable-5-1":{"draws":6,"losses":155,"wins":1},"claude-haiku-5-5":{"draws":28,"losses":84,"wins":26},"claude-opus-4-5":{"draws":69,"losses":112,"wins":53},"claude-opus-4-8":{"draws":35,"losses":74,"wins":23},"claude-opus-5":{"draws":31,"losses":193,"wins":22},"claude-opus-5-5":{"draws":8,"losses":143,"wins":5},"claude-sonnet-5":{"draws":44,"losses":64,"wins":36},"claude-sonnet-5-5":{"draws":28,"losses":89,"wins":27},"cohere/north-mini-code":{"draws":13,"losses":5,"wins":36},"deepseek/deepseek-v4-flash":{"draws":63,"losses":57,"wins":96},"deepseek/deepseek-v4-pro":{"draws":38,"losses":53,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":43,"losses":50,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":49,"losses":66,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":95,"wins":20},"elorian/glimpse":{"draws":19,"losses":36,"wins":23},"fireworks/ember-1":{"draws":44,"losses":70,"wins":30},"gemini-3.1-pro-preview":{"draws":40,"losses":67,"wins":37},"gemini-4-argon":{"draws":11,"losses":123,"wins":10},"google/gemini-3.1-flash-lite":{"draws":18,"losses":19,"wins":59},"google/gemini-3.5-flash":{"draws":38,"losses":92,"wins":50},"google/gemini-3.5-flash-lite":{"draws":64,"losses":92,"wins":96},"google/gemini-3.6-flash":{"draws":77,"losses":132,"wins":67},"google/gemini-3.8-flash":{"draws":33,"losses":86,"wins":25},"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":31,"losses":59,"wins":36},"gpt-5.4":{"draws":35,"losses":75,"wins":28},"gpt-5.4-mini":{"draws":35,"losses":24,"wins":37},"gpt-5.4-nano":{"draws":28,"losses":53,"wins":63},"gpt-5.5":{"draws":45,"losses":62,"wins":25},"gpt-5.6-luna":{"draws":46,"losses":44,"wins":54},"gpt-5.6-sol":{"draws":19,"losses":109,"wins":16},"gpt-5.6-terra":{"draws":45,"losses":56,"wins":37},"gpt-6-astra":{"draws":8,"losses":134,"wins":2},"gpt-6-luna":{"draws":53,"losses":58,"wins":33},"gpt-6-sol":{"draws":25,"losses":105,"wins":14},"gpt-6.1-sol":{"draws":12,"losses":128,"wins":4},"gpt-6.1-terra":{"draws":13,"losses":123,"wins":8},"gpt-6.1-terra-pro":{"draws":16,"losses":122,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":41,"losses":11,"wins":50},"inception/mercury-3":{"draws":34,"losses":41,"wins":21},"inclusionai/ling-3.0-flash":{"draws":39,"losses":24,"wins":39},"inclusionai/ling-3.1-flash":{"draws":7,"losses":8,"wins":7},"meituan/longcat-2.0":{"draws":41,"losses":37,"wins":78},"meta/muse-glimmer-30b":{"draws":51,"losses":26,"wins":49},"meta/muse-spark-1.2":{"draws":33,"losses":67,"wins":38},"meta/muse-spark-1.3":{"draws":27,"losses":87,"wins":30},"meta/muse-spark-open":{"draws":41,"losses":77,"wins":26},"meta/muse-wonder":{"draws":30,"losses":96,"wins":18},"minimax/minimax-m3":{"draws":24,"losses":20,"wins":34},"minimax/minimax-m3.1-flash":{"draws":31,"losses":51,"wins":44},"mistralai/mistral-large-4-0":{"draws":29,"losses":43,"wins":18},"mistralai/mistral-medium-3-5":{"draws":33,"losses":13,"wins":38},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":0},"moonshotai/kimi-k3":{"draws":38,"losses":64,"wins":36},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":119,"wins":11},"nex-agi/nex-n2-pro":{"draws":22,"losses":16,"wins":34},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":8,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":38,"wins":43},"nvidia/nemotron-3.5-super-vl":{"draws":22,"losses":25,"wins":19},"o3":{"draws":30,"losses":96,"wins":72},"openai/gpt-oss-120b":{"draws":40,"losses":35,"wins":51},"poolside/laguna-s-2.1":{"draws":39,"losses":52,"wins":47},"qwen/qwen3.7-max":{"draws":20,"losses":37,"wins":27},"qwen/qwen3.7-plus":{"draws":16,"losses":17,"wins":39},"qwen/qwen3.8-2.4t-a95b":{"draws":52,"losses":61,"wins":31},"qwen/qwen3.8-27b":{"draws":34,"losses":40,"wins":28},"qwen/qwen3.8-flash":{"draws":33,"losses":32,"wins":31},"qwen/qwen3.8-max":{"draws":42,"losses":63,"wins":39},"qwen/qwen3.8-max-0902":{"draws":48,"losses":66,"wins":30},"recursive/flint-v1.0":{"draws":11,"losses":12,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":37,"losses":50,"wins":45},"stealth/ox-alpha":{"draws":112,"losses":259,"wins":103},"stealth/space-bunny-alpha":{"draws":34,"losses":43,"wins":37},"stepfun/step-3.7-flash":{"draws":23,"losses":33,"wins":46},"stepfun/step-5-preview":{"draws":4,"losses":13,"wins":13},"tencent/hy3-preview":{"draws":27,"losses":24,"wins":27},"tencent/hy4-preview":{"draws":25,"losses":81,"wins":32},"thinkingmachines/inkling":{"draws":56,"losses":47,"wins":89},"thinkingmachines/inkling-small":{"draws":45,"losses":37,"wins":62},"unbiased/pareto-26.10":{"draws":2,"losses":46,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":46,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":19},"x-ai/grok-4.5":{"draws":34,"losses":91,"wins":19},"x-ai/grok-4.6":{"draws":34,"losses":87,"wins":23},"x-ai/grok-4.7":{"draws":15,"losses":94,"wins":17},"x-ai/grok-build-0.1":{"draws":18,"losses":15,"wins":15},"xiaomi/mimo-v2.5":{"draws":67,"losses":63,"wins":92},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":21,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":55,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":22,"losses":56,"wins":18},"z-ai/glm-5.2":{"draws":69,"losses":94,"wins":77},"z-ai/glm-5.3":{"draws":31,"losses":96,"wins":11},"z-ai/glm-5.3-flash":{"draws":28,"losses":88,"wins":28},"z-ai/glm-5.3-flashx":{"draws":32,"losses":79,"wins":33}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":23},"claude-fable-5":{"draws":8,"losses":29,"wins":11},"claude-fable-5-1":{"draws":6,"losses":46,"wins":2},"claude-haiku-5-5":{"draws":12,"losses":18,"wins":16},"claude-opus-4-5":{"draws":26,"losses":22,"wins":30},"claude-opus-4-8":{"draws":9,"losses":14,"wins":21},"claude-opus-5":{"draws":11,"losses":63,"wins":8},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":14,"losses":11,"wins":23},"claude-sonnet-5-5":{"draws":10,"losses":25,"wins":13},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":12,"wins":39},"deepseek/deepseek-v4-pro":{"draws":15,"losses":16,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":17,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":22,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":25,"wins":13},"elorian/glimpse":{"draws":7,"losses":9,"wins":10},"fireworks/ember-1":{"draws":15,"losses":13,"wins":20},"gemini-3.1-pro-preview":{"draws":12,"losses":13,"wins":23},"gemini-4-argon":{"draws":2,"losses":43,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":18,"losses":20,"wins":22},"google/gemini-3.5-flash-lite":{"draws":20,"losses":9,"wins":55},"google/gemini-3.6-flash":{"draws":20,"losses":36,"wins":36},"google/gemini-3.8-flash":{"draws":12,"losses":22,"wins":14},"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":12,"losses":8,"wins":22},"gpt-5.4":{"draws":13,"losses":25,"wins":8},"gpt-5.4-mini":{"draws":12,"losses":6,"wins":14},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":24},"gpt-5.5":{"draws":14,"losses":10,"wins":20},"gpt-5.6-luna":{"draws":11,"losses":16,"wins":21},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":12,"losses":14,"wins":20},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":9,"losses":19,"wins":20},"gpt-6-sol":{"draws":8,"losses":30,"wins":10},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":6},"gpt-6.1-terra":{"draws":6,"losses":38,"wins":4},"gpt-6.1-terra-pro":{"draws":6,"losses":38,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":6,"wins":16},"inception/mercury-3":{"draws":10,"losses":11,"wins":11},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":17},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":9,"wins":32},"meta/muse-glimmer-30b":{"draws":7,"losses":7,"wins":28},"meta/muse-spark-1.2":{"draws":11,"losses":26,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":20,"wins":20},"meta/muse-spark-open":{"draws":13,"losses":20,"wins":15},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":15},"minimax/minimax-m3.1-flash":{"draws":11,"losses":12,"wins":19},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":11},"mistralai/mistral-medium-3-5":{"draws":9,"losses":3,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":1},"moonshotai/kimi-k3":{"draws":19,"losses":16,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":36,"wins":6},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":4,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":3,"wins":13},"o3":{"draws":8,"losses":25,"wins":33},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":26},"poolside/laguna-s-2.1":{"draws":14,"losses":8,"wins":24},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":15,"wins":15},"qwen/qwen3.8-27b":{"draws":13,"losses":4,"wins":17},"qwen/qwen3.8-flash":{"draws":12,"losses":11,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-max-0902":{"draws":16,"losses":19,"wins":13},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":18,"wins":16},"stealth/ox-alpha":{"draws":43,"losses":69,"wins":46},"stealth/space-bunny-alpha":{"draws":12,"losses":6,"wins":20},"stepfun/step-3.7-flash":{"draws":8,"losses":3,"wins":23},"stepfun/step-5-preview":{"draws":4,"losses":7,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":13},"tencent/hy4-preview":{"draws":13,"losses":14,"wins":19},"thinkingmachines/inkling":{"draws":15,"losses":15,"wins":34},"thinkingmachines/inkling-small":{"draws":12,"losses":8,"wins":28},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":12,"losses":22,"wins":14},"x-ai/grok-4.7":{"draws":6,"losses":32,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":20,"losses":3,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":3,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":31,"losses":22,"wins":43},"z-ai/glm-5.3":{"draws":5,"losses":25,"wins":0},"z-ai/glm-5.3-flash":{"draws":12,"losses":20,"wins":16},"z-ai/glm-5.3-flashx":{"draws":8,"losses":24,"wins":16}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":8,"wins":21},"claude-fable-5":{"draws":10,"losses":30,"wins":8},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":12,"losses":24,"wins":10},"claude-opus-4-5":{"draws":20,"losses":25,"wins":33},"claude-opus-4-8":{"draws":6,"losses":21,"wins":17},"claude-opus-5":{"draws":14,"losses":59,"wins":9},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":11,"losses":19,"wins":18},"claude-sonnet-5-5":{"draws":10,"losses":23,"wins":15},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":10},"deepseek/deepseek-v4-flash":{"draws":27,"losses":19,"wins":26},"deepseek/deepseek-v4-pro":{"draws":9,"losses":10,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":15,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":21,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":30,"wins":8},"elorian/glimpse":{"draws":4,"losses":11,"wins":11},"fireworks/ember-1":{"draws":10,"losses":17,"wins":21},"gemini-3.1-pro-preview":{"draws":11,"losses":18,"wins":19},"gemini-4-argon":{"draws":6,"losses":38,"wins":4},"google/gemini-3.1-flash-lite":{"draws":7,"losses":7,"wins":18},"google/gemini-3.5-flash":{"draws":10,"losses":25,"wins":25},"google/gemini-3.5-flash-lite":{"draws":22,"losses":22,"wins":40},"google/gemini-3.6-flash":{"draws":23,"losses":35,"wins":34},"google/gemini-3.8-flash":{"draws":7,"losses":27,"wins":14},"google/gemma-4-31b-it":{"draws":8,"losses":7,"wins":13},"gpt-4.1":{"draws":1,"losses":8,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":14,"wins":19},"gpt-5.4":{"draws":6,"losses":23,"wins":17},"gpt-5.4-mini":{"draws":10,"losses":12,"wins":10},"gpt-5.4-nano":{"draws":12,"losses":14,"wins":22},"gpt-5.5":{"draws":11,"losses":18,"wins":15},"gpt-5.6-luna":{"draws":14,"losses":14,"wins":20},"gpt-5.6-sol":{"draws":12,"losses":27,"wins":9},"gpt-5.6-terra":{"draws":14,"losses":15,"wins":17},"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},"gpt-6.1-terra":{"draws":8,"losses":38,"wins":2},"gpt-6.1-terra-pro":{"draws":8,"losses":36,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":5,"wins":20},"inception/mercury-3":{"draws":13,"losses":15,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":12,"losses":14,"wins":26},"meta/muse-glimmer-30b":{"draws":14,"losses":7,"wins":21},"meta/muse-spark-1.2":{"draws":12,"losses":19,"wins":15},"meta/muse-spark-1.3":{"draws":8,"losses":22,"wins":18},"meta/muse-spark-open":{"draws":10,"losses":27,"wins":11},"meta/muse-wonder":{"draws":16,"losses":24,"wins":8},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":14},"minimax/minimax-m3.1-flash":{"draws":6,"losses":19,"wins":17},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":11},"mistralai/mistral-medium-3-5":{"draws":10,"losses":3,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":38,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":11,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":9},"o3":{"draws":7,"losses":28,"wins":31},"openai/gpt-oss-120b":{"draws":9,"losses":12,"wins":21},"poolside/laguna-s-2.1":{"draws":16,"losses":12,"wins":18},"qwen/qwen3.7-max":{"draws":9,"losses":9,"wins":10},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":18,"wins":17},"qwen/qwen3.8-27b":{"draws":10,"losses":12,"wins":12},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":9},"qwen/qwen3.8-max":{"draws":13,"losses":22,"wins":13},"qwen/qwen3.8-max-0902":{"draws":12,"losses":24,"wins":12},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":16,"wins":16},"stealth/ox-alpha":{"draws":31,"losses":77,"wins":50},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"wins":18},"stepfun/step-3.7-flash":{"draws":7,"losses":11,"wins":16},"stepfun/step-5-preview":{"draws":1,"losses":7,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":11},"tencent/hy4-preview":{"draws":12,"losses":22,"wins":12},"thinkingmachines/inkling":{"draws":17,"losses":17,"wins":30},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":24},"unbiased/pareto-26.10":{"draws":2,"losses":13,"wins":1},"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":7,"losses":24,"wins":17},"x-ai/grok-4.6":{"draws":17,"losses":19,"wins":12},"x-ai/grok-4.7":{"draws":6,"losses":30,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":26,"losses":12,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":8,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":11,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":32,"losses":26,"wins":38},"z-ai/glm-5.3":{"draws":11,"losses":27,"wins":8},"z-ai/glm-5.3-flash":{"draws":4,"losses":20,"wins":8},"z-ai/glm-5.3-flashx":{"draws":8,"losses":27,"wins":13}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":8,"wins":26},"claude-fable-5":{"draws":6,"losses":33,"wins":9},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":21,"wins":11},"claude-opus-4-5":{"draws":21,"losses":26,"wins":31},"claude-opus-4-8":{"draws":10,"losses":20,"wins":14},"claude-opus-5":{"draws":15,"losses":57,"wins":10},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":16,"losses":13,"wins":19},"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":17,"losses":19,"wins":36},"deepseek/deepseek-v4-pro":{"draws":16,"losses":12,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":17,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":21,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":27,"wins":11},"elorian/glimpse":{"draws":8,"losses":10,"wins":8},"fireworks/ember-1":{"draws":14,"losses":20,"wins":14},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":20},"gemini-4-argon":{"draws":6,"losses":37,"wins":5},"google/gemini-3.1-flash-lite":{"draws":11,"losses":2,"wins":19},"google/gemini-3.5-flash":{"draws":17,"losses":19,"wins":24},"google/gemini-3.5-flash-lite":{"draws":28,"losses":14,"wins":42},"google/gemini-3.6-flash":{"draws":27,"losses":37,"wins":28},"google/gemini-3.8-flash":{"draws":14,"losses":25,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":3,"losses":2,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":13,"losses":11,"wins":18},"gpt-5.4":{"draws":14,"losses":20,"wins":12},"gpt-5.4-mini":{"draws":13,"losses":5,"wins":14},"gpt-5.4-nano":{"draws":12,"losses":13,"wins":23},"gpt-5.5":{"draws":18,"losses":14,"wins":12},"gpt-5.6-luna":{"draws":14,"losses":17,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":31,"wins":7},"gpt-5.6-terra":{"draws":11,"losses":20,"wins":15},"gpt-6-astra":{"draws":7,"losses":40,"wins":1},"gpt-6-luna":{"draws":9,"losses":18,"wins":21},"gpt-6-sol":{"draws":8,"losses":29,"wins":11},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":6},"gpt-6.1-terra":{"draws":10,"losses":34,"wins":4},"gpt-6.1-terra-pro":{"draws":6,"losses":40,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":4,"wins":20},"inception/mercury-3":{"draws":10,"losses":14,"wins":8},"inclusionai/ling-3.0-flash":{"draws":14,"losses":2,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"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":7,"losses":22,"wins":17},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":16},"meta/muse-spark-open":{"draws":12,"losses":21,"wins":15},"meta/muse-wonder":{"draws":11,"losses":30,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":17},"minimax/minimax-m3.1-flash":{"draws":8,"losses":8,"wins":26},"mistralai/mistral-large-4-0":{"draws":13,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":16,"losses":14,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":35,"wins":8},"nex-agi/nex-n2-pro":{"draws":7,"losses":5,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":7,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":10},"o3":{"draws":9,"losses":15,"wins":42},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":26},"poolside/laguna-s-2.1":{"draws":18,"losses":8,"wins":20},"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":14,"losses":20,"wins":14},"recursive/flint-v1.0":{"draws":4,"losses":1,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":15,"wins":18},"stealth/ox-alpha":{"draws":33,"losses":70,"wins":55},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":19},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":24},"stepfun/step-5-preview":{"draws":2,"losses":8,"wins":2},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":19,"losses":8,"wins":37},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":32},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":13,"losses":23,"wins":12},"x-ai/grok-4.6":{"draws":10,"losses":24,"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":26,"losses":6,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":2,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":14,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":32,"losses":28,"wins":36},"z-ai/glm-5.3":{"draws":9,"losses":31,"wins":6},"z-ai/glm-5.3-flash":{"draws":10,"losses":27,"wins":11},"z-ai/glm-5.3-flashx":{"draws":6,"losses":16,"wins":10}}}}}